Predicting Interactions between Virus and Host Proteins Using Repeat Patterns and Composition of Amino Acids

Table 9

Results of 5-fold cross validation of our SVM and Barman’s SVM [22] with Barman’s dataset of 1,035 positive and 1,035 negative PPIs.

Method	Sn (%)	Sp (%)	Acc (%)	PPV (%)	NPV (%)	MCC	AUC	F1 (%)
Our SVM	73.72	83.48	78.60	81.69	76.06	0.575	0.847	77.50
Barman’s SVM	67.00	74.00	71.00	72.00	—	0.440	0.730	69.41
Barman’s Random Forest	55.66	89.08	72.41	82.26	—	0.480	0.760	66.39

Sn: sensitivity, Sp: specificity, Acc: accuracy, PPV: positive predictive value, NPV: negative predictive value, MCC: Matthews correlation coefficient, AUC: the area under the ROC curve, F1 = 2  (SN  PPV)/(SN + PPV), and “—”: not available.