Skip to main content

Table 2 Statistics of the data sets for the different targets

From: Estimation of the applicability domain of kernel-based machine learning models for virtual screening

Target

Training Compounds

Screening Compounds

Ligands

Decoys

Thrombin

88

1172

24

1148

Factor Xa

290

2156

64

2092

PDGFRβ

79

5727

124

5603