Universiti Teknologi Malaysia Institutional Repository

A two-stage method to select a smaller subset of informative genes for cancer classification

Mohamed, Mahadhir and Omatu, Sigeru and Yoshioka, Michifumi and Deris, Safaai (2009) A two-stage method to select a smaller subset of informative genes for cancer classification. International Journal of Innovative Computing, Information and Control , 5 (10). pp. 2959-2968. ISSN 13494198

Full text not available from this repository.

Abstract

Gene expression data measured by microarray machines are useful for cancer classification. However, it faces with several problems in selecting genes for the classification due to many irrelevant genes, noisy data, and the availability of a small number of samples compared to a huge number of genes (high-dimensional data). Hence, this paper proposes a two-stage gene selection method to select a smaller (near-optimal) subset of informative genes that is most relevant for the cancer classification. It has two stages: 1) pre-selecting genes using a filter method to produce a subset of genes; 2) optimising the gene subset using a multi-objective hybrid method to automatically yield a smaller subset of informative genes. Three gene expression data sets are used to test the effectiveness of the proposed method. Experimental results show that the performance of the proposed method is superior to other experimental methods and related previous works.

Item Type:Article
Uncontrolled Keywords:cancer classification, filter method, gene expression data, gene selection, genetic algorithm, hybrid method
Subjects:Q Science > QA Mathematics > QA76 Computer software
Divisions:Computer Science and Information System (Formerly known)
ID Code:12919
Deposited By: Ms Zalinda Shuratman
Deposited On:07 Jul 2011 04:33
Last Modified:07 Jul 2011 04:33

Repository Staff Only: item control page