15 target sets, 7761 actives,and 382674 inactives from high-confidencePubChem Bioassay data  
  • Image1

    Image1

  • Image2

    Image2

  • Image3

    Image3


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
Download Full data  here     
Download AVE unbiased data here     
AID   Set
 		  Target   Ligands   Actives   Inactives   PDB templates
492947   ADRB2   Beta2 adrenergic receptor   Agonists   17   311748   8
1030   ALDH1   Aldehyde dihydrogenase 1   Inhibitors   5363   101874   8
743075   ESR_ago   Estrogen receptor α   Agonists   13   4378   15
743080   ESR_antago   Estrogen receptor α   Antagonists   88   3820   15
588795   FEN1   FLAP Endonuclease   Inhibitors   360   350718   1
2101   GBA   Glucocerebrosidrase   Inhibitors   163   291241   6
602179   IDH1   Isocitrate dihydrogenase   Inhibitors   39   358757   14
504327   KAT2A   Histone acetyltransferase KAT2A   Inhibitors   194   342729   3
995   MAPK1   Mitogen-activated protein kinase 1   Inhibitors   308   61567   15
493208
 		  MTORC1   Mechanistic target of rapamycin   Inhibitors   97   32972   11
1777   OPRK1   Kappa opioid receptor   Agonists   24   269475   1
1631   PKM2   Pyruvate kinase muscle isoform 2   Inhibitors   546   244679   9
743094   PPARG   Peroxisome proliferator-activated receptor γ   Inhibitors   24   4071   15
651631   TP53   Cellular tumor antigen p53   Inhibitors   64   3345   6
504847   VDR   Vitamin D receptor   Inhibitors   655   262648   2