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

BMC Bioinformatics

Table 2 Classification results for the score matrices with SLiMs obtained from SM using 3-fold cross validation

Dataset for classification	# features	Classifier	Accuracy (%)	MCC	ROC Area
S score matrix		SVM-Polynomial	72.6	0.45	0.73
	100	RF	73.1	0.46	0.81
		k-NN (k=1)	80.6	0.61	0.81
T score matrix		SVM-Polynomial	55.0	0.11	0.55
	100	RF	68.5	0.38	0.77
		k-NN (k=1)	59.7	0.27	0.60

ISSN: 1471-2105