Identification of NAD interacting residues in proteins

BMC Bioinformatics

Table 1 Performance of SVM model developed using amino acid sequence (binary pattern) at different window lengths.

Window size	Kernel parameters	Thr*	Sen (%)	Spe (%)	Acc (%)	MCC
3	t 2 g 0.1 j 1 c 1	0	63.41	61.27	62.34	0.25
5	t 2 g 0.1 j 1 c 1	0	64.46	65.13	64.79	0.3
7	t 2 g 0.1 j 1 c 1	0	67.98	66.83	67.4	0.35
9	t 2 g 0.1 j 1 c 1	0	69.09	69.32	69.21	0.38
11	t 2 g 0.1 j 1 c 1	0	69.7	71.37	70.54	0.41
13	t 2 g 0.1 j 1 c 10	0	70.81	72.78	71.79	0.44
15	t 2 g 0.1 j 1 c 10	0	71.56	73.89	72.73	0.45
17	t 1 d 3	-0.2	70.28	76.89	74.13	0.47
19	t 2 g 0.1 j 1 c 100	0	71.27	72.49	71.88	0.44
21	t 2 g 0.1 j 1 c 10	0	70.81	73.68	72.24	0.45

*(Thr- Threshold, Sen - Sensitivity, Spe - Specificity, Acc - Accuracy, MCC - Matthew's correlation coefficient)
SVM models were trained and tested on a dataset having equal number of positive and negative data. Bold font shows the performance and parameters of selected SVM model.

ISSN: 1471-2105