Regression Modeling and Meta-Analysis of Diagnostic Accuracy of SNP-Based Pathogenicity Detection Tools for UGT1A1 Gene Mutation

Table 2

Calculated Matthew’s correlation coefficient (MCC) and accuracy (ACC) of the selected SNP-based pathogenicity detection tools and suggested model.

Detection tools	TP	FP	FN	TN	MCC	ACC
SIFT	19	7	15	18	34.19%	62.71%
PHD-SNP	1	27	1	34	3.39%	55.56%
PolyPhen2	23	3	20	13	29.89%	61.02%
fathmm	1	27	1	34	3.39%	55.56%
Provean	20	6	18	15	29.99%	59.32%
MutPred	23	3	20	13	29.89%	61.02%
Model	26	2	14	18	46.80%	73.33%

TP: true positive; TN: true negative; FP: false positive; FN: false negative; MCC: Matthew’s correlation coefficient; ACC: accuracy.