The predictive performance of short-linear motif features in the prediction of calmodulin-binding proteins

BMC Bioinformatics

Table 5 Classification results for the score matrices with SLiMs obtained from CM using FS

Dataset for classification	# features	Classifier	Accuracy (%)	MCC	ROC Area
S score matrix		SVM-Polynomial (c=1,g=0)	62.0	0.24	0.62
	11	RF	80.1	0.60	0.85
		k-NN (k=1)	78.6	0.57	0.79
T score matrix		SVM-Polynomial (c=1,g=0)	60.2	0.21	0.60
	9	RF	70.5	0.415	0.80
		k-NN (k=1)	68.7	0.38	0.69

ISSN: 1471-2105