[Show abstract][Hide abstract] ABSTRACT: In this paper, we present a gene selection method based on genetic algorithm (GA) and support vector machines (SVM) for cancer
classification. First, the Wilcoxon rank sum test is used to filter noisy and redundant genes in high dimensional microarray
data. Then, the different highly informative genes subsets are selected by GA/SVM using different training sets. The final
subset, consisting of highly discriminating genes, is obtained by analyzing the frequency of appearance of each gene in the
different gene subsets. The proposed method is tested on three open datasets: leukemia, breast cancer, and colon cancer data.
The results show that the proposed method has excellent selection and classification performance, especially for breast cancer
data, which can yield 100% classification accuracy using only four genes.