Table 1.

Enumeration of the protein targets studied, detailing counts of active compounds, decoys, the number of external validation datasets, and the respective PDB IDs used to score active compounds within each target dataset

Protein target	No. of actives	No. of decoys	No. of actives in the external validation	PDB ID
AA2AR	40	5000	10	3EML
AKT1	40	5000	10	3CQW
CDK2	40	5000	10	1H00
DPP4	47	5000	10	2I78
TDP1	51	2700	11	6N0D
PPARG	43	5000	10	2GTK
EGFR	50	5000	10	2RGP
P53	20	2300	5	6GGB