This dataset is composed of two sets of docking results for the 1.56 billion compounds of the Enamine REAL (ER) lead-like library (obtained March 2021). The intended use of the data is to serve as a giga-scale benchmarking dataset, e.g. for machine learning approaches. Both docking studies were performed with Schrödinger Suite 2021-1 Glide (v9), using the HTVS protocol.  [1] Results for the SurA target (receptor based on PDB-ID 1m5y, chain A): Enamine_REAL_lead-like_SurA_glide_HTVS_docking_scores.csv.gz [2] Results for the GAK target (receptor PDB-ID 4y8d, chain A; hydrogen-bonding constraint on Cys126 backbone amide hydrogen was used): Enamine_REAL_lead-like_GAK_glide_HTVS_docking_scores.csv.gz  Result files are gzipped, white-space separated text files with the following fields: SMILES, compound title (ER identifier), (Glide) docking score. Compounds that failed to produce any conformers in ligand preparation or failed to produce a pose during docking for any reason were assigned a score 5.0.

2023