ChEMBL
Manually curated bioactive molecule DB; backbone for most ML chemistry benchmarks.
Composite score: 97.5
Rubric (1–5 per criterion)
rigor
5/5
coverage
5/5
maintenance
5/5
adoption
5/5
quality
4/5
accessibility
5/5
industry_relevance
5/5
Metadata
Stages
Hit IDLead ID / ADMET
Modalities
small-moleculeprotein-general
Task types
bioactivitydata-resource
License
CC-BY-SA 3.0
First release
2009
Last updated
2025-05
Flags
none
Size & scope
- compounds: 2400000
- activities: 20700000
- targets: 15398
Primary paper
Title
The ChEMBL Database in 2023
Authors
Zdrazil B, Felix E, Hunter F, et al.
Year
2024
DOI / arXiv
Citations
800
Links
- Official site: https://www.ebi.ac.uk/chembl/
- GitHub: https://github.com/chembl
- Leaderboard: N/A
Hosted by (initiatives)
Experts (primary authors / maintainers)
Groups (host labs / companies / consortia)
Related benchmarks
Notes (honest caveats)
Underlies ~80% of public bioactivity ML benchmarks.