CAFA5

CAFA 5th edition — blind GO annotation eval (142k targets; Kaggle 2023, 1625 teams).

Composite
84.3
Experimental validation
Retrospective
Stages
Target ID
Modalities
protein-general
Task types
function-annotation
Size
targets: 142,000
go_terms: 43,000
License
Public
First release
2022
Last updated
2023-12
Official site
→ project page
Leaderboard
→ leaderboard
Dataset
→ dataset
Code / GitHub
→ repository
HuggingFace
→ HF
Paper
The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens · Zhou N, Jiang Y, Bergquist TR, et al. · 2019 · paper · doi:10.1186/s13059-019-1835-8 · 380 citations
Flags
none
Experts
Predrag Radivojac, Iddo Friedberg
Groups
CAFA Consortium
Hosted by
CAFA
Related benchmarks
ProteinGym

Rubric (7-criterion)

rigor
5
coverage
4
maintenance
3
adoption
5
quality
4
accessibility
5
industry_relevance
3

Notes

CAFA5 broke attendance records.

← Back to all benchmarks

Compare:
Open comparison →