Table 2. The Performance of SVM Models with different learning parameters on D1 and D2 dataset.

Features	C	g	SN	SP	ACC	MCC
Binary	8	0.008	100	100	100	1
AA	0.125	0.008	100	100	100	1

Using binary patterns and AA (amino acid) composition [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.