← All benchmarks

ClinTox

Binary classification of FDA-approved vs. trial-failed-for-toxicity compounds.
Composite score: 65.6

Rubric (1–5 per criterion)

rigor
3/5
coverage
2/5
maintenance
2/5
adoption
5/5
quality
3/5
accessibility
5/5
industry_relevance
3/5

Metadata

Stages
Lead ID / ADMETIND-enabling
Modalities
small-molecule
Task types
toxicity-classification
License
MIT
First release
2015
Last updated
2022
Flags
data-leakage-known

Size & scope

Primary paper

Title
Deep learning for drug-induced liver injury
Authors
Xu Y, Dai Z, Chen F, et al.
Year
2015
DOI / arXiv
10.1021/acs.jcim.5b00238
Citations
380

Links

Hosted by (initiatives)

Experts (primary authors / maintainers)

Groups (host labs / companies / consortia)

Related benchmarks

Notes (honest caveats)

Small, binary; saturated. Useful only as sanity check.