TITLE:
Cancer Specific Non-Synonymous Single Nucleotide Polymorphism Prediction in the Context of Haplotype and Protein Interacting Sites
AUTHORS:
Pakeeza Akram, Li Liao
KEYWORDS:
Single Nucleotide Polymorphism, Haplotype, Interaction Sites, Prediction, Cancer
JOURNAL NAME:
Journal of Biomedical Science and Engineering,
Vol.10 No.5B,
May
10,
2017
ABSTRACT: In this work, we study predicting the effect of non-synonymous SNPs on several cancers. We trained classifiers on both sequential and structural features extracted from the affected genes and assessed the predictions made by the trained classifiers using cross validation. Specifically, we investigated how the prediction performance can be improved by connecting SNPs in the context of haplotype and interacting sites of proteins encoded by affected genes. We found that accuracy was consistently enhanced by combining sequential and structural features, with increase ranging from a few percentage points up to more than 20 percentage points. The results for putting SNPs in the context of interacting sites were less consistent. Compared to individual SNPs, these that appear together in haplotype showed stronger correlation with one another and with the phenotype, and therefore led to significant improvement inprediction performance, with ROC score increased from 0.81 to 0.95. Although some similar effect has been expected for connecting SNPs to interacting sites in proteins, the performance actually got worse. This decrease in prediction accuracy may be caused by the small data set being used in the study, as many affected proteins in the study do not have known interacting sites.