Skip to main content
. 2014 Apr 23;9(4):e96202. doi: 10.1371/journal.pone.0096202

Table 5. The Performance of SVM Models on validation dataset with experimentally derived binding affinity from EhCaBPs (D7).

Features SN SP ACC MCC
AC&CC 83.33 60 72.73 0.45
AC&HC 100 80 90.91 0.83
AC&HC&HYC 83.33 80 81.82 0.63
AC&HYC&CC 83.33 60 72.73 0.45
AC&HYC 66.67 60 63.64 0.27

The Performance of SVM Models on validation dataset with experimentally derived binding affinity from EhCaBPs (D7)with different learning parameters on various hybrid models [γ (g) (in RBF kernel), c: parameter for trade-off between training error & margin] where SN–sensitivity, SP–specificity, ACC-accuracy, MCC–Matthews Correlation Coefficient, AUC/ROC-Area under curve/ Receiver Operating Curve.