. 2012 Oct 3;34(1):57–65. doi: 10.1002/humu.22225

Table 4.

Performance of Computational Prediction Methods Using the SwissVar Benchmarking Dataset

	tp	fp	tn	fn	Accuracy^a	Precision^a	Specificity^a	Sensitivity^a	NVP^a	MCC^a
Unweighted computational prediction methods
SIFT	15,634	6,318	28,236	7,716	0.74	0.79	0.82	0.67	0.71	0.49
PolyPhen 1	12,803	8,759	18,603	4,497	0.71	0.70	0.68	0.74	0.72	0.42
PANTHER	8,283	5,842	17,447	5,162	0.68	0.71	0.75	0.62	0.66	0.37
FATHMM (unweighted)	14,311	6,717	29,454	9,429	0.71	0.76	0.81	0.60	0.67	0.43
Weighted/trained computational prediction methods
PolyPhen 2 (HumDiv)	19,782	13,592	20,874	3,204	0.73	0.69	0.61	0.86	0.81	0.48
PolyPhen 2 (HumVar)	19,928	13,239	21,227	3,058	0.74	0.69	0.62	0.87	0.82	0.50
PhD-SNP Sequence	15,695	9,380	26,838	8,062	0.70	0.72	0.74	0.66	0.69	0.40
PhD-SNP Profile	17,548	7,233	27,731	5,161	0.78	0.79	0.79	0.77	0.78	0.57
PMut	13,498	12,156	23,636	10,159	0.62	0.63	0.66	0.57	0.61	0.23
SNPs&GO	17,768	3,768	29,101	5,655	0.82	0.87	0.89	0.76	0.79	0.65
MutPred	21,365	3,500	32,719	2,392	0.90	0.90	0.90	0.90	0.90	0.80
FATHMM (weighted)	15,916	3,017	19,713	4,496	0.82	0.85	0.87	0.78	0.80	0.65

tp, fp, tn, fn refer to the number of true positives, false positives, true negatives, and false negatives, respectively.

Accuracy, Precision, Specificity, Sensitivity, NVP, and MCC are calculated from normalized numbers.