Gene Selection for Tumor Classification Using Microarray Gene Expression Data

In this paper we perform a t-test for significant gene expression analysis in different dimensions based on molecular profiles from microarray data, and compare several computational intelligent techniques for classification accuracy on Leukemia, Lymphoma and Prostate cancer datasets of broad institute and Colon cancer dataset from Princeton gene expression project. This paper also describes results concerning the robustness and generalization capabilities of kernel methods in classifying. We use traditional support vector machines (SVM), biased support vector machine (BSVM) and leave-one-out model selection for support vector machines (looms) for model selection. We also evaluate the impact of kernel type and parameter values on the accuracy of a support vector machine (SVM) performing tumor classification. Through a variety of comparative experiments, it is found that SVM performs the best for detecting Leukemia and Lymphoma, BSVM performs the best for Colon and Prostate cancers. We show that classification accuracy varies with the kernel type and the parameter values; thus, with appropriately chosen parameter values, tumors can be classified by kernel machines with higher accuracy and lower false alarms. Our results demonstrate the potential of using learning machines in diagnosis of the malignancy of a tumor.