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

Table 2

Comparison of different combinations of features in 10-fold cross validation of SVM model.

Features	Sn (%)	Sp (%)	Acc (%)	PPV (%)	NPV (%)	MCC	AUC
F1	81.66	97.02	89.34	96.48	84.10	0.796	0.916
F2	69.75	85.11	77.43	82.41	73.78	0.555	0.849
F3	87.78	97.81	92.79	97.56	88.89	0.860	0.965
F1 + F2	80.88	95.61	88.24	94.85	83.33	0.773	0.925
F1 + F3	88.56	97.34	92.94	97.08	89.48	0.862	0.966
F2 + F3	87.46	96.87	92.16	96.54	88.54	0.847	0.961
F1 + F2 + F3	88.24	97.34	92.79	97.07	89.22	0.859	0.963

F1: sum of squared length of single amino acid repeats in the entire protein sequence, F2: maximum of the sum of squared length of single amino acid repeats in a window of 6 residues, F3: composition of amino acids in 5 partitions of the protein sequence, Sn: sensitivity, Sp: specificity, Acc: accuracy, PPV: positive predictive value, NPV: negative predictive value, MCC: Matthews correlation coefficient, and AUC: the area under the ROC curve.