Table 3.

Specificity and Sensitivity of Computational Prediction Methods in Four Well-Characterized Genes (BRCA1, MSH2, MLH1, and TP53)

	BRCA1		MSH2		MLH1		TP53
Algorithm	Specificity	Sensitivity	Specificity	Sensitivity	Specificity	Sensitivity	Specificity	Sensitivity
Theoretical/unweighted computational prediction methods
SIFT	0.31	0.94	0.46	0.90	0.52	0.72	0.75	0.84
Align-GVGD	0.94	0.71	0.55	0.90	0.52	0.97	1.00	0.82
FATHMM (unweighted)	0.56	0.65	0.73	0.84	0.71	0.77	1.00	0.71
Trained/weighted computational prediction methods
PolyPhen-2	0.38	0.77	0.36	0.90	0.67	0.90	1.00	0.84
X-Var	0.56	0.82	0.27	1.00	0.33	1.00	0.50	0.96
FATHMM (weighted)	0.70	0.47	0.50	0.79	0.24	0.97	NAa	1.00

^aThe specificity for our weighted method in this instance is uninformative as there was only one neutral mutation falling within conserved protein domains.

The performances of alternative computational prediction algorithms have been reproduced with permission from Hicks et al. (2011). Copyright 2012, Wiley.