Ultra-large virtual screening hit (ULVSH) dataset
Input files (protein, active site, docking poses) of the ULVSH dataset. Two directories (raw, minimized) for raw and minimized docking poses From Sindt and al. Journal of Chemical …
DataSets
PDBbind dataset 19
In-house curated input files (protein, ligand) of the PDBbind v.2019 dataset. From Volkov et al. J. Med. Chem. 2022, 65, 11, 7946–7958
LIT-PCBA
A dataset for virtual screening and machine learning. 15 target sets, 7761 actives and 382674 unique inactives selected from high-confidence PubChem Bioassay data
PPIome datasets
Druggable cavities/Ligands at and nearby protein-protein interfaces from the Protein Data Bank. da Silva et al. J Med Chem, 60, 4263-4273, 2019
Fragdock dataset
2376 ligand/protein structures aligned describing 64 different proteins.
PDBbind datasets 14
protein-ligand complexes and Set of decoy poses from the PDBbind database. Gabel et al. J Chem Inf Model, 54, 2807-2815, 2014
Docking dataset
100 input files (protein, active site, ligand) from Kellenberger and al. Protein, 2004
Screening dataset
Virtual screening datasets: Input files for receptor and ligand database (10 actives + 990 decoys) for both the tymidine kinase and the estrogen receptor alpha from Bissantz and …