DILI gold
standard dataset

Compounds curated from DILIst and DILIrank dataset from FDA with standardized smiles and DICT labels for 1,111 FDA approved/ investigational/ experimental/ withdrawn drugs. The original paper from FDA can be found here.

Download csv.gz (192 KB)


Dataset containing all nine proxy-DILI labels and the DILI labels as above. This includes both in vitro (e.g., mitochondrial toxicity, bile salt export pump inhibition) and in vivo (e.g., preclinical rat hepatotoxicity studies) for over 13,700 compounds.

Download csv.gz (2.70 MB)


This dataset contains maximum unbound concentration in plasma for over 500 compounds and maximum total concentration in plasma for around 730 compounds. The original paper can be found here.

Download csv.gz (57 KB)