The New Jersey Institute of Technology's
Electronic Theses & Dissertations Project

Title:	Risk prediction with genomic data
Author:	Jadhav, Bharati
View Online:	njit-etd2014-070 (viii, 29 pages ~ 0.9 MB pdf)
Department:	Department of Computer Science
Degree:	Master of Science
Program:	Bioinformatics
Document Type:	Thesis
Advisory Committee:	Roshan, Usman W. (Committee chair) Wang, Jason T. L. (Committee member) Wei, Zhi (Committee member)
Date:	2014-05
Keywords:	Genome wide association study (GWAS) Disease risk prediction Single Nucleotide Polymorphism (SNP) genotype data Whole Exome Wide Association Study (WEWAS)
Availability:	Unrestricted
Abstract:	Genome wide association study (GWAS) is widely used with various machine learning algorithms to predict disease risk. This thesis investigates this widely used approach of GWAS using Single Nucleotide Polymorphism (SNP) genotype data and a novel approach of disease risk prediction with whole exome sequencing data, namely Whole Exome Wide Association Study (WEWAS). It further applies a discriminating machine learning algorithm, namely a Support Vector Machine (SVM) with different Kernel functions. For this study, only SNPs generated using genotyping technology, which focuses more on common variants, are used initially for disease prediction. Later, the whole exome data generated using Next Generation Sequencing (NSG) technology is used in the prediction. Another distinction between traditional GWAS and the new approach, WEWAS, presented in this thesis is the use of insertions and deletions in the genomic sequence (INDEL) together with SNPs as a feature for prediction. A substantial improvement in the prediction accuracy is achieved using the latter approach. The success of the approach of using NSG data shows that it contains valuable information which the SNP genotyping method is unable to capture.