TB-IECS: an accurate machine learning-based scoring function for virtual screening

Table 1 Information of the diverse subset of DUD-E and LIT-PCBA after preparation

Target	PDB_ID	Active	Decoys	Total	Active/decoys %
akt1	3cqw	674	33,484	34,158	2.01
ampc	1l2s	95	5831	5926	1.63
cp3a4	3nxu	840	19,918	20,758	4.22
cxcr4	3odu	871	8779	9650	9.92
gcr	3bqd	179	8649	8828	2.07
hivpr	1xl2	3476	58,731	62,207	5.92
hivrt	3lan	867	23,265	24,132	3.73
kif11	3cjo	334	13,313	13,647	2.51
ALDH1	5l2n	7554	149,358	156,912	5.06
ESR1_ant	2iog	111	6189	6300	1.79
FEN1	5fv7	696	502,274	502,970	0.14
GBA	3ril	319	423,463	423,782	0.08
KAT2A	5h86	306	494,569	494,875	0.06
MAPK1	4qte	442	91,185	91,627	0.49
MTORC1	4dri	157	42,223	42,380	0.37
PKM2	3me3	665	301,123	301,788	0.22
TP53	3zme	113	5779	5892	1.96
VDR	3a2i	678	216,464	217,142	0.31

ISSN: 1758-2946