Skip to main content
. 2021 May 25;2021:6696012. doi: 10.1155/2021/6696012

Table 1.

Datasets for generation tasks.

Dataset Purpose
ZINC [38, 39] Commercially available compounds for virtual screening
ChEMBL [40] A manually curated database of bioactive drug-like molecules
ChEMBL [41] Named compounds from chemical patents
eMolecules Purchasable molecules
Natural [42] Natural product molecules
DrugBank FDA-approved drugs, experimental drugs, drugs available worldwide