Evaluating Accuracy of Pathogenicity Prediction Methods for Single Nucleotide Polymorphisms

Pathogenicity of single nucleotide polymorphism is the potential ability to produce disease. Testing each of the SNPs separately can lead to an erroneous measurement of the effect of the SNPs on the disease risk. In this research analysis of seven most popular tools for predicting the deleteriousness of single nucleotide polymorphisms namely SIFT, SNPs&GO, I Mutant, MUPro, Fathmn, PANTHER, and PhD-SNP was conducted. The ClinVar database was used to retrieve the pathogenic and benign SNPs, and the UniProt database to get protein sequences respectively. The SIFT, PhD-SNP, and SNP&Go outperformed all of the other prediction algorithms based on accucy and Matthews Correlation Coefficient with scores of (0.68,0.38), (0.66, 0.33) and (0.64, 0.29) respectively with highlighting error rates and recommended to avoid the use of MuPro for predicting the pathogenic variants. To improve the performance and accuracy of pathogenicity predictors the tools must be considered to upgrade