Curated DICTrank dataset from FDA with standardized SMILES, chemical names, and DICTrank labels and concern categories for 1020 FDA-approved/ investigational/ experimental/ withdrawn drugs. The original paper from the FDA can be found here.

Download csv.gz (110 kB)

Curated DICTrank dataset from FDA with standardized SMILES, chemical names, and DICTrank labels and concern categories for 82 compounds labeled ambiguous in the original paper. The predictions for these compounds from models in this study are also annotated in this dataset.

Download csv (31 kB)

1893 predictions for 817 unique targets (inhibition/antagonism) and concentration combinations (0.1, 1, 10, and 100uM) for all compounds in the DICTrank dataset. Predictions are obtained using CellSpace (IgnotaLabs). For details on CellScape, visit IgnotaLabs

Download zip (6.5 MB)

264 binary encoded MOAs and 551 known target annotations for compounds in the DICTrank dataset. Annotations are obtained from the Drug Repurposing Hub from the Broad Institute

Download csv.gz (158 kB)

Contains 1783 Cell Painting features for all compounds in the DICTrank dataset. For details see original paper

Download csv.gz (215 MB)

Contains 978 Gene Expression features for all compounds in the DICTrank dataset curated from the Ma'ayan Lab repository. For details see original paper

Download csv.gz (18 MB)

Contains 4438 annotations for all compounds in the DICTrank dataset curated from the Ma'ayan Lab repository For details see original paper

Download csv.gz (103 MB)

Contains the maximum total and unbound concentration of a drug in plasma for approximately 700 compounds that are present in the DICTrank dataset. For curation methodology, see original paper.

Download csv.gz (70 kB)

Curated SIDER dataset with all side effects and standardized SMILES. For details see MoleculeNet.

Download csv.gz (128 kB)