ISSN : 2319-7323

INTERNATIONAL JOURNAL OF COMPUTER SCIENCE ENGINEERING

ABSTRACT

Title	:	Evaluating SVM Algorithms for Bioinformatics Gene Expression Analysis
Authors	:	Heena Farooq Bhat
Keywords	:	Support Vector Machines, Bioinformatics, Gene Expression, Class Discovery, Class Prediction, Recursive Feature Elimination.
Issue Date	:	Feb 2017
Abstract	:	Support Vector Machines SVMs are trendy and dominant in learning systems because of providing good generalization properties, attending high dimensional data, their ability to classify input patterns with minimized structural classification risk and finding the optimal separating hyper-plane between two classes in feature space. Recent work in bioinformatics has seen an increasing use of SVM algorithms due to their benefits in dealing with high dimensional data, small sample size and compound data structures. The main aim of this paper is to provide a review of the most widely used SVM algorithms in bioinformatics namely gene expression based on the objectives using DNA microarrays classified into into three groups namely gene finding, class discovery and class prediction. These algorithms are then applied on cancer datasets: Leukemia and Lymphoma to produce better accuracy results.
Page(s)	:	42-52
ISSN	:	2319-7323
Source	:	Vol. 6, No.2