PEER
PEER — 14 protein property prediction tasks across structure/function/interaction.
Composite
74.4
Experimental validation
Retrospective
Stages
Target IDDevelopmental Candidate
Modalities
protein-general
Task types
protein-ml
Size
tasks: 14
License
MIT
First release
2022
Last updated
2024
Official site
Leaderboard
→ leaderboard
Dataset
→ dataset
Code / GitHub
HuggingFace
→ HF
Paper
PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding · Xu M, Yuan X, Miret S, Tang J · 2022 · paper · doi:10.48550/arXiv.2206.02096 · 130 citations
Flags
none
Experts
—
Groups
Hosted by
Related benchmarks
Rubric (7-criterion)
rigor
4
coverage
4
maintenance
3
adoption
3
quality
4
accessibility
5
industry_relevance
3
Notes
Broader than TAPE, tighter than ProteinGym; good middle ground.