Table 1. Classification performance by the trained classifier on the training and an independent test set.

Sets	TP	TN	FP	FN	SEN	SP	ACC	MCC	AUC
Train	972	2,493	134	341	0.74	0.95	0.88	0.52	0.94
Independent	360	1,983	165	100	0.78	0.92	0.90	0.45	0.93

TP = true positive; TN = true negative; FP = false positive; FN = false negative; N =  total number of proteins in dataset; SEN  =  TP/(TP+FN); SP  =  TN/(TN+FP); ACC  =  (TP+TN)/N; MCC  = (TPxTN-FPxFN)/√((TP+FN)(TP+FP)(TN+FP) (TN+FN)); AUC is described in (37).