Title: Tag SNP selection using clonal selection and majority voting algorithms

Authors: İlhan İlhan; Gülay Tezel

Addresses: Department of Mechatronic Engineering, Faculty of Engineering and Architecture, Necmettin Erbakan University, Konya, Turkey ' Department of Computer Engineering, Faculty of Engineering and Architecture, Selçuk University, Konya, Turkey

Abstract: Researchers should select a suitable subgroup that includes all SNPs and represents the rest of the SNPs with little error for very large-scale association studies. The SNPs included in the subgroup are tag SNPs or haplotype tag SNPs (htSNPs). When selecting the tag SNPs, it is critical to accurately predict and identify the smallest number of tag SNPs with minimum error. This study used the Clonal Selection Algorithm (CLONALG) to decide on the tag SNPs to be included in the subgroup. In addition, the study proposed a new method called CSMV, which used the Majority Voting (MV) method to predict the rest of the SNPs. This method was compared with the BPSO method and the CLONTagger with parameter optimisation method using datasets of different sizes. According to the experimental results of the study, the CSMV method could determine the tag SNPs with significantly higher accuracy than the other two methods.

Keywords: ABC; artificial bee colony; CLONALG; clonal selection; majority voting; SVM; support vector machines; tag SNPs; tag SNP selection; single nucleotide polymorphisms; bioinformatics; metaheuristics.

DOI: 10.1504/IJDMB.2016.082208

International Journal of Data Mining and Bioinformatics, 2016 Vol.16 No.4, pp.290 - 311

Received: 20 Feb 2016
Accepted: 26 Dec 2016

Published online: 12 Feb 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article