Skip to main content

Table 5 Virtual screening performance of support vector machines for identifying Src inhibitors from large compound libraries

From: Development and experimental test of support vector machines virtual screening method for searching Src inhibitors from large compound libraries

Inhibitors in training set Number of inhibitors 1703
Number of chemical families covered by inhibitors 493
Inhibitors in Testing Set Number of Inhibitors 44
Number of Chemical Families Covered by Inhibitors 35
Percent of Inhibitors in Chemical Families Covered by Inhibitors in Training Set 51.43%
Virtual Screening Performance Yield 70.45%
Number and Percent of Identified True Inhibitors Outside Training Chemical Families 15 (34.1%)
Number and Percent of 13.56M PubChemCompounds Identified as Inhibitors 44,843 (0.33%)
Number and Percent of the 168K MDDR Compounds Identified as Inhibitors 1,496 (0.89%)
  Number and Percent of the 9,305 MDDR Compounds Similar to the Known Inhibitors Identified as Inhibitors 719 (7.73%)