LIT-PCBA
Literature-curated dose-response PubChem BioAssay set; 15 targets with unbiased actives/inactives.
Composite score: 80.8
Rubric (1–5 per criterion)
rigor
5/5
coverage
3/5
maintenance
2/5
adoption
4/5
quality
5/5
accessibility
5/5
industry_relevance
4/5
Metadata
Stages
Hit ID
Modalities
small-molecule
Task types
virtual-screening
License
CC-BY
First release
2020-03
Last updated
2023-06
Flags
none
Size & scope
- targets: 15
- actives: 7844
- inactives: 2533936
Primary paper
Title
LIT-PCBA: An Unbiased Data Set for Machine Learning and Virtual Screening
Authors
Tran-Nguyen VK, Jacquemard C, Rognan D
Year
2020
DOI / arXiv
Citations
310
Links
- Official site: https://drugdesign.unistra.fr/LIT-PCBA/
- GitHub: https://github.com/ViktorTran-Nguyen/LIT-PCBA
- Leaderboard: N/A
Hosted by (initiatives)
- not hosted by any tracked initiative
Experts (primary authors / maintainers)
Groups (host labs / companies / consortia)
Related benchmarks
Notes (honest caveats)
Much fairer than DUD-E; small target count limits coverage.