{ "version": "2.0.0", "generated": "2026-05-12", "count": 31, "total_benchmarks_tracked": 1749, "initiatives": [ { "id": "tdc", "name": "Therapeutics Data Commons (TDC)", "kind": "meta-platform", "url": "https://tdcommons.ai/", "github": "https://github.com/mims-harvard/TDC", "description": "Open-science platform curating ML datasets/tasks across the drug discovery pipeline with unified API, splits, and leaderboards.", "benchmarks_tracked": 83, "benchmark_count_asof": "2026-05-12", "count_methodology": "Scraped tdcommons.ai single_pred/multi_pred/generation overview pages 2026-05-12: single-pred ~38 datasets (ADME/Tox/HTS/QM/Yields/Epitope/Develop/CRISPROutcome), multi-pred ~32 datasets (DTI/DDI/PPI/GDA/DrugRes/DrugSyn/PeptideMHC/AntibodyAff/MTI/Catalyst/TCREpitope/TrialOutcome/ProteinPeptide/PerturbOutcome/scDTI), generation ~13 (MolGen/RetroSyn/Reaction/SBDD). 8 named leaderboard groups.", "breakdown": { "single_prediction": 38, "multi_prediction": 32, "generation": 13, "leaderboard_groups": 8 }, "host_organization": "Zitnik Lab, Harvard Medical School (+ MIT, Stanford, Georgia Tech collaborators)", "primary_contacts": [ "Marinka Zitnik", "Kexin Huang", "Tianfan Fu" ], "founded": "2021-02", "license_model": "MIT (code); per-dataset licenses for data", "flags": [], "rubric": { "rigor": 5, "coverage": 5, "maintenance": 5, "adoption": 5, "quality": 5, "accessibility": 5, "industry_relevance": 5 }, "notes": "Most comprehensive ML-ready therapeutics benchmark hub. NeurIPS 2021 + Nat Chem Bio 2022.", "composite_score": 100.0, "hosted_benchmarks": [ { "id": "tdc:admet_group", "name": "Admet Group", "category": "Benchmark group", "url": "https://tdcommons.ai/benchmark/admet_group/overview", "leaderboard_url": "https://tdcommons.ai/benchmark/admet_group/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:docking_group", "name": "Docking Group", "category": "Benchmark group", "url": "https://tdcommons.ai/benchmark/docking_group/overview", "leaderboard_url": "https://tdcommons.ai/benchmark/docking_group/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:drugcombo_group", "name": "Drugcombo Group", "category": "Benchmark group", "url": "https://tdcommons.ai/benchmark/drugcombo_group/overview", "leaderboard_url": "https://tdcommons.ai/benchmark/drugcombo_group/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:dti_dg_group", "name": "Dti Dg Group", "category": "Benchmark group", "url": "https://tdcommons.ai/benchmark/dti_dg_group/overview", "leaderboard_url": "https://tdcommons.ai/benchmark/dti_dg_group/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:scdti_group", "name": "Scdti Group", "category": "Benchmark group", "url": "https://tdcommons.ai/benchmark/scdti_group/overview", "leaderboard_url": "https://tdcommons.ai/benchmark/scdti_group/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:counterfactual_group", "name": "Counterfactual Group", "category": "Benchmark group", "url": "https://tdcommons.ai/benchmark/counterfactual_group/overview", "leaderboard_url": "https://tdcommons.ai/benchmark/counterfactual_group/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:proteinpeptide_group", "name": "Proteinpeptide Group", "category": "Benchmark group", "url": "https://tdcommons.ai/benchmark/proteinpeptide_group/overview", "leaderboard_url": "https://tdcommons.ai/benchmark/proteinpeptide_group/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:tcrepitope_group", "name": "Tcrepitope Group", "category": "Benchmark group", "url": "https://tdcommons.ai/benchmark/tcrepitope_group/overview", "leaderboard_url": "https://tdcommons.ai/benchmark/tcrepitope_group/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:adme-absorption", "name": "ADME (absorption)", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:adme-distribution", "name": "ADME (distribution)", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:adme-metabolism", "name": "ADME (metabolism)", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:adme-excretion", "name": "ADME (excretion)", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:caco2-wang", "name": "Caco2_Wang", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:hia-hou", "name": "HIA_Hou", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:pgp-broccatelli", "name": "Pgp_Broccatelli", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:bioavailability-ma", "name": "Bioavailability_Ma", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:lipophilicity-astrazeneca", "name": "Lipophilicity_AstraZeneca", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:solubility-aqsoldb", "name": "Solubility_AqSolDB", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:hydrationfreeenergy-freesolv", "name": "HydrationFreeEnergy_FreeSolv", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:bbb-martins", "name": "BBB_Martins", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:ppbr-az", "name": "PPBR_AZ", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:vdss-lombardo", "name": "VDss_Lombardo", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:cyp2c19-veith", "name": "CYP2C19_Veith", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:cyp2d6-veith", "name": "CYP2D6_Veith", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:cyp3a4-veith", "name": "CYP3A4_Veith", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:cyp1a2-veith", "name": "CYP1A2_Veith", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:cyp2c9-veith", "name": "CYP2C9_Veith", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:cyp2d6-substrate-carbonmangels", "name": "CYP2D6_Substrate_CarbonMangels", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:cyp3a4-substrate-carbonmangels", "name": "CYP3A4_Substrate_CarbonMangels", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:cyp2c9-substrate-carbonmangels", "name": "CYP2C9_Substrate_CarbonMangels", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:half-life-obach", "name": "Half_Life_Obach", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:clearance-hepatocyte-az", "name": "Clearance_Hepatocyte_AZ", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:clearance-microsome-az", "name": "Clearance_Microsome_AZ", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:ld50-zhu", "name": "LD50_Zhu", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:herg", "name": "hERG", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:herg-karim", "name": "hERG_Karim", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:ames", "name": "AMES", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:dili", "name": "DILI", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:skin-reaction", "name": "Skin Reaction", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:carcinogens-lagunin", "name": "Carcinogens_Lagunin", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:clintox", "name": "ClinTox", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:tox21", "name": "Tox21", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:toxcast", "name": "ToxCast", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:hts-pubchem", "name": "HTS_PubChem", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:sarscov2-vitro-touret", "name": "SARSCoV2_Vitro_Touret", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:sarscov2-3clpro-diamond", "name": "SARSCoV2_3CLPro_Diamond", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:hiv", "name": "HIV", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:qm7b", "name": "QM7b", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:qm8", "name": "QM8", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:qm9", "name": "QM9", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:uspto-yields", "name": "USPTO Yields", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:buchwald-hartwig", "name": "Buchwald-Hartwig", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:sarscov2-yields", "name": "SARSCoV2 Yields", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:iedb-jespersen", "name": "IEDB_Jespersen", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:pdb-jespersen", "name": "PDB_Jespersen", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:sabdab-chen", "name": "SAbDab_Chen", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:tap", "name": "TAP", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:sabdab-developability", "name": "SAbDab Developability", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:leenay", "name": "Leenay", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:single_pred:tumor-depmap", "name": "Tumor_DepMap", "category": "Single-instance prediction", "url": "https://tdcommons.ai/single_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:bindingdb-kd", "name": "BindingDB_Kd", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:bindingdb-ki", "name": "BindingDB_Ki", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:bindingdb-ic50", "name": "BindingDB_IC50", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:davis", "name": "DAVIS", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:kiba", "name": "KIBA", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:drugbank-ddi", "name": "DrugBank_DDI", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:twosides", "name": "TWOSIDES", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:oncopolypharmacology", "name": "OncoPolyPharmacology", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:drugcomb", "name": "DrugComb", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:gdsc1", "name": "GDSC1", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:gdsc2", "name": "GDSC2", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:disgenet", "name": "DisGeNET", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:mhc1-iedb-imgt-nielsen", "name": "MHC1_IEDB-IMGT_Nielsen", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:mhc2-iedb-jensen", "name": "MHC2_IEDB_Jensen", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:peptidemhc", "name": "PeptideMHC", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:tcrepitope", "name": "TCREpitope", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:huri", "name": "HuRI", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:humanppi-saar", "name": "HumanPPI_Saar", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:catalyst-uspto", "name": "Catalyst USPTO", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:reaction-uspto", "name": "Reaction USPTO", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:retrosynthesis-uspto-50k", "name": "Retrosynthesis USPTO-50K", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:trialoutcome-hint", "name": "TrialOutcome_HINT", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:trialapproval", "name": "TrialApproval", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:scdti", "name": "scDTI", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:multi_pred:perturb-gears", "name": "Perturb_GEARS", "category": "Multi-instance prediction", "url": "https://tdcommons.ai/multi_pred_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:moses", "name": "MOSES", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:guacamol", "name": "GuacaMol", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:zinc-250k-generation", "name": "ZINC_250K_Generation", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:chembl-generation", "name": "ChEMBL_Generation", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:drd2-oracle", "name": "DRD2 oracle", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:qed-oracle", "name": "QED oracle", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:sa-oracle", "name": "SA oracle", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:logp-oracle", "name": "LogP oracle", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:uspto-retro", "name": "USPTO_Retro", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:uspto-forward", "name": "USPTO_Forward", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:reaction-ord", "name": "Reaction_ORD", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:sbdd-pdb", "name": "SBDD_PDB", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:docking-drd3", "name": "Docking_DRD3", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" }, { "id": "tdc:generation:docking-covid", "name": "Docking_Covid", "category": "Generation", "url": "https://tdcommons.ai/generation_tasks/overview", "paper_url": "https://arxiv.org/abs/2102.09548" } ], "hosted_benchmarks_count": 99 }, { "id": "casp", "name": "CASP (Critical Assessment of Structure Prediction)", "kind": "competition", "url": "https://predictioncenter.org/", "github": "N/A", "description": "Biennial blind evaluation of protein structure prediction; drove AlphaFold's validation.", "benchmarks_tracked": 16, "benchmark_count_asof": "2026-05-12", "count_methodology": "predictioncenter.org archives: CASP1 (1994) through CASP16 (2024) = 16 editions; ~100 targets \u00d7 ~5 categories per edition.", "breakdown": { "editions": 16, "categories_per_edition": 5, "targets_avg": 100 }, "host_organization": "Prediction Center, UC Davis", "primary_contacts": [ "John Moult", "Andriy Kryshtafovych" ], "founded": "1994", "license_model": "Public", "flags": [], "rubric": { "rigor": 5, "coverage": 5, "maintenance": 5, "adoption": 5, "quality": 5, "accessibility": 5, "industry_relevance": 5 }, "notes": "Historical gold standard for blind evaluation. CASP15 added ligands; CASP16 added multimer + RNA.", "composite_score": 100.0, "hosted_benchmarks": [ { "id": "casp:casp7", "name": "CASP7", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp7/", "leaderboard_url": "https://predictioncenter.org/casp7/results.cgi" }, { "id": "casp:casp8", "name": "CASP8", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp8/", "leaderboard_url": "https://predictioncenter.org/casp8/results.cgi" }, { "id": "casp:casp9", "name": "CASP9", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp9/", "leaderboard_url": "https://predictioncenter.org/casp9/results.cgi" }, { "id": "casp:casp10", "name": "CASP10", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp10/", "leaderboard_url": "https://predictioncenter.org/casp10/results.cgi" }, { "id": "casp:casp11", "name": "CASP11", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp11/", "leaderboard_url": "https://predictioncenter.org/casp11/results.cgi" }, { "id": "casp:casp12", "name": "CASP12", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp12/", "leaderboard_url": "https://predictioncenter.org/casp12/results.cgi" }, { "id": "casp:casp13", "name": "CASP13", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp13/", "leaderboard_url": "https://predictioncenter.org/casp13/results.cgi" }, { "id": "casp:casp14", "name": "CASP14", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp14/", "leaderboard_url": "https://predictioncenter.org/casp14/results.cgi" }, { "id": "casp:casp15", "name": "CASP15", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp15/", "leaderboard_url": "https://predictioncenter.org/casp15/results.cgi" }, { "id": "casp:casp16", "name": "CASP16", "category": "Structure prediction edition", "url": "https://predictioncenter.org/casp16/", "leaderboard_url": "https://predictioncenter.org/casp16/results.cgi" }, { "id": "casp:casp-commons", "name": "CASP-COMMONS", "category": "Special", "url": "https://predictioncenter.org/" }, { "id": "casp:casp-capri", "name": "CASP-CAPRI", "category": "Special", "url": "https://predictioncenter.org/" }, { "id": "casp:casp-sars2", "name": "CASP-SARS2", "category": "Special", "url": "https://predictioncenter.org/" } ], "hosted_benchmarks_count": 13 }, { "id": "proteingym", "name": "ProteinGym", "kind": "meta-platform", "url": "https://proteingym.org/", "github": "https://github.com/OATML-Markslab/ProteinGym", "description": "Large-scale benchmark for protein fitness prediction from DMS + clinical variant effects.", "benchmarks_tracked": 217, "benchmark_count_asof": "2026-05-12", "count_methodology": "ProteinGym v1.2 README + NeurIPS 2023 paper: 217 DMS substitution assays + 66 indel assays + 2525 ClinVar clinical variants.", "breakdown": { "dms_substitutions": 217, "dms_indels": 66, "mutations": 2700000, "clinical_variants": 2525 }, "host_organization": "Marks Lab (Harvard) + OATML (Oxford) + DeepMind", "primary_contacts": [ "Debora Marks", "Pascal Notin", "Yarin Gal" ], "founded": "2022", "license_model": "MIT", "flags": [], "rubric": { "rigor": 5, "coverage": 5, "maintenance": 5, "adoption": 5, "quality": 5, "accessibility": 5, "industry_relevance": 4 }, "notes": "De facto standard for variant effect prediction. Clinical track enables ESM/EVE/AlphaMissense fair comparison.", "composite_score": 97.5, "hosted_benchmarks": [ { "id": "proteingym:subs:A0A140D2T1_ZIKV_Sourisseau_2019", "name": "A0A140D2T1_ZIKV_Sourisseau_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=A0A140D2T1_ZIKV_Sourisseau_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:A0A192B1T2_9HIV1_Haddox_2018", "name": "A0A192B1T2_9HIV1_Haddox_2018", "category": "DMS substitution", "url": "https://proteingym.org/?search=A0A192B1T2_9HIV1_Haddox_2018", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:A0A1I9GEU1_NEIME_Kennouche_2019", "name": "A0A1I9GEU1_NEIME_Kennouche_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=A0A1I9GEU1_NEIME_Kennouche_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:A0A247D711_LISMN_Stadelmann_2021", "name": "A0A247D711_LISMN_Stadelmann_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=A0A247D711_LISMN_Stadelmann_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:A0A2Z5U3Z0_9INFA_Doud_2016", "name": "A0A2Z5U3Z0_9INFA_Doud_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=A0A2Z5U3Z0_9INFA_Doud_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:A0A2Z5U3Z0_9INFA_Wu_2014", "name": "A0A2Z5U3Z0_9INFA_Wu_2014", "category": "DMS substitution", "url": "https://proteingym.org/?search=A0A2Z5U3Z0_9INFA_Wu_2014", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:A4_HUMAN_Seuma_2022", "name": "A4_HUMAN_Seuma_2022", "category": "DMS substitution", "url": "https://proteingym.org/?search=A4_HUMAN_Seuma_2022", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:A4D664_9INFA_Soh_2019", "name": "A4D664_9INFA_Soh_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=A4D664_9INFA_Soh_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:A4GRB6_PSEAI_Chen_2020", "name": "A4GRB6_PSEAI_Chen_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=A4GRB6_PSEAI_Chen_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:AACC1_PSEAI_Dandage_2018", "name": "AACC1_PSEAI_Dandage_2018", "category": "DMS substitution", "url": "https://proteingym.org/?search=AACC1_PSEAI_Dandage_2018", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ACE2_HUMAN_Chan_2020", "name": "ACE2_HUMAN_Chan_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=ACE2_HUMAN_Chan_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ADRB2_HUMAN_Jones_2020", "name": "ADRB2_HUMAN_Jones_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=ADRB2_HUMAN_Jones_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:AICDA_HUMAN_Gajula_2014_3cycles", "name": "AICDA_HUMAN_Gajula_2014_3cycles", "category": "DMS substitution", "url": "https://proteingym.org/?search=AICDA_HUMAN_Gajula_2014_3cycles", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:AMFR_HUMAN_Tsuboyama_2023_4G3O", "name": "AMFR_HUMAN_Tsuboyama_2023_4G3O", "category": "DMS substitution", "url": "https://proteingym.org/?search=AMFR_HUMAN_Tsuboyama_2023_4G3O", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:AMIE_PSEAE_Wrenbeck_2017", "name": "AMIE_PSEAE_Wrenbeck_2017", "category": "DMS substitution", "url": "https://proteingym.org/?search=AMIE_PSEAE_Wrenbeck_2017", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ANCSZ_Hobbs_2022", "name": "ANCSZ_Hobbs_2022", "category": "DMS substitution", "url": "https://proteingym.org/?search=ANCSZ_Hobbs_2022", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ARGR_ECOLI_Tsuboyama_2023_1AOY", "name": "ARGR_ECOLI_Tsuboyama_2023_1AOY", "category": "DMS substitution", "url": "https://proteingym.org/?search=ARGR_ECOLI_Tsuboyama_2023_1AOY", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:B2L11_HUMAN_Dutta_2010_binding-Mcl-1", "name": "B2L11_HUMAN_Dutta_2010_binding-Mcl-1", "category": "DMS substitution", "url": "https://proteingym.org/?search=B2L11_HUMAN_Dutta_2010_binding-Mcl-1", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:BBC1_YEAST_Tsuboyama_2023_1TG0", "name": "BBC1_YEAST_Tsuboyama_2023_1TG0", "category": "DMS substitution", "url": "https://proteingym.org/?search=BBC1_YEAST_Tsuboyama_2023_1TG0", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:BCHB_CHLTE_Tsuboyama_2023_2KRU", "name": "BCHB_CHLTE_Tsuboyama_2023_2KRU", "category": "DMS substitution", "url": "https://proteingym.org/?search=BCHB_CHLTE_Tsuboyama_2023_2KRU", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:BLAT_ECOLX_Deng_2012", "name": "BLAT_ECOLX_Deng_2012", "category": "DMS substitution", "url": "https://proteingym.org/?search=BLAT_ECOLX_Deng_2012", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:BLAT_ECOLX_Firnberg_2014", "name": "BLAT_ECOLX_Firnberg_2014", "category": "DMS substitution", "url": "https://proteingym.org/?search=BLAT_ECOLX_Firnberg_2014", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:BLAT_ECOLX_Jacquier_2013", "name": "BLAT_ECOLX_Jacquier_2013", "category": "DMS substitution", "url": "https://proteingym.org/?search=BLAT_ECOLX_Jacquier_2013", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:BLAT_ECOLX_Stiffler_2015", "name": "BLAT_ECOLX_Stiffler_2015", "category": "DMS substitution", "url": "https://proteingym.org/?search=BLAT_ECOLX_Stiffler_2015", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:BRCA1_HUMAN_Findlay_2018", "name": "BRCA1_HUMAN_Findlay_2018", "category": "DMS substitution", "url": "https://proteingym.org/?search=BRCA1_HUMAN_Findlay_2018", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:BRCA2_HUMAN_Erwood_2022_HEK293T", "name": "BRCA2_HUMAN_Erwood_2022_HEK293T", "category": "DMS substitution", "url": "https://proteingym.org/?search=BRCA2_HUMAN_Erwood_2022_HEK293T", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:C6KNH7_9INFA_Lee_2018", "name": "C6KNH7_9INFA_Lee_2018", "category": "DMS substitution", "url": "https://proteingym.org/?search=C6KNH7_9INFA_Lee_2018", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CALM1_HUMAN_Weile_2017", "name": "CALM1_HUMAN_Weile_2017", "category": "DMS substitution", "url": "https://proteingym.org/?search=CALM1_HUMAN_Weile_2017", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CAPSD_AAV2S_Sinai_2021", "name": "CAPSD_AAV2S_Sinai_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=CAPSD_AAV2S_Sinai_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CAR11_HUMAN_Meitlis_2020_gof", "name": "CAR11_HUMAN_Meitlis_2020_gof", "category": "DMS substitution", "url": "https://proteingym.org/?search=CAR11_HUMAN_Meitlis_2020_gof", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CAR11_HUMAN_Meitlis_2020_lof", "name": "CAR11_HUMAN_Meitlis_2020_lof", "category": "DMS substitution", "url": "https://proteingym.org/?search=CAR11_HUMAN_Meitlis_2020_lof", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CAS9_STRP1_Spencer_2017_positive", "name": "CAS9_STRP1_Spencer_2017_positive", "category": "DMS substitution", "url": "https://proteingym.org/?search=CAS9_STRP1_Spencer_2017_positive", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CASP3_HUMAN_Roychowdhury_2020", "name": "CASP3_HUMAN_Roychowdhury_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=CASP3_HUMAN_Roychowdhury_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CASP7_HUMAN_Roychowdhury_2020", "name": "CASP7_HUMAN_Roychowdhury_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=CASP7_HUMAN_Roychowdhury_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CATR_CHLRE_Tsuboyama_2023_2AMI", "name": "CATR_CHLRE_Tsuboyama_2023_2AMI", "category": "DMS substitution", "url": "https://proteingym.org/?search=CATR_CHLRE_Tsuboyama_2023_2AMI", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CBPA2_HUMAN_Tsuboyama_2023_1O6X", "name": "CBPA2_HUMAN_Tsuboyama_2023_1O6X", "category": "DMS substitution", "url": "https://proteingym.org/?search=CBPA2_HUMAN_Tsuboyama_2023_1O6X", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CBS_HUMAN_Sun_2020", "name": "CBS_HUMAN_Sun_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=CBS_HUMAN_Sun_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CBX4_HUMAN_Tsuboyama_2023_2K28", "name": "CBX4_HUMAN_Tsuboyama_2023_2K28", "category": "DMS substitution", "url": "https://proteingym.org/?search=CBX4_HUMAN_Tsuboyama_2023_2K28", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CCDB_ECOLI_Adkar_2012", "name": "CCDB_ECOLI_Adkar_2012", "category": "DMS substitution", "url": "https://proteingym.org/?search=CCDB_ECOLI_Adkar_2012", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CCDB_ECOLI_Tripathi_2016", "name": "CCDB_ECOLI_Tripathi_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=CCDB_ECOLI_Tripathi_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CCR5_HUMAN_Gill_2023", "name": "CCR5_HUMAN_Gill_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=CCR5_HUMAN_Gill_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CD19_HUMAN_Klesmith_2019_FMC_singles", "name": "CD19_HUMAN_Klesmith_2019_FMC_singles", "category": "DMS substitution", "url": "https://proteingym.org/?search=CD19_HUMAN_Klesmith_2019_FMC_singles", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CP2C9_HUMAN_Amorosi_2021_abundance", "name": "CP2C9_HUMAN_Amorosi_2021_abundance", "category": "DMS substitution", "url": "https://proteingym.org/?search=CP2C9_HUMAN_Amorosi_2021_abundance", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CP2C9_HUMAN_Amorosi_2021_activity", "name": "CP2C9_HUMAN_Amorosi_2021_activity", "category": "DMS substitution", "url": "https://proteingym.org/?search=CP2C9_HUMAN_Amorosi_2021_activity", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CSN4_MOUSE_Tsuboyama_2023_1UFM", "name": "CSN4_MOUSE_Tsuboyama_2023_1UFM", "category": "DMS substitution", "url": "https://proteingym.org/?search=CSN4_MOUSE_Tsuboyama_2023_1UFM", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:CUE1_YEAST_Tsuboyama_2023_2MYX", "name": "CUE1_YEAST_Tsuboyama_2023_2MYX", "category": "DMS substitution", "url": "https://proteingym.org/?search=CUE1_YEAST_Tsuboyama_2023_2MYX", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:D7PM05_CLYGR_Somermeyer_2022", "name": "D7PM05_CLYGR_Somermeyer_2022", "category": "DMS substitution", "url": "https://proteingym.org/?search=D7PM05_CLYGR_Somermeyer_2022", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:DLG4_HUMAN_Faure_2021", "name": "DLG4_HUMAN_Faure_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=DLG4_HUMAN_Faure_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:DLG4_RAT_McLaughlin_2012", "name": "DLG4_RAT_McLaughlin_2012", "category": "DMS substitution", "url": "https://proteingym.org/?search=DLG4_RAT_McLaughlin_2012", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:DN7A_SACS2_Tsuboyama_2023_1JIC", "name": "DN7A_SACS2_Tsuboyama_2023_1JIC", "category": "DMS substitution", "url": "https://proteingym.org/?search=DN7A_SACS2_Tsuboyama_2023_1JIC", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:DNJA1_HUMAN_Tsuboyama_2023_2LO1", "name": "DNJA1_HUMAN_Tsuboyama_2023_2LO1", "category": "DMS substitution", "url": "https://proteingym.org/?search=DNJA1_HUMAN_Tsuboyama_2023_2LO1", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:DOCK1_MOUSE_Tsuboyama_2023_2M0Y", "name": "DOCK1_MOUSE_Tsuboyama_2023_2M0Y", "category": "DMS substitution", "url": "https://proteingym.org/?search=DOCK1_MOUSE_Tsuboyama_2023_2M0Y", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:DYR_ECOLI_Nguyen_2023", "name": "DYR_ECOLI_Nguyen_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=DYR_ECOLI_Nguyen_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:DYR_ECOLI_Thompson_2019", "name": "DYR_ECOLI_Thompson_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=DYR_ECOLI_Thompson_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ENV_HV1B9_DuenasDecamp_2016", "name": "ENV_HV1B9_DuenasDecamp_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=ENV_HV1B9_DuenasDecamp_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ENV_HV1BR_Haddox_2016", "name": "ENV_HV1BR_Haddox_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=ENV_HV1BR_Haddox_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ENVZ_ECOLI_Ghose_2023", "name": "ENVZ_ECOLI_Ghose_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=ENVZ_ECOLI_Ghose_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:EPHB2_HUMAN_Tsuboyama_2023_1F0M", "name": "EPHB2_HUMAN_Tsuboyama_2023_1F0M", "category": "DMS substitution", "url": "https://proteingym.org/?search=EPHB2_HUMAN_Tsuboyama_2023_1F0M", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ERBB2_HUMAN_Elazar_2016", "name": "ERBB2_HUMAN_Elazar_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=ERBB2_HUMAN_Elazar_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ESTA_BACSU_Nutschel_2020", "name": "ESTA_BACSU_Nutschel_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=ESTA_BACSU_Nutschel_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:F7YBW8_MESOW_Ding_2023", "name": "F7YBW8_MESOW_Ding_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=F7YBW8_MESOW_Ding_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:F7YBW8_MESOW_Aakre_2015", "name": "F7YBW8_MESOW_Aakre_2015", "category": "DMS substitution", "url": "https://proteingym.org/?search=F7YBW8_MESOW_Aakre_2015", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:FECA_ECOLI_Tsuboyama_2023_2D1U", "name": "FECA_ECOLI_Tsuboyama_2023_2D1U", "category": "DMS substitution", "url": "https://proteingym.org/?search=FECA_ECOLI_Tsuboyama_2023_2D1U", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:FKBP3_HUMAN_Tsuboyama_2023_2KFV", "name": "FKBP3_HUMAN_Tsuboyama_2023_2KFV", "category": "DMS substitution", "url": "https://proteingym.org/?search=FKBP3_HUMAN_Tsuboyama_2023_2KFV", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:GAL4_YEAST_Kitzman_2015", "name": "GAL4_YEAST_Kitzman_2015", "category": "DMS substitution", "url": "https://proteingym.org/?search=GAL4_YEAST_Kitzman_2015", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:GCN4_YEAST_Staller_2018", "name": "GCN4_YEAST_Staller_2018", "category": "DMS substitution", "url": "https://proteingym.org/?search=GCN4_YEAST_Staller_2018", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:GDIA_HUMAN_Silverstein_2021", "name": "GDIA_HUMAN_Silverstein_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=GDIA_HUMAN_Silverstein_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:GFP_AEQVI_Sarkisyan_2016", "name": "GFP_AEQVI_Sarkisyan_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=GFP_AEQVI_Sarkisyan_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:GLPA_HUMAN_Elazar_2016", "name": "GLPA_HUMAN_Elazar_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=GLPA_HUMAN_Elazar_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:GRB2_HUMAN_Faure_2021", "name": "GRB2_HUMAN_Faure_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=GRB2_HUMAN_Faure_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HCP_LAMBD_Tsuboyama_2023_2L6Q", "name": "HCP_LAMBD_Tsuboyama_2023_2L6Q", "category": "DMS substitution", "url": "https://proteingym.org/?search=HCP_LAMBD_Tsuboyama_2023_2L6Q", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HECD1_HUMAN_Tsuboyama_2023_3DKM", "name": "HECD1_HUMAN_Tsuboyama_2023_3DKM", "category": "DMS substitution", "url": "https://proteingym.org/?search=HECD1_HUMAN_Tsuboyama_2023_3DKM", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HEM3_HUMAN_Loggerenberg_2023", "name": "HEM3_HUMAN_Loggerenberg_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=HEM3_HUMAN_Loggerenberg_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HIS7_YEAST_Pokusaeva_2019", "name": "HIS7_YEAST_Pokusaeva_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=HIS7_YEAST_Pokusaeva_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HMDH_HUMAN_Jiang_2019", "name": "HMDH_HUMAN_Jiang_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=HMDH_HUMAN_Jiang_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HSP82_YEAST_Cote-Hammarlof_2020_growth-H2O2", "name": "HSP82_YEAST_Cote-Hammarlof_2020_growth-H2O2", "category": "DMS substitution", "url": "https://proteingym.org/?search=HSP82_YEAST_Cote-Hammarlof_2020_growth-H2O2", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HSP82_YEAST_Flynn_2019", "name": "HSP82_YEAST_Flynn_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=HSP82_YEAST_Flynn_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HSP82_YEAST_Mishra_2016", "name": "HSP82_YEAST_Mishra_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=HSP82_YEAST_Mishra_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HXK4_HUMAN_Gersing_2022_activity", "name": "HXK4_HUMAN_Gersing_2022_activity", "category": "DMS substitution", "url": "https://proteingym.org/?search=HXK4_HUMAN_Gersing_2022_activity", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:HXK4_HUMAN_Gersing_2023_abundance", "name": "HXK4_HUMAN_Gersing_2023_abundance", "category": "DMS substitution", "url": "https://proteingym.org/?search=HXK4_HUMAN_Gersing_2023_abundance", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:I6TAH8_I68A0_Doud_2015", "name": "I6TAH8_I68A0_Doud_2015", "category": "DMS substitution", "url": "https://proteingym.org/?search=I6TAH8_I68A0_Doud_2015", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:IF1_ECOLI_Kelsic_2016", "name": "IF1_ECOLI_Kelsic_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=IF1_ECOLI_Kelsic_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ILF3_HUMAN_Tsuboyama_2023_2L33", "name": "ILF3_HUMAN_Tsuboyama_2023_2L33", "category": "DMS substitution", "url": "https://proteingym.org/?search=ILF3_HUMAN_Tsuboyama_2023_2L33", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ISDH_STAAW_Tsuboyama_2023_2LHR", "name": "ISDH_STAAW_Tsuboyama_2023_2LHR", "category": "DMS substitution", "url": "https://proteingym.org/?search=ISDH_STAAW_Tsuboyama_2023_2LHR", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:KCNE1_HUMAN_Muhammad_2023_expression", "name": "KCNE1_HUMAN_Muhammad_2023_expression", "category": "DMS substitution", "url": "https://proteingym.org/?search=KCNE1_HUMAN_Muhammad_2023_expression", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:KCNE1_HUMAN_Muhammad_2023_function", "name": "KCNE1_HUMAN_Muhammad_2023_function", "category": "DMS substitution", "url": "https://proteingym.org/?search=KCNE1_HUMAN_Muhammad_2023_function", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:KCNH2_HUMAN_Kozek_2020", "name": "KCNH2_HUMAN_Kozek_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=KCNH2_HUMAN_Kozek_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:KCNJ2_MOUSE_Coyote-Maestas_2022_function", "name": "KCNJ2_MOUSE_Coyote-Maestas_2022_function", "category": "DMS substitution", "url": "https://proteingym.org/?search=KCNJ2_MOUSE_Coyote-Maestas_2022_function", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:KCNJ2_MOUSE_Coyote-Maestas_2022_surface", "name": "KCNJ2_MOUSE_Coyote-Maestas_2022_surface", "category": "DMS substitution", "url": "https://proteingym.org/?search=KCNJ2_MOUSE_Coyote-Maestas_2022_surface", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:KKA2_KLEPN_Melnikov_2014", "name": "KKA2_KLEPN_Melnikov_2014", "category": "DMS substitution", "url": "https://proteingym.org/?search=KKA2_KLEPN_Melnikov_2014", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:LGK_LIPST_Klesmith_2015", "name": "LGK_LIPST_Klesmith_2015", "category": "DMS substitution", "url": "https://proteingym.org/?search=LGK_LIPST_Klesmith_2015", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:LYAM1_HUMAN_Elazar_2016", "name": "LYAM1_HUMAN_Elazar_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=LYAM1_HUMAN_Elazar_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:MAFG_MOUSE_Tsuboyama_2023_1K1V", "name": "MAFG_MOUSE_Tsuboyama_2023_1K1V", "category": "DMS substitution", "url": "https://proteingym.org/?search=MAFG_MOUSE_Tsuboyama_2023_1K1V", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:MBD11_ARATH_Tsuboyama_2023_6ACV", "name": "MBD11_ARATH_Tsuboyama_2023_6ACV", "category": "DMS substitution", "url": "https://proteingym.org/?search=MBD11_ARATH_Tsuboyama_2023_6ACV", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:MET_HUMAN_Estevam_2023", "name": "MET_HUMAN_Estevam_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=MET_HUMAN_Estevam_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:MK01_HUMAN_Brenan_2016", "name": "MK01_HUMAN_Brenan_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=MK01_HUMAN_Brenan_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:MLAC_ECOLI_MacRae_2023", "name": "MLAC_ECOLI_MacRae_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=MLAC_ECOLI_MacRae_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:MSH2_HUMAN_Jia_2020", "name": "MSH2_HUMAN_Jia_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=MSH2_HUMAN_Jia_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:MTH3_HAEAE_RockahShmuel_2015", "name": "MTH3_HAEAE_RockahShmuel_2015", "category": "DMS substitution", "url": "https://proteingym.org/?search=MTH3_HAEAE_RockahShmuel_2015", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:MTHR_HUMAN_Weile_2021", "name": "MTHR_HUMAN_Weile_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=MTHR_HUMAN_Weile_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:MYO3_YEAST_Tsuboyama_2023_2BTT", "name": "MYO3_YEAST_Tsuboyama_2023_2BTT", "category": "DMS substitution", "url": "https://proteingym.org/?search=MYO3_YEAST_Tsuboyama_2023_2BTT", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:NCAP_I34A1_Doud_2015", "name": "NCAP_I34A1_Doud_2015", "category": "DMS substitution", "url": "https://proteingym.org/?search=NCAP_I34A1_Doud_2015", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:NKX31_HUMAN_Tsuboyama_2023_2L9R", "name": "NKX31_HUMAN_Tsuboyama_2023_2L9R", "category": "DMS substitution", "url": "https://proteingym.org/?search=NKX31_HUMAN_Tsuboyama_2023_2L9R", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:NPC1_HUMAN_Erwood_2022_HEK293T", "name": "NPC1_HUMAN_Erwood_2022_HEK293T", "category": "DMS substitution", "url": "https://proteingym.org/?search=NPC1_HUMAN_Erwood_2022_HEK293T", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:NPC1_HUMAN_Erwood_2022_RPE1", "name": "NPC1_HUMAN_Erwood_2022_RPE1", "category": "DMS substitution", "url": "https://proteingym.org/?search=NPC1_HUMAN_Erwood_2022_RPE1", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:NRAM_I33A0_Jiang_2016", "name": "NRAM_I33A0_Jiang_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=NRAM_I33A0_Jiang_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:NUD15_HUMAN_Suiter_2020", "name": "NUD15_HUMAN_Suiter_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=NUD15_HUMAN_Suiter_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:NUSA_ECOLI_Tsuboyama_2023_1WCL", "name": "NUSA_ECOLI_Tsuboyama_2023_1WCL", "category": "DMS substitution", "url": "https://proteingym.org/?search=NUSA_ECOLI_Tsuboyama_2023_1WCL", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:NUSG_MYCTU_Tsuboyama_2023_2MI6", "name": "NUSG_MYCTU_Tsuboyama_2023_2MI6", "category": "DMS substitution", "url": "https://proteingym.org/?search=NUSG_MYCTU_Tsuboyama_2023_2MI6", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:OBSCN_HUMAN_Tsuboyama_2023_1V1C", "name": "OBSCN_HUMAN_Tsuboyama_2023_1V1C", "category": "DMS substitution", "url": "https://proteingym.org/?search=OBSCN_HUMAN_Tsuboyama_2023_1V1C", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:ODP2_GEOSE_Tsuboyama_2023_1W4G", "name": "ODP2_GEOSE_Tsuboyama_2023_1W4G", "category": "DMS substitution", "url": "https://proteingym.org/?search=ODP2_GEOSE_Tsuboyama_2023_1W4G", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:OPSD_HUMAN_Wan_2019", "name": "OPSD_HUMAN_Wan_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=OPSD_HUMAN_Wan_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:OTC_HUMAN_Lo_2023", "name": "OTC_HUMAN_Lo_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=OTC_HUMAN_Lo_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:OTU7A_HUMAN_Tsuboyama_2023_2L2D", "name": "OTU7A_HUMAN_Tsuboyama_2023_2L2D", "category": "DMS substitution", "url": "https://proteingym.org/?search=OTU7A_HUMAN_Tsuboyama_2023_2L2D", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:OXDA_RHOTO_Vanella_2023_activity", "name": "OXDA_RHOTO_Vanella_2023_activity", "category": "DMS substitution", "url": "https://proteingym.org/?search=OXDA_RHOTO_Vanella_2023_activity", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:OXDA_RHOTO_Vanella_2023_expression", "name": "OXDA_RHOTO_Vanella_2023_expression", "category": "DMS substitution", "url": "https://proteingym.org/?search=OXDA_RHOTO_Vanella_2023_expression", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:P53_HUMAN_Giacomelli_2018_Null_Etoposide", "name": "P53_HUMAN_Giacomelli_2018_Null_Etoposide", "category": "DMS substitution", "url": "https://proteingym.org/?search=P53_HUMAN_Giacomelli_2018_Null_Etoposide", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:P53_HUMAN_Giacomelli_2018_Null_Nutlin", "name": "P53_HUMAN_Giacomelli_2018_Null_Nutlin", "category": "DMS substitution", "url": "https://proteingym.org/?search=P53_HUMAN_Giacomelli_2018_Null_Nutlin", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:P53_HUMAN_Giacomelli_2018_WT_Nutlin", "name": "P53_HUMAN_Giacomelli_2018_WT_Nutlin", "category": "DMS substitution", "url": "https://proteingym.org/?search=P53_HUMAN_Giacomelli_2018_WT_Nutlin", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:P53_HUMAN_Kotler_2018", "name": "P53_HUMAN_Kotler_2018", "category": "DMS substitution", "url": "https://proteingym.org/?search=P53_HUMAN_Kotler_2018", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:P84126_THETH_Chan_2017", "name": "P84126_THETH_Chan_2017", "category": "DMS substitution", "url": "https://proteingym.org/?search=P84126_THETH_Chan_2017", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PA_I34A1_Wu_2015", "name": "PA_I34A1_Wu_2015", "category": "DMS substitution", "url": "https://proteingym.org/?search=PA_I34A1_Wu_2015", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PABP_YEAST_Melamed_2013", "name": "PABP_YEAST_Melamed_2013", "category": "DMS substitution", "url": "https://proteingym.org/?search=PABP_YEAST_Melamed_2013", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PAI1_HUMAN_Huttinger_2021", "name": "PAI1_HUMAN_Huttinger_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=PAI1_HUMAN_Huttinger_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PHOT_CHLRE_Chen_2023", "name": "PHOT_CHLRE_Chen_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=PHOT_CHLRE_Chen_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PIN1_HUMAN_Tsuboyama_2023_1I6C", "name": "PIN1_HUMAN_Tsuboyama_2023_1I6C", "category": "DMS substitution", "url": "https://proteingym.org/?search=PIN1_HUMAN_Tsuboyama_2023_1I6C", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PITX2_HUMAN_Tsuboyama_2023_2L7M", "name": "PITX2_HUMAN_Tsuboyama_2023_2L7M", "category": "DMS substitution", "url": "https://proteingym.org/?search=PITX2_HUMAN_Tsuboyama_2023_2L7M", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PKN1_HUMAN_Tsuboyama_2023_1URF", "name": "PKN1_HUMAN_Tsuboyama_2023_1URF", "category": "DMS substitution", "url": "https://proteingym.org/?search=PKN1_HUMAN_Tsuboyama_2023_1URF", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:POLG_CXB3N_Mattenberger_2021", "name": "POLG_CXB3N_Mattenberger_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=POLG_CXB3N_Mattenberger_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:POLG_DEN26_Suphatrakul_2023", "name": "POLG_DEN26_Suphatrakul_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=POLG_DEN26_Suphatrakul_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:POLG_HCVJF_Qi_2014", "name": "POLG_HCVJF_Qi_2014", "category": "DMS substitution", "url": "https://proteingym.org/?search=POLG_HCVJF_Qi_2014", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:POLG_PESV_Tsuboyama_2023_2MXD", "name": "POLG_PESV_Tsuboyama_2023_2MXD", "category": "DMS substitution", "url": "https://proteingym.org/?search=POLG_PESV_Tsuboyama_2023_2MXD", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PPARG_HUMAN_Majithia_2016", "name": "PPARG_HUMAN_Majithia_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=PPARG_HUMAN_Majithia_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PPM1D_HUMAN_Miller_2022", "name": "PPM1D_HUMAN_Miller_2022", "category": "DMS substitution", "url": "https://proteingym.org/?search=PPM1D_HUMAN_Miller_2022", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PR40A_HUMAN_Tsuboyama_2023_1UZC", "name": "PR40A_HUMAN_Tsuboyama_2023_1UZC", "category": "DMS substitution", "url": "https://proteingym.org/?search=PR40A_HUMAN_Tsuboyama_2023_1UZC", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PRKN_HUMAN_Clausen_2023", "name": "PRKN_HUMAN_Clausen_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=PRKN_HUMAN_Clausen_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PSAE_PICP2_Tsuboyama_2023_1PSE", "name": "PSAE_PICP2_Tsuboyama_2023_1PSE", "category": "DMS substitution", "url": "https://proteingym.org/?search=PSAE_PICP2_Tsuboyama_2023_1PSE", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PTEN_HUMAN_Matreyek_2021", "name": "PTEN_HUMAN_Matreyek_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=PTEN_HUMAN_Matreyek_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:PTEN_HUMAN_Mighell_2018", "name": "PTEN_HUMAN_Mighell_2018", "category": "DMS substitution", "url": "https://proteingym.org/?search=PTEN_HUMAN_Mighell_2018", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:Q2N0S5_9HIV1_Haddox_2018", "name": "Q2N0S5_9HIV1_Haddox_2018", "category": "DMS substitution", "url": "https://proteingym.org/?search=Q2N0S5_9HIV1_Haddox_2018", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:Q53Z42_HUMAN_McShan_2019_binding-TAPBPR", "name": "Q53Z42_HUMAN_McShan_2019_binding-TAPBPR", "category": "DMS substitution", "url": "https://proteingym.org/?search=Q53Z42_HUMAN_McShan_2019_binding-TAPBPR", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:Q53Z42_HUMAN_McShan_2019_expression", "name": "Q53Z42_HUMAN_McShan_2019_expression", "category": "DMS substitution", "url": "https://proteingym.org/?search=Q53Z42_HUMAN_McShan_2019_expression", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:Q59976_STRSQ_Romero_2015", "name": "Q59976_STRSQ_Romero_2015", "category": "DMS substitution", "url": "https://proteingym.org/?search=Q59976_STRSQ_Romero_2015", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:Q6WV12_9MAXI_Somermeyer_2022", "name": "Q6WV12_9MAXI_Somermeyer_2022", "category": "DMS substitution", "url": "https://proteingym.org/?search=Q6WV12_9MAXI_Somermeyer_2022", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:Q837P4_ENTFA_Meier_2023", "name": "Q837P4_ENTFA_Meier_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=Q837P4_ENTFA_Meier_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:Q837P5_ENTFA_Meier_2023", "name": "Q837P5_ENTFA_Meier_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=Q837P5_ENTFA_Meier_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:Q8WTC7_9CNID_Somermeyer_2022", "name": "Q8WTC7_9CNID_Somermeyer_2022", "category": "DMS substitution", "url": "https://proteingym.org/?search=Q8WTC7_9CNID_Somermeyer_2022", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:R1AB_SARS2_Flynn_2022", "name": "R1AB_SARS2_Flynn_2022", "category": "DMS substitution", "url": "https://proteingym.org/?search=R1AB_SARS2_Flynn_2022", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RAD_ANTMA_Tsuboyama_2023_2CJJ", "name": "RAD_ANTMA_Tsuboyama_2023_2CJJ", "category": "DMS substitution", "url": "https://proteingym.org/?search=RAD_ANTMA_Tsuboyama_2023_2CJJ", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RAF1_HUMAN_Zinkus-Boltz_2019", "name": "RAF1_HUMAN_Zinkus-Boltz_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=RAF1_HUMAN_Zinkus-Boltz_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RASH_HUMAN_Bandaru_2017", "name": "RASH_HUMAN_Bandaru_2017", "category": "DMS substitution", "url": "https://proteingym.org/?search=RASH_HUMAN_Bandaru_2017", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RASK_HUMAN_Weng_2022_abundance", "name": "RASK_HUMAN_Weng_2022_abundance", "category": "DMS substitution", "url": "https://proteingym.org/?search=RASK_HUMAN_Weng_2022_abundance", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RASK_HUMAN_Weng_2022_binding-DARPin_K55", "name": "RASK_HUMAN_Weng_2022_binding-DARPin_K55", "category": "DMS substitution", "url": "https://proteingym.org/?search=RASK_HUMAN_Weng_2022_binding-DARPin_K55", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RBP1_HUMAN_Tsuboyama_2023_2KWH", "name": "RBP1_HUMAN_Tsuboyama_2023_2KWH", "category": "DMS substitution", "url": "https://proteingym.org/?search=RBP1_HUMAN_Tsuboyama_2023_2KWH", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RCD1_ARATH_Tsuboyama_2023_5OAO", "name": "RCD1_ARATH_Tsuboyama_2023_5OAO", "category": "DMS substitution", "url": "https://proteingym.org/?search=RCD1_ARATH_Tsuboyama_2023_5OAO", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RCRO_LAMBD_Tsuboyama_2023_1ORC", "name": "RCRO_LAMBD_Tsuboyama_2023_1ORC", "category": "DMS substitution", "url": "https://proteingym.org/?search=RCRO_LAMBD_Tsuboyama_2023_1ORC", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RD23A_HUMAN_Tsuboyama_2023_1IFY", "name": "RD23A_HUMAN_Tsuboyama_2023_1IFY", "category": "DMS substitution", "url": "https://proteingym.org/?search=RD23A_HUMAN_Tsuboyama_2023_1IFY", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RDRP_I33A0_Li_2023", "name": "RDRP_I33A0_Li_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=RDRP_I33A0_Li_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:REV_HV1H2_Fernandes_2016", "name": "REV_HV1H2_Fernandes_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=REV_HV1H2_Fernandes_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RFAH_ECOLI_Tsuboyama_2023_2LCL", "name": "RFAH_ECOLI_Tsuboyama_2023_2LCL", "category": "DMS substitution", "url": "https://proteingym.org/?search=RFAH_ECOLI_Tsuboyama_2023_2LCL", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RL20_AQUAE_Tsuboyama_2023_1GYZ", "name": "RL20_AQUAE_Tsuboyama_2023_1GYZ", "category": "DMS substitution", "url": "https://proteingym.org/?search=RL20_AQUAE_Tsuboyama_2023_1GYZ", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RL40A_YEAST_Mavor_2016", "name": "RL40A_YEAST_Mavor_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=RL40A_YEAST_Mavor_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RL40A_YEAST_Roscoe_2013", "name": "RL40A_YEAST_Roscoe_2013", "category": "DMS substitution", "url": "https://proteingym.org/?search=RL40A_YEAST_Roscoe_2013", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RL40A_YEAST_Roscoe_2014", "name": "RL40A_YEAST_Roscoe_2014", "category": "DMS substitution", "url": "https://proteingym.org/?search=RL40A_YEAST_Roscoe_2014", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RNC_ECOLI_Weeks_2023", "name": "RNC_ECOLI_Weeks_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=RNC_ECOLI_Weeks_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RPC1_BP434_Tsuboyama_2023_1R69", "name": "RPC1_BP434_Tsuboyama_2023_1R69", "category": "DMS substitution", "url": "https://proteingym.org/?search=RPC1_BP434_Tsuboyama_2023_1R69", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RPC1_LAMBD_Li_2019_high-expression", "name": "RPC1_LAMBD_Li_2019_high-expression", "category": "DMS substitution", "url": "https://proteingym.org/?search=RPC1_LAMBD_Li_2019_high-expression", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RPC1_LAMBD_Li_2019_low-expression", "name": "RPC1_LAMBD_Li_2019_low-expression", "category": "DMS substitution", "url": "https://proteingym.org/?search=RPC1_LAMBD_Li_2019_low-expression", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:RS15_GEOSE_Tsuboyama_2023_1A32", "name": "RS15_GEOSE_Tsuboyama_2023_1A32", "category": "DMS substitution", "url": "https://proteingym.org/?search=RS15_GEOSE_Tsuboyama_2023_1A32", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:S22A1_HUMAN_Yee_2023_abundance", "name": "S22A1_HUMAN_Yee_2023_abundance", "category": "DMS substitution", "url": "https://proteingym.org/?search=S22A1_HUMAN_Yee_2023_abundance", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:S22A1_HUMAN_Yee_2023_activity", "name": "S22A1_HUMAN_Yee_2023_activity", "category": "DMS substitution", "url": "https://proteingym.org/?search=S22A1_HUMAN_Yee_2023_activity", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SAV1_MOUSE_Tsuboyama_2023_2YSB", "name": "SAV1_MOUSE_Tsuboyama_2023_2YSB", "category": "DMS substitution", "url": "https://proteingym.org/?search=SAV1_MOUSE_Tsuboyama_2023_2YSB", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SBI_STAAM_Tsuboyama_2023_2JVG", "name": "SBI_STAAM_Tsuboyama_2023_2JVG", "category": "DMS substitution", "url": "https://proteingym.org/?search=SBI_STAAM_Tsuboyama_2023_2JVG", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SC6A4_HUMAN_Young_2021", "name": "SC6A4_HUMAN_Young_2021", "category": "DMS substitution", "url": "https://proteingym.org/?search=SC6A4_HUMAN_Young_2021", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SCIN_STAAR_Tsuboyama_2023_2QFF", "name": "SCIN_STAAR_Tsuboyama_2023_2QFF", "category": "DMS substitution", "url": "https://proteingym.org/?search=SCIN_STAAR_Tsuboyama_2023_2QFF", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SCN5A_HUMAN_Glazer_2019", "name": "SCN5A_HUMAN_Glazer_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=SCN5A_HUMAN_Glazer_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SDA_BACSU_Tsuboyama_2023_1PV0", "name": "SDA_BACSU_Tsuboyama_2023_1PV0", "category": "DMS substitution", "url": "https://proteingym.org/?search=SDA_BACSU_Tsuboyama_2023_1PV0", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SERC_HUMAN_Xie_2023", "name": "SERC_HUMAN_Xie_2023", "category": "DMS substitution", "url": "https://proteingym.org/?search=SERC_HUMAN_Xie_2023", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SHOC2_HUMAN_Kwon_2022", "name": "SHOC2_HUMAN_Kwon_2022", "category": "DMS substitution", "url": "https://proteingym.org/?search=SHOC2_HUMAN_Kwon_2022", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SOX30_HUMAN_Tsuboyama_2023_7JJK", "name": "SOX30_HUMAN_Tsuboyama_2023_7JJK", "category": "DMS substitution", "url": "https://proteingym.org/?search=SOX30_HUMAN_Tsuboyama_2023_7JJK", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SPA_STAAU_Tsuboyama_2023_1LP1", "name": "SPA_STAAU_Tsuboyama_2023_1LP1", "category": "DMS substitution", "url": "https://proteingym.org/?search=SPA_STAAU_Tsuboyama_2023_1LP1", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SPG1_STRSG_Olson_2014", "name": "SPG1_STRSG_Olson_2014", "category": "DMS substitution", "url": "https://proteingym.org/?search=SPG1_STRSG_Olson_2014", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SPG1_STRSG_Wu_2016", "name": "SPG1_STRSG_Wu_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=SPG1_STRSG_Wu_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SPG2_STRSG_Tsuboyama_2023_5UBS", "name": "SPG2_STRSG_Tsuboyama_2023_5UBS", "category": "DMS substitution", "url": "https://proteingym.org/?search=SPG2_STRSG_Tsuboyama_2023_5UBS", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SPIKE_SARS2_Starr_2020_binding", "name": "SPIKE_SARS2_Starr_2020_binding", "category": "DMS substitution", "url": "https://proteingym.org/?search=SPIKE_SARS2_Starr_2020_binding", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SPIKE_SARS2_Starr_2020_expression", "name": "SPIKE_SARS2_Starr_2020_expression", "category": "DMS substitution", "url": "https://proteingym.org/?search=SPIKE_SARS2_Starr_2020_expression", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SPTN1_CHICK_Tsuboyama_2023_1TUD", "name": "SPTN1_CHICK_Tsuboyama_2023_1TUD", "category": "DMS substitution", "url": "https://proteingym.org/?search=SPTN1_CHICK_Tsuboyama_2023_1TUD", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SQSTM_MOUSE_Tsuboyama_2023_2RRU", "name": "SQSTM_MOUSE_Tsuboyama_2023_2RRU", "category": "DMS substitution", "url": "https://proteingym.org/?search=SQSTM_MOUSE_Tsuboyama_2023_2RRU", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SR43C_ARATH_Tsuboyama_2023_2N88", "name": "SR43C_ARATH_Tsuboyama_2023_2N88", "category": "DMS substitution", "url": "https://proteingym.org/?search=SR43C_ARATH_Tsuboyama_2023_2N88", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SRBS1_HUMAN_Tsuboyama_2023_2O2W", "name": "SRBS1_HUMAN_Tsuboyama_2023_2O2W", "category": "DMS substitution", "url": "https://proteingym.org/?search=SRBS1_HUMAN_Tsuboyama_2023_2O2W", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SRC_HUMAN_Ahler_2019", "name": "SRC_HUMAN_Ahler_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=SRC_HUMAN_Ahler_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SRC_HUMAN_Chakraborty_2023_binding-DAS_25uM", "name": "SRC_HUMAN_Chakraborty_2023_binding-DAS_25uM", "category": "DMS substitution", "url": "https://proteingym.org/?search=SRC_HUMAN_Chakraborty_2023_binding-DAS_25uM", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SRC_HUMAN_Nguyen_2022", "name": "SRC_HUMAN_Nguyen_2022", "category": "DMS substitution", "url": "https://proteingym.org/?search=SRC_HUMAN_Nguyen_2022", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SUMO1_HUMAN_Weile_2017", "name": "SUMO1_HUMAN_Weile_2017", "category": "DMS substitution", "url": "https://proteingym.org/?search=SUMO1_HUMAN_Weile_2017", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:SYUA_HUMAN_Newberry_2020", "name": "SYUA_HUMAN_Newberry_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=SYUA_HUMAN_Newberry_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:TADBP_HUMAN_Bolognesi_2019", "name": "TADBP_HUMAN_Bolognesi_2019", "category": "DMS substitution", "url": "https://proteingym.org/?search=TADBP_HUMAN_Bolognesi_2019", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:TAT_HV1BR_Fernandes_2016", "name": "TAT_HV1BR_Fernandes_2016", "category": "DMS substitution", "url": "https://proteingym.org/?search=TAT_HV1BR_Fernandes_2016", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:TCRG1_MOUSE_Tsuboyama_2023_1E0L", "name": "TCRG1_MOUSE_Tsuboyama_2023_1E0L", "category": "DMS substitution", "url": "https://proteingym.org/?search=TCRG1_MOUSE_Tsuboyama_2023_1E0L", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:THO1_YEAST_Tsuboyama_2023_2WQG", "name": "THO1_YEAST_Tsuboyama_2023_2WQG", "category": "DMS substitution", "url": "https://proteingym.org/?search=THO1_YEAST_Tsuboyama_2023_2WQG", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:TNKS2_HUMAN_Tsuboyama_2023_5JRT", "name": "TNKS2_HUMAN_Tsuboyama_2023_5JRT", "category": "DMS substitution", "url": "https://proteingym.org/?search=TNKS2_HUMAN_Tsuboyama_2023_5JRT", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:TPK1_HUMAN_Weile_2017", "name": "TPK1_HUMAN_Weile_2017", "category": "DMS substitution", "url": "https://proteingym.org/?search=TPK1_HUMAN_Weile_2017", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:TPMT_HUMAN_Matreyek_2018", "name": "TPMT_HUMAN_Matreyek_2018", "category": "DMS substitution", "url": "https://proteingym.org/?search=TPMT_HUMAN_Matreyek_2018", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:TPOR_HUMAN_Bridgford_2020", "name": "TPOR_HUMAN_Bridgford_2020", "category": "DMS substitution", "url": "https://proteingym.org/?search=TPOR_HUMAN_Bridgford_2020", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:TRPC_SACS2_Chan_2017", "name": "TRPC_SACS2_Chan_2017", "category": "DMS substitution", "url": "https://proteingym.org/?search=TRPC_SACS2_Chan_2017", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:TRPC_THEMA_Chan_2017", "name": "TRPC_THEMA_Chan_2017", "category": "DMS substitution", "url": "https://proteingym.org/?search=TRPC_THEMA_Chan_2017", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:UBC9_HUMAN_Weile_2017", "name": "UBC9_HUMAN_Weile_2017", "category": "DMS substitution", "url": "https://proteingym.org/?search=UBC9_HUMAN_Weile_2017", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:UBE4B_HUMAN_Tsuboyama_2023_3L1X", "name": "UBE4B_HUMAN_Tsuboyama_2023_3L1X", "category": "DMS substitution", "url": "https://proteingym.org/?search=UBE4B_HUMAN_Tsuboyama_2023_3L1X", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:UBE4B_MOUSE_Starita_2013", "name": "UBE4B_MOUSE_Starita_2013", "category": "DMS substitution", "url": "https://proteingym.org/?search=UBE4B_MOUSE_Starita_2013", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:UBR5_HUMAN_Tsuboyama_2023_1I2T", "name": "UBR5_HUMAN_Tsuboyama_2023_1I2T", "category": "DMS substitution", "url": "https://proteingym.org/?search=UBR5_HUMAN_Tsuboyama_2023_1I2T", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:VG08_BPP22_Tsuboyama_2023_2GP8", "name": "VG08_BPP22_Tsuboyama_2023_2GP8", "category": "DMS substitution", "url": "https://proteingym.org/?search=VG08_BPP22_Tsuboyama_2023_2GP8", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:VILI_CHICK_Tsuboyama_2023_1YU5", "name": "VILI_CHICK_Tsuboyama_2023_1YU5", "category": "DMS substitution", "url": "https://proteingym.org/?search=VILI_CHICK_Tsuboyama_2023_1YU5", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:VKOR1_HUMAN_Chiasson_2020_abundance", "name": "VKOR1_HUMAN_Chiasson_2020_abundance", "category": "DMS substitution", "url": "https://proteingym.org/?search=VKOR1_HUMAN_Chiasson_2020_abundance", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:VKOR1_HUMAN_Chiasson_2020_activity", "name": "VKOR1_HUMAN_Chiasson_2020_activity", "category": "DMS substitution", "url": "https://proteingym.org/?search=VKOR1_HUMAN_Chiasson_2020_activity", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:VRPI_BPT7_Tsuboyama_2023_2WNM", "name": "VRPI_BPT7_Tsuboyama_2023_2WNM", "category": "DMS substitution", "url": "https://proteingym.org/?search=VRPI_BPT7_Tsuboyama_2023_2WNM", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:YAIA_ECOLI_Tsuboyama_2023_2KVT", "name": "YAIA_ECOLI_Tsuboyama_2023_2KVT", "category": "DMS substitution", "url": "https://proteingym.org/?search=YAIA_ECOLI_Tsuboyama_2023_2KVT", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:YAP1_HUMAN_Araya_2012", "name": "YAP1_HUMAN_Araya_2012", "category": "DMS substitution", "url": "https://proteingym.org/?search=YAP1_HUMAN_Araya_2012", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:subs:YNZC_BACSU_Tsuboyama_2023_2JVD", "name": "YNZC_BACSU_Tsuboyama_2023_2JVD", "category": "DMS substitution", "url": "https://proteingym.org/?search=YNZC_BACSU_Tsuboyama_2023_2JVD", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:A4_HUMAN_Seuma_2022_indels", "name": "A4_HUMAN_Seuma_2022_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=A4_HUMAN_Seuma_2022_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:AMFR_HUMAN_Tsuboyama_2023_4G3O_indels", "name": "AMFR_HUMAN_Tsuboyama_2023_4G3O_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=AMFR_HUMAN_Tsuboyama_2023_4G3O_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:ARGR_ECOLI_Tsuboyama_2023_1AOY_indels", "name": "ARGR_ECOLI_Tsuboyama_2023_1AOY_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=ARGR_ECOLI_Tsuboyama_2023_1AOY_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:B1LPA6_ECOSM_Russ_2020_indels", "name": "B1LPA6_ECOSM_Russ_2020_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=B1LPA6_ECOSM_Russ_2020_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:BBC1_YEAST_Tsuboyama_2023_1TG0_indels", "name": "BBC1_YEAST_Tsuboyama_2023_1TG0_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=BBC1_YEAST_Tsuboyama_2023_1TG0_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:BCHB_CHLTE_Tsuboyama_2023_2KRU_indels", "name": "BCHB_CHLTE_Tsuboyama_2023_2KRU_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=BCHB_CHLTE_Tsuboyama_2023_2KRU_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:BLAT_ECOLX_Gonzalez_2019_indels", "name": "BLAT_ECOLX_Gonzalez_2019_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=BLAT_ECOLX_Gonzalez_2019_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:CAPSD_AAV2S_Sinai_2021_designed_indels", "name": "CAPSD_AAV2S_Sinai_2021_designed_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=CAPSD_AAV2S_Sinai_2021_designed_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:CAPSD_AAV2S_Sinai_2021_library_indels", "name": "CAPSD_AAV2S_Sinai_2021_library_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=CAPSD_AAV2S_Sinai_2021_library_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:CATR_CHLRE_Tsuboyama_2023_2AMI_indels", "name": "CATR_CHLRE_Tsuboyama_2023_2AMI_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=CATR_CHLRE_Tsuboyama_2023_2AMI_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:CBPA2_HUMAN_Tsuboyama_2023_1O6X_indels", "name": "CBPA2_HUMAN_Tsuboyama_2023_1O6X_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=CBPA2_HUMAN_Tsuboyama_2023_1O6X_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:CBX4_HUMAN_Tsuboyama_2023_2K28_indels", "name": "CBX4_HUMAN_Tsuboyama_2023_2K28_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=CBX4_HUMAN_Tsuboyama_2023_2K28_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:CSN4_MOUSE_Tsuboyama_2023_1UFM_indels", "name": "CSN4_MOUSE_Tsuboyama_2023_1UFM_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=CSN4_MOUSE_Tsuboyama_2023_1UFM_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:CUE1_YEAST_Tsuboyama_2023_2MYX_indels", "name": "CUE1_YEAST_Tsuboyama_2023_2MYX_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=CUE1_YEAST_Tsuboyama_2023_2MYX_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:DN7A_SACS2_Tsuboyama_2023_1JIC_indels", "name": "DN7A_SACS2_Tsuboyama_2023_1JIC_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=DN7A_SACS2_Tsuboyama_2023_1JIC_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:DNJA1_HUMAN_Tsuboyama_2023_2LO1_indels", "name": "DNJA1_HUMAN_Tsuboyama_2023_2LO1_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=DNJA1_HUMAN_Tsuboyama_2023_2LO1_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:DOCK1_MOUSE_Tsuboyama_2023_2M0Y_indels", "name": "DOCK1_MOUSE_Tsuboyama_2023_2M0Y_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=DOCK1_MOUSE_Tsuboyama_2023_2M0Y_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:EPHB2_HUMAN_Tsuboyama_2023_1F0M_indels", "name": "EPHB2_HUMAN_Tsuboyama_2023_1F0M_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=EPHB2_HUMAN_Tsuboyama_2023_1F0M_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:FECA_ECOLI_Tsuboyama_2023_2D1U_indels", "name": "FECA_ECOLI_Tsuboyama_2023_2D1U_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=FECA_ECOLI_Tsuboyama_2023_2D1U_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:HCP_LAMBD_Tsuboyama_2023_2L6Q_indels", "name": "HCP_LAMBD_Tsuboyama_2023_2L6Q_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=HCP_LAMBD_Tsuboyama_2023_2L6Q_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:HECD1_HUMAN_Tsuboyama_2023_3DKM_indels", "name": "HECD1_HUMAN_Tsuboyama_2023_3DKM_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=HECD1_HUMAN_Tsuboyama_2023_3DKM_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:HIS7_YEAST_Pokusaeva_2019_indels", "name": "HIS7_YEAST_Pokusaeva_2019_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=HIS7_YEAST_Pokusaeva_2019_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:ILF3_HUMAN_Tsuboyama_2023_2L33_indels", "name": "ILF3_HUMAN_Tsuboyama_2023_2L33_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=ILF3_HUMAN_Tsuboyama_2023_2L33_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:KCNJ2_MOUSE_Macdonald_2022_indels", "name": "KCNJ2_MOUSE_Macdonald_2022_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=KCNJ2_MOUSE_Macdonald_2022_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:MAFG_MOUSE_Tsuboyama_2023_1K1V_indels", "name": "MAFG_MOUSE_Tsuboyama_2023_1K1V_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=MAFG_MOUSE_Tsuboyama_2023_1K1V_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:MBD11_ARATH_Tsuboyama_2023_6ACV_indels", "name": "MBD11_ARATH_Tsuboyama_2023_6ACV_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=MBD11_ARATH_Tsuboyama_2023_6ACV_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:MYO3_YEAST_Tsuboyama_2023_2BTT_indels", "name": "MYO3_YEAST_Tsuboyama_2023_2BTT_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=MYO3_YEAST_Tsuboyama_2023_2BTT_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:NKX31_HUMAN_Tsuboyama_2023_2L9R_indels", "name": "NKX31_HUMAN_Tsuboyama_2023_2L9R_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=NKX31_HUMAN_Tsuboyama_2023_2L9R_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:NUSA_ECOLI_Tsuboyama_2023_1WCL_indels", "name": "NUSA_ECOLI_Tsuboyama_2023_1WCL_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=NUSA_ECOLI_Tsuboyama_2023_1WCL_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:NUSG_MYCTU_Tsuboyama_2023_2MI6_indels", "name": "NUSG_MYCTU_Tsuboyama_2023_2MI6_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=NUSG_MYCTU_Tsuboyama_2023_2MI6_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:OBSCN_HUMAN_Tsuboyama_2023_1V1C_indels", "name": "OBSCN_HUMAN_Tsuboyama_2023_1V1C_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=OBSCN_HUMAN_Tsuboyama_2023_1V1C_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:ODP2_GEOSE_Tsuboyama_2023_1W4G_indels", "name": "ODP2_GEOSE_Tsuboyama_2023_1W4G_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=ODP2_GEOSE_Tsuboyama_2023_1W4G_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:OTU7A_HUMAN_Tsuboyama_2023_2L2D_indels", "name": "OTU7A_HUMAN_Tsuboyama_2023_2L2D_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=OTU7A_HUMAN_Tsuboyama_2023_2L2D_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:P53_HUMAN_Kotler_2018_indels", "name": "P53_HUMAN_Kotler_2018_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=P53_HUMAN_Kotler_2018_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:PIN1_HUMAN_Tsuboyama_2023_1I6C_indels", "name": "PIN1_HUMAN_Tsuboyama_2023_1I6C_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=PIN1_HUMAN_Tsuboyama_2023_1I6C_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:PITX2_HUMAN_Tsuboyama_2023_2L7M_indels", "name": "PITX2_HUMAN_Tsuboyama_2023_2L7M_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=PITX2_HUMAN_Tsuboyama_2023_2L7M_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:PKN1_HUMAN_Tsuboyama_2023_1URF_indels", "name": "PKN1_HUMAN_Tsuboyama_2023_1URF_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=PKN1_HUMAN_Tsuboyama_2023_1URF_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:POLG_PESV_Tsuboyama_2023_2MXD_indels", "name": "POLG_PESV_Tsuboyama_2023_2MXD_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=POLG_PESV_Tsuboyama_2023_2MXD_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:PR40A_HUMAN_Tsuboyama_2023_1UZC_indels", "name": "PR40A_HUMAN_Tsuboyama_2023_1UZC_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=PR40A_HUMAN_Tsuboyama_2023_1UZC_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:PSAE_PICP2_Tsuboyama_2023_1PSE_indels", "name": "PSAE_PICP2_Tsuboyama_2023_1PSE_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=PSAE_PICP2_Tsuboyama_2023_1PSE_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:PTEN_HUMAN_Mighell_2018_indels", "name": "PTEN_HUMAN_Mighell_2018_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=PTEN_HUMAN_Mighell_2018_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:Q8EG35_SHEON_Campbell_2022_indels", "name": "Q8EG35_SHEON_Campbell_2022_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=Q8EG35_SHEON_Campbell_2022_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:RAD_ANTMA_Tsuboyama_2023_2CJJ_indels", "name": "RAD_ANTMA_Tsuboyama_2023_2CJJ_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=RAD_ANTMA_Tsuboyama_2023_2CJJ_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:RCD1_ARATH_Tsuboyama_2023_5OAO_indels", "name": "RCD1_ARATH_Tsuboyama_2023_5OAO_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=RCD1_ARATH_Tsuboyama_2023_5OAO_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:RD23A_HUMAN_Tsuboyama_2023_1IFY_indels", "name": "RD23A_HUMAN_Tsuboyama_2023_1IFY_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=RD23A_HUMAN_Tsuboyama_2023_1IFY_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:RPC1_BP434_Tsuboyama_2023_1R69_indels", "name": "RPC1_BP434_Tsuboyama_2023_1R69_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=RPC1_BP434_Tsuboyama_2023_1R69_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:RS15_GEOSE_Tsuboyama_2023_1A32_indels", "name": "RS15_GEOSE_Tsuboyama_2023_1A32_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=RS15_GEOSE_Tsuboyama_2023_1A32_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:S22A1_HUMAN_Yee_2023_abundance_indels", "name": "S22A1_HUMAN_Yee_2023_abundance_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=S22A1_HUMAN_Yee_2023_abundance_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:S22A1_HUMAN_Yee_2023_activity_indels", "name": "S22A1_HUMAN_Yee_2023_activity_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=S22A1_HUMAN_Yee_2023_activity_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:SAV1_MOUSE_Tsuboyama_2023_2YSB_indels", "name": "SAV1_MOUSE_Tsuboyama_2023_2YSB_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=SAV1_MOUSE_Tsuboyama_2023_2YSB_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:SDA_BACSU_Tsuboyama_2023_1PV0_indels", "name": "SDA_BACSU_Tsuboyama_2023_1PV0_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=SDA_BACSU_Tsuboyama_2023_1PV0_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:SOX30_HUMAN_Tsuboyama_2023_7JJK_indels", "name": "SOX30_HUMAN_Tsuboyama_2023_7JJK_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=SOX30_HUMAN_Tsuboyama_2023_7JJK_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:SPG2_STRSG_Tsuboyama_2023_5UBS_indels", "name": "SPG2_STRSG_Tsuboyama_2023_5UBS_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=SPG2_STRSG_Tsuboyama_2023_5UBS_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:SPTN1_CHICK_Tsuboyama_2023_1TUD_indels", "name": "SPTN1_CHICK_Tsuboyama_2023_1TUD_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=SPTN1_CHICK_Tsuboyama_2023_1TUD_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:SQSTM_MOUSE_Tsuboyama_2023_2RRU_indels", "name": "SQSTM_MOUSE_Tsuboyama_2023_2RRU_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=SQSTM_MOUSE_Tsuboyama_2023_2RRU_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:SR43C_ARATH_Tsuboyama_2023_2N88_indels", "name": "SR43C_ARATH_Tsuboyama_2023_2N88_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=SR43C_ARATH_Tsuboyama_2023_2N88_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:SRBS1_HUMAN_Tsuboyama_2023_2O2W_indels", "name": "SRBS1_HUMAN_Tsuboyama_2023_2O2W_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=SRBS1_HUMAN_Tsuboyama_2023_2O2W_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:TCRG1_MOUSE_Tsuboyama_2023_1E0L_indels", "name": "TCRG1_MOUSE_Tsuboyama_2023_1E0L_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=TCRG1_MOUSE_Tsuboyama_2023_1E0L_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:THO1_YEAST_Tsuboyama_2023_2WQG_indels", "name": "THO1_YEAST_Tsuboyama_2023_2WQG_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=THO1_YEAST_Tsuboyama_2023_2WQG_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:TNKS2_HUMAN_Tsuboyama_2023_5JRT_indels", "name": "TNKS2_HUMAN_Tsuboyama_2023_5JRT_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=TNKS2_HUMAN_Tsuboyama_2023_5JRT_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:UBE4B_HUMAN_Tsuboyama_2023_3L1X_indels", "name": "UBE4B_HUMAN_Tsuboyama_2023_3L1X_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=UBE4B_HUMAN_Tsuboyama_2023_3L1X_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:UBR5_HUMAN_Tsuboyama_2023_1I2T_indels", "name": "UBR5_HUMAN_Tsuboyama_2023_1I2T_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=UBR5_HUMAN_Tsuboyama_2023_1I2T_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:VG08_BPP22_Tsuboyama_2023_2GP8_indels", "name": "VG08_BPP22_Tsuboyama_2023_2GP8_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=VG08_BPP22_Tsuboyama_2023_2GP8_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:VILI_CHICK_Tsuboyama_2023_1YU5_indels", "name": "VILI_CHICK_Tsuboyama_2023_1YU5_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=VILI_CHICK_Tsuboyama_2023_1YU5_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:VRPI_BPT7_Tsuboyama_2023_2WNM_indels", "name": "VRPI_BPT7_Tsuboyama_2023_2WNM_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=VRPI_BPT7_Tsuboyama_2023_2WNM_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" }, { "id": "proteingym:indels:YNZC_BACSU_Tsuboyama_2023_2JVD_indels", "name": "YNZC_BACSU_Tsuboyama_2023_2JVD_indels", "category": "DMS indel", "url": "https://proteingym.org/?search=YNZC_BACSU_Tsuboyama_2023_2JVD_indels", "leaderboard_url": "https://proteingym.org/benchmarks", "paper_url": "https://doi.org/10.1101/2023.12.07.570727" } ], "hosted_benchmarks_count": 283 }, { "id": "elixir", "name": "ELIXIR Infrastructure", "kind": "consortium", "url": "https://elixir-europe.org/", "github": "N/A", "description": "European life-science data infrastructure hosting benchmark-relevant resources (UniProt, Ensembl, ChEMBL, PDBe, IntAct).", "benchmarks_tracked": 18, "benchmark_count_asof": "2026-05-12", "count_methodology": "ELIXIR Core Data Resources list 2026-05: ~18 resources with benchmark/leaderboard components.", "breakdown": { "core_data_resources": 18, "member_nodes": 23 }, "host_organization": "EMBL-EBI + 23 EU member nodes", "primary_contacts": [ "Niklas Blomberg", "Andrew Smith" ], "founded": "2013", "license_model": "Mostly CC-BY", "flags": [], "rubric": { "rigor": 5, "coverage": 5, "maintenance": 5, "adoption": 5, "quality": 5, "accessibility": 5, "industry_relevance": 4 }, "notes": "Meta-resource of meta-resources.", "composite_score": 97.5, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "cameo", "name": "CAMEO", "kind": "competition", "url": "https://www.cameo3d.org/", "github": "N/A", "description": "Continuous weekly blind eval of protein 3D / multimer / ligand prediction using pre-release PDB structures.", "benchmarks_tracked": 4, "benchmark_count_asof": "2026-05-12", "count_methodology": "cameo3d.org 2026-05: 4 active categories \u2014 3D monomer, 3D multimer, model quality, ligand pocket; ~1000 targets/year.", "breakdown": { "monomer": 1, "multimer": 1, "quality_estimation": 1, "ligand": 1 }, "host_organization": "Biozentrum Basel + SIB", "primary_contacts": [ "Torsten Schwede", "J\u00fcrgen Haas" ], "founded": "2013", "license_model": "CC-BY 4.0", "flags": [], "rubric": { "rigor": 5, "coverage": 4, "maintenance": 5, "adoption": 5, "quality": 5, "accessibility": 5, "industry_relevance": 4 }, "notes": "Excellent continuous cadence complementing CASP.", "composite_score": 94.4, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "posebusters-initiative", "name": "PoseBusters Evaluation Suite", "kind": "meta-platform", "url": "https://posebusters.readthedocs.io/", "github": "https://github.com/maabuu/posebusters", "description": "Physics-aware validation of docking/co-folding poses; 19 checks + curated test sets.", "benchmarks_tracked": 3, "benchmark_count_asof": "2026-05-12", "count_methodology": "GitHub README: PoseBusters v1 (308 complexes), v2 (428), Astex Diverse Set (85) = 3 canonical suites.", "breakdown": { "test_sets": 3, "validation_checks": 19 }, "host_organization": "Oxford OPIG (Deane Lab)", "primary_contacts": [ "Charlotte Deane", "Martin Buttenschoen" ], "founded": "2023-08", "license_model": "BSD-3-Clause", "flags": [], "rubric": { "rigor": 5, "coverage": 3, "maintenance": 5, "adoption": 5, "quality": 5, "accessibility": 5, "industry_relevance": 5 }, "notes": "Changed pose-prediction evaluation norms; default pharma filter now.", "composite_score": 93.9, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "plinder-initiative", "name": "PLINDER / PINDER", "kind": "meta-platform", "url": "https://www.plinder.sh/", "github": "https://github.com/plinder-org/plinder", "description": "Leakage-controlled protein-ligand (PLINDER) and protein-protein (PINDER) docking datasets.", "benchmarks_tracked": 2, "benchmark_count_asof": "2026-05-12", "count_methodology": "plinder.sh + pinder.sh: 2 major benchmarks (PLINDER 460k systems, PINDER 267k systems).", "breakdown": { "plinder_systems": 460000, "pinder_systems": 267498 }, "host_organization": "Biozentrum Basel + VantAI + Isomorphic Labs + EPFL", "primary_contacts": [ "Torsten Schwede", "Max Jaderberg", "Andreas Fischer" ], "founded": "2024-07", "license_model": "CC-BY 4.0", "flags": [], "rubric": { "rigor": 5, "coverage": 4, "maintenance": 5, "adoption": 4, "quality": 5, "accessibility": 5, "industry_relevance": 5 }, "notes": "Replacing PDBbind/CASF for modern docking ML eval.", "composite_score": 93.9, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "openproblems", "name": "Open Problems in Single-Cell Analysis", "kind": "consortium", "url": "https://openproblems.bio/", "github": "https://github.com/openproblems-bio/openproblems", "description": "Community benchmark suite for single-cell analysis with reproducible Viash/Nextflow pipelines and NeurIPS tracks.", "benchmarks_tracked": 29, "benchmark_count_asof": "2026-05-12", "count_methodology": "openproblems.bio task registry + Luecken et al. Nat Biotech 2025: 29 benchmark tasks (batch integration, denoising, dim-reduction, label projection, perturbation, spatial, multimodal).", "breakdown": { "batch_integration": 3, "perturbation": 4, "multimodal": 6, "label_transfer": 4, "spatial": 5, "other": 7 }, "host_organization": "CZI + Helmholtz Munich + Yale + HMS", "primary_contacts": [ "Fabian Theis", "Malte Luecken", "Daniel Burkhardt", "Sandrine Dudoit" ], "founded": "2021-06", "license_model": "MIT", "flags": [], "rubric": { "rigor": 5, "coverage": 5, "maintenance": 5, "adoption": 4, "quality": 5, "accessibility": 5, "industry_relevance": 3 }, "notes": "Gold-standard single-cell benchmarking rigor; Nat Biotech 2025.", "composite_score": 91.9, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "polaris", "name": "Polaris Hub", "kind": "meta-platform", "url": "https://polarishub.io/", "github": "https://github.com/polaris-hub/polaris", "description": "Industry-curated small-molecule benchmarks with working groups on method-comparison standards.", "benchmarks_tracked": 48, "benchmark_count_asof": "2026-05-12", "count_methodology": "polarishub.io/benchmarks public listing 2026-05: ~48 public benchmarks across Recursion, Valence, Novartis, AstraZeneca, Polaris Small Molecule Steering Committee orgs.", "breakdown": { "public_benchmarks": 48, "datasets": 60, "competitions": 4 }, "host_organization": "Polaris consortium (Valence Labs, Recursion, Novartis, Pfizer, Merck, AstraZeneca)", "primary_contacts": [ "Cas Wognum", "Emmanuel Noutahi", "Jonathan Hsu" ], "founded": "2023-10", "license_model": "CC-BY or Polaris Community License per benchmark", "flags": [], "rubric": { "rigor": 5, "coverage": 4, "maintenance": 5, "adoption": 4, "quality": 5, "accessibility": 4, "industry_relevance": 5 }, "notes": "Industry-led counterweight to academic benchmarks. Strong on method-comparison rigor.", "composite_score": 91.4, "hosted_benchmarks": [ { "id": "polaris:benchmark:egfr-binders-binary-cls-v0", "name": "EGFR_binders_binary_cls-v0", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:pkis2-ret-wt-reg-v2", "name": "pkis2-ret-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-solu-reg-v1", "name": "adme-fang-SOLU-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_SOLUBILITY", "url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl4203-ki", "name": "moleculeace-CHEMBL4203-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-perm-reg-v1", "name": "adme-fang-PERM-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-1", "name": "adme-fang-RPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl236-ki", "name": "moleculeace-CHEMBL236-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl264-ki", "name": "moleculeace-CHEMBL264-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:zinc12k-v1", "name": "zinc12k-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/zinc12k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/zinc12k-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1862-ki", "name": "moleculeace-CHEMBL1862-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2835-ki", "name": "moleculeace-CHEMBL2835-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2047-ec50", "name": "moleculeace-CHEMBL2047-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-expression", "name": "bend-zeroshot-variant-effects-expression", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "metric": "roc_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v1", "name": "EGFR_binders_binary_cls-v1", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:moleculeace-chembl219-ki", "name": "moleculeace-CHEMBL219-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ec50", "name": "moleculeace-CHEMBL237-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bioavailability-ma", "name": "bioavailability-ma", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bioavailability-ma", "leaderboard_url": "https://polarishub.io/benchmarks/bioavailability-ma", "metric": "roc_auc" }, { "id": "polaris:benchmark:pkis2-lok-slk-c-1", "name": "pkis2-lok-slk-c-1", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "leaderboard_url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-250k-reg-v2", "name": "molprop-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-ret-wt-c-1", "name": "pkis2-ret-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-perm-1", "name": "adme-fang-PERM-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-c-1", "name": "pkis1-egfr-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-rclint-reg-v1", "name": "adme-fang-RCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-reg-v2", "name": "pkis2-kit-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bbb-martins", "name": "bbb-martins", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bbb-martins", "leaderboard_url": "https://polarishub.io/benchmarks/bbb-martins", "metric": "roc_auc" }, { "id": "polaris:benchmark:tox21-v1", "name": "tox21-v1", "category": "toxicity,multitask", "description": "A multitask classification benchmark for Tox21 challenge.", "url": "https://polarishub.io/benchmarks/tox21-v1", "leaderboard_url": "https://polarishub.io/benchmarks/tox21-v1", "metric": "f1" }, { "id": "polaris:benchmark:pkis2-ret-wt-r-1", "name": "pkis2-ret-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hppb-1", "name": "adme-fang-HPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HPPB", "url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-egfr-wt-r-1", "name": "pkis2-egfr-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1871-ki", "name": "moleculeace-CHEMBL1871-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl228-ki", "name": "moleculeace-CHEMBL228-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp2c9-veith", "name": "cyp2c9-veith", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-veith", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-veith", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl235-ec50", "name": "moleculeace-CHEMBL235-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-r-1", "name": "pkis1-egfr-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-egfr-wt-reg-v2", "name": "pkis2-egfr-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:molprop-250k-r-1", "name": "molprop-250k-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hclint-reg-v1", "name": "adme-fang-HCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl3979-ec50", "name": "moleculeace-CHEMBL3979-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl233-ki", "name": "moleculeace-CHEMBL233-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl238-ki", "name": "moleculeace-CHEMBL238-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:half-life-obach", "name": "half-life-obach", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/half-life-obach", "leaderboard_url": "https://polarishub.io/benchmarks/half-life-obach", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl234-ki", "name": "moleculeace-CHEMBL234-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ames", "name": "ames", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ames", "leaderboard_url": "https://polarishub.io/benchmarks/ames", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-reg", "name": "adme-novartis-cyp3a4-reg", "category": "ADME,SingleTask", "description": "Single regression task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "metric": "absolute_average_fold_error" }, { "id": "polaris:benchmark:dili", "name": "dili", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/dili", "leaderboard_url": "https://polarishub.io/benchmarks/dili", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4616-ec50", "name": "moleculeace-CHEMBL4616-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2971-ki", "name": "moleculeace-CHEMBL2971-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ki", "name": "moleculeace-CHEMBL237-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rclint-1", "name": "adme-fang-RCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl231-ki", "name": "moleculeace-CHEMBL231-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl4792-ki", "name": "moleculeace-CHEMBL4792-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-cls-v2", "name": "pkis2-lok-slk-cls-v2", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "multitask", "description": "A multitask classification benchmark for binding predictions.", "url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "metric": "f1" }, { "id": "polaris:benchmark:qm9-v1", "name": "qm9-v1", "category": "multitask", "description": "A multitask regression benchmark for QM9 dataset", "url": "https://polarishub.io/benchmarks/qm9-v1", "leaderboard_url": "https://polarishub.io/benchmarks/qm9-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2034-ki", "name": "moleculeace-CHEMBL2034-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ppbr-az", "name": "ppbr-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ppbr-az", "leaderboard_url": "https://polarishub.io/benchmarks/ppbr-az", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl287-ki", "name": "moleculeace-CHEMBL287-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:herg", "name": "herg", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/herg", "leaderboard_url": "https://polarishub.io/benchmarks/herg", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4005-ki", "name": "moleculeace-CHEMBL4005-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:vdss-lombardo", "name": "vdss-lombardo", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/vdss-lombardo", "leaderboard_url": "https://polarishub.io/benchmarks/vdss-lombardo", "metric": "spearmanr" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-disease", "name": "bend-zeroshot-variant-effects-disease", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-fang-hclint-1", "name": "adme-fang-HCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-r-1", "name": "pkis2-kit-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl262-ki", "name": "moleculeace-CHEMBL262-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:rna-expression-prediction-dataset-task", "name": "rna-expression-prediction-dataset-task", "category": "benchmark", "description": "RNA expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:rxrx-compound-gene-activity-benchmark", "name": "RxRx-compound-gene-activity-benchmark", "category": "gene,compound", "description": "This benchmark evaluates the zero-shot prediction of compound-gene activity. It is originally designed to be used with the rxrx.ai dataset releases in phenomics.", "url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "metric": "pr_auc_mean" }, { "id": "polaris:benchmark:posebusters-v1", "name": "posebusters_v1", "category": "Docking,SingleTask", "description": "Docking task benchmark for 428 proteins and ligands.", "url": "https://polarishub.io/benchmarks/posebusters-v1", "leaderboard_url": "https://polarishub.io/benchmarks/posebusters-v1", "metric": "rmsd_coverage" }, { "id": "polaris:benchmark:moleculeace-chembl204-ki", "name": "moleculeace-CHEMBL204-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-r-1", "name": "adme-fang-r-1", "category": "adme,multitask", "description": "A multitask benchmark for six ADME endpoints, utilizing a shared random split. ", "url": "https://polarishub.io/benchmarks/adme-fang-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:caco2-wang", "name": "caco2-wang", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/caco2-wang", "leaderboard_url": "https://polarishub.io/benchmarks/caco2-wang", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-r-1", "name": "pkis2-lok-slk-r-1", "category": "kinase,hit-discovery", "description": "Multitask regression benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hello-world-benchmark", "name": "hello-world-benchmark", "category": "benchmark", "description": "Single task regression for solibility", "url": "https://polarishub.io/benchmarks/hello-world-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/hello-world-benchmark", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-cls-v2", "name": "pkis2-kit-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis2-ret-wt-cls-v2", "name": "pkis2-ret-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-c-1", "name": "pkis1-kit-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-r-1", "name": "pkis1-kit-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-cls", "name": "adme-novartis-cyp3a4-cls", "category": "ADME,SingleTask", "description": "Single classification task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:molprop-250k-leadlike-r-1", "name": "molprop-250k-leadlike-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 leadlike compounds sourced from ZINC22, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-ret-wt-mut-c-1", "name": "pkis1-ret-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "Multitask classification benchmark for RET wild type, mutant V804L, and mutant Y791F.", "url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pgp-broccatelli", "name": "pgp-broccatelli", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/pgp-broccatelli", "leaderboard_url": "https://polarishub.io/benchmarks/pgp-broccatelli", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl218-ec50", "name": "moleculeace-CHEMBL218-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-reg-v1", "name": "adme-fang-RPPB-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl214-ki", "name": "moleculeace-CHEMBL214-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "leaderboard_url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-leadlike-250k-reg-v2", "name": "molprop-leadlike-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cho-dna-expression-prediction-dataset-task", "name": "cho-dna-expression-prediction-dataset-task", "category": "benchmark", "description": "DNA CHO gene expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl2147-ki", "name": "moleculeace-CHEMBL2147-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "metric": "roc_auc" }, { "id": "polaris:benchmark:clearance-microsome-az", "name": "clearance-microsome-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-microsome-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-microsome-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl239-ec50", "name": "moleculeace-CHEMBL239-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl244-ki", "name": "moleculeace-CHEMBL244-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hia-hou", "name": "hia-hou", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/hia-hou", "leaderboard_url": "https://polarishub.io/benchmarks/hia-hou", "metric": "roc_auc" }, { "id": "polaris:benchmark:ld50-zhu", "name": "ld50-zhu", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ld50-zhu", "leaderboard_url": "https://polarishub.io/benchmarks/ld50-zhu", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-c-1", "name": "pkis2-kit-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v0", "name": "EGFR_binders_binary_cls-v0", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:pkis2-ret-wt-reg-v2", "name": "pkis2-ret-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-solu-reg-v1", "name": "adme-fang-SOLU-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_SOLUBILITY", "url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl4203-ki", "name": "moleculeace-CHEMBL4203-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-perm-reg-v1", "name": "adme-fang-PERM-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-1", "name": "adme-fang-RPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl236-ki", "name": "moleculeace-CHEMBL236-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl264-ki", "name": "moleculeace-CHEMBL264-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:zinc12k-v1", "name": "zinc12k-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/zinc12k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/zinc12k-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1862-ki", "name": "moleculeace-CHEMBL1862-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2835-ki", "name": "moleculeace-CHEMBL2835-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2047-ec50", "name": "moleculeace-CHEMBL2047-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-expression", "name": "bend-zeroshot-variant-effects-expression", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "metric": "roc_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v1", "name": "EGFR_binders_binary_cls-v1", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:moleculeace-chembl219-ki", "name": "moleculeace-CHEMBL219-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ec50", "name": "moleculeace-CHEMBL237-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bioavailability-ma", "name": "bioavailability-ma", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bioavailability-ma", "leaderboard_url": "https://polarishub.io/benchmarks/bioavailability-ma", "metric": "roc_auc" }, { "id": "polaris:benchmark:pkis2-lok-slk-c-1", "name": "pkis2-lok-slk-c-1", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "leaderboard_url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-250k-reg-v2", "name": "molprop-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-ret-wt-c-1", "name": "pkis2-ret-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-perm-1", "name": "adme-fang-PERM-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-c-1", "name": "pkis1-egfr-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-rclint-reg-v1", "name": "adme-fang-RCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-reg-v2", "name": "pkis2-kit-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bbb-martins", "name": "bbb-martins", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bbb-martins", "leaderboard_url": "https://polarishub.io/benchmarks/bbb-martins", "metric": "roc_auc" }, { "id": "polaris:benchmark:tox21-v1", "name": "tox21-v1", "category": "toxicity,multitask", "description": "A multitask classification benchmark for Tox21 challenge.", "url": "https://polarishub.io/benchmarks/tox21-v1", "leaderboard_url": "https://polarishub.io/benchmarks/tox21-v1", "metric": "f1" }, { "id": "polaris:benchmark:pkis2-ret-wt-r-1", "name": "pkis2-ret-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hppb-1", "name": "adme-fang-HPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HPPB", "url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-egfr-wt-r-1", "name": "pkis2-egfr-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1871-ki", "name": "moleculeace-CHEMBL1871-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl228-ki", "name": "moleculeace-CHEMBL228-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp2c9-veith", "name": "cyp2c9-veith", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-veith", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-veith", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl235-ec50", "name": "moleculeace-CHEMBL235-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-r-1", "name": "pkis1-egfr-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-egfr-wt-reg-v2", "name": "pkis2-egfr-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:molprop-250k-r-1", "name": "molprop-250k-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hclint-reg-v1", "name": "adme-fang-HCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl3979-ec50", "name": "moleculeace-CHEMBL3979-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl233-ki", "name": "moleculeace-CHEMBL233-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl238-ki", "name": "moleculeace-CHEMBL238-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:half-life-obach", "name": "half-life-obach", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/half-life-obach", "leaderboard_url": "https://polarishub.io/benchmarks/half-life-obach", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl234-ki", "name": "moleculeace-CHEMBL234-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ames", "name": "ames", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ames", "leaderboard_url": "https://polarishub.io/benchmarks/ames", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-reg", "name": "adme-novartis-cyp3a4-reg", "category": "ADME,SingleTask", "description": "Single regression task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "metric": "absolute_average_fold_error" }, { "id": "polaris:benchmark:dili", "name": "dili", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/dili", "leaderboard_url": "https://polarishub.io/benchmarks/dili", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4616-ec50", "name": "moleculeace-CHEMBL4616-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2971-ki", "name": "moleculeace-CHEMBL2971-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ki", "name": "moleculeace-CHEMBL237-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rclint-1", "name": "adme-fang-RCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl231-ki", "name": "moleculeace-CHEMBL231-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl4792-ki", "name": "moleculeace-CHEMBL4792-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-cls-v2", "name": "pkis2-lok-slk-cls-v2", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "multitask", "description": "A multitask classification benchmark for binding predictions.", "url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "metric": "f1" }, { "id": "polaris:benchmark:qm9-v1", "name": "qm9-v1", "category": "multitask", "description": "A multitask regression benchmark for QM9 dataset", "url": "https://polarishub.io/benchmarks/qm9-v1", "leaderboard_url": "https://polarishub.io/benchmarks/qm9-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2034-ki", "name": "moleculeace-CHEMBL2034-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ppbr-az", "name": "ppbr-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ppbr-az", "leaderboard_url": "https://polarishub.io/benchmarks/ppbr-az", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl287-ki", "name": "moleculeace-CHEMBL287-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:herg", "name": "herg", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/herg", "leaderboard_url": "https://polarishub.io/benchmarks/herg", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4005-ki", "name": "moleculeace-CHEMBL4005-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:vdss-lombardo", "name": "vdss-lombardo", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/vdss-lombardo", "leaderboard_url": "https://polarishub.io/benchmarks/vdss-lombardo", "metric": "spearmanr" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-disease", "name": "bend-zeroshot-variant-effects-disease", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-fang-hclint-1", "name": "adme-fang-HCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-r-1", "name": "pkis2-kit-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl262-ki", "name": "moleculeace-CHEMBL262-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:rna-expression-prediction-dataset-task", "name": "rna-expression-prediction-dataset-task", "category": "benchmark", "description": "RNA expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:rxrx-compound-gene-activity-benchmark", "name": "RxRx-compound-gene-activity-benchmark", "category": "gene,compound", "description": "This benchmark evaluates the zero-shot prediction of compound-gene activity. It is originally designed to be used with the rxrx.ai dataset releases in phenomics.", "url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "metric": "pr_auc_mean" }, { "id": "polaris:benchmark:posebusters-v1", "name": "posebusters_v1", "category": "Docking,SingleTask", "description": "Docking task benchmark for 428 proteins and ligands.", "url": "https://polarishub.io/benchmarks/posebusters-v1", "leaderboard_url": "https://polarishub.io/benchmarks/posebusters-v1", "metric": "rmsd_coverage" }, { "id": "polaris:benchmark:moleculeace-chembl204-ki", "name": "moleculeace-CHEMBL204-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-r-1", "name": "adme-fang-r-1", "category": "adme,multitask", "description": "A multitask benchmark for six ADME endpoints, utilizing a shared random split. ", "url": "https://polarishub.io/benchmarks/adme-fang-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:caco2-wang", "name": "caco2-wang", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/caco2-wang", "leaderboard_url": "https://polarishub.io/benchmarks/caco2-wang", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-r-1", "name": "pkis2-lok-slk-r-1", "category": "kinase,hit-discovery", "description": "Multitask regression benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hello-world-benchmark", "name": "hello-world-benchmark", "category": "benchmark", "description": "Single task regression for solibility", "url": "https://polarishub.io/benchmarks/hello-world-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/hello-world-benchmark", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-cls-v2", "name": "pkis2-kit-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis2-ret-wt-cls-v2", "name": "pkis2-ret-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-c-1", "name": "pkis1-kit-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-r-1", "name": "pkis1-kit-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-cls", "name": "adme-novartis-cyp3a4-cls", "category": "ADME,SingleTask", "description": "Single classification task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:molprop-250k-leadlike-r-1", "name": "molprop-250k-leadlike-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 leadlike compounds sourced from ZINC22, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-ret-wt-mut-c-1", "name": "pkis1-ret-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "Multitask classification benchmark for RET wild type, mutant V804L, and mutant Y791F.", "url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pgp-broccatelli", "name": "pgp-broccatelli", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/pgp-broccatelli", "leaderboard_url": "https://polarishub.io/benchmarks/pgp-broccatelli", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl218-ec50", "name": "moleculeace-CHEMBL218-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-reg-v1", "name": "adme-fang-RPPB-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl214-ki", "name": "moleculeace-CHEMBL214-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "leaderboard_url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-leadlike-250k-reg-v2", "name": "molprop-leadlike-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cho-dna-expression-prediction-dataset-task", "name": "cho-dna-expression-prediction-dataset-task", "category": "benchmark", "description": "DNA CHO gene expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl2147-ki", "name": "moleculeace-CHEMBL2147-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "metric": "roc_auc" }, { "id": "polaris:benchmark:clearance-microsome-az", "name": "clearance-microsome-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-microsome-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-microsome-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl239-ec50", "name": "moleculeace-CHEMBL239-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl244-ki", "name": "moleculeace-CHEMBL244-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hia-hou", "name": "hia-hou", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/hia-hou", "leaderboard_url": "https://polarishub.io/benchmarks/hia-hou", "metric": "roc_auc" }, { "id": "polaris:benchmark:ld50-zhu", "name": "ld50-zhu", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ld50-zhu", "leaderboard_url": "https://polarishub.io/benchmarks/ld50-zhu", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-c-1", "name": "pkis2-kit-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v0", "name": "EGFR_binders_binary_cls-v0", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:pkis2-ret-wt-reg-v2", "name": "pkis2-ret-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-solu-reg-v1", "name": "adme-fang-SOLU-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_SOLUBILITY", "url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl4203-ki", "name": "moleculeace-CHEMBL4203-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-perm-reg-v1", "name": "adme-fang-PERM-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-1", "name": "adme-fang-RPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl236-ki", "name": "moleculeace-CHEMBL236-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl264-ki", "name": "moleculeace-CHEMBL264-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:zinc12k-v1", "name": "zinc12k-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/zinc12k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/zinc12k-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1862-ki", "name": "moleculeace-CHEMBL1862-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2835-ki", "name": "moleculeace-CHEMBL2835-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2047-ec50", "name": "moleculeace-CHEMBL2047-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-expression", "name": "bend-zeroshot-variant-effects-expression", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "metric": "roc_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v1", "name": "EGFR_binders_binary_cls-v1", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:moleculeace-chembl219-ki", "name": "moleculeace-CHEMBL219-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ec50", "name": "moleculeace-CHEMBL237-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bioavailability-ma", "name": "bioavailability-ma", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bioavailability-ma", "leaderboard_url": "https://polarishub.io/benchmarks/bioavailability-ma", "metric": "roc_auc" }, { "id": "polaris:benchmark:pkis2-lok-slk-c-1", "name": "pkis2-lok-slk-c-1", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "leaderboard_url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-250k-reg-v2", "name": "molprop-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-ret-wt-c-1", "name": "pkis2-ret-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-perm-1", "name": "adme-fang-PERM-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-c-1", "name": "pkis1-egfr-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-rclint-reg-v1", "name": "adme-fang-RCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-reg-v2", "name": "pkis2-kit-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bbb-martins", "name": "bbb-martins", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bbb-martins", "leaderboard_url": "https://polarishub.io/benchmarks/bbb-martins", "metric": "roc_auc" }, { "id": "polaris:benchmark:tox21-v1", "name": "tox21-v1", "category": "toxicity,multitask", "description": "A multitask classification benchmark for Tox21 challenge.", "url": "https://polarishub.io/benchmarks/tox21-v1", "leaderboard_url": "https://polarishub.io/benchmarks/tox21-v1", "metric": "f1" }, { "id": "polaris:benchmark:pkis2-ret-wt-r-1", "name": "pkis2-ret-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hppb-1", "name": "adme-fang-HPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HPPB", "url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-egfr-wt-r-1", "name": "pkis2-egfr-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1871-ki", "name": "moleculeace-CHEMBL1871-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl228-ki", "name": "moleculeace-CHEMBL228-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp2c9-veith", "name": "cyp2c9-veith", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-veith", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-veith", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl235-ec50", "name": "moleculeace-CHEMBL235-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-r-1", "name": "pkis1-egfr-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-egfr-wt-reg-v2", "name": "pkis2-egfr-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:molprop-250k-r-1", "name": "molprop-250k-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hclint-reg-v1", "name": "adme-fang-HCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl3979-ec50", "name": "moleculeace-CHEMBL3979-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl233-ki", "name": "moleculeace-CHEMBL233-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl238-ki", "name": "moleculeace-CHEMBL238-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:half-life-obach", "name": "half-life-obach", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/half-life-obach", "leaderboard_url": "https://polarishub.io/benchmarks/half-life-obach", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl234-ki", "name": "moleculeace-CHEMBL234-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ames", "name": "ames", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ames", "leaderboard_url": "https://polarishub.io/benchmarks/ames", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-reg", "name": "adme-novartis-cyp3a4-reg", "category": "ADME,SingleTask", "description": "Single regression task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "metric": "absolute_average_fold_error" }, { "id": "polaris:benchmark:dili", "name": "dili", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/dili", "leaderboard_url": "https://polarishub.io/benchmarks/dili", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4616-ec50", "name": "moleculeace-CHEMBL4616-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2971-ki", "name": "moleculeace-CHEMBL2971-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ki", "name": "moleculeace-CHEMBL237-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rclint-1", "name": "adme-fang-RCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl231-ki", "name": "moleculeace-CHEMBL231-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl4792-ki", "name": "moleculeace-CHEMBL4792-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-cls-v2", "name": "pkis2-lok-slk-cls-v2", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "multitask", "description": "A multitask classification benchmark for binding predictions.", "url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "metric": "f1" }, { "id": "polaris:benchmark:qm9-v1", "name": "qm9-v1", "category": "multitask", "description": "A multitask regression benchmark for QM9 dataset", "url": "https://polarishub.io/benchmarks/qm9-v1", "leaderboard_url": "https://polarishub.io/benchmarks/qm9-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2034-ki", "name": "moleculeace-CHEMBL2034-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ppbr-az", "name": "ppbr-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ppbr-az", "leaderboard_url": "https://polarishub.io/benchmarks/ppbr-az", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl287-ki", "name": "moleculeace-CHEMBL287-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:herg", "name": "herg", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/herg", "leaderboard_url": "https://polarishub.io/benchmarks/herg", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4005-ki", "name": "moleculeace-CHEMBL4005-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:vdss-lombardo", "name": "vdss-lombardo", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/vdss-lombardo", "leaderboard_url": "https://polarishub.io/benchmarks/vdss-lombardo", "metric": "spearmanr" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-disease", "name": "bend-zeroshot-variant-effects-disease", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-fang-hclint-1", "name": "adme-fang-HCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-r-1", "name": "pkis2-kit-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl262-ki", "name": "moleculeace-CHEMBL262-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:rna-expression-prediction-dataset-task", "name": "rna-expression-prediction-dataset-task", "category": "benchmark", "description": "RNA expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:rxrx-compound-gene-activity-benchmark", "name": "RxRx-compound-gene-activity-benchmark", "category": "gene,compound", "description": "This benchmark evaluates the zero-shot prediction of compound-gene activity. It is originally designed to be used with the rxrx.ai dataset releases in phenomics.", "url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "metric": "pr_auc_mean" }, { "id": "polaris:benchmark:posebusters-v1", "name": "posebusters_v1", "category": "Docking,SingleTask", "description": "Docking task benchmark for 428 proteins and ligands.", "url": "https://polarishub.io/benchmarks/posebusters-v1", "leaderboard_url": "https://polarishub.io/benchmarks/posebusters-v1", "metric": "rmsd_coverage" }, { "id": "polaris:benchmark:moleculeace-chembl204-ki", "name": "moleculeace-CHEMBL204-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-r-1", "name": "adme-fang-r-1", "category": "adme,multitask", "description": "A multitask benchmark for six ADME endpoints, utilizing a shared random split. ", "url": "https://polarishub.io/benchmarks/adme-fang-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:caco2-wang", "name": "caco2-wang", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/caco2-wang", "leaderboard_url": "https://polarishub.io/benchmarks/caco2-wang", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-r-1", "name": "pkis2-lok-slk-r-1", "category": "kinase,hit-discovery", "description": "Multitask regression benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hello-world-benchmark", "name": "hello-world-benchmark", "category": "benchmark", "description": "Single task regression for solibility", "url": "https://polarishub.io/benchmarks/hello-world-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/hello-world-benchmark", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-cls-v2", "name": "pkis2-kit-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis2-ret-wt-cls-v2", "name": "pkis2-ret-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-c-1", "name": "pkis1-kit-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-r-1", "name": "pkis1-kit-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-cls", "name": "adme-novartis-cyp3a4-cls", "category": "ADME,SingleTask", "description": "Single classification task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:molprop-250k-leadlike-r-1", "name": "molprop-250k-leadlike-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 leadlike compounds sourced from ZINC22, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-ret-wt-mut-c-1", "name": "pkis1-ret-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "Multitask classification benchmark for RET wild type, mutant V804L, and mutant Y791F.", "url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pgp-broccatelli", "name": "pgp-broccatelli", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/pgp-broccatelli", "leaderboard_url": "https://polarishub.io/benchmarks/pgp-broccatelli", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl218-ec50", "name": "moleculeace-CHEMBL218-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-reg-v1", "name": "adme-fang-RPPB-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl214-ki", "name": "moleculeace-CHEMBL214-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "leaderboard_url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-leadlike-250k-reg-v2", "name": "molprop-leadlike-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cho-dna-expression-prediction-dataset-task", "name": "cho-dna-expression-prediction-dataset-task", "category": "benchmark", "description": "DNA CHO gene expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl2147-ki", "name": "moleculeace-CHEMBL2147-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "metric": "roc_auc" }, { "id": "polaris:benchmark:clearance-microsome-az", "name": "clearance-microsome-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-microsome-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-microsome-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl239-ec50", "name": "moleculeace-CHEMBL239-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl244-ki", "name": "moleculeace-CHEMBL244-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hia-hou", "name": "hia-hou", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/hia-hou", "leaderboard_url": "https://polarishub.io/benchmarks/hia-hou", "metric": "roc_auc" }, { "id": "polaris:benchmark:ld50-zhu", "name": "ld50-zhu", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ld50-zhu", "leaderboard_url": "https://polarishub.io/benchmarks/ld50-zhu", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-c-1", "name": "pkis2-kit-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v0", "name": "EGFR_binders_binary_cls-v0", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:pkis2-ret-wt-reg-v2", "name": "pkis2-ret-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-solu-reg-v1", "name": "adme-fang-SOLU-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_SOLUBILITY", "url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl4203-ki", "name": "moleculeace-CHEMBL4203-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-perm-reg-v1", "name": "adme-fang-PERM-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-1", "name": "adme-fang-RPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl236-ki", "name": "moleculeace-CHEMBL236-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl264-ki", "name": "moleculeace-CHEMBL264-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:zinc12k-v1", "name": "zinc12k-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/zinc12k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/zinc12k-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1862-ki", "name": "moleculeace-CHEMBL1862-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2835-ki", "name": "moleculeace-CHEMBL2835-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2047-ec50", "name": "moleculeace-CHEMBL2047-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-expression", "name": "bend-zeroshot-variant-effects-expression", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "metric": "roc_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v1", "name": "EGFR_binders_binary_cls-v1", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:moleculeace-chembl219-ki", "name": "moleculeace-CHEMBL219-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ec50", "name": "moleculeace-CHEMBL237-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bioavailability-ma", "name": "bioavailability-ma", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bioavailability-ma", "leaderboard_url": "https://polarishub.io/benchmarks/bioavailability-ma", "metric": "roc_auc" }, { "id": "polaris:benchmark:pkis2-lok-slk-c-1", "name": "pkis2-lok-slk-c-1", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "leaderboard_url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-250k-reg-v2", "name": "molprop-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-ret-wt-c-1", "name": "pkis2-ret-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-perm-1", "name": "adme-fang-PERM-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-c-1", "name": "pkis1-egfr-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-rclint-reg-v1", "name": "adme-fang-RCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-reg-v2", "name": "pkis2-kit-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bbb-martins", "name": "bbb-martins", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bbb-martins", "leaderboard_url": "https://polarishub.io/benchmarks/bbb-martins", "metric": "roc_auc" }, { "id": "polaris:benchmark:tox21-v1", "name": "tox21-v1", "category": "toxicity,multitask", "description": "A multitask classification benchmark for Tox21 challenge.", "url": "https://polarishub.io/benchmarks/tox21-v1", "leaderboard_url": "https://polarishub.io/benchmarks/tox21-v1", "metric": "f1" }, { "id": "polaris:benchmark:pkis2-ret-wt-r-1", "name": "pkis2-ret-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hppb-1", "name": "adme-fang-HPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HPPB", "url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-egfr-wt-r-1", "name": "pkis2-egfr-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1871-ki", "name": "moleculeace-CHEMBL1871-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl228-ki", "name": "moleculeace-CHEMBL228-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp2c9-veith", "name": "cyp2c9-veith", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-veith", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-veith", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl235-ec50", "name": "moleculeace-CHEMBL235-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-r-1", "name": "pkis1-egfr-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-egfr-wt-reg-v2", "name": "pkis2-egfr-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:molprop-250k-r-1", "name": "molprop-250k-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hclint-reg-v1", "name": "adme-fang-HCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl3979-ec50", "name": "moleculeace-CHEMBL3979-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl233-ki", "name": "moleculeace-CHEMBL233-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl238-ki", "name": "moleculeace-CHEMBL238-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:half-life-obach", "name": "half-life-obach", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/half-life-obach", "leaderboard_url": "https://polarishub.io/benchmarks/half-life-obach", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl234-ki", "name": "moleculeace-CHEMBL234-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ames", "name": "ames", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ames", "leaderboard_url": "https://polarishub.io/benchmarks/ames", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-reg", "name": "adme-novartis-cyp3a4-reg", "category": "ADME,SingleTask", "description": "Single regression task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "metric": "absolute_average_fold_error" }, { "id": "polaris:benchmark:dili", "name": "dili", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/dili", "leaderboard_url": "https://polarishub.io/benchmarks/dili", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4616-ec50", "name": "moleculeace-CHEMBL4616-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2971-ki", "name": "moleculeace-CHEMBL2971-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ki", "name": "moleculeace-CHEMBL237-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rclint-1", "name": "adme-fang-RCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl231-ki", "name": "moleculeace-CHEMBL231-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl4792-ki", "name": "moleculeace-CHEMBL4792-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-cls-v2", "name": "pkis2-lok-slk-cls-v2", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "multitask", "description": "A multitask classification benchmark for binding predictions.", "url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "metric": "f1" }, { "id": "polaris:benchmark:qm9-v1", "name": "qm9-v1", "category": "multitask", "description": "A multitask regression benchmark for QM9 dataset", "url": "https://polarishub.io/benchmarks/qm9-v1", "leaderboard_url": "https://polarishub.io/benchmarks/qm9-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2034-ki", "name": "moleculeace-CHEMBL2034-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ppbr-az", "name": "ppbr-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ppbr-az", "leaderboard_url": "https://polarishub.io/benchmarks/ppbr-az", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl287-ki", "name": "moleculeace-CHEMBL287-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:herg", "name": "herg", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/herg", "leaderboard_url": "https://polarishub.io/benchmarks/herg", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4005-ki", "name": "moleculeace-CHEMBL4005-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:vdss-lombardo", "name": "vdss-lombardo", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/vdss-lombardo", "leaderboard_url": "https://polarishub.io/benchmarks/vdss-lombardo", "metric": "spearmanr" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-disease", "name": "bend-zeroshot-variant-effects-disease", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-fang-hclint-1", "name": "adme-fang-HCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-r-1", "name": "pkis2-kit-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl262-ki", "name": "moleculeace-CHEMBL262-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:rna-expression-prediction-dataset-task", "name": "rna-expression-prediction-dataset-task", "category": "benchmark", "description": "RNA expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:rxrx-compound-gene-activity-benchmark", "name": "RxRx-compound-gene-activity-benchmark", "category": "gene,compound", "description": "This benchmark evaluates the zero-shot prediction of compound-gene activity. It is originally designed to be used with the rxrx.ai dataset releases in phenomics.", "url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "metric": "pr_auc_mean" }, { "id": "polaris:benchmark:posebusters-v1", "name": "posebusters_v1", "category": "Docking,SingleTask", "description": "Docking task benchmark for 428 proteins and ligands.", "url": "https://polarishub.io/benchmarks/posebusters-v1", "leaderboard_url": "https://polarishub.io/benchmarks/posebusters-v1", "metric": "rmsd_coverage" }, { "id": "polaris:benchmark:moleculeace-chembl204-ki", "name": "moleculeace-CHEMBL204-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-r-1", "name": "adme-fang-r-1", "category": "adme,multitask", "description": "A multitask benchmark for six ADME endpoints, utilizing a shared random split. ", "url": "https://polarishub.io/benchmarks/adme-fang-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:caco2-wang", "name": "caco2-wang", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/caco2-wang", "leaderboard_url": "https://polarishub.io/benchmarks/caco2-wang", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-r-1", "name": "pkis2-lok-slk-r-1", "category": "kinase,hit-discovery", "description": "Multitask regression benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hello-world-benchmark", "name": "hello-world-benchmark", "category": "benchmark", "description": "Single task regression for solibility", "url": "https://polarishub.io/benchmarks/hello-world-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/hello-world-benchmark", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-cls-v2", "name": "pkis2-kit-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis2-ret-wt-cls-v2", "name": "pkis2-ret-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-c-1", "name": "pkis1-kit-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-r-1", "name": "pkis1-kit-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-cls", "name": "adme-novartis-cyp3a4-cls", "category": "ADME,SingleTask", "description": "Single classification task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:molprop-250k-leadlike-r-1", "name": "molprop-250k-leadlike-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 leadlike compounds sourced from ZINC22, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-ret-wt-mut-c-1", "name": "pkis1-ret-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "Multitask classification benchmark for RET wild type, mutant V804L, and mutant Y791F.", "url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pgp-broccatelli", "name": "pgp-broccatelli", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/pgp-broccatelli", "leaderboard_url": "https://polarishub.io/benchmarks/pgp-broccatelli", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl218-ec50", "name": "moleculeace-CHEMBL218-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-reg-v1", "name": "adme-fang-RPPB-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl214-ki", "name": "moleculeace-CHEMBL214-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "leaderboard_url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-leadlike-250k-reg-v2", "name": "molprop-leadlike-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cho-dna-expression-prediction-dataset-task", "name": "cho-dna-expression-prediction-dataset-task", "category": "benchmark", "description": "DNA CHO gene expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl2147-ki", "name": "moleculeace-CHEMBL2147-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "metric": "roc_auc" }, { "id": "polaris:benchmark:clearance-microsome-az", "name": "clearance-microsome-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-microsome-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-microsome-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl239-ec50", "name": "moleculeace-CHEMBL239-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl244-ki", "name": "moleculeace-CHEMBL244-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hia-hou", "name": "hia-hou", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/hia-hou", "leaderboard_url": "https://polarishub.io/benchmarks/hia-hou", "metric": "roc_auc" }, { "id": "polaris:benchmark:ld50-zhu", "name": "ld50-zhu", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ld50-zhu", "leaderboard_url": "https://polarishub.io/benchmarks/ld50-zhu", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-c-1", "name": "pkis2-kit-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v0", "name": "EGFR_binders_binary_cls-v0", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:pkis2-ret-wt-reg-v2", "name": "pkis2-ret-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-solu-reg-v1", "name": "adme-fang-SOLU-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_SOLUBILITY", "url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl4203-ki", "name": "moleculeace-CHEMBL4203-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-perm-reg-v1", "name": "adme-fang-PERM-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-1", "name": "adme-fang-RPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl236-ki", "name": "moleculeace-CHEMBL236-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl264-ki", "name": "moleculeace-CHEMBL264-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:zinc12k-v1", "name": "zinc12k-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/zinc12k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/zinc12k-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1862-ki", "name": "moleculeace-CHEMBL1862-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2835-ki", "name": "moleculeace-CHEMBL2835-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2047-ec50", "name": "moleculeace-CHEMBL2047-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-expression", "name": "bend-zeroshot-variant-effects-expression", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "metric": "roc_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v1", "name": "EGFR_binders_binary_cls-v1", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:moleculeace-chembl219-ki", "name": "moleculeace-CHEMBL219-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ec50", "name": "moleculeace-CHEMBL237-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bioavailability-ma", "name": "bioavailability-ma", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bioavailability-ma", "leaderboard_url": "https://polarishub.io/benchmarks/bioavailability-ma", "metric": "roc_auc" }, { "id": "polaris:benchmark:pkis2-lok-slk-c-1", "name": "pkis2-lok-slk-c-1", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "leaderboard_url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-250k-reg-v2", "name": "molprop-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-ret-wt-c-1", "name": "pkis2-ret-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-perm-1", "name": "adme-fang-PERM-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-c-1", "name": "pkis1-egfr-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-rclint-reg-v1", "name": "adme-fang-RCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-reg-v2", "name": "pkis2-kit-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bbb-martins", "name": "bbb-martins", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bbb-martins", "leaderboard_url": "https://polarishub.io/benchmarks/bbb-martins", "metric": "roc_auc" }, { "id": "polaris:benchmark:tox21-v1", "name": "tox21-v1", "category": "toxicity,multitask", "description": "A multitask classification benchmark for Tox21 challenge.", "url": "https://polarishub.io/benchmarks/tox21-v1", "leaderboard_url": "https://polarishub.io/benchmarks/tox21-v1", "metric": "f1" }, { "id": "polaris:benchmark:pkis2-ret-wt-r-1", "name": "pkis2-ret-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hppb-1", "name": "adme-fang-HPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HPPB", "url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-egfr-wt-r-1", "name": "pkis2-egfr-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1871-ki", "name": "moleculeace-CHEMBL1871-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl228-ki", "name": "moleculeace-CHEMBL228-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp2c9-veith", "name": "cyp2c9-veith", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-veith", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-veith", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl235-ec50", "name": "moleculeace-CHEMBL235-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-r-1", "name": "pkis1-egfr-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-egfr-wt-reg-v2", "name": "pkis2-egfr-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:molprop-250k-r-1", "name": "molprop-250k-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hclint-reg-v1", "name": "adme-fang-HCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl3979-ec50", "name": "moleculeace-CHEMBL3979-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl233-ki", "name": "moleculeace-CHEMBL233-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl238-ki", "name": "moleculeace-CHEMBL238-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:half-life-obach", "name": "half-life-obach", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/half-life-obach", "leaderboard_url": "https://polarishub.io/benchmarks/half-life-obach", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl234-ki", "name": "moleculeace-CHEMBL234-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ames", "name": "ames", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ames", "leaderboard_url": "https://polarishub.io/benchmarks/ames", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-reg", "name": "adme-novartis-cyp3a4-reg", "category": "ADME,SingleTask", "description": "Single regression task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "metric": "absolute_average_fold_error" }, { "id": "polaris:benchmark:dili", "name": "dili", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/dili", "leaderboard_url": "https://polarishub.io/benchmarks/dili", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4616-ec50", "name": "moleculeace-CHEMBL4616-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2971-ki", "name": "moleculeace-CHEMBL2971-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ki", "name": "moleculeace-CHEMBL237-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rclint-1", "name": "adme-fang-RCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl231-ki", "name": "moleculeace-CHEMBL231-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl4792-ki", "name": "moleculeace-CHEMBL4792-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-cls-v2", "name": "pkis2-lok-slk-cls-v2", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "multitask", "description": "A multitask classification benchmark for binding predictions.", "url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "metric": "f1" }, { "id": "polaris:benchmark:qm9-v1", "name": "qm9-v1", "category": "multitask", "description": "A multitask regression benchmark for QM9 dataset", "url": "https://polarishub.io/benchmarks/qm9-v1", "leaderboard_url": "https://polarishub.io/benchmarks/qm9-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2034-ki", "name": "moleculeace-CHEMBL2034-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ppbr-az", "name": "ppbr-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ppbr-az", "leaderboard_url": "https://polarishub.io/benchmarks/ppbr-az", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl287-ki", "name": "moleculeace-CHEMBL287-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:herg", "name": "herg", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/herg", "leaderboard_url": "https://polarishub.io/benchmarks/herg", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4005-ki", "name": "moleculeace-CHEMBL4005-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:vdss-lombardo", "name": "vdss-lombardo", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/vdss-lombardo", "leaderboard_url": "https://polarishub.io/benchmarks/vdss-lombardo", "metric": "spearmanr" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-disease", "name": "bend-zeroshot-variant-effects-disease", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-fang-hclint-1", "name": "adme-fang-HCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-r-1", "name": "pkis2-kit-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl262-ki", "name": "moleculeace-CHEMBL262-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:rna-expression-prediction-dataset-task", "name": "rna-expression-prediction-dataset-task", "category": "benchmark", "description": "RNA expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:rxrx-compound-gene-activity-benchmark", "name": "RxRx-compound-gene-activity-benchmark", "category": "gene,compound", "description": "This benchmark evaluates the zero-shot prediction of compound-gene activity. It is originally designed to be used with the rxrx.ai dataset releases in phenomics.", "url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "metric": "pr_auc_mean" }, { "id": "polaris:benchmark:posebusters-v1", "name": "posebusters_v1", "category": "Docking,SingleTask", "description": "Docking task benchmark for 428 proteins and ligands.", "url": "https://polarishub.io/benchmarks/posebusters-v1", "leaderboard_url": "https://polarishub.io/benchmarks/posebusters-v1", "metric": "rmsd_coverage" }, { "id": "polaris:benchmark:moleculeace-chembl204-ki", "name": "moleculeace-CHEMBL204-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-r-1", "name": "adme-fang-r-1", "category": "adme,multitask", "description": "A multitask benchmark for six ADME endpoints, utilizing a shared random split. ", "url": "https://polarishub.io/benchmarks/adme-fang-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:caco2-wang", "name": "caco2-wang", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/caco2-wang", "leaderboard_url": "https://polarishub.io/benchmarks/caco2-wang", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-r-1", "name": "pkis2-lok-slk-r-1", "category": "kinase,hit-discovery", "description": "Multitask regression benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hello-world-benchmark", "name": "hello-world-benchmark", "category": "benchmark", "description": "Single task regression for solibility", "url": "https://polarishub.io/benchmarks/hello-world-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/hello-world-benchmark", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-cls-v2", "name": "pkis2-kit-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis2-ret-wt-cls-v2", "name": "pkis2-ret-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-c-1", "name": "pkis1-kit-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-r-1", "name": "pkis1-kit-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-cls", "name": "adme-novartis-cyp3a4-cls", "category": "ADME,SingleTask", "description": "Single classification task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:molprop-250k-leadlike-r-1", "name": "molprop-250k-leadlike-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 leadlike compounds sourced from ZINC22, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-ret-wt-mut-c-1", "name": "pkis1-ret-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "Multitask classification benchmark for RET wild type, mutant V804L, and mutant Y791F.", "url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pgp-broccatelli", "name": "pgp-broccatelli", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/pgp-broccatelli", "leaderboard_url": "https://polarishub.io/benchmarks/pgp-broccatelli", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl218-ec50", "name": "moleculeace-CHEMBL218-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-reg-v1", "name": "adme-fang-RPPB-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl214-ki", "name": "moleculeace-CHEMBL214-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "leaderboard_url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-leadlike-250k-reg-v2", "name": "molprop-leadlike-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cho-dna-expression-prediction-dataset-task", "name": "cho-dna-expression-prediction-dataset-task", "category": "benchmark", "description": "DNA CHO gene expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl2147-ki", "name": "moleculeace-CHEMBL2147-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "metric": "roc_auc" }, { "id": "polaris:benchmark:clearance-microsome-az", "name": "clearance-microsome-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-microsome-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-microsome-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl239-ec50", "name": "moleculeace-CHEMBL239-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl244-ki", "name": "moleculeace-CHEMBL244-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hia-hou", "name": "hia-hou", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/hia-hou", "leaderboard_url": "https://polarishub.io/benchmarks/hia-hou", "metric": "roc_auc" }, { "id": "polaris:benchmark:ld50-zhu", "name": "ld50-zhu", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ld50-zhu", "leaderboard_url": "https://polarishub.io/benchmarks/ld50-zhu", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-c-1", "name": "pkis2-kit-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v0", "name": "EGFR_binders_binary_cls-v0", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:pkis2-ret-wt-reg-v2", "name": "pkis2-ret-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-solu-reg-v1", "name": "adme-fang-SOLU-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_SOLUBILITY", "url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl4203-ki", "name": "moleculeace-CHEMBL4203-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-perm-reg-v1", "name": "adme-fang-PERM-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-1", "name": "adme-fang-RPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl236-ki", "name": "moleculeace-CHEMBL236-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl264-ki", "name": "moleculeace-CHEMBL264-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:zinc12k-v1", "name": "zinc12k-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/zinc12k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/zinc12k-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1862-ki", "name": "moleculeace-CHEMBL1862-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2835-ki", "name": "moleculeace-CHEMBL2835-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2047-ec50", "name": "moleculeace-CHEMBL2047-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-expression", "name": "bend-zeroshot-variant-effects-expression", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "metric": "roc_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v1", "name": "EGFR_binders_binary_cls-v1", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:moleculeace-chembl219-ki", "name": "moleculeace-CHEMBL219-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ec50", "name": "moleculeace-CHEMBL237-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bioavailability-ma", "name": "bioavailability-ma", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bioavailability-ma", "leaderboard_url": "https://polarishub.io/benchmarks/bioavailability-ma", "metric": "roc_auc" }, { "id": "polaris:benchmark:pkis2-lok-slk-c-1", "name": "pkis2-lok-slk-c-1", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "leaderboard_url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-250k-reg-v2", "name": "molprop-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-ret-wt-c-1", "name": "pkis2-ret-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-perm-1", "name": "adme-fang-PERM-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-c-1", "name": "pkis1-egfr-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-rclint-reg-v1", "name": "adme-fang-RCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-reg-v2", "name": "pkis2-kit-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bbb-martins", "name": "bbb-martins", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bbb-martins", "leaderboard_url": "https://polarishub.io/benchmarks/bbb-martins", "metric": "roc_auc" }, { "id": "polaris:benchmark:tox21-v1", "name": "tox21-v1", "category": "toxicity,multitask", "description": "A multitask classification benchmark for Tox21 challenge.", "url": "https://polarishub.io/benchmarks/tox21-v1", "leaderboard_url": "https://polarishub.io/benchmarks/tox21-v1", "metric": "f1" }, { "id": "polaris:benchmark:pkis2-ret-wt-r-1", "name": "pkis2-ret-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hppb-1", "name": "adme-fang-HPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HPPB", "url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-egfr-wt-r-1", "name": "pkis2-egfr-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1871-ki", "name": "moleculeace-CHEMBL1871-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl228-ki", "name": "moleculeace-CHEMBL228-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp2c9-veith", "name": "cyp2c9-veith", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-veith", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-veith", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl235-ec50", "name": "moleculeace-CHEMBL235-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-r-1", "name": "pkis1-egfr-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-egfr-wt-reg-v2", "name": "pkis2-egfr-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:molprop-250k-r-1", "name": "molprop-250k-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hclint-reg-v1", "name": "adme-fang-HCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl3979-ec50", "name": "moleculeace-CHEMBL3979-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl233-ki", "name": "moleculeace-CHEMBL233-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl238-ki", "name": "moleculeace-CHEMBL238-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:half-life-obach", "name": "half-life-obach", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/half-life-obach", "leaderboard_url": "https://polarishub.io/benchmarks/half-life-obach", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl234-ki", "name": "moleculeace-CHEMBL234-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ames", "name": "ames", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ames", "leaderboard_url": "https://polarishub.io/benchmarks/ames", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-reg", "name": "adme-novartis-cyp3a4-reg", "category": "ADME,SingleTask", "description": "Single regression task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "metric": "absolute_average_fold_error" }, { "id": "polaris:benchmark:dili", "name": "dili", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/dili", "leaderboard_url": "https://polarishub.io/benchmarks/dili", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4616-ec50", "name": "moleculeace-CHEMBL4616-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2971-ki", "name": "moleculeace-CHEMBL2971-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ki", "name": "moleculeace-CHEMBL237-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rclint-1", "name": "adme-fang-RCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl231-ki", "name": "moleculeace-CHEMBL231-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl4792-ki", "name": "moleculeace-CHEMBL4792-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-cls-v2", "name": "pkis2-lok-slk-cls-v2", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "multitask", "description": "A multitask classification benchmark for binding predictions.", "url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "metric": "f1" }, { "id": "polaris:benchmark:qm9-v1", "name": "qm9-v1", "category": "multitask", "description": "A multitask regression benchmark for QM9 dataset", "url": "https://polarishub.io/benchmarks/qm9-v1", "leaderboard_url": "https://polarishub.io/benchmarks/qm9-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2034-ki", "name": "moleculeace-CHEMBL2034-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ppbr-az", "name": "ppbr-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ppbr-az", "leaderboard_url": "https://polarishub.io/benchmarks/ppbr-az", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl287-ki", "name": "moleculeace-CHEMBL287-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:herg", "name": "herg", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/herg", "leaderboard_url": "https://polarishub.io/benchmarks/herg", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4005-ki", "name": "moleculeace-CHEMBL4005-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:vdss-lombardo", "name": "vdss-lombardo", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/vdss-lombardo", "leaderboard_url": "https://polarishub.io/benchmarks/vdss-lombardo", "metric": "spearmanr" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-disease", "name": "bend-zeroshot-variant-effects-disease", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-fang-hclint-1", "name": "adme-fang-HCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-r-1", "name": "pkis2-kit-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl262-ki", "name": "moleculeace-CHEMBL262-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:rna-expression-prediction-dataset-task", "name": "rna-expression-prediction-dataset-task", "category": "benchmark", "description": "RNA expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:rxrx-compound-gene-activity-benchmark", "name": "RxRx-compound-gene-activity-benchmark", "category": "gene,compound", "description": "This benchmark evaluates the zero-shot prediction of compound-gene activity. It is originally designed to be used with the rxrx.ai dataset releases in phenomics.", "url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "metric": "pr_auc_mean" }, { "id": "polaris:benchmark:posebusters-v1", "name": "posebusters_v1", "category": "Docking,SingleTask", "description": "Docking task benchmark for 428 proteins and ligands.", "url": "https://polarishub.io/benchmarks/posebusters-v1", "leaderboard_url": "https://polarishub.io/benchmarks/posebusters-v1", "metric": "rmsd_coverage" }, { "id": "polaris:benchmark:moleculeace-chembl204-ki", "name": "moleculeace-CHEMBL204-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-r-1", "name": "adme-fang-r-1", "category": "adme,multitask", "description": "A multitask benchmark for six ADME endpoints, utilizing a shared random split. ", "url": "https://polarishub.io/benchmarks/adme-fang-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:caco2-wang", "name": "caco2-wang", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/caco2-wang", "leaderboard_url": "https://polarishub.io/benchmarks/caco2-wang", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-r-1", "name": "pkis2-lok-slk-r-1", "category": "kinase,hit-discovery", "description": "Multitask regression benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hello-world-benchmark", "name": "hello-world-benchmark", "category": "benchmark", "description": "Single task regression for solibility", "url": "https://polarishub.io/benchmarks/hello-world-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/hello-world-benchmark", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-cls-v2", "name": "pkis2-kit-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis2-ret-wt-cls-v2", "name": "pkis2-ret-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-c-1", "name": "pkis1-kit-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-r-1", "name": "pkis1-kit-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-cls", "name": "adme-novartis-cyp3a4-cls", "category": "ADME,SingleTask", "description": "Single classification task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:molprop-250k-leadlike-r-1", "name": "molprop-250k-leadlike-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 leadlike compounds sourced from ZINC22, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-ret-wt-mut-c-1", "name": "pkis1-ret-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "Multitask classification benchmark for RET wild type, mutant V804L, and mutant Y791F.", "url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pgp-broccatelli", "name": "pgp-broccatelli", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/pgp-broccatelli", "leaderboard_url": "https://polarishub.io/benchmarks/pgp-broccatelli", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl218-ec50", "name": "moleculeace-CHEMBL218-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-reg-v1", "name": "adme-fang-RPPB-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl214-ki", "name": "moleculeace-CHEMBL214-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "leaderboard_url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-leadlike-250k-reg-v2", "name": "molprop-leadlike-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cho-dna-expression-prediction-dataset-task", "name": "cho-dna-expression-prediction-dataset-task", "category": "benchmark", "description": "DNA CHO gene expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl2147-ki", "name": "moleculeace-CHEMBL2147-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "metric": "roc_auc" }, { "id": "polaris:benchmark:clearance-microsome-az", "name": "clearance-microsome-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-microsome-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-microsome-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl239-ec50", "name": "moleculeace-CHEMBL239-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl244-ki", "name": "moleculeace-CHEMBL244-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hia-hou", "name": "hia-hou", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/hia-hou", "leaderboard_url": "https://polarishub.io/benchmarks/hia-hou", "metric": "roc_auc" }, { "id": "polaris:benchmark:ld50-zhu", "name": "ld50-zhu", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ld50-zhu", "leaderboard_url": "https://polarishub.io/benchmarks/ld50-zhu", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-c-1", "name": "pkis2-kit-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v0", "name": "EGFR_binders_binary_cls-v0", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:pkis2-ret-wt-reg-v2", "name": "pkis2-ret-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-solu-reg-v1", "name": "adme-fang-SOLU-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_SOLUBILITY", "url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl4203-ki", "name": "moleculeace-CHEMBL4203-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-perm-reg-v1", "name": "adme-fang-PERM-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-1", "name": "adme-fang-RPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl236-ki", "name": "moleculeace-CHEMBL236-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl264-ki", "name": "moleculeace-CHEMBL264-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:zinc12k-v1", "name": "zinc12k-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/zinc12k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/zinc12k-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1862-ki", "name": "moleculeace-CHEMBL1862-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2835-ki", "name": "moleculeace-CHEMBL2835-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2047-ec50", "name": "moleculeace-CHEMBL2047-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-expression", "name": "bend-zeroshot-variant-effects-expression", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "metric": "roc_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v1", "name": "EGFR_binders_binary_cls-v1", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:moleculeace-chembl219-ki", "name": "moleculeace-CHEMBL219-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ec50", "name": "moleculeace-CHEMBL237-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bioavailability-ma", "name": "bioavailability-ma", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bioavailability-ma", "leaderboard_url": "https://polarishub.io/benchmarks/bioavailability-ma", "metric": "roc_auc" }, { "id": "polaris:benchmark:pkis2-lok-slk-c-1", "name": "pkis2-lok-slk-c-1", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "leaderboard_url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-250k-reg-v2", "name": "molprop-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-ret-wt-c-1", "name": "pkis2-ret-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-perm-1", "name": "adme-fang-PERM-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-c-1", "name": "pkis1-egfr-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-rclint-reg-v1", "name": "adme-fang-RCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-reg-v2", "name": "pkis2-kit-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bbb-martins", "name": "bbb-martins", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bbb-martins", "leaderboard_url": "https://polarishub.io/benchmarks/bbb-martins", "metric": "roc_auc" }, { "id": "polaris:benchmark:tox21-v1", "name": "tox21-v1", "category": "toxicity,multitask", "description": "A multitask classification benchmark for Tox21 challenge.", "url": "https://polarishub.io/benchmarks/tox21-v1", "leaderboard_url": "https://polarishub.io/benchmarks/tox21-v1", "metric": "f1" }, { "id": "polaris:benchmark:pkis2-ret-wt-r-1", "name": "pkis2-ret-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hppb-1", "name": "adme-fang-HPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HPPB", "url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-egfr-wt-r-1", "name": "pkis2-egfr-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1871-ki", "name": "moleculeace-CHEMBL1871-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl228-ki", "name": "moleculeace-CHEMBL228-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp2c9-veith", "name": "cyp2c9-veith", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-veith", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-veith", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl235-ec50", "name": "moleculeace-CHEMBL235-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-r-1", "name": "pkis1-egfr-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-egfr-wt-reg-v2", "name": "pkis2-egfr-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:molprop-250k-r-1", "name": "molprop-250k-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hclint-reg-v1", "name": "adme-fang-HCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl3979-ec50", "name": "moleculeace-CHEMBL3979-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl233-ki", "name": "moleculeace-CHEMBL233-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl238-ki", "name": "moleculeace-CHEMBL238-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:half-life-obach", "name": "half-life-obach", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/half-life-obach", "leaderboard_url": "https://polarishub.io/benchmarks/half-life-obach", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl234-ki", "name": "moleculeace-CHEMBL234-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ames", "name": "ames", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ames", "leaderboard_url": "https://polarishub.io/benchmarks/ames", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-reg", "name": "adme-novartis-cyp3a4-reg", "category": "ADME,SingleTask", "description": "Single regression task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "metric": "absolute_average_fold_error" }, { "id": "polaris:benchmark:dili", "name": "dili", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/dili", "leaderboard_url": "https://polarishub.io/benchmarks/dili", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4616-ec50", "name": "moleculeace-CHEMBL4616-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2971-ki", "name": "moleculeace-CHEMBL2971-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ki", "name": "moleculeace-CHEMBL237-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rclint-1", "name": "adme-fang-RCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl231-ki", "name": "moleculeace-CHEMBL231-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl4792-ki", "name": "moleculeace-CHEMBL4792-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-cls-v2", "name": "pkis2-lok-slk-cls-v2", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "multitask", "description": "A multitask classification benchmark for binding predictions.", "url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "metric": "f1" }, { "id": "polaris:benchmark:qm9-v1", "name": "qm9-v1", "category": "multitask", "description": "A multitask regression benchmark for QM9 dataset", "url": "https://polarishub.io/benchmarks/qm9-v1", "leaderboard_url": "https://polarishub.io/benchmarks/qm9-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2034-ki", "name": "moleculeace-CHEMBL2034-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ppbr-az", "name": "ppbr-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ppbr-az", "leaderboard_url": "https://polarishub.io/benchmarks/ppbr-az", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl287-ki", "name": "moleculeace-CHEMBL287-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:herg", "name": "herg", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/herg", "leaderboard_url": "https://polarishub.io/benchmarks/herg", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4005-ki", "name": "moleculeace-CHEMBL4005-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:vdss-lombardo", "name": "vdss-lombardo", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/vdss-lombardo", "leaderboard_url": "https://polarishub.io/benchmarks/vdss-lombardo", "metric": "spearmanr" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-disease", "name": "bend-zeroshot-variant-effects-disease", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-fang-hclint-1", "name": "adme-fang-HCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-r-1", "name": "pkis2-kit-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl262-ki", "name": "moleculeace-CHEMBL262-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:rna-expression-prediction-dataset-task", "name": "rna-expression-prediction-dataset-task", "category": "benchmark", "description": "RNA expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:rxrx-compound-gene-activity-benchmark", "name": "RxRx-compound-gene-activity-benchmark", "category": "gene,compound", "description": "This benchmark evaluates the zero-shot prediction of compound-gene activity. It is originally designed to be used with the rxrx.ai dataset releases in phenomics.", "url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "metric": "pr_auc_mean" }, { "id": "polaris:benchmark:posebusters-v1", "name": "posebusters_v1", "category": "Docking,SingleTask", "description": "Docking task benchmark for 428 proteins and ligands.", "url": "https://polarishub.io/benchmarks/posebusters-v1", "leaderboard_url": "https://polarishub.io/benchmarks/posebusters-v1", "metric": "rmsd_coverage" }, { "id": "polaris:benchmark:moleculeace-chembl204-ki", "name": "moleculeace-CHEMBL204-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-r-1", "name": "adme-fang-r-1", "category": "adme,multitask", "description": "A multitask benchmark for six ADME endpoints, utilizing a shared random split. ", "url": "https://polarishub.io/benchmarks/adme-fang-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:caco2-wang", "name": "caco2-wang", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/caco2-wang", "leaderboard_url": "https://polarishub.io/benchmarks/caco2-wang", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-r-1", "name": "pkis2-lok-slk-r-1", "category": "kinase,hit-discovery", "description": "Multitask regression benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hello-world-benchmark", "name": "hello-world-benchmark", "category": "benchmark", "description": "Single task regression for solibility", "url": "https://polarishub.io/benchmarks/hello-world-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/hello-world-benchmark", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-cls-v2", "name": "pkis2-kit-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis2-ret-wt-cls-v2", "name": "pkis2-ret-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-c-1", "name": "pkis1-kit-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-r-1", "name": "pkis1-kit-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-cls", "name": "adme-novartis-cyp3a4-cls", "category": "ADME,SingleTask", "description": "Single classification task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:molprop-250k-leadlike-r-1", "name": "molprop-250k-leadlike-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 leadlike compounds sourced from ZINC22, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-ret-wt-mut-c-1", "name": "pkis1-ret-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "Multitask classification benchmark for RET wild type, mutant V804L, and mutant Y791F.", "url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pgp-broccatelli", "name": "pgp-broccatelli", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/pgp-broccatelli", "leaderboard_url": "https://polarishub.io/benchmarks/pgp-broccatelli", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl218-ec50", "name": "moleculeace-CHEMBL218-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-reg-v1", "name": "adme-fang-RPPB-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl214-ki", "name": "moleculeace-CHEMBL214-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "leaderboard_url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-leadlike-250k-reg-v2", "name": "molprop-leadlike-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cho-dna-expression-prediction-dataset-task", "name": "cho-dna-expression-prediction-dataset-task", "category": "benchmark", "description": "DNA CHO gene expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl2147-ki", "name": "moleculeace-CHEMBL2147-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "metric": "roc_auc" }, { "id": "polaris:benchmark:clearance-microsome-az", "name": "clearance-microsome-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-microsome-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-microsome-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl239-ec50", "name": "moleculeace-CHEMBL239-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl244-ki", "name": "moleculeace-CHEMBL244-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hia-hou", "name": "hia-hou", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/hia-hou", "leaderboard_url": "https://polarishub.io/benchmarks/hia-hou", "metric": "roc_auc" }, { "id": "polaris:benchmark:ld50-zhu", "name": "ld50-zhu", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ld50-zhu", "leaderboard_url": "https://polarishub.io/benchmarks/ld50-zhu", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-c-1", "name": "pkis2-kit-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v0", "name": "EGFR_binders_binary_cls-v0", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:pkis2-ret-wt-reg-v2", "name": "pkis2-ret-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-solu-reg-v1", "name": "adme-fang-SOLU-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_SOLUBILITY", "url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl4203-ki", "name": "moleculeace-CHEMBL4203-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-perm-reg-v1", "name": "adme-fang-PERM-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-1", "name": "adme-fang-RPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl236-ki", "name": "moleculeace-CHEMBL236-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl264-ki", "name": "moleculeace-CHEMBL264-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:zinc12k-v1", "name": "zinc12k-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/zinc12k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/zinc12k-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1862-ki", "name": "moleculeace-CHEMBL1862-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2835-ki", "name": "moleculeace-CHEMBL2835-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2047-ec50", "name": "moleculeace-CHEMBL2047-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-expression", "name": "bend-zeroshot-variant-effects-expression", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "metric": "roc_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v1", "name": "EGFR_binders_binary_cls-v1", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:moleculeace-chembl219-ki", "name": "moleculeace-CHEMBL219-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ec50", "name": "moleculeace-CHEMBL237-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bioavailability-ma", "name": "bioavailability-ma", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bioavailability-ma", "leaderboard_url": "https://polarishub.io/benchmarks/bioavailability-ma", "metric": "roc_auc" }, { "id": "polaris:benchmark:pkis2-lok-slk-c-1", "name": "pkis2-lok-slk-c-1", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "leaderboard_url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-250k-reg-v2", "name": "molprop-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-ret-wt-c-1", "name": "pkis2-ret-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-perm-1", "name": "adme-fang-PERM-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-c-1", "name": "pkis1-egfr-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-rclint-reg-v1", "name": "adme-fang-RCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-reg-v2", "name": "pkis2-kit-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bbb-martins", "name": "bbb-martins", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bbb-martins", "leaderboard_url": "https://polarishub.io/benchmarks/bbb-martins", "metric": "roc_auc" }, { "id": "polaris:benchmark:tox21-v1", "name": "tox21-v1", "category": "toxicity,multitask", "description": "A multitask classification benchmark for Tox21 challenge.", "url": "https://polarishub.io/benchmarks/tox21-v1", "leaderboard_url": "https://polarishub.io/benchmarks/tox21-v1", "metric": "f1" }, { "id": "polaris:benchmark:pkis2-ret-wt-r-1", "name": "pkis2-ret-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hppb-1", "name": "adme-fang-HPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HPPB", "url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-egfr-wt-r-1", "name": "pkis2-egfr-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1871-ki", "name": "moleculeace-CHEMBL1871-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl228-ki", "name": "moleculeace-CHEMBL228-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp2c9-veith", "name": "cyp2c9-veith", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-veith", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-veith", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl235-ec50", "name": "moleculeace-CHEMBL235-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-r-1", "name": "pkis1-egfr-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-egfr-wt-reg-v2", "name": "pkis2-egfr-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:molprop-250k-r-1", "name": "molprop-250k-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hclint-reg-v1", "name": "adme-fang-HCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl3979-ec50", "name": "moleculeace-CHEMBL3979-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl233-ki", "name": "moleculeace-CHEMBL233-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl238-ki", "name": "moleculeace-CHEMBL238-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:half-life-obach", "name": "half-life-obach", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/half-life-obach", "leaderboard_url": "https://polarishub.io/benchmarks/half-life-obach", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl234-ki", "name": "moleculeace-CHEMBL234-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ames", "name": "ames", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ames", "leaderboard_url": "https://polarishub.io/benchmarks/ames", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-reg", "name": "adme-novartis-cyp3a4-reg", "category": "ADME,SingleTask", "description": "Single regression task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "metric": "absolute_average_fold_error" }, { "id": "polaris:benchmark:dili", "name": "dili", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/dili", "leaderboard_url": "https://polarishub.io/benchmarks/dili", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4616-ec50", "name": "moleculeace-CHEMBL4616-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2971-ki", "name": "moleculeace-CHEMBL2971-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ki", "name": "moleculeace-CHEMBL237-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rclint-1", "name": "adme-fang-RCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl231-ki", "name": "moleculeace-CHEMBL231-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl4792-ki", "name": "moleculeace-CHEMBL4792-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-cls-v2", "name": "pkis2-lok-slk-cls-v2", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "multitask", "description": "A multitask classification benchmark for binding predictions.", "url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "metric": "f1" }, { "id": "polaris:benchmark:qm9-v1", "name": "qm9-v1", "category": "multitask", "description": "A multitask regression benchmark for QM9 dataset", "url": "https://polarishub.io/benchmarks/qm9-v1", "leaderboard_url": "https://polarishub.io/benchmarks/qm9-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2034-ki", "name": "moleculeace-CHEMBL2034-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ppbr-az", "name": "ppbr-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ppbr-az", "leaderboard_url": "https://polarishub.io/benchmarks/ppbr-az", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl287-ki", "name": "moleculeace-CHEMBL287-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:herg", "name": "herg", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/herg", "leaderboard_url": "https://polarishub.io/benchmarks/herg", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4005-ki", "name": "moleculeace-CHEMBL4005-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:vdss-lombardo", "name": "vdss-lombardo", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/vdss-lombardo", "leaderboard_url": "https://polarishub.io/benchmarks/vdss-lombardo", "metric": "spearmanr" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-disease", "name": "bend-zeroshot-variant-effects-disease", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-fang-hclint-1", "name": "adme-fang-HCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-r-1", "name": "pkis2-kit-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl262-ki", "name": "moleculeace-CHEMBL262-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:rna-expression-prediction-dataset-task", "name": "rna-expression-prediction-dataset-task", "category": "benchmark", "description": "RNA expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:rxrx-compound-gene-activity-benchmark", "name": "RxRx-compound-gene-activity-benchmark", "category": "gene,compound", "description": "This benchmark evaluates the zero-shot prediction of compound-gene activity. It is originally designed to be used with the rxrx.ai dataset releases in phenomics.", "url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "metric": "pr_auc_mean" }, { "id": "polaris:benchmark:posebusters-v1", "name": "posebusters_v1", "category": "Docking,SingleTask", "description": "Docking task benchmark for 428 proteins and ligands.", "url": "https://polarishub.io/benchmarks/posebusters-v1", "leaderboard_url": "https://polarishub.io/benchmarks/posebusters-v1", "metric": "rmsd_coverage" }, { "id": "polaris:benchmark:moleculeace-chembl204-ki", "name": "moleculeace-CHEMBL204-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-r-1", "name": "adme-fang-r-1", "category": "adme,multitask", "description": "A multitask benchmark for six ADME endpoints, utilizing a shared random split. ", "url": "https://polarishub.io/benchmarks/adme-fang-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:caco2-wang", "name": "caco2-wang", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/caco2-wang", "leaderboard_url": "https://polarishub.io/benchmarks/caco2-wang", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-r-1", "name": "pkis2-lok-slk-r-1", "category": "kinase,hit-discovery", "description": "Multitask regression benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hello-world-benchmark", "name": "hello-world-benchmark", "category": "benchmark", "description": "Single task regression for solibility", "url": "https://polarishub.io/benchmarks/hello-world-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/hello-world-benchmark", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-cls-v2", "name": "pkis2-kit-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis2-ret-wt-cls-v2", "name": "pkis2-ret-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-c-1", "name": "pkis1-kit-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-r-1", "name": "pkis1-kit-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-cls", "name": "adme-novartis-cyp3a4-cls", "category": "ADME,SingleTask", "description": "Single classification task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:molprop-250k-leadlike-r-1", "name": "molprop-250k-leadlike-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 leadlike compounds sourced from ZINC22, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-ret-wt-mut-c-1", "name": "pkis1-ret-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "Multitask classification benchmark for RET wild type, mutant V804L, and mutant Y791F.", "url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pgp-broccatelli", "name": "pgp-broccatelli", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/pgp-broccatelli", "leaderboard_url": "https://polarishub.io/benchmarks/pgp-broccatelli", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl218-ec50", "name": "moleculeace-CHEMBL218-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-reg-v1", "name": "adme-fang-RPPB-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl214-ki", "name": "moleculeace-CHEMBL214-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "leaderboard_url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-leadlike-250k-reg-v2", "name": "molprop-leadlike-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cho-dna-expression-prediction-dataset-task", "name": "cho-dna-expression-prediction-dataset-task", "category": "benchmark", "description": "DNA CHO gene expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl2147-ki", "name": "moleculeace-CHEMBL2147-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "metric": "roc_auc" }, { "id": "polaris:benchmark:clearance-microsome-az", "name": "clearance-microsome-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-microsome-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-microsome-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl239-ec50", "name": "moleculeace-CHEMBL239-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl244-ki", "name": "moleculeace-CHEMBL244-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hia-hou", "name": "hia-hou", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/hia-hou", "leaderboard_url": "https://polarishub.io/benchmarks/hia-hou", "metric": "roc_auc" }, { "id": "polaris:benchmark:ld50-zhu", "name": "ld50-zhu", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ld50-zhu", "leaderboard_url": "https://polarishub.io/benchmarks/ld50-zhu", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-c-1", "name": "pkis2-kit-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v0", "name": "EGFR_binders_binary_cls-v0", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v0", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:pkis2-ret-wt-reg-v2", "name": "pkis2-ret-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-solu-reg-v1", "name": "adme-fang-SOLU-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_SOLUBILITY", "url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-solu-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl4203-ki", "name": "moleculeace-CHEMBL4203-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4203-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-perm-reg-v1", "name": "adme-fang-PERM-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-vcap-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-1", "name": "adme-fang-RPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2d6-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl236-ki", "name": "moleculeace-CHEMBL236-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl236-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl264-ki", "name": "moleculeace-CHEMBL264-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl264-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:zinc12k-v1", "name": "zinc12k-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/zinc12k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/zinc12k-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1862-ki", "name": "moleculeace-CHEMBL1862-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1862-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2835-ki", "name": "moleculeace-CHEMBL2835-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2835-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2047-ec50", "name": "moleculeace-CHEMBL2047-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2047-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-expression", "name": "bend-zeroshot-variant-effects-expression", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-expression", "metric": "roc_auc" }, { "id": "polaris:benchmark:egfr-binders-binary-cls-v1", "name": "EGFR_binders_binary_cls-v1", "category": "protein-design,singletask", "description": "Single task benchmark for protein binder design targeting the EGFR.", "url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "leaderboard_url": "https://polarishub.io/benchmarks/egfr-binders-binary-cls-v1", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:moleculeace-chembl219-ki", "name": "moleculeace-CHEMBL219-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl219-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ec50", "name": "moleculeace-CHEMBL237-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bioavailability-ma", "name": "bioavailability-ma", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bioavailability-ma", "leaderboard_url": "https://polarishub.io/benchmarks/bioavailability-ma", "metric": "roc_auc" }, { "id": "polaris:benchmark:pkis2-lok-slk-c-1", "name": "pkis2-lok-slk-c-1", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "leaderboard_url": "https://polarishub.io/benchmarks/solubility-aqsoldb", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-250k-reg-v2", "name": "molprop-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-ret-wt-c-1", "name": "pkis2-ret-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-perm-1", "name": "adme-fang-PERM-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_MDR1-MDCK_ER", "url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-perm-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-c-1", "name": "pkis1-egfr-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:adme-fang-rclint-reg-v1", "name": "adme-fang-RCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-reg-v2", "name": "pkis2-kit-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:bbb-martins", "name": "bbb-martins", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/bbb-martins", "leaderboard_url": "https://polarishub.io/benchmarks/bbb-martins", "metric": "roc_auc" }, { "id": "polaris:benchmark:tox21-v1", "name": "tox21-v1", "category": "toxicity,multitask", "description": "A multitask classification benchmark for Tox21 challenge.", "url": "https://polarishub.io/benchmarks/tox21-v1", "leaderboard_url": "https://polarishub.io/benchmarks/tox21-v1", "metric": "f1" }, { "id": "polaris:benchmark:pkis2-ret-wt-r-1", "name": "pkis2-ret-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hppb-1", "name": "adme-fang-HPPB-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HPPB", "url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hppb-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-egfr-wt-r-1", "name": "pkis2-egfr-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl1871-ki", "name": "moleculeace-CHEMBL1871-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl1871-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl228-ki", "name": "moleculeace-CHEMBL228-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl228-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp2c9-veith", "name": "cyp2c9-veith", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-veith", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-veith", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl235-ec50", "name": "moleculeace-CHEMBL235-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl235-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-egfr-wt-mut-r-1", "name": "pkis1-egfr-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for kinase EGFR wild type and L858R mutant.", "url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-egfr-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-egfr-wt-reg-v2", "name": "pkis2-egfr-wt-reg-v2", "category": "Kinase,HitDiscovery", "description": "Singletask regression benchmark for kinase EGFR wild type.", "url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-egfr-wt-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:molprop-250k-r-1", "name": "molprop-250k-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-hclint-reg-v1", "name": "adme-fang-HCLint-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp2c9-substrate-carbonmangels", "metric": "pr_auc" }, { "id": "polaris:benchmark:moleculeace-chembl3979-ec50", "name": "moleculeace-CHEMBL3979-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl3979-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl233-ki", "name": "moleculeace-CHEMBL233-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl233-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl238-ki", "name": "moleculeace-CHEMBL238-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl238-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:half-life-obach", "name": "half-life-obach", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/half-life-obach", "leaderboard_url": "https://polarishub.io/benchmarks/half-life-obach", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl234-ki", "name": "moleculeace-CHEMBL234-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl234-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ames", "name": "ames", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ames", "leaderboard_url": "https://polarishub.io/benchmarks/ames", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-reg", "name": "adme-novartis-cyp3a4-reg", "category": "ADME,SingleTask", "description": "Single regression task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-reg", "metric": "absolute_average_fold_error" }, { "id": "polaris:benchmark:dili", "name": "dili", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/dili", "leaderboard_url": "https://polarishub.io/benchmarks/dili", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4616-ec50", "name": "moleculeace-CHEMBL4616-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4616-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2971-ki", "name": "moleculeace-CHEMBL2971-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2971-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl237-ki", "name": "moleculeace-CHEMBL237-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl237-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rclint-1", "name": "adme-fang-RCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl231-ki", "name": "moleculeace-CHEMBL231-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl231-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl4792-ki", "name": "moleculeace-CHEMBL4792-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4792-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-cls-v2", "name": "pkis2-lok-slk-cls-v2", "category": "kinase,hit-discovery", "description": "Multitask classification benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "multitask", "description": "A multitask classification benchmark for binding predictions.", "url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "leaderboard_url": "https://polarishub.io/benchmarks/pcba-1328-1564k-v1", "metric": "f1" }, { "id": "polaris:benchmark:qm9-v1", "name": "qm9-v1", "category": "multitask", "description": "A multitask regression benchmark for QM9 dataset", "url": "https://polarishub.io/benchmarks/qm9-v1", "leaderboard_url": "https://polarishub.io/benchmarks/qm9-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl2034-ki", "name": "moleculeace-CHEMBL2034-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2034-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:ppbr-az", "name": "ppbr-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ppbr-az", "leaderboard_url": "https://polarishub.io/benchmarks/ppbr-az", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl287-ki", "name": "moleculeace-CHEMBL287-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl287-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:herg", "name": "herg", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/herg", "leaderboard_url": "https://polarishub.io/benchmarks/herg", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl4005-ki", "name": "moleculeace-CHEMBL4005-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl4005-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:vdss-lombardo", "name": "vdss-lombardo", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/vdss-lombardo", "leaderboard_url": "https://polarishub.io/benchmarks/vdss-lombardo", "metric": "spearmanr" }, { "id": "polaris:benchmark:bend-zeroshot-variant-effects-disease", "name": "bend-zeroshot-variant-effects-disease", "category": "benchmark", "description": "", "url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "leaderboard_url": "https://polarishub.io/benchmarks/bend-zeroshot-variant-effects-disease", "metric": "roc_auc" }, { "id": "polaris:benchmark:adme-fang-hclint-1", "name": "adme-fang-HCLint-1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_HLM_CLint", "url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-hclint-1", "metric": "pearsonr" }, { "id": "polaris:benchmark:pkis2-kit-wt-r-1", "name": "pkis2-kit-wt-r-1", "category": "kinase,hit-discovery", "description": "Singletask regression benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl262-ki", "name": "moleculeace-CHEMBL262-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl262-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-hepatocyte-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:rna-expression-prediction-dataset-task", "name": "rna-expression-prediction-dataset-task", "category": "benchmark", "description": "RNA expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/rna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "multitask", "description": "A multitask regression benchmark for ZINC12K dataset.", "url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "leaderboard_url": "https://polarishub.io/benchmarks/l1000-mcf7-v1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:rxrx-compound-gene-activity-benchmark", "name": "RxRx-compound-gene-activity-benchmark", "category": "gene,compound", "description": "This benchmark evaluates the zero-shot prediction of compound-gene activity. It is originally designed to be used with the rxrx.ai dataset releases in phenomics.", "url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/rxrx-compound-gene-activity-benchmark", "metric": "pr_auc_mean" }, { "id": "polaris:benchmark:posebusters-v1", "name": "posebusters_v1", "category": "Docking,SingleTask", "description": "Docking task benchmark for 428 proteins and ligands.", "url": "https://polarishub.io/benchmarks/posebusters-v1", "leaderboard_url": "https://polarishub.io/benchmarks/posebusters-v1", "metric": "rmsd_coverage" }, { "id": "polaris:benchmark:moleculeace-chembl204-ki", "name": "moleculeace-CHEMBL204-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl204-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-r-1", "name": "adme-fang-r-1", "category": "adme,multitask", "description": "A multitask benchmark for six ADME endpoints, utilizing a shared random split. ", "url": "https://polarishub.io/benchmarks/adme-fang-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:caco2-wang", "name": "caco2-wang", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/caco2-wang", "leaderboard_url": "https://polarishub.io/benchmarks/caco2-wang", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-lok-slk-r-1", "name": "pkis2-lok-slk-r-1", "category": "kinase,hit-discovery", "description": "Multitask regression benchmark for LOK and SLK wild type.", "url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-lok-slk-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hello-world-benchmark", "name": "hello-world-benchmark", "category": "benchmark", "description": "Single task regression for solibility", "url": "https://polarishub.io/benchmarks/hello-world-benchmark", "leaderboard_url": "https://polarishub.io/benchmarks/hello-world-benchmark", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-cls-v2", "name": "pkis2-kit-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis2-ret-wt-cls-v2", "name": "pkis2-ret-wt-cls-v2", "category": "Kinase,HitDiscovery", "description": "Single task classification benchmark for kinase RET wild type.", "url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-ret-wt-cls-v2", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-c-1", "name": "pkis1-kit-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask classification benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pkis1-kit-wt-mut-r-1", "name": "pkis1-kit-wt-mut-r-1", "category": "kinase,hit-discovery,selectivity", "description": "A multitask regression benchmark for KIT wild type, T670I mutant and KV560G_mutant.", "url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-kit-wt-mut-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-novartis-cyp3a4-cls", "name": "adme-novartis-cyp3a4-cls", "category": "ADME,SingleTask", "description": "Single classification task benchmark for CYP3A4 log_kobs", "url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "leaderboard_url": "https://polarishub.io/benchmarks/adme-novartis-cyp3a4-cls", "metric": "balanced_accuracy" }, { "id": "polaris:benchmark:molprop-250k-leadlike-r-1", "name": "molprop-250k-leadlike-r-1", "category": "representation,properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 leadlike compounds sourced from ZINC22, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-250k-leadlike-r-1", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:pkis1-ret-wt-mut-c-1", "name": "pkis1-ret-wt-mut-c-1", "category": "kinase,hit-discovery,selectivity", "description": "Multitask classification benchmark for RET wild type, mutant V804L, and mutant Y791F.", "url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis1-ret-wt-mut-c-1", "metric": "pr_auc" }, { "id": "polaris:benchmark:pgp-broccatelli", "name": "pgp-broccatelli", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/pgp-broccatelli", "leaderboard_url": "https://polarishub.io/benchmarks/pgp-broccatelli", "metric": "roc_auc" }, { "id": "polaris:benchmark:moleculeace-chembl218-ec50", "name": "moleculeace-CHEMBL218-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl218-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:adme-fang-rppb-reg-v1", "name": "adme-fang-RPPB-reg-v1", "category": "adme,singletask", "description": "Single task benchmark for ADME property LOG_RPPB", "url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "leaderboard_url": "https://polarishub.io/benchmarks/adme-fang-rppb-reg-v1", "metric": "pearsonr" }, { "id": "polaris:benchmark:moleculeace-chembl214-ki", "name": "moleculeace-CHEMBL214-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl214-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "leaderboard_url": "https://polarishub.io/benchmarks/lipophilicity-astrazeneca", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:molprop-leadlike-250k-reg-v2", "name": "molprop-leadlike-250k-reg-v2", "category": "Representation,Molecular Properties", "description": "A multitask benchmark designed to predict nine molecular properties for 250,000 compounds sourced from ZINC15, with a focus on molecular representation.", "url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "leaderboard_url": "https://polarishub.io/benchmarks/molprop-leadlike-250k-reg-v2", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cho-dna-expression-prediction-dataset-task", "name": "cho-dna-expression-prediction-dataset-task", "category": "benchmark", "description": "DNA CHO gene expression benchmark task with decile-based splits for balanced training and test datasets", "url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "leaderboard_url": "https://polarishub.io/benchmarks/cho-dna-expression-prediction-dataset-task", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:moleculeace-chembl2147-ki", "name": "moleculeace-CHEMBL2147-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl2147-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "leaderboard_url": "https://polarishub.io/benchmarks/cyp3a4-substrate-carbonmangels", "metric": "roc_auc" }, { "id": "polaris:benchmark:clearance-microsome-az", "name": "clearance-microsome-az", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/clearance-microsome-az", "leaderboard_url": "https://polarishub.io/benchmarks/clearance-microsome-az", "metric": "spearmanr" }, { "id": "polaris:benchmark:moleculeace-chembl239-ec50", "name": "moleculeace-CHEMBL239-EC50", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl239-ec50", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:moleculeace-chembl244-ki", "name": "moleculeace-CHEMBL244-Ki", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "leaderboard_url": "https://polarishub.io/benchmarks/moleculeace-chembl244-ki", "metric": "mean_squared_error" }, { "id": "polaris:benchmark:hia-hou", "name": "hia-hou", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/hia-hou", "leaderboard_url": "https://polarishub.io/benchmarks/hia-hou", "metric": "roc_auc" }, { "id": "polaris:benchmark:ld50-zhu", "name": "ld50-zhu", "category": "ADMET,singletask", "description": "", "url": "https://polarishub.io/benchmarks/ld50-zhu", "leaderboard_url": "https://polarishub.io/benchmarks/ld50-zhu", "metric": "mean_absolute_error" }, { "id": "polaris:benchmark:pkis2-kit-wt-c-1", "name": "pkis2-kit-wt-c-1", "category": "kinase,hit-discovery", "description": "Single task classification benchmark for kinase KIT wild type.", "url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "leaderboard_url": "https://polarishub.io/benchmarks/pkis2-kit-wt-c-1", "metric": "pr_auc" }, { "id": "polaris:dataset:drewry2014-pkis1-subset-v2", "name": "drewry2014-pkis1-subset-v2", "category": "dataset", "description": "A subset of PKIS dataset only including EGFR, RET, KIT kinases. PKIS is a data set of 367 small-molecule ATP-competitive kinase inhibitors that was screened by the set in activity assays with 224 recombinant kinases and 24 G protein-coupled receptors and in cellular assays of cancer cell proliferati", "url": "https://polarishub.io/datasets/drewry2014-pkis1-subset-v2" }, { "id": "polaris:dataset:moleculeace-chembl287-ki", "name": "moleculeace-chembl287-ki", "category": "dataset", "description": "Bioassay CHEMBL287 of protein Membrane receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl287-ki" }, { "id": "polaris:dataset:moleculeace-chembl3979-ec50", "name": "moleculeace-chembl3979-ec50", "category": "dataset", "description": "Bioassay CHEMBL3979 of protein Nuclear hormone receptor subfamily 1 group C member 2 molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl3979-ec50" }, { "id": "polaris:dataset:moleculeace-chembl4203-ki", "name": "moleculeace-chembl4203-ki", "category": "dataset", "description": "Bioassay CHEMBL4203 of protein CMGC protein kinase CLK family molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl4203-ki" }, { "id": "polaris:dataset:pm6-subset-v1", "name": "pm6-subset-v1", "category": "dataset", "description": "Subset of quantum chemistry dataset which uses PM6 semi-empirical computation of the quantum properties.", "url": "https://polarishub.io/datasets/pm6-subset-v1" }, { "id": "polaris:dataset:rxrx-compound-gene-activity", "name": "rxrx-compound-gene-activity", "category": "dataset", "description": "Mapping the mechanisms by which drugs exert their actions is an important challenge in advancing the use of high-dimensional biological data like phenomics. This dataset holds associations between various small molecules and genes. It is designed to accompany the RxRx3-Core dataset and OpenPhenomc-S", "url": "https://polarishub.io/datasets/rxrx-compound-gene-activity" }, { "id": "polaris:dataset:bend-histone-modification", "name": "bend-histone-modification", "category": "dataset", "description": "Multilabel classification of histone modifications in the K562 cell line from the BEND benchmark", "url": "https://polarishub.io/datasets/bend-histone-modification" }, { "id": "polaris:dataset:rna-expression-prediction", "name": "rna-expression-prediction", "category": "dataset", "description": "Collection of 13252 RNA samples with corresponding processed expression values (log scale clamped 0 to 1)", "url": "https://polarishub.io/datasets/rna-expression-prediction" }, { "id": "polaris:dataset:moleculeace-chembl236-ki", "name": "moleculeace-chembl236-ki", "category": "dataset", "description": "Bioassay CHEMBL236 of protein Opioid receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl236-ki" }, { "id": "polaris:dataset:cyp2c9-veith", "name": "cyp2c9-veith", "category": "dataset", "description": "CYP2C9 inhibition.", "url": "https://polarishub.io/datasets/cyp2c9-veith" }, { "id": "polaris:dataset:cho-dna-expression-prediction-dataset", "name": "cho-dna-expression-prediction-dataset", "category": "dataset", "description": "Collection of 11066 DNA samples from Chinese Hamster Ovary cells with corresponding processed expression values (log scale clamped 0 to 1)", "url": "https://polarishub.io/datasets/cho-dna-expression-prediction-dataset" }, { "id": "polaris:dataset:ames", "name": "ames", "category": "dataset", "description": "Drug mutagenicity.", "url": "https://polarishub.io/datasets/ames" }, { "id": "polaris:dataset:bbb-martins", "name": "bbb-martins", "category": "dataset", "description": "Ability of a drug to penetrate the blood-brain barrier.", "url": "https://polarishub.io/datasets/bbb-martins" }, { "id": "polaris:dataset:moleculeace-chembl2835-ki", "name": "moleculeace-chembl2835-ki", "category": "dataset", "description": "Bioassay CHEMBL2835 of protein Tyrosine protein kinase JakA family molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl2835-ki" }, { "id": "polaris:dataset:cyp2c9-substrate-carbonmangels", "name": "cyp2c9-substrate-carbonmangels", "category": "dataset", "description": "CYP2C9 substrate.", "url": "https://polarishub.io/datasets/cyp2c9-substrate-carbonmangels" }, { "id": "polaris:dataset:qm9-v1", "name": "qm9-v1", "category": "dataset", "description": "QM9 contains quantum chemical properties for a relevant, consistent, and comprehensive chemical space of small organic molecules", "url": "https://polarishub.io/datasets/qm9-v1" }, { "id": "polaris:dataset:cyp3a4-substrate-carbonmangels", "name": "cyp3a4-substrate-carbonmangels", "category": "dataset", "description": "CYP3A4 substrate.", "url": "https://polarishub.io/datasets/cyp3a4-substrate-carbonmangels" }, { "id": "polaris:dataset:cyp2d6-veith", "name": "cyp2d6-veith", "category": "dataset", "description": "CYP2D6 inhibition.", "url": "https://polarishub.io/datasets/cyp2d6-veith" }, { "id": "polaris:dataset:molprop-250k-1", "name": "molprop-250k-1", "category": "dataset", "description": " Molecule properties computed for ZINC15 250K dataset. Those molecular properties are used to examinate the usefullness of any pretrained models. Especially, any model for generation purpose should not fail on these tasks.", "url": "https://polarishub.io/datasets/molprop-250k-1" }, { "id": "polaris:dataset:moleculeace-chembl233-ki", "name": "moleculeace-chembl233-ki", "category": "dataset", "description": "Bioassay CHEMBL233 of protein Opioid receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl233-ki" }, { "id": "polaris:dataset:openplasmid-v1", "name": "openplasmid-v1", "category": "dataset", "description": "A dataset of ~150k multi-component plasmids originally deposited on Addgene. Features include textual descriptions, depositor/study information, annotated GenBank sequences and more.", "url": "https://polarishub.io/datasets/openplasmid-v1" }, { "id": "polaris:dataset:pcba-1328-1564k-v1", "name": "pcba-1328-1564k-v1", "category": "dataset", "description": "A subset of PubChem BioAssay, containing 1328 bioassays measured over 1564k compounds used by previous work to benchmark machine learning methods.", "url": "https://polarishub.io/datasets/pcba-1328-1564k-v1" }, { "id": "polaris:dataset:moleculeace-chembl2971-ki", "name": "moleculeace-chembl2971-ki", "category": "dataset", "description": "Bioassay CHEMBL2971 of protein Tyrosine protein kinase JakA family molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl2971-ki" }, { "id": "polaris:dataset:moleculeace-chembl228-ki", "name": "moleculeace-chembl228-ki", "category": "dataset", "description": "Bioassay CHEMBL228 of protein SLC06 neurotransmitter transporter family molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl228-ki" }, { "id": "polaris:dataset:moleculeace-chembl1862-ki", "name": "moleculeace-chembl1862-ki", "category": "dataset", "description": "Bioassay CHEMBL1862 of protein Tyrosine protein kinase Abl family molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl1862-ki" }, { "id": "polaris:dataset:moleculeace-chembl218-ec50", "name": "moleculeace-chembl218-ec50", "category": "dataset", "description": "Bioassay CHEMBL218 of protein Cannabinoid receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl218-ec50" }, { "id": "polaris:dataset:moleculeace-chembl234-ki", "name": "moleculeace-chembl234-ki", "category": "dataset", "description": "Bioassay CHEMBL234 of protein Dopamine receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl234-ki" }, { "id": "polaris:dataset:hello-world", "name": "hello-world", "category": "dataset", "description": "The two sdf files(hereby named 'solubility dataset') are originated from the Huuskonen dataset. The Huuskonen dataset contains a training set of 884 compounds and a randomly chosen test set of 413 compounds.", "url": "https://polarishub.io/datasets/hello-world" }, { "id": "polaris:dataset:az-solubility-v1", "name": "az-solubility-v1", "category": "dataset", "description": "Solubility in pH7.4 buffer experiment data released by AstraZeneca", "url": "https://polarishub.io/datasets/az-solubility-v1" }, { "id": "polaris:dataset:novartis-cyp3a4-v1", "name": "novartis-cyp3a4-v1", "category": "dataset", "description": "CYP3A4 Time-Dependent Inhibition data released by Novartis", "url": "https://polarishub.io/datasets/novartis-cyp3a4-v1" }, { "id": "polaris:dataset:moleculeace-chembl2047-ec50", "name": "moleculeace-chembl2047-ec50", "category": "dataset", "description": "Bioassay CHEMBL2047 of protein Nuclear hormone receptor subfamily 1 group H member 4 molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl2047-ec50" }, { "id": "polaris:dataset:cho-dna-expression-prediction-set", "name": "cho-dna-expression-prediction-set", "category": "dataset", "description": "Collection of 11066 DNA samples from Chinese Hamster Ovary cells with corresponding processed expression values (log scale clamped 0 to 1)", "url": "https://polarishub.io/datasets/cho-dna-expression-prediction-set" }, { "id": "polaris:dataset:proteingym", "name": "proteingym", "category": "dataset", "description": "The ProteinGym protein fitness prediction benchmark. Includes ~2.8 million mutants, including both pathogenicity prediction for clinical variants and experimental property prediction for deep mutational scans.", "url": "https://polarishub.io/datasets/proteingym" }, { "id": "polaris:dataset:hia-hou", "name": "hia-hou", "category": "dataset", "description": "Human intestinal absorption readout.", "url": "https://polarishub.io/datasets/hia-hou" }, { "id": "polaris:dataset:moleculeace-chembl214-ki", "name": "moleculeace-chembl214-ki", "category": "dataset", "description": "Bioassay CHEMBL214 of protein Serotonin receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl214-ki" }, { "id": "polaris:dataset:az-ppb-clearance-v1", "name": "az-ppb-clearance-v1", "category": "dataset", "description": "Log percent of compound unbound to whole human plasma (PPB) experiment data released by AstraZeneca", "url": "https://polarishub.io/datasets/az-ppb-clearance-v1" }, { "id": "polaris:dataset:egfr-binders-v1", "name": "EGFR_binders-v1", "category": "dataset", "description": "This dataset includes binding protein designs targeting the Epidermal growth factor receptor(EGFR), a drug target associated with various diseases.", "url": "https://polarishub.io/datasets/egfr-binders-v1" }, { "id": "polaris:dataset:molprop-leadlike-250k-v2", "name": "molprop-leadlike-250k-v2", "category": "dataset", "description": "Leadlike molecule properties computed for ZINC22 250K dataset. Those molecular properties are used to examine the usefulness of any pretrained models. Especially, any model for generation purpose should not fail on these tasks.", "url": "https://polarishub.io/datasets/molprop-leadlike-250k-v2" }, { "id": "polaris:dataset:clearance-microsome-az", "name": "clearance-microsome-az", "category": "dataset", "description": "Microsomal intrinsic clearance.", "url": "https://polarishub.io/datasets/clearance-microsome-az" }, { "id": "polaris:dataset:ld50-zhu", "name": "ld50-zhu", "category": "dataset", "description": "Acute toxicity LD50.", "url": "https://polarishub.io/datasets/ld50-zhu" }, { "id": "polaris:dataset:cyp2d6-substrate-carbonmangels", "name": "cyp2d6-substrate-carbonmangels", "category": "dataset", "description": "CYP2D6 substrate.", "url": "https://polarishub.io/datasets/cyp2d6-substrate-carbonmangels" }, { "id": "polaris:dataset:molprop-250k-v2", "name": "molprop-250k-v2", "category": "dataset", "description": " Molecule properties computed for ZINC15 250K dataset. Those molecular properties are used to examinate the usefullness of any pretrained models. Especially, any model for generation purpose should not fail on these tasks.", "url": "https://polarishub.io/datasets/molprop-250k-v2" }, { "id": "polaris:dataset:bend-variant-effects-disease", "name": "bend-variant-effects-disease", "category": "dataset", "description": "Binary classification of disease variants (ClinVar) from the BEND benchmark", "url": "https://polarishub.io/datasets/bend-variant-effects-disease" }, { "id": "polaris:dataset:kinase-pkis2-1", "name": "kinase-pkis2-1", "category": "dataset", "description": "A subset of PKIS 2 dataset only including EGFR, RET, KIT, LOK and SLK kinases. Profile of kinases PKIS2 which contains 640 small molecule for 468 kinases.", "url": "https://polarishub.io/datasets/kinase-pkis2-1" }, { "id": "polaris:dataset:moleculeace-chembl4792-ki", "name": "moleculeace-chembl4792-ki", "category": "dataset", "description": "Bioassay CHEMBL4792 of protein Orexin receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl4792-ki" }, { "id": "polaris:dataset:az-human-hlm-v1", "name": "az-human-hlm-v1", "category": "dataset", "description": "Intrinsic clearance measured in human liver microsomes experiment data released by AstraZeneca", "url": "https://polarishub.io/datasets/az-human-hlm-v1" }, { "id": "polaris:dataset:moleculeace-chembl237-ki", "name": "moleculeace-chembl237-ki", "category": "dataset", "description": "Bioassay CHEMBL237 of protein Opioid receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl237-ki" }, { "id": "polaris:dataset:moleculeace-chembl238-ki", "name": "moleculeace-chembl238-ki", "category": "dataset", "description": "Bioassay CHEMBL238 of protein SLC06 neurotransmitter transporter family molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl238-ki" }, { "id": "polaris:dataset:dili", "name": "dili", "category": "dataset", "description": "Drug induced liver injury.", "url": "https://polarishub.io/datasets/dili" }, { "id": "polaris:dataset:moleculeace-chembl244-ki", "name": "moleculeace-chembl244-ki", "category": "dataset", "description": "Bioassay CHEMBL244 of protein Serine protease S1A subfamily molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl244-ki" }, { "id": "polaris:dataset:fang-2023-dmpk", "name": "fang-2023-dmpk", "category": "dataset", "description": "120 prospective data sets, collected over 20 months across six ADME in vitro endpoints", "url": "https://polarishub.io/datasets/fang-2023-dmpk" }, { "id": "polaris:dataset:adme-fang-1", "name": "adme-fang-1", "category": "dataset", "description": "A DMPK datasets of six ADME in vitro endpoints from fang et al. 2023. ", "url": "https://polarishub.io/datasets/adme-fang-1" }, { "id": "polaris:dataset:caco2-wang", "name": "caco2-wang", "category": "dataset", "description": "Caco permeability readout.", "url": "https://polarishub.io/datasets/caco2-wang" }, { "id": "polaris:dataset:vdss-lombardo", "name": "vdss-lombardo", "category": "dataset", "description": "The volume of distribution at steady state", "url": "https://polarishub.io/datasets/vdss-lombardo" }, { "id": "polaris:dataset:az-logd-74-v1", "name": "az-logd-74-v1", "category": "dataset", "description": "Octan-1-ol/water (pH7.4) distribution coefficent experiment data released by AstraZeneca", "url": "https://polarishub.io/datasets/az-logd-74-v1" }, { "id": "polaris:dataset:rna-expression-prediction-dataset", "name": "rna-expression-prediction-dataset", "category": "dataset", "description": "Collection of 13252 RNA samples with corresponding processed expression values (log scale clamped 0 to 1)", "url": "https://polarishub.io/datasets/rna-expression-prediction-dataset" }, { "id": "polaris:dataset:tox21-v1", "name": "tox21-v1", "category": "dataset", "description": "The Tox21 compound structures and activity measurements for 12 different qHTS assays were extracted from the Tox21 Data Challenge", "url": "https://polarishub.io/datasets/tox21-v1" }, { "id": "polaris:dataset:moleculeace-chembl204-ki", "name": "moleculeace-chembl204-ki", "category": "dataset", "description": "Bioassay CHEMBL204 of protein Serine protease S1A subfamily molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl204-ki" }, { "id": "polaris:dataset:moleculeace-chembl231-ki", "name": "moleculeace-chembl231-ki", "category": "dataset", "description": "Bioassay CHEMBL231 of protein Histamine receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl231-ki" }, { "id": "polaris:dataset:d3r-cathepsin-c25s-v1", "name": "d3r-cathepsin-c25s-v1", "category": "dataset", "description": "Drug Design Data Resource Grand Challenge 4 Dataset: CathepsinS", "url": "https://polarishub.io/datasets/d3r-cathepsin-c25s-v1" }, { "id": "polaris:dataset:half-life-obach", "name": "half-life-obach", "category": "dataset", "description": "Half life duration.", "url": "https://polarishub.io/datasets/half-life-obach" }, { "id": "polaris:dataset:ncats-rlm-v1", "name": "ncats-rlm-v1", "category": "dataset", "description": "ADME RLM Stability experiment data released by the National Center for Advancing Translational Sciences", "url": "https://polarishub.io/datasets/ncats-rlm-v1" }, { "id": "polaris:dataset:moleculeace-chembl239-ec50", "name": "moleculeace-chembl239-ec50", "category": "dataset", "description": "Bioassay CHEMBL239 of protein Nuclear hormone receptor subfamily 1 group C member 1 molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl239-ec50" }, { "id": "polaris:dataset:moleculeace-chembl2147-ki", "name": "moleculeace-chembl2147-ki", "category": "dataset", "description": "Bioassay CHEMBL2147 of protein CAMK protein kinase PIM family molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl2147-ki" }, { "id": "polaris:dataset:moleculeace-chembl264-ki", "name": "moleculeace-chembl264-ki", "category": "dataset", "description": "Bioassay CHEMBL264 of protein Histamine receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl264-ki" }, { "id": "polaris:dataset:moleculeace-chembl1871-ki", "name": "moleculeace-chembl1871-ki", "category": "dataset", "description": "Bioassay CHEMBL1871 of protein Nuclear hormone receptor subfamily 3 group C member 4 molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl1871-ki" }, { "id": "polaris:dataset:kinase-pkis1-1", "name": "kinase-pkis1-1", "category": "dataset", "description": "A subset of PKIS dataset only including EGFR, RET, KIT kinases. PKIS is a data set of 367 small-molecule ATP-competitive kinase inhibitors that was screened by the set in activity assays with 224 recombinant kinases and 24 G protein-coupled receptors and in cellular assays of cancer cell proliferati", "url": "https://polarishub.io/datasets/kinase-pkis1-1" }, { "id": "polaris:dataset:ncats-solubility-v1", "name": "ncats-solubility-v1", "category": "dataset", "description": "ADME Solubility experiment data released by the National Center for Advancing Translational Sciences", "url": "https://polarishub.io/datasets/ncats-solubility-v1" }, { "id": "polaris:dataset:moleculeace-chembl262-ki", "name": "moleculeace-chembl262-ki", "category": "dataset", "description": "Bioassay CHEMBL262 of protein CMGC protein kinase GSK family molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl262-ki" }, { "id": "polaris:dataset:il7ra-binders-v1", "name": "IL7Ra_binders-v1", "category": "dataset", "description": "This dataset includes binding protein designs targeting the interleukin-7 receptor alpha chain (IL7RA), a drug target associated with various diseases.", "url": "https://polarishub.io/datasets/il7ra-binders-v1" }, { "id": "polaris:dataset:l1000-vcap-v1", "name": "l1000-vcap-v1", "category": "dataset", "description": "The LINCS L1000 is a database of high-throughput transcriptomics that screened more than 30,000 perturbations on a set of 978 landmark genes from prostate cancer cell line.", "url": "https://polarishub.io/datasets/l1000-vcap-v1" }, { "id": "polaris:dataset:molprop-250k-leadlike-1", "name": "molprop-250k-leadlike-1", "category": "dataset", "description": " Leadlike molecule properties computed for ZINC22 250K dataset. Those molecular properties are used to examine the usefulness of any pretrained models. Especially, any model for generation purpose should not fail on these tasks.", "url": "https://polarishub.io/datasets/molprop-250k-leadlike-1" }, { "id": "polaris:dataset:drewry2017-pkis2-subset-v2", "name": "drewry2017-pkis2-subset-v2", "category": "dataset", "description": "Kinases are essential drug targets due to their roles in cellular signaling and disease involvement, such as in cancer and inflammation. The PKIS2 dataset, with 645 kinase inhibitors from GSK, Takeda, and Pfizer, provides diverse chemotypes. The assays were carried out by one group under a consisten", "url": "https://polarishub.io/datasets/drewry2017-pkis2-subset-v2" }, { "id": "polaris:dataset:pgp-broccatelli", "name": "pgp-broccatelli", "category": "dataset", "description": "Pgp inhibition potency.", "url": "https://polarishub.io/datasets/pgp-broccatelli" }, { "id": "polaris:dataset:moleculeace-chembl235-ec50", "name": "moleculeace-chembl235-ec50", "category": "dataset", "description": "Bioassay CHEMBL235 of protein Nuclear hormone receptor subfamily 1 group C member 3 molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl235-ec50" }, { "id": "polaris:dataset:lipophilicity-astrazeneca", "name": "lipophilicity-astrazeneca", "category": "dataset", "description": "Activity of lipophilicity.", "url": "https://polarishub.io/datasets/lipophilicity-astrazeneca" }, { "id": "polaris:dataset:bend-variant-effects-expression", "name": "bend-variant-effects-expression", "category": "dataset", "description": "Binary classification of expression variants (eQTLs) from the BEND benchmark", "url": "https://polarishub.io/datasets/bend-variant-effects-expression" }, { "id": "polaris:dataset:moleculeace-chembl4005-ki", "name": "moleculeace-chembl4005-ki", "category": "dataset", "description": "Bioassay CHEMBL4005 of protein Transferase molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl4005-ki" }, { "id": "polaris:dataset:l1000-mcf7-v1", "name": "l1000-mcf7-v1", "category": "dataset", "description": "The LINCS L1000 is a database of high-throughput transcriptomics that screened more than 30,000 perturbations on a set of 978 landmark genes from human breast cancer cell line.", "url": "https://polarishub.io/datasets/l1000-mcf7-v1" }, { "id": "polaris:dataset:moleculeace-chembl4616-ec50", "name": "moleculeace-chembl4616-ec50", "category": "dataset", "description": "Bioassay CHEMBL4616 of protein GRP-related receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl4616-ec50" }, { "id": "polaris:dataset:rna-expression-prediction-set", "name": "rna-expression-prediction-set", "category": "dataset", "description": "Collection of 13252 RNA samples with corresponding processed expression values (log scale clamped 0 to 1)", "url": "https://polarishub.io/datasets/rna-expression-prediction-set" }, { "id": "polaris:dataset:herg", "name": "herg", "category": "dataset", "description": "hERG inhibition.", "url": "https://polarishub.io/datasets/herg" }, { "id": "polaris:dataset:ncats-cyp-v1", "name": "ncats-cyp-v1", "category": "dataset", "description": "ADME Cytochrome P450 CYP2D6, CYP3A4, CYP2C9 antagonist experiment data released by the National Center for Advancing Translational Sciences", "url": "https://polarishub.io/datasets/ncats-cyp-v1" }, { "id": "polaris:dataset:motifhallu", "name": "motifhallu", "category": "dataset", "description": "Test the molecule perception of molecular LLMs by querying the existence of motifs", "url": "https://polarishub.io/datasets/motifhallu" }, { "id": "polaris:dataset:posebusters-v1", "name": "posebusters-v1", "category": "dataset", "description": "A diverse datasset of recent high-quality protein\u2013ligand complexes which contain drug-like molecules for AI-based docking method evaluation.", "url": "https://polarishub.io/datasets/posebusters-v1" }, { "id": "polaris:dataset:cyp3a4-veith", "name": "cyp3a4-veith", "category": "dataset", "description": "CYP3A4 inhibition.", "url": "https://polarishub.io/datasets/cyp3a4-veith" }, { "id": "polaris:dataset:moleculeace-chembl2034-ki", "name": "moleculeace-chembl2034-ki", "category": "dataset", "description": "Bioassay CHEMBL2034 of protein Nuclear hormone receptor subfamily 3 group C member 1 molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl2034-ki" }, { "id": "polaris:dataset:moleculeace-chembl237-ec50", "name": "moleculeace-chembl237-ec50", "category": "dataset", "description": "Bioassay CHEMBL237 of protein Opioid receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl237-ec50" }, { "id": "polaris:dataset:bioavailability-ma", "name": "bioavailability-ma", "category": "dataset", "description": "Activity of bioavailability.", "url": "https://polarishub.io/datasets/bioavailability-ma" }, { "id": "polaris:dataset:egfr-binders-v0", "name": "egfr-binders-v0", "category": "dataset", "description": "This dataset includes binding protein designs targeting the Epidermal growth factor receptor(EGFR), a drug target associated with various diseases.", "url": "https://polarishub.io/datasets/egfr-binders-v0" }, { "id": "polaris:dataset:zinc12k-v1", "name": "zinc12k-v1", "category": "dataset", "description": "A subset (12K) of ZINC molecular graphs (250K) dataset.", "url": "https://polarishub.io/datasets/zinc12k-v1" }, { "id": "polaris:dataset:adme-fang-v1", "name": "adme-fang-v1", "category": "dataset", "description": "Assessing ADME properties helps understand a drug candidate\u2019s interaction with the body in terms of absorption, distribution, metabolism, and excretion, essential for evaluating its efficacy, safety, and clinical potential. Fang et al. (2023) presented DMPK datasets gathered over 20 months, covering", "url": "https://polarishub.io/datasets/adme-fang-v1" }, { "id": "polaris:dataset:clearance-hepatocyte-az", "name": "clearance-hepatocyte-az", "category": "dataset", "description": "Hepatocytic intrinsic clearance.", "url": "https://polarishub.io/datasets/clearance-hepatocyte-az" }, { "id": "polaris:dataset:solubility-aqsoldb", "name": "solubility-aqsoldb", "category": "dataset", "description": "Aqeuous solubility.", "url": "https://polarishub.io/datasets/solubility-aqsoldb" }, { "id": "polaris:dataset:ppbr-az", "name": "ppbr-az", "category": "dataset", "description": "Plasma protein binding rate.", "url": "https://polarishub.io/datasets/ppbr-az" }, { "id": "polaris:dataset:moleculeace-chembl219-ki", "name": "moleculeace-chembl219-ki", "category": "dataset", "description": "Bioassay CHEMBL219 of protein Dopamine receptor molecular machine learning with activity cliffs.", "url": "https://polarishub.io/datasets/moleculeace-chembl219-ki" } ], "hosted_benchmarks_count": 996 }, { "id": "insilico-scienceaibench", "name": "ScienceAIBench", "kind": "meta-platform", "url": "https://scienceaibench.insilico.com/", "github": "N/A \u2014 hosted portal", "description": "Insilico Medicine's public scientific-AI benchmark portal. Spans biology (longevity, target ID), affinity/binding, ADMET, clinical trials, biologics, materials; leaderboards benchmark frontier LLMs (GPT-5.x, Claude Opus/Sonnet 4.x, Gemini 3, Grok 4.1, DeepSeek v3.2, Kimi K2.x).", "benchmarks_tracked": 227, "benchmark_count_asof": "2026-05-12", "count_methodology": "Fetched https://scienceaibench.insilico.com/api/benchmarks on 2026-05-12; meta.totalBenchmarks=227 across 7 taxonomy categories \u00d7 17 suites. Leaderboard submitters are external frontier LLMs (top entries: Grok 4.1, GPT 5.1/5.2, Claude Opus 4.5/4.6, Gemini 3 Flash, DeepSeek v3.2, Kimi K2.5). Not self-referential \u2014 Insilico's own models are not on the leaderboards.", "breakdown": { "Biology (TargetBench + Longevity)": 29, "Affinity and Binding": 94, "Chemical Synthesis (Retrosynthesis)": 2, "ADMET, PK & Safety": 50, "Clinical Trials (ClinBench Quarterly)": 25, "Biologics": 6, "Materials (MatBench + others)": 21 }, "host_organization": "Insilico Medicine", "primary_contacts": [ "Alex Zhavoronkov", "Alex Aliper", "Alex Zhebrak" ], "founded": "2025", "license_model": "CC-BY (per portal); academic-friendly", "flags": [], "rubric": { "rigor": 4, "coverage": 5, "maintenance": 5, "adoption": 4, "quality": 4, "accessibility": 5, "industry_relevance": 5 }, "notes": "Biggest of the three Insilico portals. Live leaderboards regenerate against frontier LLMs \u2014 therefore NOT flagged self-referential. Strong longevity / aging benchmark slice (unique). Moves up the aging-relevance ranking.", "composite_score": 90.6, "hosted_benchmarks": [ { "id": "sab:bio-targetbench-target-identification-cancer", "name": "Target Identification - Cancer", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Cancer. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-cancer", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-cancer", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-targetbench-target-identification-cardiovascular-disease", "name": "Target Identification - Cardiovascular disease", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Cardiovascular disease. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-cardiovascular-disease", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-cardiovascular-disease", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-targetbench-target-identification-endocrine-and-metabolic-diseases", "name": "Target Identification - Endocrine and metabolic diseases", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Endocrine and metabolic diseases. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-endocrine-and-metabolic-diseases", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-endocrine-and-metabolic-diseases", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-targetbench-target-identification-fibrotic-disease", "name": "Target Identification - Fibrotic disease", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Fibrotic disease. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-fibrotic-disease", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-fibrotic-disease", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-targetbench-target-identification-inflammation-and-immunology", "name": "Target Identification - Inflammation and Immunology", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Inflammation and Immunology. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-inflammation-and-immunology", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-inflammation-and-immunology", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-targetbench-target-identification-mental-or-behavioural-disorder", "name": "Target Identification - Mental or behavioural disorder", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Mental or behavioural disorder. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-mental-or-behavioural-disorder", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-mental-or-behavioural-disorder", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-targetbench-target-identification-neurologic-diseases", "name": "Target Identification - Neurologic diseases", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Neurologic diseases. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-neurologic-diseases", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-neurologic-diseases", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-targetbench-target-identification-ophthalmology", "name": "Target Identification - Ophthalmology", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Ophthalmology. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-ophthalmology", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-ophthalmology", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-targetbench-target-identification-other-diseases-multi-causes", "name": "Target Identification - Other Diseases - Multi-Causes", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Other Diseases - Multi-Causes. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-other-diseases-multi-causes", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-other-diseases-multi-causes", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-targetbench-target-identification-reproductiveness-pregnancy-and-childbirth", "name": "Target Identification - Reproductiveness, Pregnancy and childbirth", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Reproductiveness, Pregnancy and childbirth. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-reproductiveness-pregnancy-and-childbirth", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-targetbench-target-identification-reproductiveness-pregnancy-and-childbirth", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-aging-prediction", "name": "Aging Prediction", "category": "Biology", "suite": "Longevity Benchmark", "description": "General aging-related prediction task.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-aging-prediction", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-aging-prediction", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-gtex-expression", "name": "GTEx Expression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Gene expression level prediction from GTEx data.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-expression", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-expression", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-gtex-generative", "name": "GTEx Generative", "category": "Biology", "suite": "Longevity Benchmark", "description": "Generative task for GTEx gene expression patterns.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-generative", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-generative", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-gtex-pairwise-binary", "name": "GTEx Pairwise Binary", "category": "Biology", "suite": "Longevity Benchmark", "description": "Binary pairwise comparison of gene expression from GTEx.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-binary", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-binary", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-gtex-pairwise-ternary", "name": "GTEx Pairwise Ternary", "category": "Biology", "suite": "Longevity Benchmark", "description": "Ternary pairwise comparison of GTEx gene expression.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-ternary", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-ternary", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-longevity-synergy-full", "name": "Longevity Synergy (Full)", "category": "Biology", "suite": "Longevity Benchmark", "description": "Predicting synergistic effects of longevity interventions (full context).", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-full", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-full", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-longevity-synergy-minimal", "name": "Longevity Synergy (Minimal)", "category": "Biology", "suite": "Longevity Benchmark", "description": "Predicting synergistic effects of longevity interventions (minimal context).", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-minimal", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-minimal", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-methylation-age-choice", "name": "Methylation Age Choice", "category": "Biology", "suite": "Longevity Benchmark", "description": "Multiple choice task for methylation-based age prediction.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-choice", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-choice", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-methylation-age-pairwise", "name": "Methylation Age Pairwise", "category": "Biology", "suite": "Longevity Benchmark", "description": "Comparing biological age from DNA methylation patterns.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-pairwise", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-pairwise", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-methylation-age-regression", "name": "Methylation Age Regression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Regression task for exact biological age from methylation.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-regression", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-regression", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:bio-longevity-benchmark-nhanes-mortality-classification", "name": "NHANES Mortality Classification", "category": "Biology", "suite": "Longevity Benchmark", "description": "Binary classification of mortality risk using NHANES health survey data.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-mortality-classification", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-mortality-classification", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-nhanes-pairwise-comparison", "name": "NHANES Pairwise Comparison", "category": "Biology", "suite": "Longevity Benchmark", "description": "Pairwise comparison of individuals based on health indicators.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-pairwise-comparison", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-pairwise-comparison", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-nhanes-time-to-event", "name": "NHANES Time-to-Event", "category": "Biology", "suite": "Longevity Benchmark", "description": "Multi-class time-to-event prediction from NHANES data.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-time-to-event", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-time-to-event", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-nhanes-tte-regression", "name": "NHANES TTE Regression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Regression task for exact time-to-event prediction.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-tte-regression", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-tte-regression", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-olink-generative", "name": "Olink Generative", "category": "Biology", "suite": "Longevity Benchmark", "description": "Generative task for Olink protein biomarkers.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-olink-generative", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-olink-generative", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-olink-pairwise-comparison", "name": "Olink Pairwise Comparison", "category": "Biology", "suite": "Longevity Benchmark", "description": "Pairwise comparison using Olink protein biomarkers.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-olink-pairwise-comparison", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-olink-pairwise-comparison", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-olink-protein-classification", "name": "Olink Protein Classification", "category": "Biology", "suite": "Longevity Benchmark", "description": "Classifying samples based on Olink proteomics markers.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-olink-protein-classification", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-olink-protein-classification", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-synergy-regression", "name": "Synergy Regression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Regression task for quantifying synergy effects.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-synergy-regression", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-synergy-regression", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-longevity-benchmark-tcga-survival-prediction", "name": "TCGA Survival Prediction", "category": "Biology", "suite": "Longevity Benchmark", "description": "Predicting cancer patient survival outcomes from TCGA genomic data.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-tcga-survival-prediction", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-longevity-benchmark-tcga-survival-prediction", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht1a-ic50", "name": "5-HT1A IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT1A IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht1a-ki", "name": "5-HT1A KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT1A KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht1c-ki", "name": "5-HT1C KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT1C KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1c-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1c-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht2a-ic50", "name": "5-HT2A IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT2A IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht2a-ki", "name": "5-HT2A KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT2A KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht2b-ki", "name": "5-HT2B KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT2B KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2b-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2b-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht5a-ki", "name": "5-HT5A KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT5A KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht5a-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht5a-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht6-ic50", "name": "5-HT6 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT6 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht6-ki", "name": "5-HT6 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT6 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-5-ht7-ki", "name": "5-HT7 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR 5-HT7 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht7-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht7-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-a1-ic50", "name": "A1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR A1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-a1-ki", "name": "A1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR A1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-a2a-ic50", "name": "A2A IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR A2A IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-a2a-ki", "name": "A2A KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR A2A KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-a2b-ic50", "name": "A2B IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR A2B IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-a2b-ki", "name": "A2B KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR A2B KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-a3-ki", "name": "A3 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR A3 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a3-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a3-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-alpha1a-ki", "name": "ALPHA1A KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR ALPHA1A KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-alpha1a-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-alpha1a-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-b1-ic50", "name": "B1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR B1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-b1-ki", "name": "B1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR B1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-casr-ic50", "name": "CASR IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CASR IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-casr-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-casr-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-cb1-ic50", "name": "CB1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CB1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-cb1-ki", "name": "CB1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CB1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-cb2-ic50", "name": "CB2 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CB2 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-cb2-ki", "name": "CB2 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CB2 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ccr1-ic50", "name": "CCR1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CCR1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ccr2-ic50", "name": "CCR2 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CCR2 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr2-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr2-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ccr3-ic50", "name": "CCR3 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CCR3 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr3-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr3-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ccr5-ic50", "name": "CCR5 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CCR5 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr5-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr5-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-crhr1-ic50", "name": "CRHR1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CRHR1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-crhr1-ki", "name": "CRHR1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CRHR1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-cxcr3-ic50", "name": "CXCR3 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CXCR3 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr3-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr3-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-cxcr4-ic50", "name": "CXCR4 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR CXCR4 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr4-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr4-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-d1-ki", "name": "D1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR D1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-d2-ic50", "name": "D2 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR D2 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-d2-ki", "name": "D2 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR D2 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-d3-ki", "name": "D3 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR D3 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d3-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d3-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-d4-ki", "name": "D4 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR D4 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d4-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d4-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ep2-ic50", "name": "EP2 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR EP2 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep2-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep2-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ep4-ic50", "name": "EP4 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR EP4 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep4-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep4-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-eta-ic50", "name": "ETA IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR ETA IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-eta-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-eta-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ghs-r-ic50", "name": "GHS-R IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR GHS-R IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ghs-r-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ghs-r-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-glucagon-ic50", "name": "GLUCAGON IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR GLUCAGON IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-glucagon-ki", "name": "GLUCAGON KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR GLUCAGON KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-gnrhr-ic50", "name": "GNRHR IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR GNRHR IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-gnrhr-ki", "name": "GNRHR KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR GNRHR KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-gpr44-ic50", "name": "GPR44 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR GPR44 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-gpr44-ki", "name": "GPR44 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR GPR44 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-il8rb-ic50", "name": "IL8RB IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR IL8RB IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-il8rb-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-il8rb-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-machrm1-ic50", "name": "MACHRM1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MACHRM1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-machrm1-ki", "name": "MACHRM1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MACHRM1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-machrm2-ki", "name": "MACHRM2 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MACHRM2 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm2-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm2-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-machrm3-ki", "name": "MACHRM3 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MACHRM3 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm3-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm3-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-machrm4-ic50", "name": "MACHRM4 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MACHRM4 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-machrm4-ki", "name": "MACHRM4 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MACHRM4 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-mc3r-ki", "name": "MC3R KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MC3R KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc3r-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc3r-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-mc4r-ic50", "name": "MC4R IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MC4R IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-mc4r-ki", "name": "MC4R KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MC4R KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-mc5r-ki", "name": "MC5R KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MC5R KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc5r-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc5r-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-mglur1-ic50", "name": "MGLUR1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MGLUR1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-mglur2-ic50", "name": "MGLUR2 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MGLUR2 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur2-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur2-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-mglur5-ic50", "name": "MGLUR5 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MGLUR5 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-mglur5-ki", "name": "MGLUR5 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR MGLUR5 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-nk1-ki", "name": "NK1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR NK1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-nk2-ic50", "name": "NK2 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR NK2 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-nk2-ki", "name": "NK2 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR NK2 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-nk3-ic50", "name": "NK3 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR NK3 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-nk3-ki", "name": "NK3 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR NK3 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-npy1r-ki", "name": "NPY1R KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR NPY1R KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy1r-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy1r-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-npy2r-ic50", "name": "NPY2R IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR NPY2R IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy2r-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy2r-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-npy5r-ic50", "name": "NPY5R IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR NPY5R IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-npy5r-ki", "name": "NPY5R KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR NPY5R KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-oprd1-ic50", "name": "OPRD1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OPRD1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-oprd1-ki", "name": "OPRD1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OPRD1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-oprk1-ic50", "name": "OPRK1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OPRK1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-oprk1-ki", "name": "OPRK1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OPRK1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-oprm1-ic50", "name": "OPRM1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OPRM1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-oprm1-ki", "name": "OPRM1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OPRM1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ox1-ic50", "name": "OX1 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OX1 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ox1-ki", "name": "OX1 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OX1 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ox2-ic50", "name": "OX2 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OX2 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-ox2-ki", "name": "OX2 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR OX2 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-thrombin-ic50", "name": "THROMBIN IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR THROMBIN IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-thrombin-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-thrombin-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-v1a-ic50", "name": "V1A IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR V1A IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-v1a-ki", "name": "V1A KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR V1A KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-v2-ic50", "name": "V2 IC50", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR V2 IC50 affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-gpcr-affinity-suite-v2-ki", "name": "V2 KI", "category": "Affinity and Binding", "suite": "ISM Benchmarks: GPCRs", "description": "GPCR V2 KI affinity prediction (IC50 or Ki).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ki", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ki", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:aff-ic50-prediction-ic50-prediction-cold-drug", "name": "IC50 Prediction (Cold Drug)", "category": "Affinity and Binding", "suite": "ISM Benchmarks: IC50 Prediction", "description": "Evaluates IC50 (half-maximal inhibitory concentration) prediction using BindingDB dataset with Cold Drug split. IC50 is a fundamental measure of drug potency, representing the concentration of a compound required to inhibit a biological target by 50%. This benchmark tests model ability to predict IC50 values when provided with inhibitor SMILES and protein target sequences, using few-shot inference with ground truth examples from the training split.", "url": "https://scienceaibench.insilico.com/?benchmark=aff-ic50-prediction-ic50-prediction-cold-drug", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-ic50-prediction-ic50-prediction-cold-drug", "paper_url": null, "leaderboard_entries": 6 }, { "id": "sab:aff-molecular-mechanics-energy-mmff-energy-prediction", "name": "MMFF Energy Prediction", "category": "Affinity and Binding", "suite": "Molecular Mechanics Energy", "description": "Predicting Molecular Mechanics (MM) energy for diverse 3D conformations. A computationally designed drug is useless if it instantly unfolds or repels itself in physical reality. Ensuring small molecules have low-energy conformations is a vital sanity check in AI-driven drug design. Chemistry42 platform was used to generate diverse conformations for drug-like molecules; models predict the resulting MM energy.", "url": "https://scienceaibench.insilico.com/?benchmark=aff-molecular-mechanics-energy-mmff-energy-prediction", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-molecular-mechanics-energy-mmff-energy-prediction", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:aff-pdbbind-number-of-interactions-number-of-non-covalent-interactions", "name": "Number of Non-Covalent Interactions", "category": "Affinity and Binding", "suite": "PDBBind Number of Interactions", "description": "Evaluates prediction of the number of non-covalent interactions in protein-ligand complexes using LP-PDBBind dataset. Ground truth is generated by Chemistry42 protein pharmacophores engine. Dataset: LP-PDBBind (https://pubmed.ncbi.nlm.nih.gov/37645037/).", "url": "https://scienceaibench.insilico.com/?benchmark=aff-pdbbind-number-of-interactions-number-of-non-covalent-interactions", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-pdbbind-number-of-interactions-number-of-non-covalent-interactions", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:aff-pdbbind-restore-interactions-3d-interactions-restoration", "name": "3D Interactions Restoration", "category": "Affinity and Binding", "suite": "PDBBind Restore Interactions", "description": "Evaluates the ability to restore 3D protein-ligand interactions from LP-PDBBind dataset. Measures the ratio of restored interactions, power of restored interactions, and fake interactions, along with validity fraction.", "url": "https://scienceaibench.insilico.com/?benchmark=aff-pdbbind-restore-interactions-3d-interactions-restoration", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-pdbbind-restore-interactions-3d-interactions-restoration", "paper_url": null, "leaderboard_entries": 6 }, { "id": "sab:aff-pkis2-kinase-inhibition-suite-pkis2-egfr", "name": "PKIS2 EGFR", "category": "Affinity and Binding", "suite": "PKIS2 Kinase Inhibition Suite", "description": "Kinase inhibition prediction for EGFR (Published Kinase Inhibitor Set 2). Essential for designing selective kinase inhibitors in cancer therapy.", "url": "https://scienceaibench.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-egfr", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-egfr", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:aff-pkis2-kinase-inhibition-suite-pkis2-kit", "name": "PKIS2 KIT", "category": "Affinity and Binding", "suite": "PKIS2 Kinase Inhibition Suite", "description": "Kinase inhibition prediction for KIT (Published Kinase Inhibitor Set 2). Essential for designing selective kinase inhibitors in cancer therapy.", "url": "https://scienceaibench.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-kit", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-kit", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:aff-pkis2-kinase-inhibition-suite-pkis2-ret", "name": "PKIS2 RET", "category": "Affinity and Binding", "suite": "PKIS2 Kinase Inhibition Suite", "description": "Kinase inhibition prediction for RET (Published Kinase Inhibitor Set 2). Predicting how small molecules interact with the RET kinase pocket is essential for designing selective kinase inhibitors in cancer therapy.", "url": "https://scienceaibench.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-ret", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-ret", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:syn-retrosynthesis-suite-single-step-retrosynthesis-ursa-expert-2026-dataset", "name": "Single-step retrosynthesis, URSA-expert-2026 dataset", "category": "Chemical Synthesis", "suite": "ISM Benchmarks: Retrosynthesis", "description": "Evaluates single-step retrosynthesis task performance on URSA-expert-2026 dataset across various ChemCensor metrics.", "url": "https://scienceaibench.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-ursa-expert-2026-dataset", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-ursa-expert-2026-dataset", "paper_url": "https://arxiv.org/abs/2602.03554", "leaderboard_entries": 11 }, { "id": "sab:syn-retrosynthesis-suite-single-step-retrosynthesis-uspto-50k-test-sample-dataset", "name": "Single-step retrosynthesis, USPTO-50k-test sample dataset", "category": "Chemical Synthesis", "suite": "ISM Benchmarks: Retrosynthesis", "description": "Evaluates single-step retrosynthesis task performance on representative 10% sample from USPTO-50k-test dataset across various ChemCensor metrics.", "url": "https://scienceaibench.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-uspto-50k-test-sample-dataset", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-uspto-50k-test-sample-dataset", "paper_url": "https://arxiv.org/abs/2602.03554", "leaderboard_entries": 11 }, { "id": "sab:adm-ism-benchmarks-admet-bcrp-inhibition", "name": "BCRP Inhibition", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Breast Cancer Resistance Protein (BCRP/ABCG2) inhibition prediction. BCRP is an efflux transporter affecting oral absorption, tissue distribution, and renal/biliary excretion of drugs. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-bcrp-inhibition", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-bcrp-inhibition", "paper_url": null, "leaderboard_entries": 10 }, { "id": "sab:adm-ism-benchmarks-admet-caco-2-efflux-ratio", "name": "Caco-2 Efflux Ratio", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Caco-2 efflux ratio measures the ratio of basolateral-to-apical vs apical-to-basolateral transport, indicating active efflux by transporters like P-gp. High efflux ratios suggest limited oral absorption. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-efflux-ratio", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-efflux-ratio", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-caco-2-permeability", "name": "Caco-2 Permeability", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Caco-2 cell effective permeability (Papp) using human colon carcinoma cells to model passive diffusion and active transport in the intestine. A key predictor of oral drug absorption. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-permeability", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-permeability", "paper_url": null, "leaderboard_entries": 10 }, { "id": "sab:adm-ism-benchmarks-admet-clearance-human-hepatocytes", "name": "Clearance Human Hepatocytes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in human hepatocytes captures both Phase I (CYP-mediated) and Phase II (conjugation) metabolism. Provides a more complete metabolic assessment than microsomes. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-hepatocytes", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-hepatocytes", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-clearance-human-liver-microsomes", "name": "Clearance Human Liver Microsomes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in human liver microsomes (HLM) evaluates CYP-mediated oxidative metabolism. A standard early-stage assay for predicting hepatic clearance. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-liver-microsomes", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-liver-microsomes", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:adm-ism-benchmarks-admet-clearance-mouse-liver-microsomes", "name": "Clearance Mouse Liver Microsomes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in mouse liver microsomes (MLM). Mouse is a common preclinical species; predicting species-specific clearance is essential for PK translation. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-mouse-liver-microsomes", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-mouse-liver-microsomes", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:adm-ism-benchmarks-admet-clearance-rat-liver-microsomes", "name": "Clearance Rat Liver Microsomes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in rat liver microsomes (RLM). Rat is the most widely used preclinical species for PK studies. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-rat-liver-microsomes", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-rat-liver-microsomes", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:adm-ism-benchmarks-admet-cyp1a2-inhibition-ic50", "name": "CYP1A2 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP1A2 inhibition potency (IC50) prediction. CYP1A2 metabolizes several important drugs including caffeine and theophylline; inhibition can cause clinically significant drug-drug interactions. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp1a2-inhibition-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp1a2-inhibition-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-cyp2c19-inhibition-ic50", "name": "CYP2C19 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP2C19 inhibition potency (IC50) prediction. CYP2C19 is a highly polymorphic enzyme metabolizing proton pump inhibitors and clopidogrel. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c19-inhibition-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c19-inhibition-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-cyp2c9-inhibition-ic50", "name": "CYP2C9 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP2C9 inhibition potency (IC50) prediction. CYP2C9 metabolizes ~15% of clinical drugs including warfarin and NSAIDs; inhibition poses significant safety risks. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c9-inhibition-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c9-inhibition-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-cyp2d6-inhibition-ic50", "name": "CYP2D6 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP2D6 inhibition potency (IC50) prediction. CYP2D6 metabolizes ~25% of marketed drugs and is highly polymorphic in the population. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2d6-inhibition-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2d6-inhibition-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-cyp3a4-inhibition-ic50", "name": "CYP3A4 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP3A4 inhibition potency (IC50) prediction. CYP3A4 is the most abundant hepatic CYP, metabolizing ~50% of marketed drugs. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp3a4-inhibition-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp3a4-inhibition-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-half-life-human", "name": "Half Life Human", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Human plasma half-life (T1/2) in hours. Determines how long a drug remains active in the body and directly impacts dosing regimen design. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-half-life-human", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-half-life-human", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-hek293-cc50", "name": "HEK293 CC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CC50 (cytotoxic concentration 50%) in HEK293 cells measures the concentration required to reduce cell viability by 50%. Important for assessing compound toxicity and therapeutic window. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-hek293-cc50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-hek293-cc50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "sab:adm-ism-benchmarks-admet-hepg2-cc50", "name": "HepG2 CC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CC50 (cytotoxic concentration 50%) in HepG2 hepatocellular carcinoma cells. A key indicator of hepatotoxicity risk and general cytotoxicity. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-hepg2-cc50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-hepg2-cc50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "sab:adm-ism-benchmarks-admet-herg-ic50", "name": "hERG IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "hERG potassium channel inhibition potency (IC50) prediction. hERG inhibition causes QT prolongation and potentially fatal cardiac arrhythmias, making it a critical safety endpoint. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-herg-ic50", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-herg-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-kinetic-solubility", "name": "Kinetic Solubility", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Kinetic solubility measures the concentration at which a compound precipitates from a DMSO stock solution in aqueous buffer. A critical early-stage screening parameter for compound prioritization in drug discovery. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-kinetic-solubility", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-kinetic-solubility", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-logd", "name": "LogD", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "LogD (distribution coefficient at pH 7.4) measures the ratio of a compound's concentration in octanol vs aqueous phase accounting for ionization. A key physicochemical property affecting absorption and distribution. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-logd", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-logd", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-ism-benchmarks-admet-logp", "name": "LogP", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "LogP (partition coefficient) measures the lipophilicity of a neutral compound between octanol and water. A fundamental physicochemical descriptor influencing membrane permeability and drug-likeness. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-logp", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-logp", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-ism-benchmarks-admet-mdck-mdr1-efflux-ratio", "name": "MDCK-MDR1 Efflux Ratio", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "MDCK-MDR1 efflux ratio measures P-gp-mediated efflux using MDCK cells overexpressing MDR1. High efflux ratios indicate P-gp substrates likely to have limited oral absorption or CNS penetration. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-efflux-ratio", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-efflux-ratio", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-ism-benchmarks-admet-mdck-mdr1-permeability", "name": "MDCK-MDR1 Permeability", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "MDCK-MDR1 apparent permeability (Papp) measures drug transport across MDCK cells expressing the MDR1 P-glycoprotein transporter. Used to assess intestinal absorption and blood-brain barrier penetration. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-permeability", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-permeability", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-ism-benchmarks-admet-p-gp-inhibition", "name": "P-gp Inhibition", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "P-glycoprotein (P-gp/MDR1) inhibition prediction. P-gp is a major efflux transporter; its inhibition can alter pharmacokinetics and cause drug-drug interactions affecting absorption and brain exposure. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-p-gp-inhibition", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-p-gp-inhibition", "paper_url": null, "leaderboard_entries": 10 }, { "id": "sab:adm-ism-benchmarks-admet-pampa-permeability", "name": "PAMPA Permeability", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Parallel Artificial Membrane Permeability Assay (PAMPA) provides a cell-free, high-throughput measure of passive transcellular permeability. Complementary to Caco-2 for absorption prediction. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-pampa-permeability", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-pampa-permeability", "paper_url": null, "leaderboard_entries": 10 }, { "id": "sab:adm-ism-benchmarks-admet-ppb-human", "name": "PPB Human", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Plasma protein binding (PPB) in human plasma. Only the unbound fraction of a drug can cross membranes and engage its target. Critical for efficacy predictions and dose selection. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-human", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-human", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:adm-ism-benchmarks-admet-ppb-mouse", "name": "PPB Mouse", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Plasma protein binding (PPB) in mouse plasma. Species-specific binding differences are essential for translating preclinical data to human. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-mouse", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-mouse", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:adm-ism-benchmarks-admet-ppb-rat", "name": "PPB Rat", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Plasma protein binding (PPB) in rat plasma. Species-specific binding is critical for PK translation from the most common preclinical species. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-rat", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-rat", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:adm-ism-benchmarks-admet-thermodynamic-solubility", "name": "Thermodynamic Solubility", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Thermodynamic solubility is the equilibrium solubility of the most stable crystalline form in aqueous media. A definitive measure of compound solubility important for formulation development. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-thermodynamic-solubility", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-thermodynamic-solubility", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-ism-benchmarks-admet-vdss", "name": "VDss", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Volume of distribution at steady state (VDss) measures how extensively a drug distributes from plasma into body tissues. A key PK parameter for dose calculation. Proprietary Chemistry42 data.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-vdss", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-ism-benchmarks-admet-vdss", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-tdc-admet-ames-mutagenicity", "name": "AMES Mutagenicity", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Ames mutagenicity test classification predicting whether a compound is mutagenic. The Ames test is a regulatory requirement for drug candidates and uses bacterial reverse mutation to detect genotoxic potential. 7,255 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-ames-mutagenicity", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-ames-mutagenicity", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-tdc-admet-bbb-penetration", "name": "BBB Penetration", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Blood-brain barrier penetration classification predicting whether a compound can cross the BBB. Essential for CNS drug design and for avoiding CNS-related toxicity in peripherally-targeted drugs. Dataset from Martins et al., 1,975 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-bbb-penetration", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-bbb-penetration", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-bioavailability", "name": "Bioavailability", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Oral bioavailability classification predicting whether a drug achieves sufficient systemic exposure after oral administration (>20% bioavailable = positive). Dataset from Ma et al., 640 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-bioavailability", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-bioavailability", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-caco-2-permeability", "name": "Caco-2 Permeability", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Caco-2 cell effective permeability measures a compound's ability to cross the intestinal epithelial barrier via passive diffusion and active transport. Essential for predicting oral drug absorption. Dataset from Wang et al., 906 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-caco-2-permeability", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-caco-2-permeability", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-clearance-hepatocyte", "name": "Clearance Hepatocyte", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Intrinsic clearance measured in hepatocytes (\u00b5L/min/10^6 cells). Provides a more physiologically complete assessment of drug metabolism than microsomes, capturing both Phase I and Phase II metabolism. Dataset from AstraZeneca, 1,020 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-clearance-hepatocyte", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-clearance-hepatocyte", "paper_url": null, "leaderboard_entries": 11 }, { "id": "sab:adm-tdc-admet-clearance-microsome", "name": "Clearance Microsome", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Intrinsic clearance measured in liver microsomes (mL/min/g). Reflects the rate of drug metabolism by microsomal enzymes, primarily CYP450s. Dataset from AstraZeneca, 1,102 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-clearance-microsome", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-clearance-microsome", "paper_url": null, "leaderboard_entries": 11 }, { "id": "sab:adm-tdc-admet-cyp2c9-inhibition", "name": "CYP2C9 Inhibition", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP2C9 inhibition classification predicting whether a compound inhibits the CYP2C9 enzyme. CYP2C9 metabolizes ~15% of clinically used drugs; inhibition can cause dangerous drug-drug interactions. Dataset from Veith et al., 12,092 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp2c9-inhibition", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp2c9-inhibition", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-cyp2c9-substrate", "name": "CYP2C9 Substrate", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP2C9 substrate classification predicting whether a compound is metabolized by the CYP2C9 enzyme. Important for predicting drug metabolism routes and potential drug-drug interactions. Dataset from CarbonMangels et al., 666 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp2c9-substrate", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp2c9-substrate", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-tdc-admet-cyp2d6-inhibition", "name": "CYP2D6 Inhibition", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP2D6 inhibition classification predicting whether a compound inhibits the CYP2D6 enzyme. CYP2D6 metabolizes ~25% of marketed drugs; inhibition can lead to severe adverse effects. Dataset from Veith et al., 13,130 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp2d6-inhibition", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp2d6-inhibition", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-cyp2d6-substrate", "name": "CYP2D6 Substrate", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP2D6 substrate classification predicting whether a compound is metabolized by the CYP2D6 enzyme. CYP2D6 is highly polymorphic, making substrate prediction critical for personalized medicine. Dataset from CarbonMangels et al., 664 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp2d6-substrate", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp2d6-substrate", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-cyp3a4-inhibition", "name": "CYP3A4 Inhibition", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP3A4 inhibition classification predicting whether a compound inhibits the CYP3A4 enzyme. Given CYP3A4's dominant role in drug metabolism, inhibition poses major drug-drug interaction risks. Dataset from Veith et al., 12,328 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp3a4-inhibition", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp3a4-inhibition", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-cyp3a4-substrate", "name": "CYP3A4 Substrate", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP3A4 substrate classification predicting whether a compound is metabolized by the CYP3A4 enzyme. CYP3A4 is the most abundant hepatic CYP and metabolizes ~50% of marketed drugs. Dataset from CarbonMangels et al., 667 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp3a4-substrate", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-cyp3a4-substrate", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-dili", "name": "DILI", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Drug-Induced Liver Injury (DILI) classification predicting whether a drug causes liver damage. DILI is a leading cause of drug withdrawals and clinical trial failures. 475 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-dili", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-dili", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-tdc-admet-half-life", "name": "Half Life", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Drug half-life (hours) measures the time required for the plasma concentration to decrease by 50%. Critical for determining dosing frequency and achieving steady-state concentrations. Dataset from Obach et al., 667 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-half-life", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-half-life", "paper_url": null, "leaderboard_entries": 11 }, { "id": "sab:adm-tdc-admet-herg-blockers", "name": "hERG Blockers", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "hERG channel blocker classification predicting whether a compound inhibits the human ether-\u00e0-go-go-related gene potassium channel. hERG inhibition can cause fatal cardiac arrhythmias (QT prolongation). Dataset from 648 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-herg-blockers", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-herg-blockers", "paper_url": null, "leaderboard_entries": 8 }, { "id": "sab:adm-tdc-admet-hia", "name": "HIA", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Human intestinal absorption (HIA) classification predicting whether a drug is absorbed through the human intestine (>80% absorbed = positive). A critical first step in oral drug bioavailability. Dataset from Hou et al., 578 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-hia", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-hia", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-ld50-acute-toxicity", "name": "LD50 Acute Toxicity", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Acute toxicity prediction as LD50 in log(1/(mol/kg)). LD50 is the dose required to kill 50% of test animals and is a fundamental safety metric in drug development. Dataset from Zhu et al., 7,385 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-ld50-acute-toxicity", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-ld50-acute-toxicity", "paper_url": null, "leaderboard_entries": 6 }, { "id": "sab:adm-tdc-admet-lipophilicity", "name": "Lipophilicity", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Experimental lipophilicity measured as octanol/water distribution coefficient (logD at pH 7.4). A key physicochemical property influencing absorption, distribution, metabolism, and toxicity. Dataset from AstraZeneca, 4,200 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-lipophilicity", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-lipophilicity", "paper_url": null, "leaderboard_entries": 10 }, { "id": "sab:adm-tdc-admet-p-gp-inhibition", "name": "P-gp Inhibition", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "P-glycoprotein (P-gp) inhibition classification. P-gp is an efflux transporter that limits oral drug absorption and brain penetration. Inhibiting P-gp can alter drug pharmacokinetics and cause drug-drug interactions. Dataset from Broccatelli et al., 1,212 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-p-gp-inhibition", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-p-gp-inhibition", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-ppbr", "name": "PPBR", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Plasma protein binding rate (%) from AstraZeneca. Only the unbound fraction of a drug is pharmacologically active; high binding reduces free drug concentration and can affect efficacy and clearance. 1,797 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-ppbr", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-ppbr", "paper_url": null, "leaderboard_entries": 7 }, { "id": "sab:adm-tdc-admet-solubility", "name": "Solubility", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Aqueous solubility prediction in log mol/L. Solubility directly impacts oral bioavailability and is a critical parameter in drug formulation and development. Dataset from AqSolDB, 9,982 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-solubility", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-solubility", "paper_url": null, "leaderboard_entries": 10 }, { "id": "sab:adm-tdc-admet-vdss", "name": "VDss", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Volume of distribution at steady state (L/kg) measures how extensively a drug distributes from plasma into body tissues. A key pharmacokinetic parameter for determining dosing regimens. Dataset from Lombardo et al., 1,130 compounds.", "url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-vdss", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=adm-tdc-admet-vdss", "paper_url": null, "leaderboard_entries": 11 }, { "id": "sab:cli-clinbench-quarterly-all-phases-2025q1", "name": "All Phases - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q1. N=356 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-all-phases-2025q2", "name": "All Phases - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q2. N=454 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q2", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-all-phases-2025q3", "name": "All Phases - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q3. N=297 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q3", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-all-phases-2025q4", "name": "All Phases - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q4. N=293 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q4", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-all-phases-2026q1", "name": "All Phases - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2026Q1. N=87 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2026q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-1-2025q1", "name": "Phase 1 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q1. N=56 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-1-2025q2", "name": "Phase 1 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q2. N=127 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q2", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-1-2025q3", "name": "Phase 1 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q3. N=30 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q3", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-1-2025q4", "name": "Phase 1 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q4. N=23 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q4", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-1-2026q1", "name": "Phase 1 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2026Q1. N=3 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2026q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-2-2025q1", "name": "Phase 2 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q1. N=146 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-2-2025q2", "name": "Phase 2 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q2. N=163 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q2", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-2-2025q3", "name": "Phase 2 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q3. N=145 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q3", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-2-2025q4", "name": "Phase 2 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q4. N=114 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q4", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-2-2026q1", "name": "Phase 2 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2026Q1. N=40 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2026q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-3-2025q1", "name": "Phase 3 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q1. N=119 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-3-2025q2", "name": "Phase 3 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q2. N=133 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q2", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-3-2025q3", "name": "Phase 3 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q3. N=100 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q3", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-3-2025q4", "name": "Phase 3 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q4. N=113 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q4", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-3-2026q1", "name": "Phase 3 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2026Q1. N=38 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2026q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-4-2025q1", "name": "Phase 4 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q1. N=35 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-4-2025q2", "name": "Phase 4 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q2. N=31 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q2", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-4-2025q3", "name": "Phase 4 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q3. N=22 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q3", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-4-2025q4", "name": "Phase 4 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q4. N=43 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q4", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:cli-clinbench-quarterly-phase-4-2026q1", "name": "Phase 4 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2026Q1. N=6 samples.", "url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2026q1", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "sab:bio-polyreactivity-cho-polyreactivity", "name": "CHO Polyreactivity", "category": "Biologics", "suite": "Polyreactivity ", "description": "Evaluates antibody binding to CHO-cell membrane proteins (CHO) as a measure of polyreactivity. Polyreactivity is the propensity of an antibody to bind nonspecifically to unrelated antigens and is widely used as an indicator of nonspecific binding risk, which can impact antibody specificity, safety, and overall developability.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-polyreactivity-cho-polyreactivity", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-polyreactivity-cho-polyreactivity", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-polyreactivity-ovalbumin-polyreactivity", "name": "Ovalbumin Polyreactivity", "category": "Biologics", "suite": "Polyreactivity ", "description": "Evaluates antibody binding to Ovalbumin as a measure of polyreactivity. Polyreactivity is the propensity of an antibody to bind nonspecifically to unrelated antigens and is widely used as an indicator of nonspecific binding risk, which can impact antibody specificity, safety, and overall developability.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-polyreactivity-ovalbumin-polyreactivity", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-polyreactivity-ovalbumin-polyreactivity", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-sec-smac-sec-monomer", "name": "SEC %Monomer", "category": "Biologics", "suite": "SEC SMAC ", "description": "SEC %Monomer, assessed by size-exclusion chromatography, reflects the proportion of monomeric antibody and serves as an indicator of molecular integrity and aggregation risk, impacting stability, efficacy, manufacturability, and overall developability.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-sec-smac-sec-monomer", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-sec-smac-sec-monomer", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-sec-smac-smac", "name": "SMAC", "category": "Biologics", "suite": "SEC SMAC ", "description": "SMAC measures antibody retention time using standup monolayer affinity chromatography, where longer retention reflects stronger surface interactions and provides insight into surface interaction propensity and developability-related biophysical characteristics.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-sec-smac-smac", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-sec-smac-smac", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-tm-and-titer-titer", "name": "Titer", "category": "Biologics", "suite": "Tm and Titer", "description": "Evaluates titer using Spearman correlation.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-tm-and-titer-titer", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-tm-and-titer-titer", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:bio-tm-and-titer-tm", "name": "Tm", "category": "Biologics", "suite": "Tm and Titer", "description": "Evaluates Tm using Spearman correlation.", "url": "https://scienceaibench.insilico.com/?benchmark=bio-tm-and-titer-tm", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=bio-tm-and-titer-tm", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-2d-exfoliation-energy", "name": "2D Exfoliation Energy", "category": "Materials", "suite": "MatBench", "description": "Prediction of exfoliation energy (meV) from crystal structure. 636 structures from the JARVIS-DFT 2D database.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-2d-exfoliation-energy", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-2d-exfoliation-energy", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-experimental-band-gap", "name": "Experimental Band Gap", "category": "Materials", "suite": "MatBench", "description": "Prediction of experimentally measured band gap (eV) from chemical formula. 4,604 compounds from the AFLOW database.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-experimental-band-gap", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-experimental-band-gap", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-glass-forming-ability", "name": "Glass Forming Ability", "category": "Materials", "suite": "MatBench", "description": "Classification of glass forming ability from chemical formula. Predicts whether a composition forms an amorphous phase. 5,680 compositions.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-glass-forming-ability", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-glass-forming-ability", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-metalnon-metal-classification", "name": "Metal/Non-Metal Classification", "category": "Materials", "suite": "MatBench", "description": "Classification of materials as metal or non-metal from chemical formula. 4,921 compositions from the AFLOW database.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-metalnon-metal-classification", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-metalnon-metal-classification", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-mp-band-gap-pbe", "name": "MP Band Gap (PBE)", "category": "Materials", "suite": "MatBench", "description": "Prediction of PBE band gap (eV) from crystal structure. 1,000 structures (sampled from 106,113) from the Materials Project.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-mp-band-gap-pbe", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-mp-band-gap-pbe", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-mp-formation-energy", "name": "MP Formation Energy", "category": "Materials", "suite": "MatBench", "description": "Prediction of DFT formation energy per atom (eV/atom) from crystal structure. 1,000 structures (sampled from 132,752) from the Materials Project.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-mp-formation-energy", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-mp-formation-energy", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-mp-metalnon-metal-classification", "name": "MP Metal/Non-Metal Classification", "category": "Materials", "suite": "MatBench", "description": "Classification of materials as metal or non-metal from crystal structure. 1,000 structures (sampled from 106,113) from the Materials Project.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-mp-metalnon-metal-classification", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-mp-metalnon-metal-classification", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-perovskite-formation-energy", "name": "Perovskite Formation Energy", "category": "Materials", "suite": "MatBench", "description": "Prediction of heat of formation (eV) of 5-atom perovskite cells from crystal structure. 1,000 structures (sampled from 18,928) computed by RPBE GGA-DFT.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-perovskite-formation-energy", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-perovskite-formation-energy", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-phonon-peak-frequency", "name": "Phonon Peak Frequency", "category": "Materials", "suite": "MatBench", "description": "Prediction of the highest frequency optical phonon mode peak (1/cm) from crystal structure. 1,265 structures from the Materials Project.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-phonon-peak-frequency", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-phonon-peak-frequency", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-refractive-index", "name": "Refractive Index", "category": "Materials", "suite": "MatBench", "description": "Prediction of refractive index from crystal structure. 1,000 structures (sampled from 4,764) from the Materials Project.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-refractive-index", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-refractive-index", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-shear-modulus-log-g_vrh", "name": "Shear Modulus (log G_VRH)", "category": "Materials", "suite": "MatBench", "description": "Prediction of log10 of DFT Voigt-Reuss-Hill shear modulus (GPa) from crystal structure. 1,000 structures (sampled from 10,987) from the Materials Project.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-shear-modulus-log-g_vrh", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-shear-modulus-log-g_vrh", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-matbench-steel-yield-strength", "name": "Steel Yield Strength", "category": "Materials", "suite": "MatBench", "description": "Prediction of experimentally measured steel yield strengths (MPa) from chemical formula. 312 steel compositions from the Citrine dataset.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-steel-yield-strength", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-matbench-steel-yield-strength", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-properties-prediction-for-materials-accessible-surface-area-asa", "name": "Accessible Surface Area (ASA)", "category": "Materials", "suite": "Properties prediction for materials", "description": "Accessible Surface Area (ASA) is the probe-accessible internal surface of a porous framework, computed by rolling a spherical probe of radius 1.65 Angstrom (CO2-sized) over the framework atoms treated as hard spheres. Zeo++ determines accessibility via Voronoi-network analysis and includes only surfaces reachable by the probe center through the connected pore system. The -ha option ensures high-resolution sampling. The value is reported in m^2/g.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-accessible-surface-area-asa", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-accessible-surface-area-asa", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-properties-prediction-for-materials-accessible-volume-av", "name": "Accessible Volume (AV)", "category": "Materials", "suite": "Properties prediction for materials", "description": "Accessible Volume is the probe-accessible void space inside a porous framework, defined as the volume that can be occupied by the center of a spherical probe of radius 1.65 Angstrom (CO2-sized). Zeo++ determines accessibility using Voronoi-network analysis and includes only regions connected through the pore system that allow probe passage. The -ha option ensures high-resolution sampling. The value is reported in cm^3/g.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-accessible-volume-av", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-accessible-volume-av", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-properties-prediction-for-materials-band-gap", "name": "Band Gap", "category": "Materials", "suite": "Properties prediction for materials", "description": "Band gap (DFT, VASP): Electronic band gap computed from plane-wave periodic DFT using VASP with PBE exchange-correlation functional + Grimme D3 dispersion with Becke\u2013Johnson damping (D3(BJ)). Settings used during calculation: 520 eV cutoff; k-point density ~1000 per number of atoms; PAW potentials; symmetry disabled; SCF tolerance 1e-6 eV and max 150 iterations; Initial magnetic moments for spin-polarization: d-block metals (excluding Zn, Cd, Hg) initialized to 5 muB; f-block elements (excluding Lu, Lr) initialized to 7 muB; others to 0. The value is reported in eV.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-band-gap", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-band-gap", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-properties-prediction-for-materials-density", "name": "Density", "category": "Materials", "suite": "Properties prediction for materials", "description": "Density: Crystal density of the MOF (mass per unit cell volume). Density is calculated as the total molar mass of atoms in the unit cell divided by Avogadro's constant to obtain the unit cell mass, followed by division by the unit cell volume (converted from Angstrom^3 to cm^3). The result is reported in g/cm^3.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-density", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-density", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-properties-prediction-for-materials-dimensionality", "name": "Dimensionality", "category": "Materials", "suite": "Properties prediction for materials", "description": "Dimensionality (Larsen) is an integer in 0, 1, 2, or 3 describing how a bonded atomic network percolates through periodic boundary conditions in a crystal structure. It is computed from a bonded crystal graph and reports the highest dimensionality among all bonded components in the structure (e.g., framework + any guests). Output values (interpretation): 0D \u2014 isolated clusters / molecules / ions (finite in all directions); 1D \u2014 infinite chain (connectivity extends periodically along one lattice direction); 2D \u2014 infinite layer / sheet (extends along two independent directions); 3D \u2014 fully connected framework (extends along three independent lattice directions).", "url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-dimensionality", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-dimensionality", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-properties-prediction-for-materials-largest-cavity-diameter-lcd", "name": "Largest Cavity Diameter (LCD)", "category": "Materials", "suite": "Properties prediction for materials", "description": "The Largest Cavity Diameter (LCD or Largest Included Sphere, reported by Zeo++ as Di) is the diameter of the largest sphere that can be placed anywhere inside the structure's void space without intersecting the framework atoms (atoms are treated as hard spheres with assigned radii). It is a measure of the size of the largest cavity/pocket in the material. Zeo++ represents void space using a Voronoi-network (Voronoi decomposition) graph of the periodic structure and evaluates the maximum local clearance to the framework; LCD corresponds to twice the largest locally admissible sphere radius anywhere in the accessible void geometry. By default Zeo++ uses CCDC radii. The value is reported in Angstrom.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-largest-cavity-diameter-lcd", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-largest-cavity-diameter-lcd", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-properties-prediction-for-materials-net-magnetic-moment", "name": "Net Magnetic Moment", "category": "Materials", "suite": "Properties prediction for materials", "description": "Net magnetic moment (DFT, VASP): Total magnetic moment of the relaxed structure from plane-wave periodic DFT using VASP with PBE exchange-correlation functional + Grimme D3 dispersion with Becke\u2013Johnson damping (D3(BJ)). Settings used during calculation: 520 eV cutoff; k-point density ~1000 per number of atoms; PAW potentials; symmetry disabled; SCF tolerance 1e-6 eV and max 150 iterations; Initial magnetic moments for spin-polarization: d-block metals (excluding Zn, Cd, Hg) initialized to 5 muB; f-block elements (excluding Lu, Lr) initialized to 7 muB; others to 0. Magnetic moments allowed to relax during SCF to a converged local-minimum configuration. The value is reported in muB per cell.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-net-magnetic-moment", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-net-magnetic-moment", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-properties-prediction-for-materials-open-metal-site-oms", "name": "Open Metal Site (OMS)", "category": "Materials", "suite": "Properties prediction for materials", "description": "OMS (open metal site) in MOFs is a metal ion or metal cluster/node that has at least one vacant coordination position (i.e., the metal is coordinatively unsaturated) that is exposed to the pore/void and can act as a Lewis-acid binding site for guest molecules. OMS are also commonly called CUS (coordinatively unsaturated sites) or OCS (open coordination sites). Many MOFs are synthesized with solvent or water molecules coordinated to the metal center. During activation (e.g., evacuation/heating/solvent exchange), these labile ligands can be removed, creating a coordination vacancy - the OMS/CUS. The value is reported to be boolean.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-open-metal-site-oms", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-open-metal-site-oms", "paper_url": null, "leaderboard_entries": 9 }, { "id": "sab:mat-properties-prediction-for-materials-pore-limiting-diameter-pld", "name": "Pore Limiting Diameter (PLD)", "category": "Materials", "suite": "Properties prediction for materials", "description": "The Pore Limiting Diameter (PLD, or Largest Free Sphere, reported by Zeo++ as Df) is the diameter of the largest sphere that can diffuse through the pore structure without overlapping with framework atoms. It represents the bottleneck for molecular diffusion in the material - the narrowest opening a molecule must pass through to traverse the pore network. Zeo++ analyzes the Voronoi network to find the minimum clearance along pathways through the accessible void space; Df corresponds to twice the smallest locally passable sphere radius on continuous paths through the structure. By default Zeo++ uses CCDC radii. The value is reported in Angstrom.", "url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-pore-limiting-diameter-pld", "leaderboard_url": "https://scienceaibench.insilico.com/?benchmark=mat-properties-prediction-for-materials-pore-limiting-diameter-pld", "paper_url": null, "leaderboard_entries": 9 } ], "hosted_benchmarks_count": 227 }, { "id": "dream", "name": "DREAM Challenges", "kind": "competition", "url": "https://dreamchallenges.org/", "github": "https://github.com/dreamchallenges", "description": "Long-running crowd-sourced biomedical prediction challenges, many pharma-sponsored.", "benchmarks_tracked": 74, "benchmark_count_asof": "2026-05-12", "count_methodology": "dreamchallenges.org/closed-challenges + /active as of 2026-05: 74 completed/active challenges; ~38 drug-discovery-relevant.", "breakdown": { "drug_sensitivity": 9, "target_prediction": 6, "toxicity": 5, "disease_subtyping": 12, "other_biomed": 42 }, "host_organization": "Sage Bionetworks + IBM + academic partners", "primary_contacts": [ "Gustavo Stolovitzky", "Justin Guinney", "Pablo Meyer" ], "founded": "2006", "license_model": "Per-challenge (mostly CC-BY-NC)", "flags": [], "rubric": { "rigor": 5, "coverage": 4, "maintenance": 3, "adoption": 5, "quality": 5, "accessibility": 4, "industry_relevance": 5 }, "notes": "Historical impact on field norms. Cadence has slowed 2022+.", "composite_score": 89.4, "hosted_benchmarks": [ { "id": "dream:nci-dream-drug-sensitivity", "name": "NCI-DREAM Drug Sensitivity", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=NCI-DREAM%20Drug%20Sensitivity", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:astrazeneca-sanger-drug-combination-prediction", "name": "AstraZeneca-Sanger Drug Combination Prediction", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=AstraZeneca-Sanger%20Drug%20Combination%20Prediction", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream5-transcription-factor-binding", "name": "DREAM5 Transcription Factor Binding", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM5%20Transcription%20Factor%20Binding", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream-pancancer-drug-sensitivity", "name": "DREAM Pancancer Drug Sensitivity", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM%20Pancancer%20Drug%20Sensitivity", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:encode-dream-tf-binding", "name": "ENCODE-DREAM TF Binding", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=ENCODE-DREAM%20TF%20Binding", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream-somatic-mutation-calling", "name": "DREAM Somatic Mutation Calling", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM%20Somatic%20Mutation%20Calling", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream-idea-challenge", "name": "DREAM Idea Challenge", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM%20Idea%20Challenge", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream-proteogenomics", "name": "DREAM Proteogenomics", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM%20Proteogenomics", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream-tumor-deconvolution", "name": "DREAM Tumor Deconvolution", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM%20Tumor%20Deconvolution", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream-gene-essentiality", "name": "DREAM Gene Essentiality", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM%20Gene%20Essentiality", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream-single-cell-data-integration", "name": "DREAM Single-Cell Data Integration", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM%20Single-Cell%20Data%20Integration", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream-pooled-crispr", "name": "DREAM Pooled CRISPR", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM%20Pooled%20CRISPR", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:sc1-sc-rnaseq-benchmark", "name": "SC1 sc-RNAseq Benchmark", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=SC1%20sc-RNAseq%20Benchmark", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:digital-mammography-dream", "name": "Digital Mammography DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Digital%20Mammography%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:alzheimer-s-dream-challenge", "name": "Alzheimer\u2019s DREAM Challenge", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Alzheimer%E2%80%99s%20DREAM%20Challenge", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:preterm-birth-dream", "name": "Preterm Birth DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Preterm%20Birth%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:ra2-dream-challenge", "name": "RA2 DREAM Challenge", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=RA2%20DREAM%20Challenge", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:sleep-apnea-heart-rate-dream", "name": "Sleep Apnea Heart Rate DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Sleep%20Apnea%20Heart%20Rate%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:cancer-drug-response-dream", "name": "Cancer Drug Response DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Cancer%20Drug%20Response%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:smc-het-dream", "name": "SMC-Het DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=SMC-Het%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:smc-dna-dream", "name": "SMC-DNA DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=SMC-DNA%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:smc-rna-dream", "name": "SMC-RNA DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=SMC-RNA%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:icgc-tcga-dream", "name": "ICGC-TCGA DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=ICGC-TCGA%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:proteogenomics-nsclc-dream", "name": "Proteogenomics NSCLC DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Proteogenomics%20NSCLC%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:breast-cancer-dream", "name": "Breast Cancer DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Breast%20Cancer%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:multi-targeted-qsar-dream", "name": "Multi-Targeted QSAR DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Multi-Targeted%20QSAR%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:dream-pancan-survival", "name": "DREAM PANCAN Survival", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=DREAM%20PANCAN%20Survival", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:epitope-dream", "name": "Epitope DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Epitope%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" }, { "id": "dream:gene-expression-dream", "name": "Gene Expression DREAM", "category": "DREAM Challenge", "url": "https://dreamchallenges.org/?s=Gene%20Expression%20DREAM", "leaderboard_url": "https://dreamchallenges.org/" } ], "hosted_benchmarks_count": 29 }, { "id": "mimic", "name": "MIMIC-IV / eICU", "kind": "data-platform", "url": "https://physionet.org/content/mimiciv/", "github": "https://github.com/MIT-LCP/mimic-code", "description": "ICU EHR datasets used for clinical outcome, adverse-event, and PK/PD benchmarks.", "benchmarks_tracked": 14, "benchmark_count_asof": "2026-05-12", "count_methodology": "PhysioNet + BigBio MIMIC-IV benchmarks 2026-05: 14 derived benchmarks (mortality, LOS, readmission, sepsis, AKI, drug dosing, phenotyping).", "breakdown": { "outcome_prediction": 6, "drug_dosing": 3, "adverse_event": 3, "phenotyping": 2 }, "host_organization": "MIT Lab for Computational Physiology", "primary_contacts": [ "Leo Anthony Celi", "Alistair Johnson", "Roger Mark" ], "founded": "2016 / 2020 (v4)", "license_model": "PhysioNet credentialed", "flags": [], "rubric": { "rigor": 5, "coverage": 4, "maintenance": 5, "adoption": 5, "quality": 5, "accessibility": 3, "industry_relevance": 4 }, "notes": "Canonical for clinical ML. US-centric.", "composite_score": 89.4, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "czi-virtual-cell", "name": "CZI Virtual Cell / CellxGene / VCC", "kind": "consortium", "url": "https://chanzuckerberg.com/science/programs-resources/virtual-cells/", "github": "https://github.com/chanzuckerberg", "description": "Umbrella for CZI-funded virtual-cell benchmark initiatives: CellxGene, Virtual Cell Challenge, Tabula atlases.", "benchmarks_tracked": 12, "benchmark_count_asof": "2026-05-12", "count_methodology": "chanzuckerberg.com/science 2026-05: Virtual Cell Challenge (4 tracks), CellxGene Census benchmarks (4), Tabula Sapiens-derived eval suites (4).", "breakdown": { "virtual_cell_challenge": 4, "cellxgene": 4, "tabula": 4 }, "host_organization": "Chan Zuckerberg Initiative / CZ Biohub", "primary_contacts": [ "Jonah Cool", "Stephen Quake", "Ambrose Carr" ], "founded": "2016 / 2024 (VCC)", "license_model": "CC-BY 4.0", "flags": [], "rubric": { "rigor": 5, "coverage": 4, "maintenance": 5, "adoption": 4, "quality": 5, "accessibility": 4, "industry_relevance": 4 }, "notes": "VCC is becoming the canonical virtual-cell benchmark.", "composite_score": 88.9, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "open-reaction-database", "name": "Open Reaction Database (ORD)", "kind": "data-platform", "url": "https://open-reaction-database.org/", "github": "https://github.com/open-reaction-database", "description": "Open reaction repository in a schema-validated format; enables reaction / yield / retrosynthesis benchmarks.", "benchmarks_tracked": 1, "benchmark_count_asof": "2026-05-12", "count_methodology": "open-reaction-database.org 2026-05: ~2.1M reactions as single versioned benchmark corpus.", "breakdown": { "reactions": 2100000, "contributing_orgs": 30 }, "host_organization": "ORD consortium (Doyle, Coley, Pfizer, Merck, BASF)", "primary_contacts": [ "Connor Coley", "Abigail Doyle", "Steven Kearnes" ], "founded": "2021-07", "license_model": "CC-BY-SA 4.0", "flags": [], "rubric": { "rigor": 5, "coverage": 4, "maintenance": 4, "adoption": 4, "quality": 5, "accessibility": 5, "industry_relevance": 4 }, "notes": "Biggest open reaction corpus; industry donations accelerating.", "composite_score": 88.9, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "insilico-ddb", "name": "Drug Discovery Benchmarks (DDB)", "kind": "meta-platform", "url": "https://ddb.insilico.com/", "github": "N/A \u2014 hosted portal", "description": "Insilico's drug-discovery-specific benchmark portal: TargetBench, Longevity Benchmark, GPCR affinity, PDBbind-style tasks, ISM ADMET, TDC ADMET mirror, ClinBench, biologics.", "benchmarks_tracked": 206, "benchmark_count_asof": "2026-05-12", "count_methodology": "Fetched https://ddb.insilico.com/api/benchmarks on 2026-05-12; meta.totalBenchmarks=206 across 6 categories \u00d7 15 suites.", "breakdown": { "Biology (TargetBench + Longevity)": 29, "Affinity and Binding": 94, "Chemical Synthesis": 2, "ADMET, PK & Safety": 50, "Clinical Trials": 25, "Biologics": 6 }, "host_organization": "Insilico Medicine", "primary_contacts": [ "Alex Zhavoronkov", "Alex Aliper" ], "founded": "2025", "license_model": "CC-BY (per portal)", "flags": [], "rubric": { "rigor": 4, "coverage": 5, "maintenance": 5, "adoption": 3, "quality": 4, "accessibility": 5, "industry_relevance": 5 }, "notes": "Drug-discovery focused cut. Includes a mirror of TDC ADMET for cross-platform comparability.", "composite_score": 87.6, "hosted_benchmarks": [ { "id": "ddb:bio-targetbench-target-identification-cancer", "name": "Target Identification - Cancer", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Cancer. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-cancer", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-cancer", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-targetbench-target-identification-cardiovascular-disease", "name": "Target Identification - Cardiovascular disease", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Cardiovascular disease. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-cardiovascular-disease", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-cardiovascular-disease", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-targetbench-target-identification-endocrine-and-metabolic-diseases", "name": "Target Identification - Endocrine and metabolic diseases", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Endocrine and metabolic diseases. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-endocrine-and-metabolic-diseases", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-endocrine-and-metabolic-diseases", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-targetbench-target-identification-fibrotic-disease", "name": "Target Identification - Fibrotic disease", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Fibrotic disease. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-fibrotic-disease", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-fibrotic-disease", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-targetbench-target-identification-inflammation-and-immunology", "name": "Target Identification - Inflammation and Immunology", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Inflammation and Immunology. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-inflammation-and-immunology", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-inflammation-and-immunology", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-targetbench-target-identification-mental-or-behavioural-disorder", "name": "Target Identification - Mental or behavioural disorder", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Mental or behavioural disorder. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-mental-or-behavioural-disorder", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-mental-or-behavioural-disorder", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-targetbench-target-identification-neurologic-diseases", "name": "Target Identification - Neurologic diseases", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Neurologic diseases. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-neurologic-diseases", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-neurologic-diseases", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-targetbench-target-identification-ophthalmology", "name": "Target Identification - Ophthalmology", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Ophthalmology. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-ophthalmology", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-ophthalmology", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-targetbench-target-identification-other-diseases-multi-causes", "name": "Target Identification - Other Diseases - Multi-Causes", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Other Diseases - Multi-Causes. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-other-diseases-multi-causes", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-other-diseases-multi-causes", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-targetbench-target-identification-reproductiveness-pregnancy-and-childbirth", "name": "Target Identification - Reproductiveness, Pregnancy and childbirth", "category": "Biology", "suite": "TargetBench", "description": "Evaluation of AI models on target identification for Reproductiveness, Pregnancy and childbirth. Models are assessed on their ability to identify clinically relevant targets and predict high-quality novel targets.", "url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-reproductiveness-pregnancy-and-childbirth", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-targetbench-target-identification-reproductiveness-pregnancy-and-childbirth", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-aging-prediction", "name": "Aging Prediction", "category": "Biology", "suite": "Longevity Benchmark", "description": "General aging-related prediction task.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-aging-prediction", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-aging-prediction", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-gtex-expression", "name": "GTEx Expression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Gene expression level prediction from GTEx data.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-gtex-expression", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-gtex-expression", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-gtex-generative", "name": "GTEx Generative", "category": "Biology", "suite": "Longevity Benchmark", "description": "Generative task for GTEx gene expression patterns.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-gtex-generative", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-gtex-generative", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-gtex-pairwise-binary", "name": "GTEx Pairwise Binary", "category": "Biology", "suite": "Longevity Benchmark", "description": "Binary pairwise comparison of gene expression from GTEx.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-binary", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-binary", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-gtex-pairwise-ternary", "name": "GTEx Pairwise Ternary", "category": "Biology", "suite": "Longevity Benchmark", "description": "Ternary pairwise comparison of GTEx gene expression.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-ternary", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-ternary", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-longevity-synergy-full", "name": "Longevity Synergy (Full)", "category": "Biology", "suite": "Longevity Benchmark", "description": "Predicting synergistic effects of longevity interventions (full context).", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-full", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-full", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-longevity-synergy-minimal", "name": "Longevity Synergy (Minimal)", "category": "Biology", "suite": "Longevity Benchmark", "description": "Predicting synergistic effects of longevity interventions (minimal context).", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-minimal", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-minimal", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-methylation-age-choice", "name": "Methylation Age Choice", "category": "Biology", "suite": "Longevity Benchmark", "description": "Multiple choice task for methylation-based age prediction.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-choice", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-choice", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-methylation-age-pairwise", "name": "Methylation Age Pairwise", "category": "Biology", "suite": "Longevity Benchmark", "description": "Comparing biological age from DNA methylation patterns.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-pairwise", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-pairwise", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-methylation-age-regression", "name": "Methylation Age Regression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Regression task for exact biological age from methylation.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-regression", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-regression", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:bio-longevity-benchmark-nhanes-mortality-classification", "name": "NHANES Mortality Classification", "category": "Biology", "suite": "Longevity Benchmark", "description": "Binary classification of mortality risk using NHANES health survey data.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-mortality-classification", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-mortality-classification", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-nhanes-pairwise-comparison", "name": "NHANES Pairwise Comparison", "category": "Biology", "suite": "Longevity Benchmark", "description": "Pairwise comparison of individuals based on health indicators.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-pairwise-comparison", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-pairwise-comparison", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-nhanes-time-to-event", "name": "NHANES Time-to-Event", "category": "Biology", "suite": "Longevity Benchmark", "description": "Multi-class time-to-event prediction from NHANES data.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-time-to-event", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-time-to-event", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-nhanes-tte-regression", "name": "NHANES TTE Regression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Regression task for exact time-to-event prediction.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-tte-regression", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-tte-regression", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-olink-generative", "name": "Olink Generative", "category": "Biology", "suite": "Longevity Benchmark", "description": "Generative task for Olink protein biomarkers.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-olink-generative", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-olink-generative", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-olink-pairwise-comparison", "name": "Olink Pairwise Comparison", "category": "Biology", "suite": "Longevity Benchmark", "description": "Pairwise comparison using Olink protein biomarkers.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-olink-pairwise-comparison", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-olink-pairwise-comparison", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-olink-protein-classification", "name": "Olink Protein Classification", "category": "Biology", "suite": "Longevity Benchmark", "description": "Classifying samples based on Olink proteomics markers.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-olink-protein-classification", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-olink-protein-classification", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-synergy-regression", "name": "Synergy Regression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Regression task for quantifying synergy effects.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-synergy-regression", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-synergy-regression", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-longevity-benchmark-tcga-survival-prediction", "name": "TCGA Survival Prediction", "category": "Biology", "suite": "Longevity Benchmark", "description": "Predicting cancer patient survival outcomes from TCGA genomic data.", "url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-tcga-survival-prediction", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-longevity-benchmark-tcga-survival-prediction", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht1a-ic50", "name": "5-HT1A IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT1A IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht1a-ki", "name": "5-HT1A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT1A KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht1c-ki", "name": "5-HT1C KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT1C KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1c-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1c-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht2a-ic50", "name": "5-HT2A IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT2A IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht2a-ki", "name": "5-HT2A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT2A KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht2b-ki", "name": "5-HT2B KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT2B KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2b-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2b-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht5a-ki", "name": "5-HT5A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT5A KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht5a-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht5a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht6-ic50", "name": "5-HT6 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT6 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht6-ki", "name": "5-HT6 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT6 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-5-ht7-ki", "name": "5-HT7 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT7 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht7-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht7-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-a1-ic50", "name": "A1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-a1-ki", "name": "A1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-a2a-ic50", "name": "A2A IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A2A IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-a2a-ki", "name": "A2A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A2A KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-a2b-ic50", "name": "A2B IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A2B IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-a2b-ki", "name": "A2B KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A2B KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-a3-ki", "name": "A3 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A3 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a3-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-a3-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-alpha1a-ki", "name": "ALPHA1A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR ALPHA1A KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-alpha1a-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-alpha1a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-b1-ic50", "name": "B1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR B1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-b1-ki", "name": "B1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR B1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-casr-ic50", "name": "CASR IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CASR IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-casr-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-casr-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-cb1-ic50", "name": "CB1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CB1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-cb1-ki", "name": "CB1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CB1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-cb2-ic50", "name": "CB2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CB2 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-cb2-ki", "name": "CB2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CB2 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ccr1-ic50", "name": "CCR1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CCR1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ccr2-ic50", "name": "CCR2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CCR2 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr2-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ccr3-ic50", "name": "CCR3 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CCR3 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr3-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr3-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ccr5-ic50", "name": "CCR5 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CCR5 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr5-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr5-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-crhr1-ic50", "name": "CRHR1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CRHR1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-crhr1-ki", "name": "CRHR1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CRHR1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-cxcr3-ic50", "name": "CXCR3 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CXCR3 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr3-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr3-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-cxcr4-ic50", "name": "CXCR4 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CXCR4 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr4-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr4-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-d1-ki", "name": "D1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-d2-ic50", "name": "D2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D2 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-d2-ki", "name": "D2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D2 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-d3-ki", "name": "D3 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D3 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d3-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d3-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-d4-ki", "name": "D4 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D4 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d4-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-d4-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ep2-ic50", "name": "EP2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR EP2 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep2-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ep4-ic50", "name": "EP4 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR EP4 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep4-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep4-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-eta-ic50", "name": "ETA IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR ETA IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-eta-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-eta-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ghs-r-ic50", "name": "GHS-R IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GHS-R IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ghs-r-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ghs-r-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-glucagon-ic50", "name": "GLUCAGON IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GLUCAGON IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-glucagon-ki", "name": "GLUCAGON KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GLUCAGON KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-gnrhr-ic50", "name": "GNRHR IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GNRHR IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-gnrhr-ki", "name": "GNRHR KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GNRHR KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-gpr44-ic50", "name": "GPR44 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GPR44 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-gpr44-ki", "name": "GPR44 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GPR44 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-il8rb-ic50", "name": "IL8RB IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR IL8RB IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-il8rb-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-il8rb-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-machrm1-ic50", "name": "MACHRM1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-machrm1-ki", "name": "MACHRM1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-machrm2-ki", "name": "MACHRM2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM2 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm2-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-machrm3-ki", "name": "MACHRM3 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM3 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm3-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm3-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-machrm4-ic50", "name": "MACHRM4 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM4 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-machrm4-ki", "name": "MACHRM4 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM4 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-mc3r-ki", "name": "MC3R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MC3R KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc3r-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc3r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-mc4r-ic50", "name": "MC4R IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MC4R IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-mc4r-ki", "name": "MC4R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MC4R KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-mc5r-ki", "name": "MC5R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MC5R KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc5r-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc5r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-mglur1-ic50", "name": "MGLUR1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MGLUR1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-mglur2-ic50", "name": "MGLUR2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MGLUR2 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur2-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-mglur5-ic50", "name": "MGLUR5 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MGLUR5 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-mglur5-ki", "name": "MGLUR5 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MGLUR5 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-nk1-ki", "name": "NK1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-nk2-ic50", "name": "NK2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK2 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-nk2-ki", "name": "NK2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK2 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-nk3-ic50", "name": "NK3 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK3 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-nk3-ki", "name": "NK3 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK3 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-npy1r-ki", "name": "NPY1R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NPY1R KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy1r-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy1r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-npy2r-ic50", "name": "NPY2R IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NPY2R IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy2r-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy2r-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-npy5r-ic50", "name": "NPY5R IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NPY5R IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-npy5r-ki", "name": "NPY5R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NPY5R KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-oprd1-ic50", "name": "OPRD1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRD1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-oprd1-ki", "name": "OPRD1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRD1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-oprk1-ic50", "name": "OPRK1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRK1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-oprk1-ki", "name": "OPRK1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRK1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-oprm1-ic50", "name": "OPRM1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRM1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-oprm1-ki", "name": "OPRM1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRM1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ox1-ic50", "name": "OX1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OX1 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ox1-ki", "name": "OX1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OX1 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ox2-ic50", "name": "OX2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OX2 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-ox2-ki", "name": "OX2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OX2 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-thrombin-ic50", "name": "THROMBIN IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR THROMBIN IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-thrombin-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-thrombin-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-v1a-ic50", "name": "V1A IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR V1A IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-v1a-ki", "name": "V1A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR V1A KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-v2-ic50", "name": "V2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR V2 IC50 affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-gpcr-affinity-suite-v2-ki", "name": "V2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR V2 KI affinity prediction (IC50 or Ki).", "url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ki", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:aff-ic50-prediction-ic50-prediction-cold-drug", "name": "IC50 Prediction (Cold Drug)", "category": "Affinity and Binding", "suite": "IC50 prediction", "description": "Evaluates IC50 (half-maximal inhibitory concentration) prediction using BindingDB dataset with Cold Drug split. IC50 is a fundamental measure of drug potency, representing the concentration of a compound required to inhibit a biological target by 50%. This benchmark tests model ability to predict IC50 values when provided with inhibitor SMILES and protein target sequences, using few-shot inference with ground truth examples from the training split.", "url": "https://ddb.insilico.com/?benchmark=aff-ic50-prediction-ic50-prediction-cold-drug", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-ic50-prediction-ic50-prediction-cold-drug", "paper_url": null, "leaderboard_entries": 6 }, { "id": "ddb:aff-molecular-mechanics-energy-mmff-energy-prediction", "name": "MMFF Energy Prediction", "category": "Affinity and Binding", "suite": "Molecular Mechanics Energy", "description": "Predicting Molecular Mechanics (MM) energy for diverse 3D conformations. A computationally designed drug is useless if it instantly unfolds or repels itself in physical reality. Ensuring small molecules have low-energy conformations is a vital sanity check in AI-driven drug design. Chemistry42 platform was used to generate diverse conformations for drug-like molecules; models predict the resulting MM energy.", "url": "https://ddb.insilico.com/?benchmark=aff-molecular-mechanics-energy-mmff-energy-prediction", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-molecular-mechanics-energy-mmff-energy-prediction", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ddb:aff-pdbbind-number-of-interactions-number-of-non-covalent-interactions", "name": "Number of Non-Covalent Interactions", "category": "Affinity and Binding", "suite": "PDBBind Number of Interactions", "description": "Evaluates prediction of the number of non-covalent interactions in protein-ligand complexes using LP-PDBBind dataset. Ground truth is generated by Chemistry42 protein pharmacophores engine. Dataset: LP-PDBBind (https://pubmed.ncbi.nlm.nih.gov/37645037/).", "url": "https://ddb.insilico.com/?benchmark=aff-pdbbind-number-of-interactions-number-of-non-covalent-interactions", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-pdbbind-number-of-interactions-number-of-non-covalent-interactions", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:aff-pdbbind-restore-interactions-3d-interactions-restoration", "name": "3D Interactions Restoration", "category": "Affinity and Binding", "suite": "PDBBind Restore Interactions", "description": "Evaluates the ability to restore 3D protein-ligand interactions from LP-PDBBind dataset. Measures the ratio of restored interactions, power of restored interactions, and fake interactions, along with validity fraction.", "url": "https://ddb.insilico.com/?benchmark=aff-pdbbind-restore-interactions-3d-interactions-restoration", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-pdbbind-restore-interactions-3d-interactions-restoration", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ddb:aff-pkis2-kinase-inhibition-suite-pkis2-egfr", "name": "PKIS2 EGFR", "category": "Affinity and Binding", "suite": "PKIS2 Kinase Inhibition Suite", "description": "Kinase inhibition prediction for EGFR (Published Kinase Inhibitor Set 2). Essential for designing selective kinase inhibitors in cancer therapy.", "url": "https://ddb.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-egfr", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-egfr", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:aff-pkis2-kinase-inhibition-suite-pkis2-kit", "name": "PKIS2 KIT", "category": "Affinity and Binding", "suite": "PKIS2 Kinase Inhibition Suite", "description": "Kinase inhibition prediction for KIT (Published Kinase Inhibitor Set 2). Essential for designing selective kinase inhibitors in cancer therapy.", "url": "https://ddb.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-kit", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-kit", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:aff-pkis2-kinase-inhibition-suite-pkis2-ret", "name": "PKIS2 RET", "category": "Affinity and Binding", "suite": "PKIS2 Kinase Inhibition Suite", "description": "Kinase inhibition prediction for RET (Published Kinase Inhibitor Set 2). Predicting how small molecules interact with the RET kinase pocket is essential for designing selective kinase inhibitors in cancer therapy.", "url": "https://ddb.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-ret", "leaderboard_url": "https://ddb.insilico.com/?benchmark=aff-pkis2-kinase-inhibition-suite-pkis2-ret", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:syn-retrosynthesis-suite-single-step-retrosynthesis-ursa-expert-2026-dataset", "name": "Single-step retrosynthesis, URSA-expert-2026 dataset", "category": "Chemical Synthesis", "suite": "ISM Benchmarks: Retrosynthesis", "description": "Evaluates single-step retrosynthesis task performance on URSA-expert-2026 dataset across various ChemCensor metrics.", "url": "https://ddb.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-ursa-expert-2026-dataset", "leaderboard_url": "https://ddb.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-ursa-expert-2026-dataset", "paper_url": "https://arxiv.org/abs/2602.03554", "leaderboard_entries": 11 }, { "id": "ddb:syn-retrosynthesis-suite-single-step-retrosynthesis-uspto-50k-test-sample-dataset", "name": "Single-step retrosynthesis, USPTO-50k-test sample dataset", "category": "Chemical Synthesis", "suite": "ISM Benchmarks: Retrosynthesis", "description": "Evaluates single-step retrosynthesis task performance on representative 10% sample from USPTO-50k-test dataset across various ChemCensor metrics.", "url": "https://ddb.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-uspto-50k-test-sample-dataset", "leaderboard_url": "https://ddb.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-uspto-50k-test-sample-dataset", "paper_url": "https://arxiv.org/abs/2602.03554", "leaderboard_entries": 11 }, { "id": "ddb:adm-ism-benchmarks-admet-bcrp-inhibition", "name": "BCRP Inhibition", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Breast Cancer Resistance Protein (BCRP/ABCG2) inhibition prediction. BCRP is an efflux transporter affecting oral absorption, tissue distribution, and renal/biliary excretion of drugs. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-bcrp-inhibition", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-bcrp-inhibition", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ddb:adm-ism-benchmarks-admet-caco-2-efflux-ratio", "name": "Caco-2 Efflux Ratio", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Caco-2 efflux ratio measures the ratio of basolateral-to-apical vs apical-to-basolateral transport, indicating active efflux by transporters like P-gp. High efflux ratios suggest limited oral absorption. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-efflux-ratio", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-efflux-ratio", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-ism-benchmarks-admet-caco-2-permeability", "name": "Caco-2 Permeability", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Caco-2 cell effective permeability (Papp) using human colon carcinoma cells to model passive diffusion and active transport in the intestine. A key predictor of oral drug absorption. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-permeability", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-permeability", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ddb:adm-ism-benchmarks-admet-clearance-human-hepatocytes", "name": "Clearance Human Hepatocytes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in human hepatocytes captures both Phase I (CYP-mediated) and Phase II (conjugation) metabolism. Provides a more complete metabolic assessment than microsomes. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-hepatocytes", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-hepatocytes", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-ism-benchmarks-admet-clearance-human-liver-microsomes", "name": "Clearance Human Liver Microsomes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in human liver microsomes (HLM) evaluates CYP-mediated oxidative metabolism. A standard early-stage assay for predicting hepatic clearance. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-liver-microsomes", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-liver-microsomes", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:adm-ism-benchmarks-admet-clearance-mouse-liver-microsomes", "name": "Clearance Mouse Liver Microsomes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in mouse liver microsomes (MLM). Mouse is a common preclinical species; predicting species-specific clearance is essential for PK translation. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-mouse-liver-microsomes", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-mouse-liver-microsomes", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:adm-ism-benchmarks-admet-clearance-rat-liver-microsomes", "name": "Clearance Rat Liver Microsomes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in rat liver microsomes (RLM). Rat is the most widely used preclinical species for PK studies. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-rat-liver-microsomes", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-rat-liver-microsomes", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:adm-ism-benchmarks-admet-cyp1a2-inhibition-ic50", "name": "CYP1A2 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP1A2 inhibition potency (IC50) prediction. CYP1A2 metabolizes several important drugs including caffeine and theophylline; inhibition can cause clinically significant drug-drug interactions. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp1a2-inhibition-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp1a2-inhibition-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-ism-benchmarks-admet-cyp2c19-inhibition-ic50", "name": "CYP2C19 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP2C19 inhibition potency (IC50) prediction. CYP2C19 is a highly polymorphic enzyme metabolizing proton pump inhibitors and clopidogrel. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c19-inhibition-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c19-inhibition-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-ism-benchmarks-admet-cyp2c9-inhibition-ic50", "name": "CYP2C9 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP2C9 inhibition potency (IC50) prediction. CYP2C9 metabolizes ~15% of clinical drugs including warfarin and NSAIDs; inhibition poses significant safety risks. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c9-inhibition-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c9-inhibition-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-ism-benchmarks-admet-cyp2d6-inhibition-ic50", "name": "CYP2D6 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP2D6 inhibition potency (IC50) prediction. CYP2D6 metabolizes ~25% of marketed drugs and is highly polymorphic in the population. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2d6-inhibition-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2d6-inhibition-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-ism-benchmarks-admet-cyp3a4-inhibition-ic50", "name": "CYP3A4 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP3A4 inhibition potency (IC50) prediction. CYP3A4 is the most abundant hepatic CYP, metabolizing ~50% of marketed drugs. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp3a4-inhibition-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp3a4-inhibition-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-ism-benchmarks-admet-half-life-human", "name": "Half Life Human", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Human plasma half-life (T1/2) in hours. Determines how long a drug remains active in the body and directly impacts dosing regimen design. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-half-life-human", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-half-life-human", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-ism-benchmarks-admet-hek293-cc50", "name": "HEK293 CC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CC50 (cytotoxic concentration 50%) in HEK293 cells measures the concentration required to reduce cell viability by 50%. Important for assessing compound toxicity and therapeutic window. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-hek293-cc50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-hek293-cc50", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ddb:adm-ism-benchmarks-admet-hepg2-cc50", "name": "HepG2 CC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CC50 (cytotoxic concentration 50%) in HepG2 hepatocellular carcinoma cells. A key indicator of hepatotoxicity risk and general cytotoxicity. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-hepg2-cc50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-hepg2-cc50", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ddb:adm-ism-benchmarks-admet-herg-ic50", "name": "hERG IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "hERG potassium channel inhibition potency (IC50) prediction. hERG inhibition causes QT prolongation and potentially fatal cardiac arrhythmias, making it a critical safety endpoint. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-herg-ic50", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-herg-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-ism-benchmarks-admet-kinetic-solubility", "name": "Kinetic Solubility", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Kinetic solubility measures the concentration at which a compound precipitates from a DMSO stock solution in aqueous buffer. A critical early-stage screening parameter for compound prioritization in drug discovery. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-kinetic-solubility", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-kinetic-solubility", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-ism-benchmarks-admet-logd", "name": "LogD", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "LogD (distribution coefficient at pH 7.4) measures the ratio of a compound's concentration in octanol vs aqueous phase accounting for ionization. A key physicochemical property affecting absorption and distribution. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-logd", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-logd", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ddb:adm-ism-benchmarks-admet-logp", "name": "LogP", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "LogP (partition coefficient) measures the lipophilicity of a neutral compound between octanol and water. A fundamental physicochemical descriptor influencing membrane permeability and drug-likeness. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-logp", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-logp", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ddb:adm-ism-benchmarks-admet-mdck-mdr1-efflux-ratio", "name": "MDCK-MDR1 Efflux Ratio", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "MDCK-MDR1 efflux ratio measures P-gp-mediated efflux using MDCK cells overexpressing MDR1. High efflux ratios indicate P-gp substrates likely to have limited oral absorption or CNS penetration. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-efflux-ratio", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-efflux-ratio", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ddb:adm-ism-benchmarks-admet-mdck-mdr1-permeability", "name": "MDCK-MDR1 Permeability", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "MDCK-MDR1 apparent permeability (Papp) measures drug transport across MDCK cells expressing the MDR1 P-glycoprotein transporter. Used to assess intestinal absorption and blood-brain barrier penetration. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-permeability", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-permeability", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ddb:adm-ism-benchmarks-admet-p-gp-inhibition", "name": "P-gp Inhibition", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "P-glycoprotein (P-gp/MDR1) inhibition prediction. P-gp is a major efflux transporter; its inhibition can alter pharmacokinetics and cause drug-drug interactions affecting absorption and brain exposure. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-p-gp-inhibition", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-p-gp-inhibition", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ddb:adm-ism-benchmarks-admet-pampa-permeability", "name": "PAMPA Permeability", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Parallel Artificial Membrane Permeability Assay (PAMPA) provides a cell-free, high-throughput measure of passive transcellular permeability. Complementary to Caco-2 for absorption prediction. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-pampa-permeability", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-pampa-permeability", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ddb:adm-ism-benchmarks-admet-ppb-human", "name": "PPB Human", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Plasma protein binding (PPB) in human plasma. Only the unbound fraction of a drug can cross membranes and engage its target. Critical for efficacy predictions and dose selection. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-human", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-human", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:adm-ism-benchmarks-admet-ppb-mouse", "name": "PPB Mouse", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Plasma protein binding (PPB) in mouse plasma. Species-specific binding differences are essential for translating preclinical data to human. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-mouse", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-mouse", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:adm-ism-benchmarks-admet-ppb-rat", "name": "PPB Rat", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Plasma protein binding (PPB) in rat plasma. Species-specific binding is critical for PK translation from the most common preclinical species. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-rat", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-rat", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:adm-ism-benchmarks-admet-thermodynamic-solubility", "name": "Thermodynamic Solubility", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Thermodynamic solubility is the equilibrium solubility of the most stable crystalline form in aqueous media. A definitive measure of compound solubility important for formulation development. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-thermodynamic-solubility", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-thermodynamic-solubility", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-ism-benchmarks-admet-vdss", "name": "VDss", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Volume of distribution at steady state (VDss) measures how extensively a drug distributes from plasma into body tissues. A key PK parameter for dose calculation. Proprietary Chemistry42 data.", "url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-vdss", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-ism-benchmarks-admet-vdss", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-ames-mutagenicity", "name": "AMES Mutagenicity", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Ames mutagenicity test classification predicting whether a compound is mutagenic. The Ames test is a regulatory requirement for drug candidates and uses bacterial reverse mutation to detect genotoxic potential. 7,255 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-ames-mutagenicity", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-ames-mutagenicity", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-tdc-admet-bbb-penetration", "name": "BBB Penetration", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Blood-brain barrier penetration classification predicting whether a compound can cross the BBB. Essential for CNS drug design and for avoiding CNS-related toxicity in peripherally-targeted drugs. Dataset from Martins et al., 1,975 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-bbb-penetration", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-bbb-penetration", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-bioavailability", "name": "Bioavailability", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Oral bioavailability classification predicting whether a drug achieves sufficient systemic exposure after oral administration (>20% bioavailable = positive). Dataset from Ma et al., 640 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-bioavailability", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-bioavailability", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-caco-2-permeability", "name": "Caco-2 Permeability", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Caco-2 cell effective permeability measures a compound's ability to cross the intestinal epithelial barrier via passive diffusion and active transport. Essential for predicting oral drug absorption. Dataset from Wang et al., 906 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-caco-2-permeability", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-caco-2-permeability", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-clearance-hepatocyte", "name": "Clearance Hepatocyte", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Intrinsic clearance measured in hepatocytes (\u00b5L/min/10^6 cells). Provides a more physiologically complete assessment of drug metabolism than microsomes, capturing both Phase I and Phase II metabolism. Dataset from AstraZeneca, 1,020 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-clearance-hepatocyte", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-clearance-hepatocyte", "paper_url": null, "leaderboard_entries": 12 }, { "id": "ddb:adm-tdc-admet-clearance-microsome", "name": "Clearance Microsome", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Intrinsic clearance measured in liver microsomes (mL/min/g). Reflects the rate of drug metabolism by microsomal enzymes, primarily CYP450s. Dataset from AstraZeneca, 1,102 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-clearance-microsome", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-clearance-microsome", "paper_url": null, "leaderboard_entries": 12 }, { "id": "ddb:adm-tdc-admet-cyp2c9-inhibition", "name": "CYP2C9 Inhibition", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP2C9 inhibition classification predicting whether a compound inhibits the CYP2C9 enzyme. CYP2C9 metabolizes ~15% of clinically used drugs; inhibition can cause dangerous drug-drug interactions. Dataset from Veith et al., 12,092 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp2c9-inhibition", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp2c9-inhibition", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-cyp2c9-substrate", "name": "CYP2C9 Substrate", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP2C9 substrate classification predicting whether a compound is metabolized by the CYP2C9 enzyme. Important for predicting drug metabolism routes and potential drug-drug interactions. Dataset from CarbonMangels et al., 666 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp2c9-substrate", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp2c9-substrate", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-tdc-admet-cyp2d6-inhibition", "name": "CYP2D6 Inhibition", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP2D6 inhibition classification predicting whether a compound inhibits the CYP2D6 enzyme. CYP2D6 metabolizes ~25% of marketed drugs; inhibition can lead to severe adverse effects. Dataset from Veith et al., 13,130 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp2d6-inhibition", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp2d6-inhibition", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-cyp2d6-substrate", "name": "CYP2D6 Substrate", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP2D6 substrate classification predicting whether a compound is metabolized by the CYP2D6 enzyme. CYP2D6 is highly polymorphic, making substrate prediction critical for personalized medicine. Dataset from CarbonMangels et al., 664 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp2d6-substrate", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp2d6-substrate", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-cyp3a4-inhibition", "name": "CYP3A4 Inhibition", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP3A4 inhibition classification predicting whether a compound inhibits the CYP3A4 enzyme. Given CYP3A4's dominant role in drug metabolism, inhibition poses major drug-drug interaction risks. Dataset from Veith et al., 12,328 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp3a4-inhibition", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp3a4-inhibition", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-cyp3a4-substrate", "name": "CYP3A4 Substrate", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "CYP3A4 substrate classification predicting whether a compound is metabolized by the CYP3A4 enzyme. CYP3A4 is the most abundant hepatic CYP and metabolizes ~50% of marketed drugs. Dataset from CarbonMangels et al., 667 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp3a4-substrate", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-cyp3a4-substrate", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-dili", "name": "DILI", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Drug-Induced Liver Injury (DILI) classification predicting whether a drug causes liver damage. DILI is a leading cause of drug withdrawals and clinical trial failures. 475 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-dili", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-dili", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-tdc-admet-half-life", "name": "Half Life", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Drug half-life (hours) measures the time required for the plasma concentration to decrease by 50%. Critical for determining dosing frequency and achieving steady-state concentrations. Dataset from Obach et al., 667 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-half-life", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-half-life", "paper_url": null, "leaderboard_entries": 12 }, { "id": "ddb:adm-tdc-admet-herg-blockers", "name": "hERG Blockers", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "hERG channel blocker classification predicting whether a compound inhibits the human ether-\u00e0-go-go-related gene potassium channel. hERG inhibition can cause fatal cardiac arrhythmias (QT prolongation). Dataset from 648 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-herg-blockers", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-herg-blockers", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:adm-tdc-admet-hia", "name": "HIA", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Human intestinal absorption (HIA) classification predicting whether a drug is absorbed through the human intestine (>80% absorbed = positive). A critical first step in oral drug bioavailability. Dataset from Hou et al., 578 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-hia", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-hia", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-ld50-acute-toxicity", "name": "LD50 Acute Toxicity", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Acute toxicity prediction as LD50 in log(1/(mol/kg)). LD50 is the dose required to kill 50% of test animals and is a fundamental safety metric in drug development. Dataset from Zhu et al., 7,385 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-ld50-acute-toxicity", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-ld50-acute-toxicity", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ddb:adm-tdc-admet-lipophilicity", "name": "Lipophilicity", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Experimental lipophilicity measured as octanol/water distribution coefficient (logD at pH 7.4). A key physicochemical property influencing absorption, distribution, metabolism, and toxicity. Dataset from AstraZeneca, 4,200 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-lipophilicity", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-lipophilicity", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ddb:adm-tdc-admet-p-gp-inhibition", "name": "P-gp Inhibition", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "P-glycoprotein (P-gp) inhibition classification. P-gp is an efflux transporter that limits oral drug absorption and brain penetration. Inhibiting P-gp can alter drug pharmacokinetics and cause drug-drug interactions. Dataset from Broccatelli et al., 1,212 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-p-gp-inhibition", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-p-gp-inhibition", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-ppbr", "name": "PPBR", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Plasma protein binding rate (%) from AstraZeneca. Only the unbound fraction of a drug is pharmacologically active; high binding reduces free drug concentration and can affect efficacy and clearance. 1,797 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-ppbr", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-ppbr", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ddb:adm-tdc-admet-solubility", "name": "Solubility", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Aqueous solubility prediction in log mol/L. Solubility directly impacts oral bioavailability and is a critical parameter in drug formulation and development. Dataset from AqSolDB, 9,982 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-solubility", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-solubility", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ddb:adm-tdc-admet-vdss", "name": "VDss", "category": "ADMET, PK & Safety", "suite": "TDC ADMET", "description": "Volume of distribution at steady state (L/kg) measures how extensively a drug distributes from plasma into body tissues. A key pharmacokinetic parameter for determining dosing regimens. Dataset from Lombardo et al., 1,130 compounds.", "url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-vdss", "leaderboard_url": "https://ddb.insilico.com/?benchmark=adm-tdc-admet-vdss", "paper_url": null, "leaderboard_entries": 12 }, { "id": "ddb:cli-clinbench-quarterly-all-phases-2025q1", "name": "All Phases - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q1. N=356 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-all-phases-2025q2", "name": "All Phases - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q2. N=454 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q2", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-all-phases-2025q3", "name": "All Phases - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q3. N=297 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q3", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-all-phases-2025q4", "name": "All Phases - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q4. N=293 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q4", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-all-phases-2026q1", "name": "All Phases - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2026Q1. N=87 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2026q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-1-2025q1", "name": "Phase 1 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q1. N=56 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-1-2025q2", "name": "Phase 1 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q2. N=127 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q2", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-1-2025q3", "name": "Phase 1 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q3. N=30 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q3", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-1-2025q4", "name": "Phase 1 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q4. N=23 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q4", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-1-2026q1", "name": "Phase 1 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2026Q1. N=3 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2026q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-2-2025q1", "name": "Phase 2 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q1. N=146 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-2-2025q2", "name": "Phase 2 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q2. N=163 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q2", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-2-2025q3", "name": "Phase 2 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q3. N=145 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q3", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-2-2025q4", "name": "Phase 2 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q4. N=114 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q4", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-2-2026q1", "name": "Phase 2 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2026Q1. N=40 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2026q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-3-2025q1", "name": "Phase 3 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q1. N=119 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-3-2025q2", "name": "Phase 3 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q2. N=133 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q2", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-3-2025q3", "name": "Phase 3 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q3. N=100 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q3", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-3-2025q4", "name": "Phase 3 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q4. N=113 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q4", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-3-2026q1", "name": "Phase 3 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2026Q1. N=38 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2026q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-4-2025q1", "name": "Phase 4 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q1. N=35 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-4-2025q2", "name": "Phase 4 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q2. N=31 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q2", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-4-2025q3", "name": "Phase 4 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q3. N=22 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q3", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-4-2025q4", "name": "Phase 4 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q4. N=43 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q4", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:cli-clinbench-quarterly-phase-4-2026q1", "name": "Phase 4 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2026Q1. N=6 samples.", "url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2026q1", "leaderboard_url": "https://ddb.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ddb:bio-polyreactivity-cho-polyreactivity", "name": "CHO Polyreactivity", "category": "Biologics", "suite": "Polyreactivity ", "description": "Evaluates antibody binding to CHO-cell membrane proteins (CHO) as a measure of polyreactivity. Polyreactivity is the propensity of an antibody to bind nonspecifically to unrelated antigens and is widely used as an indicator of nonspecific binding risk, which can impact antibody specificity, safety, and overall developability.", "url": "https://ddb.insilico.com/?benchmark=bio-polyreactivity-cho-polyreactivity", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-polyreactivity-cho-polyreactivity", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-polyreactivity-ovalbumin-polyreactivity", "name": "Ovalbumin Polyreactivity", "category": "Biologics", "suite": "Polyreactivity ", "description": "Evaluates antibody binding to Ovalbumin as a measure of polyreactivity. Polyreactivity is the propensity of an antibody to bind nonspecifically to unrelated antigens and is widely used as an indicator of nonspecific binding risk, which can impact antibody specificity, safety, and overall developability.", "url": "https://ddb.insilico.com/?benchmark=bio-polyreactivity-ovalbumin-polyreactivity", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-polyreactivity-ovalbumin-polyreactivity", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-sec-smac-sec-monomer", "name": "SEC %Monomer", "category": "Biologics", "suite": "SEC SMAC ", "description": "SEC %Monomer, assessed by size-exclusion chromatography, reflects the proportion of monomeric antibody and serves as an indicator of molecular integrity and aggregation risk, impacting stability, efficacy, manufacturability, and overall developability.", "url": "https://ddb.insilico.com/?benchmark=bio-sec-smac-sec-monomer", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-sec-smac-sec-monomer", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:bio-sec-smac-smac", "name": "SMAC", "category": "Biologics", "suite": "SEC SMAC ", "description": "SMAC measures antibody retention time using standup monolayer affinity chromatography, where longer retention reflects stronger surface interactions and provides insight into surface interaction propensity and developability-related biophysical characteristics.", "url": "https://ddb.insilico.com/?benchmark=bio-sec-smac-smac", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-sec-smac-smac", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ddb:bio-tm-and-titer-titer", "name": "Titer", "category": "Biologics", "suite": "Tm and Titer", "description": "Evaluates titer using Spearman correlation.", "url": "https://ddb.insilico.com/?benchmark=bio-tm-and-titer-titer", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-tm-and-titer-titer", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ddb:bio-tm-and-titer-tm", "name": "Tm", "category": "Biologics", "suite": "Tm and Titer", "description": "Evaluates Tm using Spearman correlation.", "url": "https://ddb.insilico.com/?benchmark=bio-tm-and-titer-tm", "leaderboard_url": "https://ddb.insilico.com/?benchmark=bio-tm-and-titer-tm", "paper_url": null, "leaderboard_entries": 9 } ], "hosted_benchmarks_count": 206 }, { "id": "cafa", "name": "CAFA", "kind": "competition", "url": "https://biofunctionprediction.org/", "github": "N/A", "description": "Blind eval of protein function prediction against time-delayed UniProt-GOA.", "benchmarks_tracked": 6, "benchmark_count_asof": "2026-05-12", "count_methodology": "biofunctionprediction.org archives: CAFA1\u20135 (2010\u20132023) + CAFA6 announced 2025 = 6 editions.", "breakdown": { "editions": 6, "cafa5_targets": 142000 }, "host_organization": "Radivojac / Friedberg / Jiang consortium", "primary_contacts": [ "Predrag Radivojac", "Iddo Friedberg" ], "founded": "2010", "license_model": "Public", "flags": [], "rubric": { "rigor": 5, "coverage": 4, "maintenance": 4, "adoption": 5, "quality": 4, "accessibility": 5, "industry_relevance": 3 }, "notes": "CAFA5 (Kaggle, 2023) drew 1625 teams.", "composite_score": 86.8, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "capri", "name": "CAPRI", "kind": "competition", "url": "https://www.ebi.ac.uk/pdbe/complex-pred/capri/", "github": "N/A", "description": "Blind prediction of protein-protein complexes, protein-peptide, and protein-ligand assemblies.", "benchmarks_tracked": 56, "benchmark_count_asof": "2026-05-12", "count_methodology": "EBI CAPRI archive: Round 1 (2001) through Round 56 (2024).", "breakdown": { "rounds": 56, "targets_total_approx": 300 }, "host_organization": "EBI + CCP4", "primary_contacts": [ "Marc Lensink", "Shoshana Wodak" ], "founded": "2001", "license_model": "Public", "flags": [], "rubric": { "rigor": 5, "coverage": 4, "maintenance": 4, "adoption": 4, "quality": 5, "accessibility": 4, "industry_relevance": 4 }, "notes": "Oldest PPI prediction benchmark.", "composite_score": 86.3, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "faers", "name": "FAERS / SIDER / OffSides / TWOSIDES", "kind": "data-platform", "url": "https://www.fda.gov/drugs/surveillance/questions-and-answers-fdas-adverse-event-reporting-system-faers", "github": "N/A", "description": "FDA adverse event reports + SIDER/OffSides/TWOSIDES derivatives for post-market signal detection.", "benchmarks_tracked": 4, "benchmark_count_asof": "2026-05-12", "count_methodology": "FAERS (19M+ reports) + 3 derived benchmarks (SIDER, OffSides, TWOSIDES) = 4.", "breakdown": { "faers_reports": 19000000, "sider_pairs": 139000, "offsides_signals": 438000, "twosides_combo": 870000 }, "host_organization": "FDA CDER + Tatonetti Lab", "primary_contacts": [ "Nick Tatonetti", "FDA CDER" ], "founded": "1969 / 2012", "license_model": "Public / CC-BY", "flags": [], "rubric": { "rigor": 4, "coverage": 4, "maintenance": 4, "adoption": 5, "quality": 3, "accessibility": 5, "industry_relevance": 5 }, "notes": "Essential for pharmacovigilance ML. Known reporting biases.", "composite_score": 85.6, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "insilico-insilicobench", "name": "InsilicoBench", "kind": "meta-platform", "url": "https://insilicobench.insilico.com/", "github": "N/A \u2014 hosted portal", "description": "Compact cut of the Insilico benchmark stack focused on biology (longevity), GPCR affinity, retrosynthesis, ADMET, and clinical trials.", "benchmarks_tracked": 162, "benchmark_count_asof": "2026-05-12", "count_methodology": "Fetched https://insilicobench.insilico.com/api/benchmarks on 2026-05-12; meta.totalBenchmarks=162 across 5 categories (Biology 19, Affinity/Binding 88, Chemical Synthesis 2, ADMET 28, Clinical Trials 25).", "breakdown": { "Biology (Longevity)": 19, "Affinity and Binding": 88, "Chemical Synthesis": 2, "ADMET, PK & Safety": 28, "Clinical Trials": 25 }, "host_organization": "Insilico Medicine", "primary_contacts": [ "Alex Zhavoronkov", "Alex Aliper" ], "founded": "2025", "license_model": "CC-BY (per portal)", "flags": [], "rubric": { "rigor": 4, "coverage": 4, "maintenance": 5, "adoption": 3, "quality": 4, "accessibility": 5, "industry_relevance": 5 }, "notes": "Curated subset of ScienceAIBench. Same leaderboard model pool \u2192 also NOT self-referential.", "composite_score": 84.6, "hosted_benchmarks": [ { "id": "ib:bio-longevity-benchmark-aging-prediction", "name": "Aging Prediction", "category": "Biology", "suite": "Longevity Benchmark", "description": "General aging-related prediction task.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-aging-prediction", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-aging-prediction", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-gtex-expression", "name": "GTEx Expression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Gene expression level prediction from GTEx data.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-expression", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-expression", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-gtex-generative", "name": "GTEx Generative", "category": "Biology", "suite": "Longevity Benchmark", "description": "Generative task for GTEx gene expression patterns.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-generative", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-generative", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-gtex-pairwise-binary", "name": "GTEx Pairwise Binary", "category": "Biology", "suite": "Longevity Benchmark", "description": "Binary pairwise comparison of gene expression from GTEx.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-binary", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-binary", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-gtex-pairwise-ternary", "name": "GTEx Pairwise Ternary", "category": "Biology", "suite": "Longevity Benchmark", "description": "Ternary pairwise comparison of GTEx gene expression.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-ternary", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-gtex-pairwise-ternary", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-longevity-synergy-full", "name": "Longevity Synergy (Full)", "category": "Biology", "suite": "Longevity Benchmark", "description": "Predicting synergistic effects of longevity interventions (full context).", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-full", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-full", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-longevity-synergy-minimal", "name": "Longevity Synergy (Minimal)", "category": "Biology", "suite": "Longevity Benchmark", "description": "Predicting synergistic effects of longevity interventions (minimal context).", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-minimal", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-longevity-synergy-minimal", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-methylation-age-choice", "name": "Methylation Age Choice", "category": "Biology", "suite": "Longevity Benchmark", "description": "Multiple choice task for methylation-based age prediction.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-choice", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-choice", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-methylation-age-pairwise", "name": "Methylation Age Pairwise", "category": "Biology", "suite": "Longevity Benchmark", "description": "Comparing biological age from DNA methylation patterns.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-pairwise", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-pairwise", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-methylation-age-regression", "name": "Methylation Age Regression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Regression task for exact biological age from methylation.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-regression", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-methylation-age-regression", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ib:bio-longevity-benchmark-nhanes-mortality-classification", "name": "NHANES Mortality Classification", "category": "Biology", "suite": "Longevity Benchmark", "description": "Binary classification of mortality risk using NHANES health survey data.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-mortality-classification", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-mortality-classification", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-nhanes-pairwise-comparison", "name": "NHANES Pairwise Comparison", "category": "Biology", "suite": "Longevity Benchmark", "description": "Pairwise comparison of individuals based on health indicators.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-pairwise-comparison", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-pairwise-comparison", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-nhanes-time-to-event", "name": "NHANES Time-to-Event", "category": "Biology", "suite": "Longevity Benchmark", "description": "Multi-class time-to-event prediction from NHANES data.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-time-to-event", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-time-to-event", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-nhanes-tte-regression", "name": "NHANES TTE Regression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Regression task for exact time-to-event prediction.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-tte-regression", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-nhanes-tte-regression", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-olink-generative", "name": "Olink Generative", "category": "Biology", "suite": "Longevity Benchmark", "description": "Generative task for Olink protein biomarkers.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-olink-generative", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-olink-generative", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-olink-pairwise-comparison", "name": "Olink Pairwise Comparison", "category": "Biology", "suite": "Longevity Benchmark", "description": "Pairwise comparison using Olink protein biomarkers.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-olink-pairwise-comparison", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-olink-pairwise-comparison", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-olink-protein-classification", "name": "Olink Protein Classification", "category": "Biology", "suite": "Longevity Benchmark", "description": "Classifying samples based on Olink proteomics markers.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-olink-protein-classification", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-olink-protein-classification", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-synergy-regression", "name": "Synergy Regression", "category": "Biology", "suite": "Longevity Benchmark", "description": "Regression task for quantifying synergy effects.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-synergy-regression", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-synergy-regression", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:bio-longevity-benchmark-tcga-survival-prediction", "name": "TCGA Survival Prediction", "category": "Biology", "suite": "Longevity Benchmark", "description": "Predicting cancer patient survival outcomes from TCGA genomic data.", "url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-tcga-survival-prediction", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=bio-longevity-benchmark-tcga-survival-prediction", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht1a-ic50", "name": "5-HT1A IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT1A IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht1a-ki", "name": "5-HT1A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT1A KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht1c-ki", "name": "5-HT1C KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT1C KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1c-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht1c-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht2a-ic50", "name": "5-HT2A IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT2A IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht2a-ki", "name": "5-HT2A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT2A KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht2b-ki", "name": "5-HT2B KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT2B KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2b-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht2b-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht5a-ki", "name": "5-HT5A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT5A KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht5a-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht5a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht6-ic50", "name": "5-HT6 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT6 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht6-ki", "name": "5-HT6 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT6 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht6-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-5-ht7-ki", "name": "5-HT7 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR 5-HT7 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht7-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-5-ht7-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-a1-ic50", "name": "A1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-a1-ki", "name": "A1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-a2a-ic50", "name": "A2A IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A2A IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-a2a-ki", "name": "A2A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A2A KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-a2b-ic50", "name": "A2B IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A2B IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-a2b-ki", "name": "A2B KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A2B KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a2b-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-a3-ki", "name": "A3 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR A3 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a3-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-a3-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-alpha1a-ki", "name": "ALPHA1A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR ALPHA1A KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-alpha1a-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-alpha1a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-b1-ic50", "name": "B1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR B1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-b1-ki", "name": "B1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR B1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-b1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-casr-ic50", "name": "CASR IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CASR IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-casr-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-casr-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-cb1-ic50", "name": "CB1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CB1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-cb1-ki", "name": "CB1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CB1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-cb2-ic50", "name": "CB2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CB2 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-cb2-ki", "name": "CB2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CB2 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cb2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ccr1-ic50", "name": "CCR1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CCR1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ccr2-ic50", "name": "CCR2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CCR2 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr2-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ccr3-ic50", "name": "CCR3 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CCR3 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr3-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr3-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ccr5-ic50", "name": "CCR5 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CCR5 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr5-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ccr5-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-crhr1-ic50", "name": "CRHR1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CRHR1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-crhr1-ki", "name": "CRHR1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CRHR1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-crhr1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-cxcr3-ic50", "name": "CXCR3 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CXCR3 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr3-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr3-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-cxcr4-ic50", "name": "CXCR4 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR CXCR4 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr4-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-cxcr4-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-d1-ki", "name": "D1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-d2-ic50", "name": "D2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D2 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-d2-ki", "name": "D2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D2 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-d3-ki", "name": "D3 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D3 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d3-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d3-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-d4-ki", "name": "D4 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR D4 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d4-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-d4-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ep2-ic50", "name": "EP2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR EP2 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep2-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ep4-ic50", "name": "EP4 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR EP4 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep4-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ep4-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-eta-ic50", "name": "ETA IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR ETA IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-eta-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-eta-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ghs-r-ic50", "name": "GHS-R IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GHS-R IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ghs-r-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ghs-r-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-glucagon-ic50", "name": "GLUCAGON IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GLUCAGON IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-glucagon-ki", "name": "GLUCAGON KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GLUCAGON KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-glucagon-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-gnrhr-ic50", "name": "GNRHR IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GNRHR IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-gnrhr-ki", "name": "GNRHR KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GNRHR KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gnrhr-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-gpr44-ic50", "name": "GPR44 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GPR44 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-gpr44-ki", "name": "GPR44 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR GPR44 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-gpr44-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-il8rb-ic50", "name": "IL8RB IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR IL8RB IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-il8rb-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-il8rb-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-machrm1-ic50", "name": "MACHRM1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-machrm1-ki", "name": "MACHRM1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-machrm2-ki", "name": "MACHRM2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM2 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm2-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-machrm3-ki", "name": "MACHRM3 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM3 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm3-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm3-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-machrm4-ic50", "name": "MACHRM4 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM4 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-machrm4-ki", "name": "MACHRM4 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MACHRM4 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-machrm4-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-mc3r-ki", "name": "MC3R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MC3R KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc3r-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc3r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-mc4r-ic50", "name": "MC4R IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MC4R IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-mc4r-ki", "name": "MC4R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MC4R KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc4r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-mc5r-ki", "name": "MC5R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MC5R KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc5r-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mc5r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-mglur1-ic50", "name": "MGLUR1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MGLUR1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-mglur2-ic50", "name": "MGLUR2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MGLUR2 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur2-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-mglur5-ic50", "name": "MGLUR5 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MGLUR5 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-mglur5-ki", "name": "MGLUR5 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR MGLUR5 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-mglur5-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-nk1-ki", "name": "NK1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-nk2-ic50", "name": "NK2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK2 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-nk2-ki", "name": "NK2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK2 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-nk3-ic50", "name": "NK3 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK3 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-nk3-ki", "name": "NK3 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NK3 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-nk3-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-npy1r-ki", "name": "NPY1R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NPY1R KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy1r-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy1r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-npy2r-ic50", "name": "NPY2R IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NPY2R IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy2r-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy2r-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-npy5r-ic50", "name": "NPY5R IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NPY5R IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-npy5r-ki", "name": "NPY5R KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR NPY5R KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-npy5r-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-oprd1-ic50", "name": "OPRD1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRD1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-oprd1-ki", "name": "OPRD1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRD1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprd1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-oprk1-ic50", "name": "OPRK1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRK1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-oprk1-ki", "name": "OPRK1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRK1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprk1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-oprm1-ic50", "name": "OPRM1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRM1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-oprm1-ki", "name": "OPRM1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OPRM1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-oprm1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ox1-ic50", "name": "OX1 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OX1 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ox1-ki", "name": "OX1 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OX1 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox1-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ox2-ic50", "name": "OX2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OX2 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-ox2-ki", "name": "OX2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR OX2 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-ox2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-thrombin-ic50", "name": "THROMBIN IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR THROMBIN IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-thrombin-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-thrombin-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-v1a-ic50", "name": "V1A IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR V1A IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-v1a-ki", "name": "V1A KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR V1A KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v1a-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-v2-ic50", "name": "V2 IC50", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR V2 IC50 affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ic50", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-gpcr-affinity-suite-v2-ki", "name": "V2 KI", "category": "Affinity and Binding", "suite": "GPCR Affinity Suite", "description": "GPCR V2 KI affinity prediction (IC50 or Ki).", "url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ki", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-gpcr-affinity-suite-v2-ki", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:aff-ic50-prediction-ic50-prediction-cold-drug", "name": "IC50 Prediction (Cold Drug)", "category": "Affinity and Binding", "suite": "IC50 prediction", "description": "Evaluates IC50 (half-maximal inhibitory concentration) prediction using BindingDB dataset with Cold Drug split. IC50 is a fundamental measure of drug potency, representing the concentration of a compound required to inhibit a biological target by 50%. This benchmark tests model ability to predict IC50 values when provided with inhibitor SMILES and protein target sequences, using few-shot inference with ground truth examples from the training split.", "url": "https://insilicobench.insilico.com/?benchmark=aff-ic50-prediction-ic50-prediction-cold-drug", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=aff-ic50-prediction-ic50-prediction-cold-drug", "paper_url": null, "leaderboard_entries": 6 }, { "id": "ib:syn-retrosynthesis-suite-single-step-retrosynthesis-ursa-expert-2026-dataset", "name": "Single-step retrosynthesis, URSA-expert-2026 dataset", "category": "Chemical Synthesis", "suite": "Retrosynthesis Suite", "description": "Evaluates single-step retrosynthesis task performance on URSA-expert-2026 dataset across various ChemCensor metrics.", "url": "https://insilicobench.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-ursa-expert-2026-dataset", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-ursa-expert-2026-dataset", "paper_url": "https://arxiv.org/abs/2602.03554", "leaderboard_entries": 11 }, { "id": "ib:syn-retrosynthesis-suite-single-step-retrosynthesis-uspto-50k-test-sample-dataset", "name": "Single-step retrosynthesis, USPTO-50k-test sample dataset", "category": "Chemical Synthesis", "suite": "Retrosynthesis Suite", "description": "Evaluates single-step retrosynthesis task performance on representative 10% sample from USPTO-50k-test dataset across various ChemCensor metrics.", "url": "https://insilicobench.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-uspto-50k-test-sample-dataset", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=syn-retrosynthesis-suite-single-step-retrosynthesis-uspto-50k-test-sample-dataset", "paper_url": "https://arxiv.org/abs/2602.03554", "leaderboard_entries": 11 }, { "id": "ib:adm-ism-benchmarks-admet-bcrp-inhibition", "name": "BCRP Inhibition", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Breast Cancer Resistance Protein (BCRP/ABCG2) inhibition prediction. BCRP is an efflux transporter affecting oral absorption, tissue distribution, and renal/biliary excretion of drugs. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-bcrp-inhibition", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-bcrp-inhibition", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ib:adm-ism-benchmarks-admet-caco-2-efflux-ratio", "name": "Caco-2 Efflux Ratio", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Caco-2 efflux ratio measures the ratio of basolateral-to-apical vs apical-to-basolateral transport, indicating active efflux by transporters like P-gp. High efflux ratios suggest limited oral absorption. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-efflux-ratio", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-efflux-ratio", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ib:adm-ism-benchmarks-admet-caco-2-permeability", "name": "Caco-2 Permeability", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Caco-2 cell effective permeability (Papp) using human colon carcinoma cells to model passive diffusion and active transport in the intestine. A key predictor of oral drug absorption. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-permeability", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-caco-2-permeability", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ib:adm-ism-benchmarks-admet-clearance-human-hepatocytes", "name": "Clearance Human Hepatocytes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in human hepatocytes captures both Phase I (CYP-mediated) and Phase II (conjugation) metabolism. Provides a more complete metabolic assessment than microsomes. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-hepatocytes", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-hepatocytes", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:adm-ism-benchmarks-admet-clearance-human-liver-microsomes", "name": "Clearance Human Liver Microsomes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in human liver microsomes (HLM) evaluates CYP-mediated oxidative metabolism. A standard early-stage assay for predicting hepatic clearance. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-liver-microsomes", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-human-liver-microsomes", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:adm-ism-benchmarks-admet-clearance-mouse-liver-microsomes", "name": "Clearance Mouse Liver Microsomes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in mouse liver microsomes (MLM). Mouse is a common preclinical species; predicting species-specific clearance is essential for PK translation. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-mouse-liver-microsomes", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-mouse-liver-microsomes", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:adm-ism-benchmarks-admet-clearance-rat-liver-microsomes", "name": "Clearance Rat Liver Microsomes", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Intrinsic clearance in rat liver microsomes (RLM). Rat is the most widely used preclinical species for PK studies. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-rat-liver-microsomes", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-clearance-rat-liver-microsomes", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:adm-ism-benchmarks-admet-cyp1a2-inhibition-ic50", "name": "CYP1A2 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP1A2 inhibition potency (IC50) prediction. CYP1A2 metabolizes several important drugs including caffeine and theophylline; inhibition can cause clinically significant drug-drug interactions. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp1a2-inhibition-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp1a2-inhibition-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:adm-ism-benchmarks-admet-cyp2c19-inhibition-ic50", "name": "CYP2C19 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP2C19 inhibition potency (IC50) prediction. CYP2C19 is a highly polymorphic enzyme metabolizing proton pump inhibitors and clopidogrel. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c19-inhibition-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c19-inhibition-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ib:adm-ism-benchmarks-admet-cyp2c9-inhibition-ic50", "name": "CYP2C9 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP2C9 inhibition potency (IC50) prediction. CYP2C9 metabolizes ~15% of clinical drugs including warfarin and NSAIDs; inhibition poses significant safety risks. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c9-inhibition-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2c9-inhibition-ic50", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ib:adm-ism-benchmarks-admet-cyp2d6-inhibition-ic50", "name": "CYP2D6 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP2D6 inhibition potency (IC50) prediction. CYP2D6 metabolizes ~25% of marketed drugs and is highly polymorphic in the population. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2d6-inhibition-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp2d6-inhibition-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:adm-ism-benchmarks-admet-cyp3a4-inhibition-ic50", "name": "CYP3A4 Inhibition IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CYP3A4 inhibition potency (IC50) prediction. CYP3A4 is the most abundant hepatic CYP, metabolizing ~50% of marketed drugs. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp3a4-inhibition-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-cyp3a4-inhibition-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:adm-ism-benchmarks-admet-half-life-human", "name": "Half Life Human", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Human plasma half-life (T1/2) in hours. Determines how long a drug remains active in the body and directly impacts dosing regimen design. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-half-life-human", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-half-life-human", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ib:adm-ism-benchmarks-admet-hek293-cc50", "name": "HEK293 CC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CC50 (cytotoxic concentration 50%) in HEK293 cells measures the concentration required to reduce cell viability by 50%. Important for assessing compound toxicity and therapeutic window. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-hek293-cc50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-hek293-cc50", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ib:adm-ism-benchmarks-admet-hepg2-cc50", "name": "HepG2 CC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "CC50 (cytotoxic concentration 50%) in HepG2 hepatocellular carcinoma cells. A key indicator of hepatotoxicity risk and general cytotoxicity. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-hepg2-cc50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-hepg2-cc50", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ib:adm-ism-benchmarks-admet-herg-ic50", "name": "hERG IC50", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "hERG potassium channel inhibition potency (IC50) prediction. hERG inhibition causes QT prolongation and potentially fatal cardiac arrhythmias, making it a critical safety endpoint. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-herg-ic50", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-herg-ic50", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:adm-ism-benchmarks-admet-kinetic-solubility", "name": "Kinetic Solubility", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Kinetic solubility measures the concentration at which a compound precipitates from a DMSO stock solution in aqueous buffer. A critical early-stage screening parameter for compound prioritization in drug discovery. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-kinetic-solubility", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-kinetic-solubility", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:adm-ism-benchmarks-admet-logd", "name": "LogD", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "LogD (distribution coefficient at pH 7.4) measures the ratio of a compound's concentration in octanol vs aqueous phase accounting for ionization. A key physicochemical property affecting absorption and distribution. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-logd", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-logd", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ib:adm-ism-benchmarks-admet-logp", "name": "LogP", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "LogP (partition coefficient) measures the lipophilicity of a neutral compound between octanol and water. A fundamental physicochemical descriptor influencing membrane permeability and drug-likeness. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-logp", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-logp", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ib:adm-ism-benchmarks-admet-mdck-mdr1-efflux-ratio", "name": "MDCK-MDR1 Efflux Ratio", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "MDCK-MDR1 efflux ratio measures P-gp-mediated efflux using MDCK cells overexpressing MDR1. High efflux ratios indicate P-gp substrates likely to have limited oral absorption or CNS penetration. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-efflux-ratio", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-efflux-ratio", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ib:adm-ism-benchmarks-admet-mdck-mdr1-permeability", "name": "MDCK-MDR1 Permeability", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "MDCK-MDR1 apparent permeability (Papp) measures drug transport across MDCK cells expressing the MDR1 P-glycoprotein transporter. Used to assess intestinal absorption and blood-brain barrier penetration. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-permeability", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-mdck-mdr1-permeability", "paper_url": null, "leaderboard_entries": 7 }, { "id": "ib:adm-ism-benchmarks-admet-p-gp-inhibition", "name": "P-gp Inhibition", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "P-glycoprotein (P-gp/MDR1) inhibition prediction. P-gp is a major efflux transporter; its inhibition can alter pharmacokinetics and cause drug-drug interactions affecting absorption and brain exposure. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-p-gp-inhibition", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-p-gp-inhibition", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ib:adm-ism-benchmarks-admet-pampa-permeability", "name": "PAMPA Permeability", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Parallel Artificial Membrane Permeability Assay (PAMPA) provides a cell-free, high-throughput measure of passive transcellular permeability. Complementary to Caco-2 for absorption prediction. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-pampa-permeability", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-pampa-permeability", "paper_url": null, "leaderboard_entries": 11 }, { "id": "ib:adm-ism-benchmarks-admet-ppb-human", "name": "PPB Human", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Plasma protein binding (PPB) in human plasma. Only the unbound fraction of a drug can cross membranes and engage its target. Critical for efficacy predictions and dose selection. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-human", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-human", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:adm-ism-benchmarks-admet-ppb-mouse", "name": "PPB Mouse", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Plasma protein binding (PPB) in mouse plasma. Species-specific binding differences are essential for translating preclinical data to human. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-mouse", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-mouse", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:adm-ism-benchmarks-admet-ppb-rat", "name": "PPB Rat", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Plasma protein binding (PPB) in rat plasma. Species-specific binding is critical for PK translation from the most common preclinical species. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-rat", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-ppb-rat", "paper_url": null, "leaderboard_entries": 10 }, { "id": "ib:adm-ism-benchmarks-admet-thermodynamic-solubility", "name": "Thermodynamic Solubility", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Thermodynamic solubility is the equilibrium solubility of the most stable crystalline form in aqueous media. A definitive measure of compound solubility important for formulation development. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-thermodynamic-solubility", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-thermodynamic-solubility", "paper_url": null, "leaderboard_entries": 9 }, { "id": "ib:adm-ism-benchmarks-admet-vdss", "name": "VDss", "category": "ADMET, PK & Safety", "suite": "ISM Benchmarks: ADMET", "description": "Volume of distribution at steady state (VDss) measures how extensively a drug distributes from plasma into body tissues. A key PK parameter for dose calculation. Proprietary Chemistry42 data.", "url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-vdss", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=adm-ism-benchmarks-admet-vdss", "paper_url": null, "leaderboard_entries": 8 }, { "id": "ib:cli-clinbench-quarterly-all-phases-2025q1", "name": "All Phases - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q1. N=356 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-all-phases-2025q2", "name": "All Phases - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q2. N=454 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q2", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-all-phases-2025q3", "name": "All Phases - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q3. N=297 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q3", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-all-phases-2025q4", "name": "All Phases - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2025Q4. N=293 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q4", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-all-phases-2026q1", "name": "All Phases - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (All Phases) for trials with results submitted in 2026Q1. N=87 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2026q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-all-phases-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-1-2025q1", "name": "Phase 1 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q1. N=56 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-1-2025q2", "name": "Phase 1 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q2. N=127 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q2", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-1-2025q3", "name": "Phase 1 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q3. N=30 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q3", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-1-2025q4", "name": "Phase 1 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2025Q4. N=23 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q4", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-1-2026q1", "name": "Phase 1 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 1) for trials with results submitted in 2026Q1. N=3 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2026q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-1-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-2-2025q1", "name": "Phase 2 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q1. N=146 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-2-2025q2", "name": "Phase 2 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q2. N=163 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q2", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-2-2025q3", "name": "Phase 2 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q3. N=145 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q3", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-2-2025q4", "name": "Phase 2 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2025Q4. N=114 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q4", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-2-2026q1", "name": "Phase 2 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 2) for trials with results submitted in 2026Q1. N=40 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2026q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-2-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-3-2025q1", "name": "Phase 3 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q1. N=119 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-3-2025q2", "name": "Phase 3 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q2. N=133 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q2", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-3-2025q3", "name": "Phase 3 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q3. N=100 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q3", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-3-2025q4", "name": "Phase 3 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2025Q4. N=113 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q4", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-3-2026q1", "name": "Phase 3 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 3) for trials with results submitted in 2026Q1. N=38 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2026q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-3-2026q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-4-2025q1", "name": "Phase 4 - 2025Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q1. N=35 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q1", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-4-2025q2", "name": "Phase 4 - 2025Q2", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q2. N=31 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q2", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q2", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-4-2025q3", "name": "Phase 4 - 2025Q3", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q3. N=22 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q3", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q3", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-4-2025q4", "name": "Phase 4 - 2025Q4", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2025Q4. N=43 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q4", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2025q4", "paper_url": null, "leaderboard_entries": 14 }, { "id": "ib:cli-clinbench-quarterly-phase-4-2026q1", "name": "Phase 4 - 2026Q1", "category": "Clinical Trials", "suite": "ClinBench Quarterly", "description": "Clinical trial outcome prediction (Phase 4) for trials with results submitted in 2026Q1. N=6 samples.", "url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2026q1", "leaderboard_url": "https://insilicobench.insilico.com/?benchmark=cli-clinbench-quarterly-phase-4-2026q1", "paper_url": null, "leaderboard_entries": 14 } ], "hosted_benchmarks_count": 162 }, { "id": "flip", "name": "FLIP", "kind": "meta-platform", "url": "https://benchmark.protein.properties/", "github": "https://github.com/J-SNACKKB/FLIP", "description": "Protein fitness benchmarks focused on realistic train/test splits (AAV, GB1, Meltome, SCL, Bind).", "benchmarks_tracked": 15, "benchmark_count_asof": "2026-05-12", "count_methodology": "FLIP README: 5 landscapes \u00d7 3 splits = 15 benchmarks.", "breakdown": { "landscapes": 5, "splits_per_landscape": 3 }, "host_organization": "Rostlab TUM + AlQuraishi Lab Columbia", "primary_contacts": [ "Burkhard Rost", "Mohammed AlQuraishi", "Christian Dallago" ], "founded": "2021-12", "license_model": "CC-BY 4.0", "flags": [], "rubric": { "rigor": 5, "coverage": 3, "maintenance": 3, "adoption": 4, "quality": 5, "accessibility": 5, "industry_relevance": 3 }, "notes": "Complementary to ProteinGym (smaller but careful splits).", "composite_score": 80.8, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "cptac", "name": "CPTAC", "kind": "consortium", "url": "https://proteomics.cancer.gov/programs/cptac", "github": "https://github.com/PayneLab/cptac", "description": "Integrated proteogenomic datasets across 10 tumor types; hosts DREAM proteogenomic benchmarks.", "benchmarks_tracked": 10, "benchmark_count_asof": "2026-05-12", "count_methodology": "CPTAC data portal 2026-05: 10 tumor types with full proteogenomic characterization (BR, CO, EN, GBM, HNSCC, LSCC, LUAD, OV, PDAC, CCRCC).", "breakdown": { "tumor_types": 10, "samples": 1600, "omics_layers": 6 }, "host_organization": "NCI Office of Cancer Clinical Proteomics Research", "primary_contacts": [ "Henry Rodriguez", "Amanda Paulovich", "Bing Zhang" ], "founded": "2011", "license_model": "dbGaP controlled / public tiers", "flags": [], "rubric": { "rigor": 5, "coverage": 3, "maintenance": 4, "adoption": 4, "quality": 5, "accessibility": 3, "industry_relevance": 4 }, "notes": "Deep but narrow (oncology).", "composite_score": 80.8, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "deepchem", "name": "DeepChem", "kind": "meta-platform", "url": "https://deepchem.io/", "github": "https://github.com/deepchem/deepchem", "description": "OSS library bundling molecular ML benchmark datasets and baselines; hosts MoleculeNet.", "benchmarks_tracked": 40, "benchmark_count_asof": "2026-05-12", "count_methodology": "deepchem.molnet module listing: ~40 packaged datasets (MoleculeNet core + extensions).", "breakdown": { "moleculenet_core": 17, "adme_tox_extensions": 10, "protein": 5, "materials": 4, "misc": 4 }, "host_organization": "DeepChem community", "primary_contacts": [ "Bharath Ramsundar", "Peter Eastman" ], "founded": "2016", "license_model": "MIT", "flags": [], "rubric": { "rigor": 4, "coverage": 4, "maintenance": 4, "adoption": 4, "quality": 4, "accessibility": 5, "industry_relevance": 3 }, "notes": "Excellent reproducibility \u2014 one-liner dataset loaders.", "composite_score": 80.0, "hosted_benchmarks": [ { "id": "deepchem:delaney-esol", "name": "Delaney (ESOL)", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:freesolv", "name": "FreeSolv", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:lipophilicity", "name": "Lipophilicity", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:bace", "name": "BACE", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:bbbp", "name": "BBBP", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:clintox", "name": "ClinTox", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:hiv", "name": "HIV", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:muv", "name": "MUV", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:pcba", "name": "PCBA", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:pdbbind", "name": "PDBbind", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:qm7", "name": "QM7", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:qm8", "name": "QM8", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:qm9", "name": "QM9", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:sider", "name": "SIDER", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:tox21", "name": "Tox21", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:toxcast", "name": "ToxCast", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:chembl", "name": "Chembl", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:hopv", "name": "HOPV", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:kaggle", "name": "KAGGLE", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:uspto", "name": "USPTO", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:nci", "name": "NCI", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:hppb", "name": "HPPB", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:solubility", "name": "Solubility", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:uv", "name": "UV", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:kinase", "name": "Kinase", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:thermosol", "name": "Thermosol", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:hydration", "name": "Hydration", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:electrolytes", "name": "Electrolytes", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:factors", "name": "Factors", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:platinum", "name": "Platinum", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:polymernet", "name": "PolymerNet", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:moleculenet-mirror", "name": "MoleculeNet mirror", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:ppb", "name": "PPB", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:phos", "name": "Phos", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:dili", "name": "DILI", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:ames", "name": "AMES", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:pkd1", "name": "PKD1", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:pkd2", "name": "PKD2", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:mda-mb-231", "name": "MDA-MB-231", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" }, { "id": "deepchem:beta-secretase", "name": "Beta-Secretase", "category": "DeepChem dataset", "url": "https://deepchem.io/", "leaderboard_url": "https://deepchem.io/" } ], "hosted_benchmarks_count": 40 }, { "id": "moleculenet", "name": "MoleculeNet", "kind": "meta-platform", "url": "https://moleculenet.org/", "github": "https://github.com/deepchem/deepchem", "description": "Benchmark suite covering quantum, physical, biophysical, physiological molecular ML tasks.", "benchmarks_tracked": 17, "benchmark_count_asof": "2026-05-12", "count_methodology": "Wu et al. 2018 Chem Sci + DeepChem repo enumeration: QM7/QM7b/QM8/QM9, ESOL, FreeSolv, Lipophilicity, PCBA, MUV, HIV, BACE, BBBP, Tox21, ToxCast, SIDER, ClinTox, PDBbind (17).", "breakdown": { "quantum": 4, "physical_chem": 3, "biophysics": 4, "physiology": 6 }, "host_organization": "DeepChem community (Pande Lab alumni)", "primary_contacts": [ "Bharath Ramsundar", "Vijay Pande" ], "founded": "2018-03", "license_model": "MIT", "flags": [ "data-leakage-known" ], "rubric": { "rigor": 4, "coverage": 4, "maintenance": 2, "adoption": 5, "quality": 3, "accessibility": 5, "industry_relevance": 4 }, "notes": "Historically foundational; many splits have documented leakage. Community has largely moved to TDC / Polaris for new work.", "composite_score": 78.0, "hosted_benchmarks": [ { "id": "moleculenet:qm7", "name": "QM7", "category": "quantum", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:qm7b", "name": "QM7b", "category": "quantum", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:qm8", "name": "QM8", "category": "quantum", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:qm9", "name": "QM9", "category": "quantum", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:esol", "name": "ESOL", "category": "physchem", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:freesolv", "name": "FreeSolv", "category": "physchem", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:lipophilicity", "name": "Lipophilicity", "category": "physchem", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:pcba", "name": "PCBA", "category": "biophysics", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:muv", "name": "MUV", "category": "biophysics", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:hiv", "name": "HIV", "category": "biophysics", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:bace", "name": "BACE", "category": "biophysics", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:pdbbind", "name": "PDBbind", "category": "biophysics", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:bbbp", "name": "BBBP", "category": "physiology", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:tox21", "name": "Tox21", "category": "physiology", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:toxcast", "name": "ToxCast", "category": "physiology", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:sider", "name": "SIDER", "category": "physiology", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" }, { "id": "moleculenet:clintox", "name": "ClinTox", "category": "physiology", "url": "https://moleculenet.org/datasets-1", "leaderboard_url": "https://moleculenet.org/full-results", "paper_url": "https://arxiv.org/abs/1703.00564" } ], "hosted_benchmarks_count": 17 }, { "id": "trialbench", "name": "TrialBench / HINT / TOP", "kind": "meta-platform", "url": "https://github.com/futianfan/clinical-trial-outcome-prediction", "github": "https://github.com/futianfan/clinical-trial-outcome-prediction", "description": "Suite of benchmarks for clinical trial outcome prediction.", "benchmarks_tracked": 4, "benchmark_count_asof": "2026-05-12", "count_methodology": "Fu et al. 2022-2024: HINT (17k trials), TOP (17k), TrialBench (21k trials, 12k drugs), CT-Outcome.", "breakdown": { "hint_trials": 17000, "top_trials": 17000, "trialbench_trials": 21000, "task_variants": 12 }, "host_organization": "Fu/Sun Lab, Georgia Tech + HMS", "primary_contacts": [ "Tianfan Fu", "Jimeng Sun", "Marinka Zitnik" ], "founded": "2022", "license_model": "MIT", "flags": [], "rubric": { "rigor": 4, "coverage": 3, "maintenance": 4, "adoption": 3, "quality": 4, "accessibility": 5, "industry_relevance": 4 }, "notes": "First rigorous ML benchmarks on trial outcomes. Limited by CTgov quality.", "composite_score": 76.5, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "clawbio", "name": "ClawBio Benchmarks", "kind": "meta-platform", "url": "https://clawbio.ai/benchmarks.html", "github": "https://github.com/biostochastics/clawbio_bench", "description": "Public scientific-correctness leaderboard for bio-analysis skills. Independent third-party benchmark (clawbio_bench, authored by Biostochastics LLC) tests ClawBio skills on safety, correctness, honesty. Public failure surface with remediation tasks.", "benchmarks_tracked": 10, "benchmark_count_asof": "2026-05-03", "count_methodology": "Scraped https://clawbio.ai/benchmarks.html on 2026-05-12; last bench run 2026-05-03 against ClawBio commit 7820473 using clawbio_bench v0.1.5. 10 skills audited: claw-metagenomics, equity-scorer, nutrigx-advisor, bio-orchestrator, pharmgx-reporter, fine-mapping, clinical-variant-reporter, cvr-acmg-correctness, gwas-prs, cvr-variant-identity. 168/182 tests passing (92.3%).", "breakdown": { "skills_audited": 10, "tests_total": 182, "tests_passing": 168, "pass_rate_pct": 92.3 }, "host_organization": "ClawBio (open source, MIT)", "primary_contacts": [ "ClawBio maintainers", "Biostochastics LLC (bench author)" ], "founded": "2026-04", "license_model": "MIT", "flags": [], "rubric": { "rigor": 5, "coverage": 2, "maintenance": 5, "adoption": 2, "quality": 4, "accessibility": 5, "industry_relevance": 3 }, "notes": "Independent third-party bench in a separate repo \u2014 structurally NOT self-referential. Coverage narrow (bio-analysis skills) but rigor is exemplary (safety \u00d7 correctness \u00d7 honesty tri-dimensional). Model for how skill/agent correctness should be audited.", "composite_score": 74.2, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "euos", "name": "EU-OPENSCREEN / EUbOPEN", "kind": "consortium", "url": "https://www.eu-openscreen.eu/", "github": "N/A", "description": "EU chemical biology ERIC compound libraries + EUbOPEN chemogenomic probes.", "benchmarks_tracked": 5, "benchmark_count_asof": "2026-05-12", "count_methodology": "eu-openscreen.eu + eubopen.org 2026-05: ECBD (1), Bioactivity sets (2), EUbOPEN probe set (1), EUOS solubility (1).", "breakdown": { "chem_libraries": 2, "bioactivity_benchmarks": 2, "probe_sets": 1 }, "host_organization": "EU-OPENSCREEN ERIC + IMI EUbOPEN", "primary_contacts": [ "Philip Gribbon", "Susanne M\u00fcller-Knapp" ], "founded": "2018", "license_model": "CC-BY", "flags": [], "rubric": { "rigor": 4, "coverage": 3, "maintenance": 4, "adoption": 3, "quality": 4, "accessibility": 4, "industry_relevance": 4 }, "notes": "EUOS solubility benchmark (on Polaris) is most ML-ready.", "composite_score": 73.9, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "pku-aidd", "name": "PKU-AIDD / ChinaDrug Benchmarks", "kind": "consortium", "url": "https://aidd.pku.edu.cn/", "github": "https://github.com/pku-aidd", "description": "PKU AI Drug Discovery + SIMM CAS + Tsinghua + Baidu + Huawei benchmark releases.", "benchmarks_tracked": 7, "benchmark_count_asof": "2026-05-12", "count_methodology": "PKU-AIDD + SIMM CAS + BDBench GitHub 2026-05: 7 public releases (PocketBench, ProteinInvBench, GeoMol-CN, HelixFold-Bench, UniMol-Bench, BDBench, PDBbind-China).", "breakdown": { "pocket": 1, "inverse_folding": 1, "molecular_geometry": 1, "foundation_models": 3, "pdbbind": 1 }, "host_organization": "PKU + SIMM CAS + Tsinghua + Baidu + Huawei", "primary_contacts": [ "Jianfeng Pei", "Luhua Lai", "Jianzhu Ma" ], "founded": "2020", "license_model": "Apache-2.0 / MIT", "flags": [ "self_referential" ], "rubric": { "rigor": 4, "coverage": 3, "maintenance": 4, "adoption": 3, "quality": 4, "accessibility": 5, "industry_relevance": 3 }, "notes": "Growing Chinese benchmark ecosystem. Some self-referential flags (HelixFold on its own bench).", "composite_score": 73.9, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "kaggle-bio", "name": "Kaggle \u2014 Pharma / Bio Competitions", "kind": "competition", "url": "https://www.kaggle.com/competitions", "github": "N/A", "description": "Industry-sponsored ML competitions (Merck MAC 2012, Open Problems \u00d73, NovoZymes, BMS, CAFA 5).", "benchmarks_tracked": 23, "benchmark_count_asof": "2026-05-12", "count_methodology": "Kaggle search for bio/chem/pharma competitions 2010-2025: 23 distinct drug-discovery-adjacent competitions identified.", "breakdown": { "molecule_activity": 5, "single_cell": 4, "protein_function": 4, "histopathology": 6, "other": 4 }, "host_organization": "Google / Kaggle + sponsoring companies", "primary_contacts": [ "Competition hosts vary" ], "founded": "2010", "license_model": "Per-competition", "flags": [], "rubric": { "rigor": 4, "coverage": 3, "maintenance": 2, "adoption": 4, "quality": 4, "accessibility": 4, "industry_relevance": 4 }, "notes": "Impactful one-off events; leaderboards go stale post-close.", "composite_score": 71.9, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "papers-with-code-drug", "name": "Papers With Code \u2014 Drug Discovery", "kind": "meta-platform", "url": "https://paperswithcode.com/area/medical", "github": "N/A", "description": "Aggregates published ML benchmarks with linked code; crowd-curated.", "benchmarks_tracked": 120, "benchmark_count_asof": "2026-05-12", "count_methodology": "paperswithcode.com/area/medical + /task search 2026-05: ~120 drug-discovery-adjacent benchmarks (DTI, generation, ADMET, structure, drug response, etc.).", "breakdown": { "dti": 18, "molecule_generation": 15, "admet": 14, "protein_structure": 22, "drug_response": 11, "other": 40 }, "host_organization": "Meta AI / Papers With Code community", "primary_contacts": [ "PwC community moderators" ], "founded": "2018", "license_model": "Per benchmark", "flags": [], "rubric": { "rigor": 3, "coverage": 5, "maintenance": 3, "adoption": 4, "quality": 2, "accessibility": 5, "industry_relevance": 3 }, "notes": "Useful for discovery; curation quality varies sharply.", "composite_score": 71.6, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "pdbbind-casf", "name": "PDBbind / CASF", "kind": "meta-platform", "url": "http://www.pdbbind.org.cn/", "github": "N/A", "description": "Curated experimental binding affinities for PDB complexes + CASF scoring power tests.", "benchmarks_tracked": 6, "benchmark_count_asof": "2026-05-12", "count_methodology": "pdbbind.org.cn: 2 splits (refined + general) \u00d7 3 CASF editions (2013, 2016, 2020) = 6 configurations.", "breakdown": { "pdbbind_refined_2020": 5316, "pdbbind_general_2020": 19443, "casf_editions": 3 }, "host_organization": "SIMM, Chinese Academy of Sciences", "primary_contacts": [ "Renxiao Wang" ], "founded": "2004", "license_model": "Academic-only", "flags": [ "data-leakage-known" ], "rubric": { "rigor": 4, "coverage": 4, "maintenance": 2, "adoption": 5, "quality": 3, "accessibility": 3, "industry_relevance": 3 }, "notes": "Known leakage; still dominant in published benchmarks. Academic-only licensing limits pharma use.", "composite_score": 70.4, "hosted_benchmarks": [], "hosted_benchmarks_count": 0 }, { "id": "huggingface-biobench", "name": "HuggingFace \u2014 Bio/Chem Datasets", "kind": "data-platform", "url": "https://huggingface.co/datasets", "github": "N/A", "description": "HuggingFace Datasets hub filtered for bio/chem benchmarks (tdc, bigbio, InstaDeep).", "benchmarks_tracked": 310, "benchmark_count_asof": "2026-05-12", "count_methodology": "huggingface.co/datasets tag search (biology/chemistry/medical/drug-discovery) + curated orgs tdc/bigbio/InstaDeepAI 2026-05: ~310 entries, with duplication.", "breakdown": { "molecular": 90, "protein": 70, "clinical_text": 80, "genomic": 40, "other": 30 }, "host_organization": "HuggingFace + community uploaders", "primary_contacts": [ "HF community" ], "founded": "2020", "license_model": "Per-dataset", "flags": [], "rubric": { "rigor": 2, "coverage": 5, "maintenance": 4, "adoption": 4, "quality": 2, "accessibility": 5, "industry_relevance": 2 }, "notes": "High discoverability, low quality floor.", "composite_score": 67.8, "hosted_benchmarks": [ { "id": "hf:MMMU/MMMU", "name": "MMMU/MMMU", "category": "HF-biology", "url": "https://huggingface.co/datasets/MMMU/MMMU", "leaderboard_url": "https://huggingface.co/datasets/MMMU/MMMU", "downloads": 114143 }, { "id": "hf:pulmo/ncbi-genbank-complete", "name": "pulmo/ncbi-genbank-complete", "category": "HF-biology", "url": "https://huggingface.co/datasets/pulmo/ncbi-genbank-complete", "leaderboard_url": "https://huggingface.co/datasets/pulmo/ncbi-genbank-complete", "downloads": 66825 }, { "id": "hf:MMMU/MMMU_Pro", "name": "MMMU/MMMU_Pro", "category": "HF-biology", "url": "https://huggingface.co/datasets/MMMU/MMMU_Pro", "leaderboard_url": "https://huggingface.co/datasets/MMMU/MMMU_Pro", "downloads": 65649 }, { "id": "hf:tahoebio/Tahoe-100M", "name": "tahoebio/Tahoe-100M", "category": "HF-biology", "url": "https://huggingface.co/datasets/tahoebio/Tahoe-100M", "leaderboard_url": "https://huggingface.co/datasets/tahoebio/Tahoe-100M", "downloads": 47356 }, { "id": "hf:huggingworld/ncbi-refseq-complete", "name": "huggingworld/ncbi-refseq-complete", "category": "HF-biology", "url": "https://huggingface.co/datasets/huggingworld/ncbi-refseq-complete", "leaderboard_url": "https://huggingface.co/datasets/huggingworld/ncbi-refseq-complete", "downloads": 40936 }, { "id": "hf:DSIMB/PATHOS-PLM-EMBEDDINGS", "name": "DSIMB/PATHOS-PLM-EMBEDDINGS", "category": "HF-biology", "url": "https://huggingface.co/datasets/DSIMB/PATHOS-PLM-EMBEDDINGS", "leaderboard_url": "https://huggingface.co/datasets/DSIMB/PATHOS-PLM-EMBEDDINGS", "downloads": 27998 }, { "id": "hf:RosettaCommons/ProteinMPNN", "name": "RosettaCommons/ProteinMPNN", "category": "HF-biology", "url": "https://huggingface.co/datasets/RosettaCommons/ProteinMPNN", "leaderboard_url": "https://huggingface.co/datasets/RosettaCommons/ProteinMPNN", "downloads": 23956 }, { "id": "hf:SciCode/SciCode-Domain-Code", "name": "SciCode/SciCode-Domain-Code", "category": "HF-biology", "url": "https://huggingface.co/datasets/SciCode/SciCode-Domain-Code", "leaderboard_url": "https://huggingface.co/datasets/SciCode/SciCode-Domain-Code", "downloads": 22926 }, { "id": "hf:AI4Math/MathVista", "name": "AI4Math/MathVista", "category": "HF-biology", "url": "https://huggingface.co/datasets/AI4Math/MathVista", "leaderboard_url": "https://huggingface.co/datasets/AI4Math/MathVista", "downloads": 21384 }, { "id": "hf:SciCodePile/SciCode-Domain-Code", "name": "SciCodePile/SciCode-Domain-Code", "category": "HF-biology", "url": "https://huggingface.co/datasets/SciCodePile/SciCode-Domain-Code", "leaderboard_url": "https://huggingface.co/datasets/SciCodePile/SciCode-Domain-Code", "downloads": 21185 }, { "id": "hf:qyp111/mdCATH", "name": "qyp111/mdCATH", "category": "HF-biology", "url": "https://huggingface.co/datasets/qyp111/mdCATH", "leaderboard_url": "https://huggingface.co/datasets/qyp111/mdCATH", "downloads": 18518 }, { "id": "hf:derek-thomas/ScienceQA", "name": "derek-thomas/ScienceQA", "category": "HF-biology", "url": "https://huggingface.co/datasets/derek-thomas/ScienceQA", "leaderboard_url": "https://huggingface.co/datasets/derek-thomas/ScienceQA", "downloads": 18485 }, { "id": "hf:xlangai/BRIGHT", "name": "xlangai/BRIGHT", "category": "HF-biology", "url": "https://huggingface.co/datasets/xlangai/BRIGHT", "leaderboard_url": "https://huggingface.co/datasets/xlangai/BRIGHT", "downloads": 16754 }, { "id": "hf:compsciencelab/mdCATH", "name": "compsciencelab/mdCATH", "category": "HF-biology", "url": "https://huggingface.co/datasets/compsciencelab/mdCATH", "leaderboard_url": "https://huggingface.co/datasets/compsciencelab/mdCATH", "downloads": 16523 }, { "id": "hf:ddrg/MUSES", "name": "ddrg/MUSES", "category": "HF-biology", "url": "https://huggingface.co/datasets/ddrg/MUSES", "leaderboard_url": "https://huggingface.co/datasets/ddrg/MUSES", "downloads": 14171 }, { "id": "hf:ProteinMPNN/group_mpnn", "name": "ProteinMPNN/group_mpnn", "category": "HF-biology", "url": "https://huggingface.co/datasets/ProteinMPNN/group_mpnn", "leaderboard_url": "https://huggingface.co/datasets/ProteinMPNN/group_mpnn", "downloads": 13979 }, { "id": "hf:CohereLabs/include-base-44", "name": "CohereLabs/include-base-44", "category": "HF-biology", "url": "https://huggingface.co/datasets/CohereLabs/include-base-44", "leaderboard_url": "https://huggingface.co/datasets/CohereLabs/include-base-44", "downloads": 13194 }, { "id": "hf:imageomics/TreeOfLife-200M", "name": "imageomics/TreeOfLife-200M", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/TreeOfLife-200M", "leaderboard_url": "https://huggingface.co/datasets/imageomics/TreeOfLife-200M", "downloads": 13051 }, { "id": "hf:allenai/peS2o", "name": "allenai/peS2o", "category": "HF-biology", "url": "https://huggingface.co/datasets/allenai/peS2o", "leaderboard_url": "https://huggingface.co/datasets/allenai/peS2o", "downloads": 12761 }, { "id": "hf:futurehouse/lab-bench", "name": "futurehouse/lab-bench", "category": "HF-biology", "url": "https://huggingface.co/datasets/futurehouse/lab-bench", "leaderboard_url": "https://huggingface.co/datasets/futurehouse/lab-bench", "downloads": 12536 }, { "id": "hf:hyf015/EgoExoLearn", "name": "hyf015/EgoExoLearn", "category": "HF-biology", "url": "https://huggingface.co/datasets/hyf015/EgoExoLearn", "leaderboard_url": "https://huggingface.co/datasets/hyf015/EgoExoLearn", "downloads": 12275 }, { "id": "hf:BrentLab/mahendrawada_2025", "name": "BrentLab/mahendrawada_2025", "category": "HF-biology", "url": "https://huggingface.co/datasets/BrentLab/mahendrawada_2025", "leaderboard_url": "https://huggingface.co/datasets/BrentLab/mahendrawada_2025", "downloads": 11799 }, { "id": "hf:jackkuo/arXiv-metadata-oai-snapshot", "name": "jackkuo/arXiv-metadata-oai-snapshot", "category": "HF-biology", "url": "https://huggingface.co/datasets/jackkuo/arXiv-metadata-oai-snapshot", "leaderboard_url": "https://huggingface.co/datasets/jackkuo/arXiv-metadata-oai-snapshot", "downloads": 11790 }, { "id": "hf:EMBO/SourceData", "name": "EMBO/SourceData", "category": "HF-biology", "url": "https://huggingface.co/datasets/EMBO/SourceData", "leaderboard_url": "https://huggingface.co/datasets/EMBO/SourceData", "downloads": 10342 }, { "id": "hf:nicoboou/IDRCell100k", "name": "nicoboou/IDRCell100k", "category": "HF-biology", "url": "https://huggingface.co/datasets/nicoboou/IDRCell100k", "leaderboard_url": "https://huggingface.co/datasets/nicoboou/IDRCell100k", "downloads": 10236 }, { "id": "hf:EarthSpeciesProject/NatureLM-audio-training", "name": "EarthSpeciesProject/NatureLM-audio-training", "category": "HF-biology", "url": "https://huggingface.co/datasets/EarthSpeciesProject/NatureLM-audio-training", "leaderboard_url": "https://huggingface.co/datasets/EarthSpeciesProject/NatureLM-audio-training", "downloads": 9516 }, { "id": "hf:slaf-project/Tahoe-100M", "name": "slaf-project/Tahoe-100M", "category": "HF-biology", "url": "https://huggingface.co/datasets/slaf-project/Tahoe-100M", "leaderboard_url": "https://huggingface.co/datasets/slaf-project/Tahoe-100M", "downloads": 8983 }, { "id": "hf:songlab/TraitGym", "name": "songlab/TraitGym", "category": "HF-biology", "url": "https://huggingface.co/datasets/songlab/TraitGym", "leaderboard_url": "https://huggingface.co/datasets/songlab/TraitGym", "downloads": 8744 }, { "id": "hf:mansoorbaloch/chimera-bench", "name": "mansoorbaloch/chimera-bench", "category": "HF-biology", "url": "https://huggingface.co/datasets/mansoorbaloch/chimera-bench", "leaderboard_url": "https://huggingface.co/datasets/mansoorbaloch/chimera-bench", "downloads": 8220 }, { "id": "hf:1aurent/PatchCamelyon", "name": "1aurent/PatchCamelyon", "category": "HF-biology", "url": "https://huggingface.co/datasets/1aurent/PatchCamelyon", "leaderboard_url": "https://huggingface.co/datasets/1aurent/PatchCamelyon", "downloads": 7720 }, { "id": "hf:arcinstitute/opengenome2", "name": "arcinstitute/opengenome2", "category": "HF-biology", "url": "https://huggingface.co/datasets/arcinstitute/opengenome2", "leaderboard_url": "https://huggingface.co/datasets/arcinstitute/opengenome2", "downloads": 7673 }, { "id": "hf:FreedomIntelligence/medical-o1-reasoning-SFT", "name": "FreedomIntelligence/medical-o1-reasoning-SFT", "category": "HF-biology", "url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT", "leaderboard_url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT", "downloads": 6998 }, { "id": "hf:perturbai/wholebrain_crispr_atlas", "name": "perturbai/wholebrain_crispr_atlas", "category": "HF-biology", "url": "https://huggingface.co/datasets/perturbai/wholebrain_crispr_atlas", "leaderboard_url": "https://huggingface.co/datasets/perturbai/wholebrain_crispr_atlas", "downloads": 6690 }, { "id": "hf:ShengyouDuan/SwarmEvo", "name": "ShengyouDuan/SwarmEvo", "category": "HF-biology", "url": "https://huggingface.co/datasets/ShengyouDuan/SwarmEvo", "leaderboard_url": "https://huggingface.co/datasets/ShengyouDuan/SwarmEvo", "downloads": 6557 }, { "id": "hf:SciCode1/SciCode", "name": "SciCode1/SciCode", "category": "HF-biology", "url": "https://huggingface.co/datasets/SciCode1/SciCode", "leaderboard_url": "https://huggingface.co/datasets/SciCode1/SciCode", "downloads": 6419 }, { "id": "hf:fish-gang/deepscan-dataset", "name": "fish-gang/deepscan-dataset", "category": "HF-biology", "url": "https://huggingface.co/datasets/fish-gang/deepscan-dataset", "leaderboard_url": "https://huggingface.co/datasets/fish-gang/deepscan-dataset", "downloads": 6091 }, { "id": "hf:haitengzhao/molecule_property_instruction", "name": "haitengzhao/molecule_property_instruction", "category": "HF-biology", "url": "https://huggingface.co/datasets/haitengzhao/molecule_property_instruction", "leaderboard_url": "https://huggingface.co/datasets/haitengzhao/molecule_property_instruction", "downloads": 5936 }, { "id": "hf:R-Bench/R-Bench", "name": "R-Bench/R-Bench", "category": "HF-biology", "url": "https://huggingface.co/datasets/R-Bench/R-Bench", "leaderboard_url": "https://huggingface.co/datasets/R-Bench/R-Bench", "downloads": 5746 }, { "id": "hf:GreatCaptainNemo/BioProBench", "name": "GreatCaptainNemo/BioProBench", "category": "HF-biology", "url": "https://huggingface.co/datasets/GreatCaptainNemo/BioProBench", "leaderboard_url": "https://huggingface.co/datasets/GreatCaptainNemo/BioProBench", "downloads": 5566 }, { "id": "hf:nphamdinh/mobilemold", "name": "nphamdinh/mobilemold", "category": "HF-biology", "url": "https://huggingface.co/datasets/nphamdinh/mobilemold", "leaderboard_url": "https://huggingface.co/datasets/nphamdinh/mobilemold", "downloads": 5524 }, { "id": "hf:jiawennnn/STimage-1K4M", "name": "jiawennnn/STimage-1K4M", "category": "HF-biology", "url": "https://huggingface.co/datasets/jiawennnn/STimage-1K4M", "leaderboard_url": "https://huggingface.co/datasets/jiawennnn/STimage-1K4M", "downloads": 5039 }, { "id": "hf:yatin-superintelligence/Edge-Agent-Reasoning-WebSearch-260K", "name": "yatin-superintelligence/Edge-Agent-Reasoning-WebSearch-260K", "category": "HF-biology", "url": "https://huggingface.co/datasets/yatin-superintelligence/Edge-Agent-Reasoning-WebSearch-260K", "leaderboard_url": "https://huggingface.co/datasets/yatin-superintelligence/Edge-Agent-Reasoning-WebSearch-260K", "downloads": 4935 }, { "id": "hf:PatoFlamejanteTV/geral-edu-ptbr", "name": "PatoFlamejanteTV/geral-edu-ptbr", "category": "HF-biology", "url": "https://huggingface.co/datasets/PatoFlamejanteTV/geral-edu-ptbr", "leaderboard_url": "https://huggingface.co/datasets/PatoFlamejanteTV/geral-edu-ptbr", "downloads": 4701 }, { "id": "hf:Xiaoxin888888/STimage-1K4M", "name": "Xiaoxin888888/STimage-1K4M", "category": "HF-biology", "url": "https://huggingface.co/datasets/Xiaoxin888888/STimage-1K4M", "leaderboard_url": "https://huggingface.co/datasets/Xiaoxin888888/STimage-1K4M", "downloads": 4630 }, { "id": "hf:Open-Orca/SlimOrca-Dedup", "name": "Open-Orca/SlimOrca-Dedup", "category": "HF-biology", "url": "https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup", "leaderboard_url": "https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup", "downloads": 4521 }, { "id": "hf:BrentLab/rossi_2021", "name": "BrentLab/rossi_2021", "category": "HF-biology", "url": "https://huggingface.co/datasets/BrentLab/rossi_2021", "leaderboard_url": "https://huggingface.co/datasets/BrentLab/rossi_2021", "downloads": 4444 }, { "id": "hf:hicai-zju/SciKnowEval", "name": "hicai-zju/SciKnowEval", "category": "HF-biology", "url": "https://huggingface.co/datasets/hicai-zju/SciKnowEval", "leaderboard_url": "https://huggingface.co/datasets/hicai-zju/SciKnowEval", "downloads": 4316 }, { "id": "hf:stanford-crfm/image2struct-latex-v1", "name": "stanford-crfm/image2struct-latex-v1", "category": "HF-biology", "url": "https://huggingface.co/datasets/stanford-crfm/image2struct-latex-v1", "leaderboard_url": "https://huggingface.co/datasets/stanford-crfm/image2struct-latex-v1", "downloads": 4097 }, { "id": "hf:hheiden/PubChem-124M-SMILES-SELFIES-InChI-IUPAC", "name": "hheiden/PubChem-124M-SMILES-SELFIES-InChI-IUPAC", "category": "HF-biology", "url": "https://huggingface.co/datasets/hheiden/PubChem-124M-SMILES-SELFIES-InChI-IUPAC", "leaderboard_url": "https://huggingface.co/datasets/hheiden/PubChem-124M-SMILES-SELFIES-InChI-IUPAC", "downloads": 4064 }, { "id": "hf:usersaico/modular-s2orc", "name": "usersaico/modular-s2orc", "category": "HF-biology", "url": "https://huggingface.co/datasets/usersaico/modular-s2orc", "leaderboard_url": "https://huggingface.co/datasets/usersaico/modular-s2orc", "downloads": 3989 }, { "id": "hf:FIFCO/De_vuelta_a_casa", "name": "FIFCO/De_vuelta_a_casa", "category": "HF-biology", "url": "https://huggingface.co/datasets/FIFCO/De_vuelta_a_casa", "leaderboard_url": "https://huggingface.co/datasets/FIFCO/De_vuelta_a_casa", "downloads": 3935 }, { "id": "hf:CohereLabs/include-lite-44", "name": "CohereLabs/include-lite-44", "category": "HF-biology", "url": "https://huggingface.co/datasets/CohereLabs/include-lite-44", "leaderboard_url": "https://huggingface.co/datasets/CohereLabs/include-lite-44", "downloads": 3915 }, { "id": "hf:DataQuests/Dyna_Repo_Inria_MDPosit_Files", "name": "DataQuests/Dyna_Repo_Inria_MDPosit_Files", "category": "HF-biology", "url": "https://huggingface.co/datasets/DataQuests/Dyna_Repo_Inria_MDPosit_Files", "leaderboard_url": "https://huggingface.co/datasets/DataQuests/Dyna_Repo_Inria_MDPosit_Files", "downloads": 3744 }, { "id": "hf:ConvergeBio/uniref100", "name": "ConvergeBio/uniref100", "category": "HF-biology", "url": "https://huggingface.co/datasets/ConvergeBio/uniref100", "leaderboard_url": "https://huggingface.co/datasets/ConvergeBio/uniref100", "downloads": 3708 }, { "id": "hf:RosettaCommons/SAbDab_raw", "name": "RosettaCommons/SAbDab_raw", "category": "HF-biology", "url": "https://huggingface.co/datasets/RosettaCommons/SAbDab_raw", "leaderboard_url": "https://huggingface.co/datasets/RosettaCommons/SAbDab_raw", "downloads": 3607 }, { "id": "hf:sankalpa1998/cat-dog-yolo-dataset", "name": "sankalpa1998/cat-dog-yolo-dataset", "category": "HF-biology", "url": "https://huggingface.co/datasets/sankalpa1998/cat-dog-yolo-dataset", "leaderboard_url": "https://huggingface.co/datasets/sankalpa1998/cat-dog-yolo-dataset", "downloads": 3592 }, { "id": "hf:introvoyz041/ZINC20", "name": "introvoyz041/ZINC20", "category": "HF-biology", "url": "https://huggingface.co/datasets/introvoyz041/ZINC20", "leaderboard_url": "https://huggingface.co/datasets/introvoyz041/ZINC20", "downloads": 3558 }, { "id": "hf:DEMIRUNC/Edge-Agent-Reasoning-WebSearch-260K", "name": "DEMIRUNC/Edge-Agent-Reasoning-WebSearch-260K", "category": "HF-biology", "url": "https://huggingface.co/datasets/DEMIRUNC/Edge-Agent-Reasoning-WebSearch-260K", "leaderboard_url": "https://huggingface.co/datasets/DEMIRUNC/Edge-Agent-Reasoning-WebSearch-260K", "downloads": 3537 }, { "id": "hf:imageomics/fish-vista", "name": "imageomics/fish-vista", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/fish-vista", "leaderboard_url": "https://huggingface.co/datasets/imageomics/fish-vista", "downloads": 3473 }, { "id": "hf:futurehouse/hle-gold-bio-chem", "name": "futurehouse/hle-gold-bio-chem", "category": "HF-biology", "url": "https://huggingface.co/datasets/futurehouse/hle-gold-bio-chem", "leaderboard_url": "https://huggingface.co/datasets/futurehouse/hle-gold-bio-chem", "downloads": 3463 }, { "id": "hf:laion/Wikipedia-Abstract", "name": "laion/Wikipedia-Abstract", "category": "HF-biology", "url": "https://huggingface.co/datasets/laion/Wikipedia-Abstract", "leaderboard_url": "https://huggingface.co/datasets/laion/Wikipedia-Abstract", "downloads": 3420 }, { "id": "hf:ScienceOne-AI/S1-MMAlign", "name": "ScienceOne-AI/S1-MMAlign", "category": "HF-biology", "url": "https://huggingface.co/datasets/ScienceOne-AI/S1-MMAlign", "leaderboard_url": "https://huggingface.co/datasets/ScienceOne-AI/S1-MMAlign", "downloads": 3414 }, { "id": "hf:BlueIsGreen/Edge-Agent-Reasoning-WebSearch-260K", "name": "BlueIsGreen/Edge-Agent-Reasoning-WebSearch-260K", "category": "HF-biology", "url": "https://huggingface.co/datasets/BlueIsGreen/Edge-Agent-Reasoning-WebSearch-260K", "leaderboard_url": "https://huggingface.co/datasets/BlueIsGreen/Edge-Agent-Reasoning-WebSearch-260K", "downloads": 3249 }, { "id": "hf:claran/modular-s2orc", "name": "claran/modular-s2orc", "category": "HF-biology", "url": "https://huggingface.co/datasets/claran/modular-s2orc", "leaderboard_url": "https://huggingface.co/datasets/claran/modular-s2orc", "downloads": 3204 }, { "id": "hf:JosselinSom/Latex-VLM", "name": "JosselinSom/Latex-VLM", "category": "HF-biology", "url": "https://huggingface.co/datasets/JosselinSom/Latex-VLM", "leaderboard_url": "https://huggingface.co/datasets/JosselinSom/Latex-VLM", "downloads": 3131 }, { "id": "hf:satputekuldip/opengenome2", "name": "satputekuldip/opengenome2", "category": "HF-biology", "url": "https://huggingface.co/datasets/satputekuldip/opengenome2", "leaderboard_url": "https://huggingface.co/datasets/satputekuldip/opengenome2", "downloads": 3120 }, { "id": "hf:introvoyz041/vesm_scores", "name": "introvoyz041/vesm_scores", "category": "HF-biology", "url": "https://huggingface.co/datasets/introvoyz041/vesm_scores", "leaderboard_url": "https://huggingface.co/datasets/introvoyz041/vesm_scores", "downloads": 3069 }, { "id": "hf:nds029/Tahoe-100M", "name": "nds029/Tahoe-100M", "category": "HF-biology", "url": "https://huggingface.co/datasets/nds029/Tahoe-100M", "leaderboard_url": "https://huggingface.co/datasets/nds029/Tahoe-100M", "downloads": 3047 }, { "id": "hf:Torenn/Edge-Agent-Reasoning-WebSearch-260K", "name": "Torenn/Edge-Agent-Reasoning-WebSearch-260K", "category": "HF-biology", "url": "https://huggingface.co/datasets/Torenn/Edge-Agent-Reasoning-WebSearch-260K", "leaderboard_url": "https://huggingface.co/datasets/Torenn/Edge-Agent-Reasoning-WebSearch-260K", "downloads": 3006 }, { "id": "hf:cgeorgiaw/merfish", "name": "cgeorgiaw/merfish", "category": "HF-biology", "url": "https://huggingface.co/datasets/cgeorgiaw/merfish", "leaderboard_url": "https://huggingface.co/datasets/cgeorgiaw/merfish", "downloads": 2999 }, { "id": "hf:LumiOpen/opengpt-x_mmlux", "name": "LumiOpen/opengpt-x_mmlux", "category": "HF-biology", "url": "https://huggingface.co/datasets/LumiOpen/opengpt-x_mmlux", "leaderboard_url": "https://huggingface.co/datasets/LumiOpen/opengpt-x_mmlux", "downloads": 2998 }, { "id": "hf:AllTheBacteria/BacCorpus-intergenic-dna-90", "name": "AllTheBacteria/BacCorpus-intergenic-dna-90", "category": "HF-biology", "url": "https://huggingface.co/datasets/AllTheBacteria/BacCorpus-intergenic-dna-90", "leaderboard_url": "https://huggingface.co/datasets/AllTheBacteria/BacCorpus-intergenic-dna-90", "downloads": 2686 }, { "id": "hf:imageomics/invasive_plants_hawaii", "name": "imageomics/invasive_plants_hawaii", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/invasive_plants_hawaii", "leaderboard_url": "https://huggingface.co/datasets/imageomics/invasive_plants_hawaii", "downloads": 2539 }, { "id": "hf:imageomics/mmla_mpala", "name": "imageomics/mmla_mpala", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/mmla_mpala", "leaderboard_url": "https://huggingface.co/datasets/imageomics/mmla_mpala", "downloads": 2489 }, { "id": "hf:Animas1024/MarineEval", "name": "Animas1024/MarineEval", "category": "HF-biology", "url": "https://huggingface.co/datasets/Animas1024/MarineEval", "leaderboard_url": "https://huggingface.co/datasets/Animas1024/MarineEval", "downloads": 2472 }, { "id": "hf:bens-bots/marrs-global-coral-reef-soundscapes", "name": "bens-bots/marrs-global-coral-reef-soundscapes", "category": "HF-biology", "url": "https://huggingface.co/datasets/bens-bots/marrs-global-coral-reef-soundscapes", "leaderboard_url": "https://huggingface.co/datasets/bens-bots/marrs-global-coral-reef-soundscapes", "downloads": 2469 }, { "id": "hf:mm1109/scRegNet", "name": "mm1109/scRegNet", "category": "HF-biology", "url": "https://huggingface.co/datasets/mm1109/scRegNet", "leaderboard_url": "https://huggingface.co/datasets/mm1109/scRegNet", "downloads": 2410 }, { "id": "hf:SZU-ADDG/ZINC-Curated", "name": "SZU-ADDG/ZINC-Curated", "category": "HF-biology", "url": "https://huggingface.co/datasets/SZU-ADDG/ZINC-Curated", "leaderboard_url": "https://huggingface.co/datasets/SZU-ADDG/ZINC-Curated", "downloads": 2398 }, { "id": "hf:imageomics/TreeOfLife-10M", "name": "imageomics/TreeOfLife-10M", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/TreeOfLife-10M", "leaderboard_url": "https://huggingface.co/datasets/imageomics/TreeOfLife-10M", "downloads": 2360 }, { "id": "hf:Mxode/BiST", "name": "Mxode/BiST", "category": "HF-biology", "url": "https://huggingface.co/datasets/Mxode/BiST", "leaderboard_url": "https://huggingface.co/datasets/Mxode/BiST", "downloads": 2261 }, { "id": "hf:CoastalEcology/SeagrassMapper", "name": "CoastalEcology/SeagrassMapper", "category": "HF-biology", "url": "https://huggingface.co/datasets/CoastalEcology/SeagrassMapper", "leaderboard_url": "https://huggingface.co/datasets/CoastalEcology/SeagrassMapper", "downloads": 2258 }, { "id": "hf:OATML-Markslab/ProteinGym_v1", "name": "OATML-Markslab/ProteinGym_v1", "category": "HF-biology", "url": "https://huggingface.co/datasets/OATML-Markslab/ProteinGym_v1", "leaderboard_url": "https://huggingface.co/datasets/OATML-Markslab/ProteinGym_v1", "downloads": 2179 }, { "id": "hf:kanepi-1977/Agent-Reasoning-WebSearch-260K", "name": "kanepi-1977/Agent-Reasoning-WebSearch-260K", "category": "HF-biology", "url": "https://huggingface.co/datasets/kanepi-1977/Agent-Reasoning-WebSearch-260K", "leaderboard_url": "https://huggingface.co/datasets/kanepi-1977/Agent-Reasoning-WebSearch-260K", "downloads": 2178 }, { "id": "hf:GrunCrow/BIRDeep_AudioAnnotations", "name": "GrunCrow/BIRDeep_AudioAnnotations", "category": "HF-biology", "url": "https://huggingface.co/datasets/GrunCrow/BIRDeep_AudioAnnotations", "leaderboard_url": "https://huggingface.co/datasets/GrunCrow/BIRDeep_AudioAnnotations", "downloads": 2163 }, { "id": "hf:RosettaCommons/SAbDab", "name": "RosettaCommons/SAbDab", "category": "HF-biology", "url": "https://huggingface.co/datasets/RosettaCommons/SAbDab", "leaderboard_url": "https://huggingface.co/datasets/RosettaCommons/SAbDab", "downloads": 2146 }, { "id": "hf:AllTheBacteria/BacCorpus-prot-90", "name": "AllTheBacteria/BacCorpus-prot-90", "category": "HF-biology", "url": "https://huggingface.co/datasets/AllTheBacteria/BacCorpus-prot-90", "leaderboard_url": "https://huggingface.co/datasets/AllTheBacteria/BacCorpus-prot-90", "downloads": 2122 }, { "id": "hf:zjunlp/Mol-Instructions", "name": "zjunlp/Mol-Instructions", "category": "HF-biology", "url": "https://huggingface.co/datasets/zjunlp/Mol-Instructions", "leaderboard_url": "https://huggingface.co/datasets/zjunlp/Mol-Instructions", "downloads": 2112 }, { "id": "hf:mteb/BRIGHT", "name": "mteb/BRIGHT", "category": "HF-biology", "url": "https://huggingface.co/datasets/mteb/BRIGHT", "leaderboard_url": "https://huggingface.co/datasets/mteb/BRIGHT", "downloads": 2085 }, { "id": "hf:UniqueData/brain-mri-dataset", "name": "UniqueData/brain-mri-dataset", "category": "HF-biology", "url": "https://huggingface.co/datasets/UniqueData/brain-mri-dataset", "leaderboard_url": "https://huggingface.co/datasets/UniqueData/brain-mri-dataset", "downloads": 2076 }, { "id": "hf:kunikohunter/IEDB_pHLA_binding_data", "name": "kunikohunter/IEDB_pHLA_binding_data", "category": "HF-biology", "url": "https://huggingface.co/datasets/kunikohunter/IEDB_pHLA_binding_data", "leaderboard_url": "https://huggingface.co/datasets/kunikohunter/IEDB_pHLA_binding_data", "downloads": 2065 }, { "id": "hf:longevity-genie/cell2sentence4longevity-data", "name": "longevity-genie/cell2sentence4longevity-data", "category": "HF-biology", "url": "https://huggingface.co/datasets/longevity-genie/cell2sentence4longevity-data", "leaderboard_url": "https://huggingface.co/datasets/longevity-genie/cell2sentence4longevity-data", "downloads": 2044 }, { "id": "hf:HPAI-BSC/CareQA", "name": "HPAI-BSC/CareQA", "category": "HF-biology", "url": "https://huggingface.co/datasets/HPAI-BSC/CareQA", "leaderboard_url": "https://huggingface.co/datasets/HPAI-BSC/CareQA", "downloads": 1963 }, { "id": "hf:BGLab/BioTrove", "name": "BGLab/BioTrove", "category": "HF-biology", "url": "https://huggingface.co/datasets/BGLab/BioTrove", "leaderboard_url": "https://huggingface.co/datasets/BGLab/BioTrove", "downloads": 1962 }, { "id": "hf:tsynbio/ProteinLMBench", "name": "tsynbio/ProteinLMBench", "category": "HF-biology", "url": "https://huggingface.co/datasets/tsynbio/ProteinLMBench", "leaderboard_url": "https://huggingface.co/datasets/tsynbio/ProteinLMBench", "downloads": 1956 }, { "id": "hf:silicobio/peleke_antibody-antigen_sabdab", "name": "silicobio/peleke_antibody-antigen_sabdab", "category": "HF-biology", "url": "https://huggingface.co/datasets/silicobio/peleke_antibody-antigen_sabdab", "leaderboard_url": "https://huggingface.co/datasets/silicobio/peleke_antibody-antigen_sabdab", "downloads": 1924 }, { "id": "hf:mohanty/PlantVillage", "name": "mohanty/PlantVillage", "category": "HF-biology", "url": "https://huggingface.co/datasets/mohanty/PlantVillage", "leaderboard_url": "https://huggingface.co/datasets/mohanty/PlantVillage", "downloads": 1876 }, { "id": "hf:DORI-SRKW/DORI-ONC", "name": "DORI-SRKW/DORI-ONC", "category": "HF-biology", "url": "https://huggingface.co/datasets/DORI-SRKW/DORI-ONC", "leaderboard_url": "https://huggingface.co/datasets/DORI-SRKW/DORI-ONC", "downloads": 1871 }, { "id": "hf:ConvergeBio/uniref90", "name": "ConvergeBio/uniref90", "category": "HF-biology", "url": "https://huggingface.co/datasets/ConvergeBio/uniref90", "leaderboard_url": "https://huggingface.co/datasets/ConvergeBio/uniref90", "downloads": 1869 }, { "id": "hf:Mxode/I_Wonder_Why-Chinese", "name": "Mxode/I_Wonder_Why-Chinese", "category": "HF-biology", "url": "https://huggingface.co/datasets/Mxode/I_Wonder_Why-Chinese", "leaderboard_url": "https://huggingface.co/datasets/Mxode/I_Wonder_Why-Chinese", "downloads": 1864 }, { "id": "hf:Horama/wow_scraped", "name": "Horama/wow_scraped", "category": "HF-biology", "url": "https://huggingface.co/datasets/Horama/wow_scraped", "leaderboard_url": "https://huggingface.co/datasets/Horama/wow_scraped", "downloads": 1840 }, { "id": "hf:SZU-ADDG/MLM-Scaling-datasets", "name": "SZU-ADDG/MLM-Scaling-datasets", "category": "HF-biology", "url": "https://huggingface.co/datasets/SZU-ADDG/MLM-Scaling-datasets", "leaderboard_url": "https://huggingface.co/datasets/SZU-ADDG/MLM-Scaling-datasets", "downloads": 1833 }, { "id": "hf:NeuroTec/SWEC_iEEG_Dataset", "name": "NeuroTec/SWEC_iEEG_Dataset", "category": "HF-biology", "url": "https://huggingface.co/datasets/NeuroTec/SWEC_iEEG_Dataset", "leaderboard_url": "https://huggingface.co/datasets/NeuroTec/SWEC_iEEG_Dataset", "downloads": 1759 }, { "id": "hf:YinkaiW/LSV", "name": "YinkaiW/LSV", "category": "HF-biology", "url": "https://huggingface.co/datasets/YinkaiW/LSV", "leaderboard_url": "https://huggingface.co/datasets/YinkaiW/LSV", "downloads": 1757 }, { "id": "hf:zgcarvalho/uniref50-test", "name": "zgcarvalho/uniref50-test", "category": "HF-biology", "url": "https://huggingface.co/datasets/zgcarvalho/uniref50-test", "leaderboard_url": "https://huggingface.co/datasets/zgcarvalho/uniref50-test", "downloads": 1746 }, { "id": "hf:MMMGBench/MMMG", "name": "MMMGBench/MMMG", "category": "HF-biology", "url": "https://huggingface.co/datasets/MMMGBench/MMMG", "leaderboard_url": "https://huggingface.co/datasets/MMMGBench/MMMG", "downloads": 1709 }, { "id": "hf:haydn-jones/PubChem", "name": "haydn-jones/PubChem", "category": "HF-biology", "url": "https://huggingface.co/datasets/haydn-jones/PubChem", "leaderboard_url": "https://huggingface.co/datasets/haydn-jones/PubChem", "downloads": 1694 }, { "id": "hf:jiahuizhang/PepBenchData", "name": "jiahuizhang/PepBenchData", "category": "HF-biology", "url": "https://huggingface.co/datasets/jiahuizhang/PepBenchData", "leaderboard_url": "https://huggingface.co/datasets/jiahuizhang/PepBenchData", "downloads": 1694 }, { "id": "hf:VerisimilitudeX/mobius-data", "name": "VerisimilitudeX/mobius-data", "category": "HF-biology", "url": "https://huggingface.co/datasets/VerisimilitudeX/mobius-data", "leaderboard_url": "https://huggingface.co/datasets/VerisimilitudeX/mobius-data", "downloads": 1664 }, { "id": "hf:instruction-pretrain/medicine-instruction-augmented-corpora", "name": "instruction-pretrain/medicine-instruction-augmented-corpora", "category": "HF-biology", "url": "https://huggingface.co/datasets/instruction-pretrain/medicine-instruction-augmented-corpora", "leaderboard_url": "https://huggingface.co/datasets/instruction-pretrain/medicine-instruction-augmented-corpora", "downloads": 1653 }, { "id": "hf:imageomics/2018-NEON-beetles", "name": "imageomics/2018-NEON-beetles", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/2018-NEON-beetles", "leaderboard_url": "https://huggingface.co/datasets/imageomics/2018-NEON-beetles", "downloads": 1639 }, { "id": "hf:Nekochu/Luminia-mixture", "name": "Nekochu/Luminia-mixture", "category": "HF-biology", "url": "https://huggingface.co/datasets/Nekochu/Luminia-mixture", "leaderboard_url": "https://huggingface.co/datasets/Nekochu/Luminia-mixture", "downloads": 1617 }, { "id": "hf:hardlyworking/Vagina-Vision-Image-Folder-Captions-Included", "name": "hardlyworking/Vagina-Vision-Image-Folder-Captions-Included", "category": "HF-biology", "url": "https://huggingface.co/datasets/hardlyworking/Vagina-Vision-Image-Folder-Captions-Included", "leaderboard_url": "https://huggingface.co/datasets/hardlyworking/Vagina-Vision-Image-Folder-Captions-Included", "downloads": 1606 }, { "id": "hf:FreedomIntelligence/medical-o1-verifiable-problem", "name": "FreedomIntelligence/medical-o1-verifiable-problem", "category": "HF-biology", "url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-verifiable-problem", "leaderboard_url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-verifiable-problem", "downloads": 1594 }, { "id": "hf:1aurent/NCT-CRC-HE", "name": "1aurent/NCT-CRC-HE", "category": "HF-biology", "url": "https://huggingface.co/datasets/1aurent/NCT-CRC-HE", "leaderboard_url": "https://huggingface.co/datasets/1aurent/NCT-CRC-HE", "downloads": 1566 }, { "id": "hf:datatab/serbian-llm-benchmark", "name": "datatab/serbian-llm-benchmark", "category": "HF-biology", "url": "https://huggingface.co/datasets/datatab/serbian-llm-benchmark", "leaderboard_url": "https://huggingface.co/datasets/datatab/serbian-llm-benchmark", "downloads": 1532 }, { "id": "hf:IVN-RIN/BioBERT_Italian", "name": "IVN-RIN/BioBERT_Italian", "category": "HF-biology", "url": "https://huggingface.co/datasets/IVN-RIN/BioBERT_Italian", "leaderboard_url": "https://huggingface.co/datasets/IVN-RIN/BioBERT_Italian", "downloads": 1531 }, { "id": "hf:imageomics/IDLE-OO-Camera-Traps", "name": "imageomics/IDLE-OO-Camera-Traps", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/IDLE-OO-Camera-Traps", "leaderboard_url": "https://huggingface.co/datasets/imageomics/IDLE-OO-Camera-Traps", "downloads": 1506 }, { "id": "hf:RosettaCommons/FPbase", "name": "RosettaCommons/FPbase", "category": "HF-biology", "url": "https://huggingface.co/datasets/RosettaCommons/FPbase", "leaderboard_url": "https://huggingface.co/datasets/RosettaCommons/FPbase", "downloads": 1483 }, { "id": "hf:imageomics/VLM4Bio", "name": "imageomics/VLM4Bio", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/VLM4Bio", "leaderboard_url": "https://huggingface.co/datasets/imageomics/VLM4Bio", "downloads": 1477 }, { "id": "hf:imageomics/mmla_wilds", "name": "imageomics/mmla_wilds", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/mmla_wilds", "leaderboard_url": "https://huggingface.co/datasets/imageomics/mmla_wilds", "downloads": 1466 }, { "id": "hf:MBZUAI/medix-rl-data", "name": "MBZUAI/medix-rl-data", "category": "HF-biology", "url": "https://huggingface.co/datasets/MBZUAI/medix-rl-data", "leaderboard_url": "https://huggingface.co/datasets/MBZUAI/medix-rl-data", "downloads": 1465 }, { "id": "hf:Petra-AI/ZalmatiAI", "name": "Petra-AI/ZalmatiAI", "category": "HF-biology", "url": "https://huggingface.co/datasets/Petra-AI/ZalmatiAI", "leaderboard_url": "https://huggingface.co/datasets/Petra-AI/ZalmatiAI", "downloads": 1456 }, { "id": "hf:EPFL-ECEO/coralscapes", "name": "EPFL-ECEO/coralscapes", "category": "HF-biology", "url": "https://huggingface.co/datasets/EPFL-ECEO/coralscapes", "leaderboard_url": "https://huggingface.co/datasets/EPFL-ECEO/coralscapes", "downloads": 1455 }, { "id": "hf:songlab/clinvar_vs_benign", "name": "songlab/clinvar_vs_benign", "category": "HF-biology", "url": "https://huggingface.co/datasets/songlab/clinvar_vs_benign", "leaderboard_url": "https://huggingface.co/datasets/songlab/clinvar_vs_benign", "downloads": 1438 }, { "id": "hf:JierunChen/MMMU_with_difficulty_level", "name": "JierunChen/MMMU_with_difficulty_level", "category": "HF-biology", "url": "https://huggingface.co/datasets/JierunChen/MMMU_with_difficulty_level", "leaderboard_url": "https://huggingface.co/datasets/JierunChen/MMMU_with_difficulty_level", "downloads": 1385 }, { "id": "hf:ginkgo-datapoints/GDPx3", "name": "ginkgo-datapoints/GDPx3", "category": "HF-biology", "url": "https://huggingface.co/datasets/ginkgo-datapoints/GDPx3", "leaderboard_url": "https://huggingface.co/datasets/ginkgo-datapoints/GDPx3", "downloads": 1376 }, { "id": "hf:InternScience/SFE", "name": "InternScience/SFE", "category": "HF-biology", "url": "https://huggingface.co/datasets/InternScience/SFE", "leaderboard_url": "https://huggingface.co/datasets/InternScience/SFE", "downloads": 1339 }, { "id": "hf:computage/computage_bench", "name": "computage/computage_bench", "category": "HF-biology", "url": "https://huggingface.co/datasets/computage/computage_bench", "leaderboard_url": "https://huggingface.co/datasets/computage/computage_bench", "downloads": 1324 }, { "id": "hf:velaiola/Tahoe-100M", "name": "velaiola/Tahoe-100M", "category": "HF-biology", "url": "https://huggingface.co/datasets/velaiola/Tahoe-100M", "leaderboard_url": "https://huggingface.co/datasets/velaiola/Tahoe-100M", "downloads": 1310 }, { "id": "hf:InternScience/SGI-DeepResearch", "name": "InternScience/SGI-DeepResearch", "category": "HF-biology", "url": "https://huggingface.co/datasets/InternScience/SGI-DeepResearch", "leaderboard_url": "https://huggingface.co/datasets/InternScience/SGI-DeepResearch", "downloads": 1304 }, { "id": "hf:ConvergeBio/uniclust30", "name": "ConvergeBio/uniclust30", "category": "HF-biology", "url": "https://huggingface.co/datasets/ConvergeBio/uniclust30", "leaderboard_url": "https://huggingface.co/datasets/ConvergeBio/uniclust30", "downloads": 1298 }, { "id": "hf:xuan-liu/FGBench", "name": "xuan-liu/FGBench", "category": "HF-biology", "url": "https://huggingface.co/datasets/xuan-liu/FGBench", "leaderboard_url": "https://huggingface.co/datasets/xuan-liu/FGBench", "downloads": 1269 }, { "id": "hf:SMAResearch/sma-evidence-graph", "name": "SMAResearch/sma-evidence-graph", "category": "HF-biology", "url": "https://huggingface.co/datasets/SMAResearch/sma-evidence-graph", "leaderboard_url": "https://huggingface.co/datasets/SMAResearch/sma-evidence-graph", "downloads": 1245 }, { "id": "hf:BIOMEDICA/biomedica_webdataset_24M", "name": "BIOMEDICA/biomedica_webdataset_24M", "category": "HF-biology", "url": "https://huggingface.co/datasets/BIOMEDICA/biomedica_webdataset_24M", "leaderboard_url": "https://huggingface.co/datasets/BIOMEDICA/biomedica_webdataset_24M", "downloads": 1239 }, { "id": "hf:farmaieu/plantorgans", "name": "farmaieu/plantorgans", "category": "HF-biology", "url": "https://huggingface.co/datasets/farmaieu/plantorgans", "leaderboard_url": "https://huggingface.co/datasets/farmaieu/plantorgans", "downloads": 1226 }, { "id": "hf:jmhb/microvqa", "name": "jmhb/microvqa", "category": "HF-biology", "url": "https://huggingface.co/datasets/jmhb/microvqa", "leaderboard_url": "https://huggingface.co/datasets/jmhb/microvqa", "downloads": 1207 }, { "id": "hf:FreedomIntelligence/PubMedVision", "name": "FreedomIntelligence/PubMedVision", "category": "HF-biology", "url": "https://huggingface.co/datasets/FreedomIntelligence/PubMedVision", "leaderboard_url": "https://huggingface.co/datasets/FreedomIntelligence/PubMedVision", "downloads": 1183 }, { "id": "hf:FreedomIntelligence/CMB", "name": "FreedomIntelligence/CMB", "category": "HF-biology", "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB", "leaderboard_url": "https://huggingface.co/datasets/FreedomIntelligence/CMB", "downloads": 1182 }, { "id": "hf:imageomics/rare-species", "name": "imageomics/rare-species", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/rare-species", "leaderboard_url": "https://huggingface.co/datasets/imageomics/rare-species", "downloads": 1180 }, { "id": "hf:zacharielegault/PatchCamelyon", "name": "zacharielegault/PatchCamelyon", "category": "HF-biology", "url": "https://huggingface.co/datasets/zacharielegault/PatchCamelyon", "leaderboard_url": "https://huggingface.co/datasets/zacharielegault/PatchCamelyon", "downloads": 1157 }, { "id": "hf:restor/tcd", "name": "restor/tcd", "category": "HF-biology", "url": "https://huggingface.co/datasets/restor/tcd", "leaderboard_url": "https://huggingface.co/datasets/restor/tcd", "downloads": 1147 }, { "id": "hf:rootsautomation/pubmed-ocr", "name": "rootsautomation/pubmed-ocr", "category": "HF-biology", "url": "https://huggingface.co/datasets/rootsautomation/pubmed-ocr", "leaderboard_url": "https://huggingface.co/datasets/rootsautomation/pubmed-ocr", "downloads": 1142 }, { "id": "hf:ConvergeBio/uniref50", "name": "ConvergeBio/uniref50", "category": "HF-biology", "url": "https://huggingface.co/datasets/ConvergeBio/uniref50", "leaderboard_url": "https://huggingface.co/datasets/ConvergeBio/uniref50", "downloads": 1139 }, { "id": "hf:EarthSpeciesProject/BEANS-Zero", "name": "EarthSpeciesProject/BEANS-Zero", "category": "HF-biology", "url": "https://huggingface.co/datasets/EarthSpeciesProject/BEANS-Zero", "leaderboard_url": "https://huggingface.co/datasets/EarthSpeciesProject/BEANS-Zero", "downloads": 1133 }, { "id": "hf:OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B", "name": "OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B", "category": "HF-biology", "url": "https://huggingface.co/datasets/OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B", "leaderboard_url": "https://huggingface.co/datasets/OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B", "downloads": 1115 }, { "id": "hf:ArlingtonCL2/Dog-Vocal-Separation", "name": "ArlingtonCL2/Dog-Vocal-Separation", "category": "HF-biology", "url": "https://huggingface.co/datasets/ArlingtonCL2/Dog-Vocal-Separation", "leaderboard_url": "https://huggingface.co/datasets/ArlingtonCL2/Dog-Vocal-Separation", "downloads": 1103 }, { "id": "hf:findshuo/Protap", "name": "findshuo/Protap", "category": "HF-biology", "url": "https://huggingface.co/datasets/findshuo/Protap", "leaderboard_url": "https://huggingface.co/datasets/findshuo/Protap", "downloads": 1092 }, { "id": "hf:kadzaki/FrBMedQA", "name": "kadzaki/FrBMedQA", "category": "HF-biology", "url": "https://huggingface.co/datasets/kadzaki/FrBMedQA", "leaderboard_url": "https://huggingface.co/datasets/kadzaki/FrBMedQA", "downloads": 1078 }, { "id": "hf:songlab/cosmic", "name": "songlab/cosmic", "category": "HF-biology", "url": "https://huggingface.co/datasets/songlab/cosmic", "leaderboard_url": "https://huggingface.co/datasets/songlab/cosmic", "downloads": 1073 }, { "id": "hf:UniqueData/brain-anomaly-detection", "name": "UniqueData/brain-anomaly-detection", "category": "HF-biology", "url": "https://huggingface.co/datasets/UniqueData/brain-anomaly-detection", "leaderboard_url": "https://huggingface.co/datasets/UniqueData/brain-anomaly-detection", "downloads": 1052 }, { "id": "hf:scikit-fingerprints/MoleculeNet_BACE", "name": "scikit-fingerprints/MoleculeNet_BACE", "category": "HF-biology", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_BACE", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_BACE", "downloads": 1045 }, { "id": "hf:Niche-Squad/COLO", "name": "Niche-Squad/COLO", "category": "HF-biology", "url": "https://huggingface.co/datasets/Niche-Squad/COLO", "leaderboard_url": "https://huggingface.co/datasets/Niche-Squad/COLO", "downloads": 1034 }, { "id": "hf:wanglab/kegg", "name": "wanglab/kegg", "category": "HF-biology", "url": "https://huggingface.co/datasets/wanglab/kegg", "leaderboard_url": "https://huggingface.co/datasets/wanglab/kegg", "downloads": 1015 }, { "id": "hf:Feibo-112358/SpatialCorpus-110M", "name": "Feibo-112358/SpatialCorpus-110M", "category": "HF-biology", "url": "https://huggingface.co/datasets/Feibo-112358/SpatialCorpus-110M", "leaderboard_url": "https://huggingface.co/datasets/Feibo-112358/SpatialCorpus-110M", "downloads": 1012 }, { "id": "hf:polymathic-ai/active_matter", "name": "polymathic-ai/active_matter", "category": "HF-biology", "url": "https://huggingface.co/datasets/polymathic-ai/active_matter", "leaderboard_url": "https://huggingface.co/datasets/polymathic-ai/active_matter", "downloads": 1008 }, { "id": "hf:songlab/ldsc", "name": "songlab/ldsc", "category": "HF-biology", "url": "https://huggingface.co/datasets/songlab/ldsc", "leaderboard_url": "https://huggingface.co/datasets/songlab/ldsc", "downloads": 1003 }, { "id": "hf:gasparyanartur/things-eeg2", "name": "gasparyanartur/things-eeg2", "category": "HF-biology", "url": "https://huggingface.co/datasets/gasparyanartur/things-eeg2", "leaderboard_url": "https://huggingface.co/datasets/gasparyanartur/things-eeg2", "downloads": 999 }, { "id": "hf:biomap-research/enzyme_catalytic_efficiency", "name": "biomap-research/enzyme_catalytic_efficiency", "category": "HF-biology", "url": "https://huggingface.co/datasets/biomap-research/enzyme_catalytic_efficiency", "leaderboard_url": "https://huggingface.co/datasets/biomap-research/enzyme_catalytic_efficiency", "downloads": 984 }, { "id": "hf:Joemgu/sumstew", "name": "Joemgu/sumstew", "category": "HF-biology", "url": "https://huggingface.co/datasets/Joemgu/sumstew", "leaderboard_url": "https://huggingface.co/datasets/Joemgu/sumstew", "downloads": 975 }, { "id": "hf:UniqueData/multiple-sclerosis-dataset", "name": "UniqueData/multiple-sclerosis-dataset", "category": "HF-biology", "url": "https://huggingface.co/datasets/UniqueData/multiple-sclerosis-dataset", "leaderboard_url": "https://huggingface.co/datasets/UniqueData/multiple-sclerosis-dataset", "downloads": 973 }, { "id": "hf:RosettaCommons/PISCES-CulledPDB", "name": "RosettaCommons/PISCES-CulledPDB", "category": "HF-biology", "url": "https://huggingface.co/datasets/RosettaCommons/PISCES-CulledPDB", "leaderboard_url": "https://huggingface.co/datasets/RosettaCommons/PISCES-CulledPDB", "downloads": 964 }, { "id": "hf:kewserseid/biomedical-instruction-dataset", "name": "kewserseid/biomedical-instruction-dataset", "category": "HF-biology", "url": "https://huggingface.co/datasets/kewserseid/biomedical-instruction-dataset", "leaderboard_url": "https://huggingface.co/datasets/kewserseid/biomedical-instruction-dataset", "downloads": 961 }, { "id": "hf:biomap-research/metal_ion_binding", "name": "biomap-research/metal_ion_binding", "category": "HF-biology", "url": "https://huggingface.co/datasets/biomap-research/metal_ion_binding", "leaderboard_url": "https://huggingface.co/datasets/biomap-research/metal_ion_binding", "downloads": 949 }, { "id": "hf:GenerTeam/prokaryotic-gener-tasks", "name": "GenerTeam/prokaryotic-gener-tasks", "category": "HF-biology", "url": "https://huggingface.co/datasets/GenerTeam/prokaryotic-gener-tasks", "leaderboard_url": "https://huggingface.co/datasets/GenerTeam/prokaryotic-gener-tasks", "downloads": 945 }, { "id": "hf:AgMMU/AgMMU_v1", "name": "AgMMU/AgMMU_v1", "category": "HF-biology", "url": "https://huggingface.co/datasets/AgMMU/AgMMU_v1", "leaderboard_url": "https://huggingface.co/datasets/AgMMU/AgMMU_v1", "downloads": 943 }, { "id": "hf:MBARI-org/DeepSea-MOT", "name": "MBARI-org/DeepSea-MOT", "category": "HF-biology", "url": "https://huggingface.co/datasets/MBARI-org/DeepSea-MOT", "leaderboard_url": "https://huggingface.co/datasets/MBARI-org/DeepSea-MOT", "downloads": 942 }, { "id": "hf:Jimut123/RV-PBS", "name": "Jimut123/RV-PBS", "category": "HF-biology", "url": "https://huggingface.co/datasets/Jimut123/RV-PBS", "leaderboard_url": "https://huggingface.co/datasets/Jimut123/RV-PBS", "downloads": 942 }, { "id": "hf:lukaskim/ChEMBL-36", "name": "lukaskim/ChEMBL-36", "category": "HF-biology", "url": "https://huggingface.co/datasets/lukaskim/ChEMBL-36", "leaderboard_url": "https://huggingface.co/datasets/lukaskim/ChEMBL-36", "downloads": 934 }, { "id": "hf:galaxyMindAiLabs/stem-reasoning-complex", "name": "galaxyMindAiLabs/stem-reasoning-complex", "category": "HF-biology", "url": "https://huggingface.co/datasets/galaxyMindAiLabs/stem-reasoning-complex", "leaderboard_url": "https://huggingface.co/datasets/galaxyMindAiLabs/stem-reasoning-complex", "downloads": 932 }, { "id": "hf:U4R/DocGenome", "name": "U4R/DocGenome", "category": "HF-biology", "url": "https://huggingface.co/datasets/U4R/DocGenome", "leaderboard_url": "https://huggingface.co/datasets/U4R/DocGenome", "downloads": 911 }, { "id": "hf:songlab/omim", "name": "songlab/omim", "category": "HF-biology", "url": "https://huggingface.co/datasets/songlab/omim", "leaderboard_url": "https://huggingface.co/datasets/songlab/omim", "downloads": 900 }, { "id": "hf:alejoacelas/uniref50-2025-10", "name": "alejoacelas/uniref50-2025-10", "category": "HF-biology", "url": "https://huggingface.co/datasets/alejoacelas/uniref50-2025-10", "leaderboard_url": "https://huggingface.co/datasets/alejoacelas/uniref50-2025-10", "downloads": 900 }, { "id": "hf:introvoyz041/ZINC-Curated", "name": "introvoyz041/ZINC-Curated", "category": "HF-biology", "url": "https://huggingface.co/datasets/introvoyz041/ZINC-Curated", "leaderboard_url": "https://huggingface.co/datasets/introvoyz041/ZINC-Curated", "downloads": 900 }, { "id": "hf:biomap-research/peptide_HLA_MHC_affinity", "name": "biomap-research/peptide_HLA_MHC_affinity", "category": "HF-biology", "url": "https://huggingface.co/datasets/biomap-research/peptide_HLA_MHC_affinity", "leaderboard_url": "https://huggingface.co/datasets/biomap-research/peptide_HLA_MHC_affinity", "downloads": 899 }, { "id": "hf:slaab/NCERT-Parallel-Dataset-Indic", "name": "slaab/NCERT-Parallel-Dataset-Indic", "category": "HF-biology", "url": "https://huggingface.co/datasets/slaab/NCERT-Parallel-Dataset-Indic", "leaderboard_url": "https://huggingface.co/datasets/slaab/NCERT-Parallel-Dataset-Indic", "downloads": 888 }, { "id": "hf:BrentLab/hughes_2006", "name": "BrentLab/hughes_2006", "category": "HF-biology", "url": "https://huggingface.co/datasets/BrentLab/hughes_2006", "leaderboard_url": "https://huggingface.co/datasets/BrentLab/hughes_2006", "downloads": 887 }, { "id": "hf:ai-forever/POLLUX", "name": "ai-forever/POLLUX", "category": "HF-biology", "url": "https://huggingface.co/datasets/ai-forever/POLLUX", "leaderboard_url": "https://huggingface.co/datasets/ai-forever/POLLUX", "downloads": 886 }, { "id": "hf:introvoyz041/Gargantua-R1-Compact", "name": "introvoyz041/Gargantua-R1-Compact", "category": "HF-biology", "url": "https://huggingface.co/datasets/introvoyz041/Gargantua-R1-Compact", "leaderboard_url": "https://huggingface.co/datasets/introvoyz041/Gargantua-R1-Compact", "downloads": 882 }, { "id": "hf:RainPPR/china-textbook", "name": "RainPPR/china-textbook", "category": "HF-biology", "url": "https://huggingface.co/datasets/RainPPR/china-textbook", "leaderboard_url": "https://huggingface.co/datasets/RainPPR/china-textbook", "downloads": 880 }, { "id": "hf:songlab/gnomad_balanced", "name": "songlab/gnomad_balanced", "category": "HF-biology", "url": "https://huggingface.co/datasets/songlab/gnomad_balanced", "leaderboard_url": "https://huggingface.co/datasets/songlab/gnomad_balanced", "downloads": 875 }, { "id": "hf:FreedomIntelligence/Medical_Multimodal_Evaluation_Data", "name": "FreedomIntelligence/Medical_Multimodal_Evaluation_Data", "category": "HF-biology", "url": "https://huggingface.co/datasets/FreedomIntelligence/Medical_Multimodal_Evaluation_Data", "leaderboard_url": "https://huggingface.co/datasets/FreedomIntelligence/Medical_Multimodal_Evaluation_Data", "downloads": 851 }, { "id": "hf:BUAADreamer/llava-med-zh-instruct-60k", "name": "BUAADreamer/llava-med-zh-instruct-60k", "category": "HF-biology", "url": "https://huggingface.co/datasets/BUAADreamer/llava-med-zh-instruct-60k", "leaderboard_url": "https://huggingface.co/datasets/BUAADreamer/llava-med-zh-instruct-60k", "downloads": 849 }, { "id": "hf:scikit-fingerprints/MoleculeNet_PCBA", "name": "scikit-fingerprints/MoleculeNet_PCBA", "category": "HF-biology", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_PCBA", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_PCBA", "downloads": 849 }, { "id": "hf:songlab/clinvar", "name": "songlab/clinvar", "category": "HF-biology", "url": "https://huggingface.co/datasets/songlab/clinvar", "leaderboard_url": "https://huggingface.co/datasets/songlab/clinvar", "downloads": 846 }, { "id": "hf:allenai/us-patents", "name": "allenai/us-patents", "category": "HF-biology", "url": "https://huggingface.co/datasets/allenai/us-patents", "leaderboard_url": "https://huggingface.co/datasets/allenai/us-patents", "downloads": 834 }, { "id": "hf:xuejun72/HR-VILAGE-3K3M", "name": "xuejun72/HR-VILAGE-3K3M", "category": "HF-biology", "url": "https://huggingface.co/datasets/xuejun72/HR-VILAGE-3K3M", "leaderboard_url": "https://huggingface.co/datasets/xuejun72/HR-VILAGE-3K3M", "downloads": 831 }, { "id": "hf:Eurolingua/mmlux", "name": "Eurolingua/mmlux", "category": "HF-biology", "url": "https://huggingface.co/datasets/Eurolingua/mmlux", "leaderboard_url": "https://huggingface.co/datasets/Eurolingua/mmlux", "downloads": 830 }, { "id": "hf:Yangximiao/PlantCAD2_zero_shot_tasks", "name": "Yangximiao/PlantCAD2_zero_shot_tasks", "category": "HF-biology", "url": "https://huggingface.co/datasets/Yangximiao/PlantCAD2_zero_shot_tasks", "leaderboard_url": "https://huggingface.co/datasets/Yangximiao/PlantCAD2_zero_shot_tasks", "downloads": 830 }, { "id": "hf:biomap-research/fitness_prediction", "name": "biomap-research/fitness_prediction", "category": "HF-biology", "url": "https://huggingface.co/datasets/biomap-research/fitness_prediction", "leaderboard_url": "https://huggingface.co/datasets/biomap-research/fitness_prediction", "downloads": 821 }, { "id": "hf:wanglab/variant_effect_coding", "name": "wanglab/variant_effect_coding", "category": "HF-biology", "url": "https://huggingface.co/datasets/wanglab/variant_effect_coding", "leaderboard_url": "https://huggingface.co/datasets/wanglab/variant_effect_coding", "downloads": 815 }, { "id": "hf:biomap-research/stability_prediction", "name": "biomap-research/stability_prediction", "category": "HF-biology", "url": "https://huggingface.co/datasets/biomap-research/stability_prediction", "leaderboard_url": "https://huggingface.co/datasets/biomap-research/stability_prediction", "downloads": 812 }, { "id": "hf:KokosDev/single-cell-brain-zarr", "name": "KokosDev/single-cell-brain-zarr", "category": "HF-biology", "url": "https://huggingface.co/datasets/KokosDev/single-cell-brain-zarr", "leaderboard_url": "https://huggingface.co/datasets/KokosDev/single-cell-brain-zarr", "downloads": 812 }, { "id": "hf:chandar-lab/CoPeP", "name": "chandar-lab/CoPeP", "category": "HF-biology", "url": "https://huggingface.co/datasets/chandar-lab/CoPeP", "leaderboard_url": "https://huggingface.co/datasets/chandar-lab/CoPeP", "downloads": 809 }, { "id": "hf:DavidVivancos/NeuraxonLife2.5-100K-TimeSeries", "name": "DavidVivancos/NeuraxonLife2.5-100K-TimeSeries", "category": "HF-biology", "url": "https://huggingface.co/datasets/DavidVivancos/NeuraxonLife2.5-100K-TimeSeries", "leaderboard_url": "https://huggingface.co/datasets/DavidVivancos/NeuraxonLife2.5-100K-TimeSeries", "downloads": 800 }, { "id": "hf:biomap-research/fold_prediction", "name": "biomap-research/fold_prediction", "category": "HF-biology", "url": "https://huggingface.co/datasets/biomap-research/fold_prediction", "leaderboard_url": "https://huggingface.co/datasets/biomap-research/fold_prediction", "downloads": 794 }, { "id": "hf:scikit-fingerprints/MoleculeNet_ESOL", "name": "scikit-fingerprints/MoleculeNet_ESOL", "category": "HF-biology", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_ESOL", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_ESOL", "downloads": 793 }, { "id": "hf:songlab/gpn-msa-sapiens-dataset", "name": "songlab/gpn-msa-sapiens-dataset", "category": "HF-biology", "url": "https://huggingface.co/datasets/songlab/gpn-msa-sapiens-dataset", "leaderboard_url": "https://huggingface.co/datasets/songlab/gpn-msa-sapiens-dataset", "downloads": 791 }, { "id": "hf:imageomics/upper-waiakea-PAM", "name": "imageomics/upper-waiakea-PAM", "category": "HF-biology", "url": "https://huggingface.co/datasets/imageomics/upper-waiakea-PAM", "leaderboard_url": "https://huggingface.co/datasets/imageomics/upper-waiakea-PAM", "downloads": 791 }, { "id": "hf:agentlans/FreedomIntelligence-medical", "name": "agentlans/FreedomIntelligence-medical", "category": "HF-biology", "url": "https://huggingface.co/datasets/agentlans/FreedomIntelligence-medical", "leaderboard_url": "https://huggingface.co/datasets/agentlans/FreedomIntelligence-medical", "downloads": 781 }, { "id": "hf:proteinglm/fluorescence_prediction", "name": "proteinglm/fluorescence_prediction", "category": "HF-biology", "url": "https://huggingface.co/datasets/proteinglm/fluorescence_prediction", "leaderboard_url": "https://huggingface.co/datasets/proteinglm/fluorescence_prediction", "downloads": 779 }, { "id": "hf:gaianet/chemistry", "name": "gaianet/chemistry", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/gaianet/chemistry", "leaderboard_url": "https://huggingface.co/datasets/gaianet/chemistry", "downloads": 8857 }, { "id": "hf:XythicK/Chemistry", "name": "XythicK/Chemistry", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/XythicK/Chemistry", "leaderboard_url": "https://huggingface.co/datasets/XythicK/Chemistry", "downloads": 8818 }, { "id": "hf:Narimanka/Abuhuesos", "name": "Narimanka/Abuhuesos", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/Narimanka/Abuhuesos", "leaderboard_url": "https://huggingface.co/datasets/Narimanka/Abuhuesos", "downloads": 6136 }, { "id": "hf:Airtel4141/Sssdmdsff", "name": "Airtel4141/Sssdmdsff", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/Airtel4141/Sssdmdsff", "leaderboard_url": "https://huggingface.co/datasets/Airtel4141/Sssdmdsff", "downloads": 5636 }, { "id": "hf:UniParser/MolParser-7M", "name": "UniParser/MolParser-7M", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/UniParser/MolParser-7M", "leaderboard_url": "https://huggingface.co/datasets/UniParser/MolParser-7M", "downloads": 3854 }, { "id": "hf:jablonkagroup/chempile-mlift", "name": "jablonkagroup/chempile-mlift", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/chempile-mlift", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/chempile-mlift", "downloads": 3377 }, { "id": "hf:openadmet/pxr-challenge-train-test", "name": "openadmet/pxr-challenge-train-test", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/openadmet/pxr-challenge-train-test", "leaderboard_url": "https://huggingface.co/datasets/openadmet/pxr-challenge-train-test", "downloads": 3069 }, { "id": "hf:jablonkagroup/corral-QAs-reports", "name": "jablonkagroup/corral-QAs-reports", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/corral-QAs-reports", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/corral-QAs-reports", "downloads": 2983 }, { "id": "hf:Battery-Life/BatteryLife_Processed", "name": "Battery-Life/BatteryLife_Processed", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/Battery-Life/BatteryLife_Processed", "leaderboard_url": "https://huggingface.co/datasets/Battery-Life/BatteryLife_Processed", "downloads": 2832 }, { "id": "hf:jablonkagroup/ChemBench", "name": "jablonkagroup/ChemBench", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/ChemBench", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/ChemBench", "downloads": 2685 }, { "id": "hf:jablonkagroup/corral-traces", "name": "jablonkagroup/corral-traces", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/corral-traces", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/corral-traces", "downloads": 2523 }, { "id": "hf:LeMaterial/LeMat-Bulk", "name": "LeMaterial/LeMat-Bulk", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/LeMaterial/LeMat-Bulk", "leaderboard_url": "https://huggingface.co/datasets/LeMaterial/LeMat-Bulk", "downloads": 2273 }, { "id": "hf:jablonkagroup/corral-QAs-topic_reports", "name": "jablonkagroup/corral-QAs-topic_reports", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/corral-QAs-topic_reports", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/corral-QAs-topic_reports", "downloads": 2178 }, { "id": "hf:nfsrulesFR/mega-moledit-large", "name": "nfsrulesFR/mega-moledit-large", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/nfsrulesFR/mega-moledit-large", "leaderboard_url": "https://huggingface.co/datasets/nfsrulesFR/mega-moledit-large", "downloads": 2056 }, { "id": "hf:datamol-io/safe-gpt", "name": "datamol-io/safe-gpt", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/datamol-io/safe-gpt", "leaderboard_url": "https://huggingface.co/datasets/datamol-io/safe-gpt", "downloads": 2022 }, { "id": "hf:osunlp/SMolInstruct", "name": "osunlp/SMolInstruct", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/osunlp/SMolInstruct", "leaderboard_url": "https://huggingface.co/datasets/osunlp/SMolInstruct", "downloads": 1999 }, { "id": "hf:jglaser/binding_affinity", "name": "jglaser/binding_affinity", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jglaser/binding_affinity", "leaderboard_url": "https://huggingface.co/datasets/jglaser/binding_affinity", "downloads": 1968 }, { "id": "hf:jglaser/pdb_protein_ligand_complexes", "name": "jglaser/pdb_protein_ligand_complexes", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jglaser/pdb_protein_ligand_complexes", "leaderboard_url": "https://huggingface.co/datasets/jglaser/pdb_protein_ligand_complexes", "downloads": 1959 }, { "id": "hf:yqj01/SimNMR-PubChem", "name": "yqj01/SimNMR-PubChem", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/yqj01/SimNMR-PubChem", "leaderboard_url": "https://huggingface.co/datasets/yqj01/SimNMR-PubChem", "downloads": 1729 }, { "id": "hf:roman-bushuiev/MassSpecGym", "name": "roman-bushuiev/MassSpecGym", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/roman-bushuiev/MassSpecGym", "leaderboard_url": "https://huggingface.co/datasets/roman-bushuiev/MassSpecGym", "downloads": 1584 }, { "id": "hf:jablonkagroup/chempile-lift", "name": "jablonkagroup/chempile-lift", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/chempile-lift", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/chempile-lift", "downloads": 1502 }, { "id": "hf:daman1209arora/jeebench", "name": "daman1209arora/jeebench", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/daman1209arora/jeebench", "leaderboard_url": "https://huggingface.co/datasets/daman1209arora/jeebench", "downloads": 1325 }, { "id": "hf:jablonkagroup/MaCBench", "name": "jablonkagroup/MaCBench", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/MaCBench", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/MaCBench", "downloads": 1307 }, { "id": "hf:DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Nozzle_Cam", "name": "DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Nozzle_Cam", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Nozzle_Cam", "leaderboard_url": "https://huggingface.co/datasets/DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Nozzle_Cam", "downloads": 1258 }, { "id": "hf:Metanova/SAVI-2020", "name": "Metanova/SAVI-2020", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/Metanova/SAVI-2020", "leaderboard_url": "https://huggingface.co/datasets/Metanova/SAVI-2020", "downloads": 1255 }, { "id": "hf:InternSVG/SAgoge", "name": "InternSVG/SAgoge", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/InternSVG/SAgoge", "leaderboard_url": "https://huggingface.co/datasets/InternSVG/SAgoge", "downloads": 1238 }, { "id": "hf:rouskinlab/PDB", "name": "rouskinlab/PDB", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/rouskinlab/PDB", "leaderboard_url": "https://huggingface.co/datasets/rouskinlab/PDB", "downloads": 1236 }, { "id": "hf:DeweiFeng/SmellNet", "name": "DeweiFeng/SmellNet", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/DeweiFeng/SmellNet", "leaderboard_url": "https://huggingface.co/datasets/DeweiFeng/SmellNet", "downloads": 1226 }, { "id": "hf:avaliev/ChemistryQA", "name": "avaliev/ChemistryQA", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/avaliev/ChemistryQA", "leaderboard_url": "https://huggingface.co/datasets/avaliev/ChemistryQA", "downloads": 1220 }, { "id": "hf:camel-ai/loong", "name": "camel-ai/loong", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/camel-ai/loong", "leaderboard_url": "https://huggingface.co/datasets/camel-ai/loong", "downloads": 1103 }, { "id": "hf:jablonkagroup/chempile-reasoning", "name": "jablonkagroup/chempile-reasoning", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/chempile-reasoning", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/chempile-reasoning", "downloads": 1065 }, { "id": "hf:jablonkagroup/chempile-paper", "name": "jablonkagroup/chempile-paper", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/chempile-paper", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/chempile-paper", "downloads": 1063 }, { "id": "hf:YuRiVeRTi/V1Q", "name": "YuRiVeRTi/V1Q", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/YuRiVeRTi/V1Q", "leaderboard_url": "https://huggingface.co/datasets/YuRiVeRTi/V1Q", "downloads": 1030 }, { "id": "hf:zihaojing/MuMo-Pretraining", "name": "zihaojing/MuMo-Pretraining", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/zihaojing/MuMo-Pretraining", "leaderboard_url": "https://huggingface.co/datasets/zihaojing/MuMo-Pretraining", "downloads": 939 }, { "id": "hf:WithinUsAI/Chemistry_25k", "name": "WithinUsAI/Chemistry_25k", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/WithinUsAI/Chemistry_25k", "leaderboard_url": "https://huggingface.co/datasets/WithinUsAI/Chemistry_25k", "downloads": 920 }, { "id": "hf:jablonkagroup/corral-oss-trace-logprobs", "name": "jablonkagroup/corral-oss-trace-logprobs", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/corral-oss-trace-logprobs", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/corral-oss-trace-logprobs", "downloads": 862 }, { "id": "hf:laion/chemrXiv-pdf", "name": "laion/chemrXiv-pdf", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/laion/chemrXiv-pdf", "leaderboard_url": "https://huggingface.co/datasets/laion/chemrXiv-pdf", "downloads": 817 }, { "id": "hf:AI4Chem/ChemPref-DPO-for-Chemistry-data-en", "name": "AI4Chem/ChemPref-DPO-for-Chemistry-data-en", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/AI4Chem/ChemPref-DPO-for-Chemistry-data-en", "leaderboard_url": "https://huggingface.co/datasets/AI4Chem/ChemPref-DPO-for-Chemistry-data-en", "downloads": 804 }, { "id": "hf:scikit-fingerprints/MoleculeNet_HIV", "name": "scikit-fingerprints/MoleculeNet_HIV", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_HIV", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_HIV", "downloads": 768 }, { "id": "hf:RosettaCommons/MegaScale", "name": "RosettaCommons/MegaScale", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/RosettaCommons/MegaScale", "leaderboard_url": "https://huggingface.co/datasets/RosettaCommons/MegaScale", "downloads": 765 }, { "id": "hf:liuganghuggingface/moltextnet", "name": "liuganghuggingface/moltextnet", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/liuganghuggingface/moltextnet", "leaderboard_url": "https://huggingface.co/datasets/liuganghuggingface/moltextnet", "downloads": 758 }, { "id": "hf:EricLu/SCP-116K", "name": "EricLu/SCP-116K", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/EricLu/SCP-116K", "leaderboard_url": "https://huggingface.co/datasets/EricLu/SCP-116K", "downloads": 753 }, { "id": "hf:ZehuaZhao/SUPERChem", "name": "ZehuaZhao/SUPERChem", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/ZehuaZhao/SUPERChem", "leaderboard_url": "https://huggingface.co/datasets/ZehuaZhao/SUPERChem", "downloads": 746 }, { "id": "hf:karina-zadorozhny/ATOMICA", "name": "karina-zadorozhny/ATOMICA", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/karina-zadorozhny/ATOMICA", "leaderboard_url": "https://huggingface.co/datasets/karina-zadorozhny/ATOMICA", "downloads": 737 }, { "id": "hf:scikit-fingerprints/MoleculeNet_Tox21", "name": "scikit-fingerprints/MoleculeNet_Tox21", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_Tox21", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_Tox21", "downloads": 732 }, { "id": "hf:katielink/moleculenet-benchmark", "name": "katielink/moleculenet-benchmark", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/katielink/moleculenet-benchmark", "leaderboard_url": "https://huggingface.co/datasets/katielink/moleculenet-benchmark", "downloads": 731 }, { "id": "hf:AlexLoong/S1-MMAlign", "name": "AlexLoong/S1-MMAlign", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/AlexLoong/S1-MMAlign", "leaderboard_url": "https://huggingface.co/datasets/AlexLoong/S1-MMAlign", "downloads": 731 }, { "id": "hf:jablonkagroup/chempile-education", "name": "jablonkagroup/chempile-education", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/chempile-education", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/chempile-education", "downloads": 719 }, { "id": "hf:akselformo/Vex", "name": "akselformo/Vex", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/akselformo/Vex", "leaderboard_url": "https://huggingface.co/datasets/akselformo/Vex", "downloads": 719 }, { "id": "hf:nvidia/ProfBench", "name": "nvidia/ProfBench", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/nvidia/ProfBench", "leaderboard_url": "https://huggingface.co/datasets/nvidia/ProfBench", "downloads": 704 }, { "id": "hf:sequelbox/Celestia3-DeepSeek-R1-0528", "name": "sequelbox/Celestia3-DeepSeek-R1-0528", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/sequelbox/Celestia3-DeepSeek-R1-0528", "leaderboard_url": "https://huggingface.co/datasets/sequelbox/Celestia3-DeepSeek-R1-0528", "downloads": 693 }, { "id": "hf:scikit-fingerprints/MoleculeNet_BBBP", "name": "scikit-fingerprints/MoleculeNet_BBBP", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_BBBP", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_BBBP", "downloads": 692 }, { "id": "hf:liupf/ChEBI-20-MM", "name": "liupf/ChEBI-20-MM", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/liupf/ChEBI-20-MM", "leaderboard_url": "https://huggingface.co/datasets/liupf/ChEBI-20-MM", "downloads": 685 }, { "id": "hf:zake7749/OpenScience-Chinese-Reasoning-SFT", "name": "zake7749/OpenScience-Chinese-Reasoning-SFT", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/zake7749/OpenScience-Chinese-Reasoning-SFT", "leaderboard_url": "https://huggingface.co/datasets/zake7749/OpenScience-Chinese-Reasoning-SFT", "downloads": 680 }, { "id": "hf:QizhiPei/BioMatrix-SFT", "name": "QizhiPei/BioMatrix-SFT", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/QizhiPei/BioMatrix-SFT", "leaderboard_url": "https://huggingface.co/datasets/QizhiPei/BioMatrix-SFT", "downloads": 677 }, { "id": "hf:Mxode/CAMS", "name": "Mxode/CAMS", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/Mxode/CAMS", "leaderboard_url": "https://huggingface.co/datasets/Mxode/CAMS", "downloads": 675 }, { "id": "hf:AmirMasoud/GMD", "name": "AmirMasoud/GMD", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/AmirMasoud/GMD", "leaderboard_url": "https://huggingface.co/datasets/AmirMasoud/GMD", "downloads": 668 }, { "id": "hf:microsoft/msr-acc-tae25", "name": "microsoft/msr-acc-tae25", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/microsoft/msr-acc-tae25", "leaderboard_url": "https://huggingface.co/datasets/microsoft/msr-acc-tae25", "downloads": 660 }, { "id": "hf:scikit-fingerprints/MoleculeNet_Lipophilicity", "name": "scikit-fingerprints/MoleculeNet_Lipophilicity", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_Lipophilicity", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_Lipophilicity", "downloads": 659 }, { "id": "hf:AnonymouScientist/MaterialsSaddles", "name": "AnonymouScientist/MaterialsSaddles", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/AnonymouScientist/MaterialsSaddles", "leaderboard_url": "https://huggingface.co/datasets/AnonymouScientist/MaterialsSaddles", "downloads": 650 }, { "id": "hf:prithivMLmods/Gargantua-R1-Compact", "name": "prithivMLmods/Gargantua-R1-Compact", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/prithivMLmods/Gargantua-R1-Compact", "leaderboard_url": "https://huggingface.co/datasets/prithivMLmods/Gargantua-R1-Compact", "downloads": 648 }, { "id": "hf:RosettaCommons/MIP", "name": "RosettaCommons/MIP", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/RosettaCommons/MIP", "leaderboard_url": "https://huggingface.co/datasets/RosettaCommons/MIP", "downloads": 638 }, { "id": "hf:scikit-fingerprints/MoleculeNet_ToxCast", "name": "scikit-fingerprints/MoleculeNet_ToxCast", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_ToxCast", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_ToxCast", "downloads": 636 }, { "id": "hf:scikit-fingerprints/MoleculeNet_SIDER", "name": "scikit-fingerprints/MoleculeNet_SIDER", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_SIDER", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_SIDER", "downloads": 619 }, { "id": "hf:scikit-fingerprints/MoleculeNet_ClinTox", "name": "scikit-fingerprints/MoleculeNet_ClinTox", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_ClinTox", "leaderboard_url": "https://huggingface.co/datasets/scikit-fingerprints/MoleculeNet_ClinTox", "downloads": 612 }, { "id": "hf:jablonkagroup/questions4manual_annotation", "name": "jablonkagroup/questions4manual_annotation", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/jablonkagroup/questions4manual_annotation", "leaderboard_url": "https://huggingface.co/datasets/jablonkagroup/questions4manual_annotation", "downloads": 599 }, { "id": "hf:liuhangbiao/SciCode-Domain-Code", "name": "liuhangbiao/SciCode-Domain-Code", "category": "HF-chemistry", "url": "https://huggingface.co/datasets/liuhangbiao/SciCode-Domain-Code", "leaderboard_url": "https://huggingface.co/datasets/liuhangbiao/SciCode-Domain-Code", "downloads": 596 }, { "id": "hf:mrmrx/CADS-dataset", "name": "mrmrx/CADS-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/mrmrx/CADS-dataset", "leaderboard_url": "https://huggingface.co/datasets/mrmrx/CADS-dataset", "downloads": 1130573 }, { "id": "hf:ibrahimhamamci/CT-RATE", "name": "ibrahimhamamci/CT-RATE", "category": "HF-medical", "url": "https://huggingface.co/datasets/ibrahimhamamci/CT-RATE", "leaderboard_url": "https://huggingface.co/datasets/ibrahimhamamci/CT-RATE", "downloads": 117665 }, { "id": "hf:opendatalab/Sci-Base", "name": "opendatalab/Sci-Base", "category": "HF-medical", "url": "https://huggingface.co/datasets/opendatalab/Sci-Base", "leaderboard_url": "https://huggingface.co/datasets/opendatalab/Sci-Base", "downloads": 79680 }, { "id": "hf:Williamsanderson/MedQA-Darija-MultiLingual", "name": "Williamsanderson/MedQA-Darija-MultiLingual", "category": "HF-medical", "url": "https://huggingface.co/datasets/Williamsanderson/MedQA-Darija-MultiLingual", "leaderboard_url": "https://huggingface.co/datasets/Williamsanderson/MedQA-Darija-MultiLingual", "downloads": 51545 }, { "id": "hf:Forithmus/MR-RATE", "name": "Forithmus/MR-RATE", "category": "HF-medical", "url": "https://huggingface.co/datasets/Forithmus/MR-RATE", "leaderboard_url": "https://huggingface.co/datasets/Forithmus/MR-RATE", "downloads": 46980 }, { "id": "hf:sunghong/CADS-dataset", "name": "sunghong/CADS-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/sunghong/CADS-dataset", "leaderboard_url": "https://huggingface.co/datasets/sunghong/CADS-dataset", "downloads": 32264 }, { "id": "hf:kantor3/CADS-dataset", "name": "kantor3/CADS-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/kantor3/CADS-dataset", "leaderboard_url": "https://huggingface.co/datasets/kantor3/CADS-dataset", "downloads": 30480 }, { "id": "hf:General-Medical-AI/GMAI-VL-5.5M", "name": "General-Medical-AI/GMAI-VL-5.5M", "category": "HF-medical", "url": "https://huggingface.co/datasets/General-Medical-AI/GMAI-VL-5.5M", "leaderboard_url": "https://huggingface.co/datasets/General-Medical-AI/GMAI-VL-5.5M", "downloads": 27231 }, { "id": "hf:bio-nlp-umass/MedThinkVQA", "name": "bio-nlp-umass/MedThinkVQA", "category": "HF-medical", "url": "https://huggingface.co/datasets/bio-nlp-umass/MedThinkVQA", "leaderboard_url": "https://huggingface.co/datasets/bio-nlp-umass/MedThinkVQA", "downloads": 23176 }, { "id": "hf:TokyoTechMagicYang/RAM-H1200-v1", "name": "TokyoTechMagicYang/RAM-H1200-v1", "category": "HF-medical", "url": "https://huggingface.co/datasets/TokyoTechMagicYang/RAM-H1200-v1", "leaderboard_url": "https://huggingface.co/datasets/TokyoTechMagicYang/RAM-H1200-v1", "downloads": 21870 }, { "id": "hf:RichardChenZH/MedForge-90K", "name": "RichardChenZH/MedForge-90K", "category": "HF-medical", "url": "https://huggingface.co/datasets/RichardChenZH/MedForge-90K", "leaderboard_url": "https://huggingface.co/datasets/RichardChenZH/MedForge-90K", "downloads": 18181 }, { "id": "hf:AVS-Net/knee_fast_mri", "name": "AVS-Net/knee_fast_mri", "category": "HF-medical", "url": "https://huggingface.co/datasets/AVS-Net/knee_fast_mri", "leaderboard_url": "https://huggingface.co/datasets/AVS-Net/knee_fast_mri", "downloads": 16982 }, { "id": "hf:junma/CVPR-BiomedSegFM", "name": "junma/CVPR-BiomedSegFM", "category": "HF-medical", "url": "https://huggingface.co/datasets/junma/CVPR-BiomedSegFM", "leaderboard_url": "https://huggingface.co/datasets/junma/CVPR-BiomedSegFM", "downloads": 16189 }, { "id": "hf:CYX1998/Meissa-SFT", "name": "CYX1998/Meissa-SFT", "category": "HF-medical", "url": "https://huggingface.co/datasets/CYX1998/Meissa-SFT", "leaderboard_url": "https://huggingface.co/datasets/CYX1998/Meissa-SFT", "downloads": 12670 }, { "id": "hf:Chandanmanvi/MedDialog-Audio", "name": "Chandanmanvi/MedDialog-Audio", "category": "HF-medical", "url": "https://huggingface.co/datasets/Chandanmanvi/MedDialog-Audio", "leaderboard_url": "https://huggingface.co/datasets/Chandanmanvi/MedDialog-Audio", "downloads": 11459 }, { "id": "hf:kyegorov/mcd_rppg", "name": "kyegorov/mcd_rppg", "category": "HF-medical", "url": "https://huggingface.co/datasets/kyegorov/mcd_rppg", "leaderboard_url": "https://huggingface.co/datasets/kyegorov/mcd_rppg", "downloads": 11450 }, { "id": "hf:SimulaMet/Kvasir-VQA-x1", "name": "SimulaMet/Kvasir-VQA-x1", "category": "HF-medical", "url": "https://huggingface.co/datasets/SimulaMet/Kvasir-VQA-x1", "leaderboard_url": "https://huggingface.co/datasets/SimulaMet/Kvasir-VQA-x1", "downloads": 10866 }, { "id": "hf:flaviagiammarino/vqa-rad", "name": "flaviagiammarino/vqa-rad", "category": "HF-medical", "url": "https://huggingface.co/datasets/flaviagiammarino/vqa-rad", "leaderboard_url": "https://huggingface.co/datasets/flaviagiammarino/vqa-rad", "downloads": 10682 }, { "id": "hf:Forithmus/MR-RATE-coreg", "name": "Forithmus/MR-RATE-coreg", "category": "HF-medical", "url": "https://huggingface.co/datasets/Forithmus/MR-RATE-coreg", "leaderboard_url": "https://huggingface.co/datasets/Forithmus/MR-RATE-coreg", "downloads": 9984 }, { "id": "hf:huggingface/CADS-dataset", "name": "huggingface/CADS-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/huggingface/CADS-dataset", "leaderboard_url": "https://huggingface.co/datasets/huggingface/CADS-dataset", "downloads": 9588 }, { "id": "hf:mercor/APEX-v1-extended", "name": "mercor/APEX-v1-extended", "category": "HF-medical", "url": "https://huggingface.co/datasets/mercor/APEX-v1-extended", "leaderboard_url": "https://huggingface.co/datasets/mercor/APEX-v1-extended", "downloads": 9490 }, { "id": "hf:MedRAG/pubmed", "name": "MedRAG/pubmed", "category": "HF-medical", "url": "https://huggingface.co/datasets/MedRAG/pubmed", "leaderboard_url": "https://huggingface.co/datasets/MedRAG/pubmed", "downloads": 9314 }, { "id": "hf:harvardairobotics/FairSeg", "name": "harvardairobotics/FairSeg", "category": "HF-medical", "url": "https://huggingface.co/datasets/harvardairobotics/FairSeg", "leaderboard_url": "https://huggingface.co/datasets/harvardairobotics/FairSeg", "downloads": 9212 }, { "id": "hf:CTPLab-DBE-UniBas/staining-robustness-evaluation", "name": "CTPLab-DBE-UniBas/staining-robustness-evaluation", "category": "HF-medical", "url": "https://huggingface.co/datasets/CTPLab-DBE-UniBas/staining-robustness-evaluation", "leaderboard_url": "https://huggingface.co/datasets/CTPLab-DBE-UniBas/staining-robustness-evaluation", "downloads": 8434 }, { "id": "hf:RichardChenZH/Med-Banana-50K", "name": "RichardChenZH/Med-Banana-50K", "category": "HF-medical", "url": "https://huggingface.co/datasets/RichardChenZH/Med-Banana-50K", "leaderboard_url": "https://huggingface.co/datasets/RichardChenZH/Med-Banana-50K", "downloads": 8000 }, { "id": "hf:flaviagiammarino/path-vqa", "name": "flaviagiammarino/path-vqa", "category": "HF-medical", "url": "https://huggingface.co/datasets/flaviagiammarino/path-vqa", "leaderboard_url": "https://huggingface.co/datasets/flaviagiammarino/path-vqa", "downloads": 7852 }, { "id": "hf:wanglab/CT_DeepLesion-MedSAM2", "name": "wanglab/CT_DeepLesion-MedSAM2", "category": "HF-medical", "url": "https://huggingface.co/datasets/wanglab/CT_DeepLesion-MedSAM2", "leaderboard_url": "https://huggingface.co/datasets/wanglab/CT_DeepLesion-MedSAM2", "downloads": 7160 }, { "id": "hf:SnivellusSnape/iiyi_dataset", "name": "SnivellusSnape/iiyi_dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/SnivellusSnape/iiyi_dataset", "leaderboard_url": "https://huggingface.co/datasets/SnivellusSnape/iiyi_dataset", "downloads": 7080 }, { "id": "hf:novcor/CADS-dataset", "name": "novcor/CADS-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/novcor/CADS-dataset", "leaderboard_url": "https://huggingface.co/datasets/novcor/CADS-dataset", "downloads": 6813 }, { "id": "hf:AbdomenAtlas/AbdomenAtlas1.0Mini", "name": "AbdomenAtlas/AbdomenAtlas1.0Mini", "category": "HF-medical", "url": "https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas1.0Mini", "leaderboard_url": "https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas1.0Mini", "downloads": 6738 }, { "id": "hf:loupk/CADS-dataset", "name": "loupk/CADS-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/loupk/CADS-dataset", "leaderboard_url": "https://huggingface.co/datasets/loupk/CADS-dataset", "downloads": 6344 }, { "id": "hf:ctmedtech/DDR-dataset", "name": "ctmedtech/DDR-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/ctmedtech/DDR-dataset", "leaderboard_url": "https://huggingface.co/datasets/ctmedtech/DDR-dataset", "downloads": 5751 }, { "id": "hf:BoKelvin/SLAKE", "name": "BoKelvin/SLAKE", "category": "HF-medical", "url": "https://huggingface.co/datasets/BoKelvin/SLAKE", "leaderboard_url": "https://huggingface.co/datasets/BoKelvin/SLAKE", "downloads": 5265 }, { "id": "hf:FLARE-MedFM/FLARE-Task4-CT-FM", "name": "FLARE-MedFM/FLARE-Task4-CT-FM", "category": "HF-medical", "url": "https://huggingface.co/datasets/FLARE-MedFM/FLARE-Task4-CT-FM", "leaderboard_url": "https://huggingface.co/datasets/FLARE-MedFM/FLARE-Task4-CT-FM", "downloads": 5116 }, { "id": "hf:TLAIM/TAIX-Ray", "name": "TLAIM/TAIX-Ray", "category": "HF-medical", "url": "https://huggingface.co/datasets/TLAIM/TAIX-Ray", "leaderboard_url": "https://huggingface.co/datasets/TLAIM/TAIX-Ray", "downloads": 4995 }, { "id": "hf:martagm17/test", "name": "martagm17/test", "category": "HF-medical", "url": "https://huggingface.co/datasets/martagm17/test", "leaderboard_url": "https://huggingface.co/datasets/martagm17/test", "downloads": 4822 }, { "id": "hf:Dearcat/CPathPatchFeature", "name": "Dearcat/CPathPatchFeature", "category": "HF-medical", "url": "https://huggingface.co/datasets/Dearcat/CPathPatchFeature", "leaderboard_url": "https://huggingface.co/datasets/Dearcat/CPathPatchFeature", "downloads": 4732 }, { "id": "hf:Voxel51/cholect50", "name": "Voxel51/cholect50", "category": "HF-medical", "url": "https://huggingface.co/datasets/Voxel51/cholect50", "leaderboard_url": "https://huggingface.co/datasets/Voxel51/cholect50", "downloads": 4657 }, { "id": "hf:TsinghuaC3I/MedXpertQA", "name": "TsinghuaC3I/MedXpertQA", "category": "HF-medical", "url": "https://huggingface.co/datasets/TsinghuaC3I/MedXpertQA", "leaderboard_url": "https://huggingface.co/datasets/TsinghuaC3I/MedXpertQA", "downloads": 4634 }, { "id": "hf:Forithmus/MR-RATE-nvseg-ctmr", "name": "Forithmus/MR-RATE-nvseg-ctmr", "category": "HF-medical", "url": "https://huggingface.co/datasets/Forithmus/MR-RATE-nvseg-ctmr", "leaderboard_url": "https://huggingface.co/datasets/Forithmus/MR-RATE-nvseg-ctmr", "downloads": 4611 }, { "id": "hf:ikala/tmmluplus", "name": "ikala/tmmluplus", "category": "HF-medical", "url": "https://huggingface.co/datasets/ikala/tmmluplus", "leaderboard_url": "https://huggingface.co/datasets/ikala/tmmluplus", "downloads": 4334 }, { "id": "hf:AbdomenAtlas/AbdomenAtlas1.0MiniBeta", "name": "AbdomenAtlas/AbdomenAtlas1.0MiniBeta", "category": "HF-medical", "url": "https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas1.0MiniBeta", "leaderboard_url": "https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas1.0MiniBeta", "downloads": 4333 }, { "id": "hf:Angelou0516/totalsegmentator-organs", "name": "Angelou0516/totalsegmentator-organs", "category": "HF-medical", "url": "https://huggingface.co/datasets/Angelou0516/totalsegmentator-organs", "leaderboard_url": "https://huggingface.co/datasets/Angelou0516/totalsegmentator-organs", "downloads": 4266 }, { "id": "hf:msancheza/microCube-Duke-Breast-MRI", "name": "msancheza/microCube-Duke-Breast-MRI", "category": "HF-medical", "url": "https://huggingface.co/datasets/msancheza/microCube-Duke-Breast-MRI", "leaderboard_url": "https://huggingface.co/datasets/msancheza/microCube-Duke-Breast-MRI", "downloads": 4038 }, { "id": "hf:MIL-UT/Japanese-Medical-VQA-12m", "name": "MIL-UT/Japanese-Medical-VQA-12m", "category": "HF-medical", "url": "https://huggingface.co/datasets/MIL-UT/Japanese-Medical-VQA-12m", "leaderboard_url": "https://huggingface.co/datasets/MIL-UT/Japanese-Medical-VQA-12m", "downloads": 3856 }, { "id": "hf:alexanderdann/CTSpine1K", "name": "alexanderdann/CTSpine1K", "category": "HF-medical", "url": "https://huggingface.co/datasets/alexanderdann/CTSpine1K", "leaderboard_url": "https://huggingface.co/datasets/alexanderdann/CTSpine1K", "downloads": 3829 }, { "id": "hf:DermaVLM/PMC-Clinical-VQA", "name": "DermaVLM/PMC-Clinical-VQA", "category": "HF-medical", "url": "https://huggingface.co/datasets/DermaVLM/PMC-Clinical-VQA", "leaderboard_url": "https://huggingface.co/datasets/DermaVLM/PMC-Clinical-VQA", "downloads": 3801 }, { "id": "hf:Forithmus/MR-RATE-atlas", "name": "Forithmus/MR-RATE-atlas", "category": "HF-medical", "url": "https://huggingface.co/datasets/Forithmus/MR-RATE-atlas", "leaderboard_url": "https://huggingface.co/datasets/Forithmus/MR-RATE-atlas", "downloads": 3763 }, { "id": "hf:eltorio/ROCOv2-radiology", "name": "eltorio/ROCOv2-radiology", "category": "HF-medical", "url": "https://huggingface.co/datasets/eltorio/ROCOv2-radiology", "leaderboard_url": "https://huggingface.co/datasets/eltorio/ROCOv2-radiology", "downloads": 3615 }, { "id": "hf:FreedomIntelligence/huatuo26M-testdatasets", "name": "FreedomIntelligence/huatuo26M-testdatasets", "category": "HF-medical", "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo26M-testdatasets", "leaderboard_url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo26M-testdatasets", "downloads": 3581 }, { "id": "hf:rajpurkarlab/3DReasonKnee", "name": "rajpurkarlab/3DReasonKnee", "category": "HF-medical", "url": "https://huggingface.co/datasets/rajpurkarlab/3DReasonKnee", "leaderboard_url": "https://huggingface.co/datasets/rajpurkarlab/3DReasonKnee", "downloads": 3532 }, { "id": "hf:WY-0206/CADS-dataset", "name": "WY-0206/CADS-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/WY-0206/CADS-dataset", "leaderboard_url": "https://huggingface.co/datasets/WY-0206/CADS-dataset", "downloads": 3514 }, { "id": "hf:staryutong999/GAMMA", "name": "staryutong999/GAMMA", "category": "HF-medical", "url": "https://huggingface.co/datasets/staryutong999/GAMMA", "leaderboard_url": "https://huggingface.co/datasets/staryutong999/GAMMA", "downloads": 3467 }, { "id": "hf:medalpaca/medical_meadow_medqa", "name": "medalpaca/medical_meadow_medqa", "category": "HF-medical", "url": "https://huggingface.co/datasets/medalpaca/medical_meadow_medqa", "leaderboard_url": "https://huggingface.co/datasets/medalpaca/medical_meadow_medqa", "downloads": 3419 }, { "id": "hf:mks-logic/SPY", "name": "mks-logic/SPY", "category": "HF-medical", "url": "https://huggingface.co/datasets/mks-logic/SPY", "leaderboard_url": "https://huggingface.co/datasets/mks-logic/SPY", "downloads": 3349 }, { "id": "hf:YongchengYAO/MedVision", "name": "YongchengYAO/MedVision", "category": "HF-medical", "url": "https://huggingface.co/datasets/YongchengYAO/MedVision", "leaderboard_url": "https://huggingface.co/datasets/YongchengYAO/MedVision", "downloads": 3308 }, { "id": "hf:AbdomenAtlas/AbdomenAtlas3.0Mini", "name": "AbdomenAtlas/AbdomenAtlas3.0Mini", "category": "HF-medical", "url": "https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas3.0Mini", "leaderboard_url": "https://huggingface.co/datasets/AbdomenAtlas/AbdomenAtlas3.0Mini", "downloads": 3097 }, { "id": "hf:Angelou0516/Adrenal-ACC-Ki67-Seg", "name": "Angelou0516/Adrenal-ACC-Ki67-Seg", "category": "HF-medical", "url": "https://huggingface.co/datasets/Angelou0516/Adrenal-ACC-Ki67-Seg", "leaderboard_url": "https://huggingface.co/datasets/Angelou0516/Adrenal-ACC-Ki67-Seg", "downloads": 3023 }, { "id": "hf:HajihajihaJimmy/Totalsegmentor_Pelvis_Bone_Recon_Dataset", "name": "HajihajihaJimmy/Totalsegmentor_Pelvis_Bone_Recon_Dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/HajihajihaJimmy/Totalsegmentor_Pelvis_Bone_Recon_Dataset", "leaderboard_url": "https://huggingface.co/datasets/HajihajihaJimmy/Totalsegmentor_Pelvis_Bone_Recon_Dataset", "downloads": 2863 }, { "id": "hf:Flmc/MedRCube", "name": "Flmc/MedRCube", "category": "HF-medical", "url": "https://huggingface.co/datasets/Flmc/MedRCube", "leaderboard_url": "https://huggingface.co/datasets/Flmc/MedRCube", "downloads": 2825 }, { "id": "hf:Voxel51/SLAKE", "name": "Voxel51/SLAKE", "category": "HF-medical", "url": "https://huggingface.co/datasets/Voxel51/SLAKE", "leaderboard_url": "https://huggingface.co/datasets/Voxel51/SLAKE", "downloads": 2691 }, { "id": "hf:OpenMed/synthvision-annotated-qwen", "name": "OpenMed/synthvision-annotated-qwen", "category": "HF-medical", "url": "https://huggingface.co/datasets/OpenMed/synthvision-annotated-qwen", "leaderboard_url": "https://huggingface.co/datasets/OpenMed/synthvision-annotated-qwen", "downloads": 2680 }, { "id": "hf:TwanAPI/data1", "name": "TwanAPI/data1", "category": "HF-medical", "url": "https://huggingface.co/datasets/TwanAPI/data1", "leaderboard_url": "https://huggingface.co/datasets/TwanAPI/data1", "downloads": 2567 }, { "id": "hf:Voxel51/MedXpertQA", "name": "Voxel51/MedXpertQA", "category": "HF-medical", "url": "https://huggingface.co/datasets/Voxel51/MedXpertQA", "leaderboard_url": "https://huggingface.co/datasets/Voxel51/MedXpertQA", "downloads": 2535 }, { "id": "hf:Amod/mental_health_counseling_conversations", "name": "Amod/mental_health_counseling_conversations", "category": "HF-medical", "url": "https://huggingface.co/datasets/Amod/mental_health_counseling_conversations", "leaderboard_url": "https://huggingface.co/datasets/Amod/mental_health_counseling_conversations", "downloads": 2400 }, { "id": "hf:lavita/medical-qa-datasets", "name": "lavita/medical-qa-datasets", "category": "HF-medical", "url": "https://huggingface.co/datasets/lavita/medical-qa-datasets", "leaderboard_url": "https://huggingface.co/datasets/lavita/medical-qa-datasets", "downloads": 2366 }, { "id": "hf:gOLIVES/OLIVES_Dataset", "name": "gOLIVES/OLIVES_Dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/gOLIVES/OLIVES_Dataset", "leaderboard_url": "https://huggingface.co/datasets/gOLIVES/OLIVES_Dataset", "downloads": 2348 }, { "id": "hf:Voxel51/BTCV-CT-as-video-MedSAM2-dataset", "name": "Voxel51/BTCV-CT-as-video-MedSAM2-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/Voxel51/BTCV-CT-as-video-MedSAM2-dataset", "leaderboard_url": "https://huggingface.co/datasets/Voxel51/BTCV-CT-as-video-MedSAM2-dataset", "downloads": 2246 }, { "id": "hf:arekborucki/CADS-dataset", "name": "arekborucki/CADS-dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/arekborucki/CADS-dataset", "leaderboard_url": "https://huggingface.co/datasets/arekborucki/CADS-dataset", "downloads": 2171 }, { "id": "hf:lavita/MedQuAD", "name": "lavita/MedQuAD", "category": "HF-medical", "url": "https://huggingface.co/datasets/lavita/MedQuAD", "leaderboard_url": "https://huggingface.co/datasets/lavita/MedQuAD", "downloads": 2169 }, { "id": "hf:Nj-1111/Glaucoma_Dataset", "name": "Nj-1111/Glaucoma_Dataset", "category": "HF-medical", "url": "https://huggingface.co/datasets/Nj-1111/Glaucoma_Dataset", "leaderboard_url": "https://huggingface.co/datasets/Nj-1111/Glaucoma_Dataset", "downloads": 2107 }, { "id": "hf:luojunyu/SemiEvol", "name": "luojunyu/SemiEvol", "category": "HF-medical", "url": "https://huggingface.co/datasets/luojunyu/SemiEvol", "leaderboard_url": "https://huggingface.co/datasets/luojunyu/SemiEvol", "downloads": 2104 }, { "id": "hf:anon-meddial-2026/meddialbench", "name": "anon-meddial-2026/meddialbench", "category": "HF-medical", "url": "https://huggingface.co/datasets/anon-meddial-2026/meddialbench", "leaderboard_url": "https://huggingface.co/datasets/anon-meddial-2026/meddialbench", "downloads": 2077 }, { "id": "hf:FLARE-MedFM/FLARE-Task1-PancancerRECIST-to-3D", "name": "FLARE-MedFM/FLARE-Task1-PancancerRECIST-to-3D", "category": "HF-medical", "url": "https://huggingface.co/datasets/FLARE-MedFM/FLARE-Task1-PancancerRECIST-to-3D", "leaderboard_url": "https://huggingface.co/datasets/FLARE-MedFM/FLARE-Task1-PancancerRECIST-to-3D", "downloads": 2043 } ], "hosted_benchmarks_count": 341 } ], "total_hosted_links": 2413 }