A multi-objective strategy in genetic algorithm for gene selection of gene expression data

Microarray device offers the ability to measure the expression levels of thousands of genes simultaneously. It is used to collect information from tissue and cell samples regarding gene expression differences that could be useful for cancer classification. However, the urgent issues in the use of gene expression data are the availability of huge number of genes relative to the small number of available samples, and many of the genes are not relevant to the classification. It has been shown that selecting a small subset of genes can lead to an improved accuracy of the classification. Hence, this paper proposes a solution to the problem of gene selection by using a multi-objective strategy in genetic algorithm. This approach is experimented on two benchmark gene expression data sets and it presented the experimental results. It obtains encouraging result on those data sets as compared with an approach that uses single-objective strategy in genetic algorithm.