Mutual Information in stages for informative gene selection

An important issue in the design of gene selection algorithm for microarray data analysis is the formation of a suitable criterion function for measuring the relevance between different gene expressions. Mutual Information (MI) is widely used criterion function but it calculates the relevance on the entire samples only once which cannot exactly identifies the informative genes. This paper proposes a novel idea of computing MI in stages. The proposed method computes MI, initially using all the samples and again repeatedly using only unclassified samples, after performing a preliminary classification using Back Propagation Network (BPN). The performance of the proposed approach is evaluated using six gene expression data (Colon Cancer, Lymphoma, Prostate Cancer, Leukemia, RAC and RAOA). Simulation result shows that the proposed method selects highly informative genes and produces comparable classification accuracy. Further the proposed approach helps to improve the evaluation of discriminate power of the genes with regard to the target diseases of a microarray sample.