Table 3.

Prediction accuracies, sensitivities, specificities, AUC values and Matthew's correlation coefficients (MCC) compared between methods (based on COBR dataset)

Tool	Accuracy	Sensitivity	Specificity	AUC	MCC
CHASM	50%	0%	100%	0.36	0.08
MutationAssessor	70%	91%	50%	0.74	0.46
Condel	66%	66%	66%	0.68	0.33
PolyPhen-2	65%	63%	66%	0.63	0.30
SIFT	64%	73%	55%	0.63	0.29
SNAP	62%	45%	78%	0.59	0.26
mCluster	50%	0%	100%	0.46	0
logRE	54%	44%	64%	0.53	0.08