Classification of cancer gene expressions from micro-array analysis

The role of micro array expression data in cancer diagnosis is very significant. Mining for useful information from such micro array data consisting of thousands of genes and a small number of samples is often a tough task. Colon cancer is the second most common cause of cancer mortality in Western countries. According to the WHO 2006 report colorectal cancer causes 655,000 deaths worldwide per year. All the genes used in the expression profile are not informative; also many of them are redundant. Reducing the number of genes by feature selection and still retaining best class prediction accuracy for the classifier is vital in case of tumor classification. The emphasis in cancer classification is both on methods of gene selection and on choice of classifier. It is proposed to study various classification algorithms.