Multi-objective optimization using genetic algorithm for gene selection from microarray data

Microarray technology has been increasingly used in cancer research because of its potential for measuring expression levels of thousands of genes simultaneously in tissue samples. It is used to collect the information from tissue samples regarding gene expression differences that could be useful for cancer classification. However, this classification task faces many challenges due to availability of a smaller number of samples compared to the huge number of genes, 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 approach in genetic algorithm. This approach is experimented on two microarray data sets such as lung cancer and mixed-lineage leukemia cancer. It obtains encouraging result on those data sets as compared with an approach that uses single objective approach.