Datasets

BindingDB is the first public database of protein-small molecule affinity data.

PubChem provides information on the biological activities of small molecules.

ChEMBL is a database of bioactive compounds, their quantitative properties and bioactivities (binding constants, pharmacology and ADMET, etc).

ESOL (Estimated SOLubility) dataset [[1]](1), part of MoleculeNet [[2]](2) benchmark.

Load and return the ClinTox dataset, part of MoleculeNet [[1]](1) benchmark.

Tox21 dataset [[1]](1), part of MoleculeNet [[2]](2) benchmark.

HIV dataset [[1]](1), part of MoleculeNet [[2]](2) benchmark.

BBBP (Blood-Brain Barrier Penetration) dataset [[1]](1), part of MoleculeNet [[2]](2) benchmark.