Applying filter approach and genetic algorithm wrapper for gene selection from gene expression data

Abstract

Gene expression microarray data is expected to significantly aid in the development of efficient cancer diagnosis and classification platforms. One problem arising from this data is how to select a small subset of genes from thousands of genes and much fewer samples that are inherently noisy. This research deals with finding a small subset of informative genes from the gene expression data which maximize the classification accuracy and minimize the running time. This paper proposed a model of gene expression classification by using filter approach and an improved Genetic Algorithm wrapper approach. We show that the classification accuracy and execution time of the proposed model are useful for cancer classification of two widely used gene expression benchmark data sets.