Gene Selection and Tissue Classification Based on Support Vector Machine and Genetic Algorithm

The main problems in tissue classification by using DNA Microarray data are selecting genes relevant for a given tumor and constructing the optimized classifiers. This paper proposes a new gene selection and tissue classification method based on support vector machines and genetic algorithm. Firstly, the Wilcoxon-test is used as a coarse gene selection method to remove most of the irrelevant genes. Then the fine selection on the basis of its classification ability of a single gene with support vector machine is conducted to get the final gene subset. Finally, genetic algorithm is used to optimize the parameters of support vector machine to find out the best parameters with the gene subset. The experimental results with the Leukemia and breast cancer dataset show that the proposed strategy is more effective and competitive to the previous methods.