A Combined Genetic Programming for Microarray Data Analysis

Microarray technology is a powerful tool to monitor gene expression or gene expression changes of hundreds or thousands of genes in a single experiment. Meta-Genetic Programming is the meta learning technique of evolving a genetic programming system to predict cancer classes for better understanding of different types of cancers and to find the possible biomarkers for diseases. A new technique which is known as Majority Voting Genetic Programming Classifier (MVGPC) combined with meta-genetic programming (MGP) is proposed which combines meta-genetic programming and majority voting technique to predict the cancer class for a given patient sample with higher accuracy and minimum computational time. This paper also aims to provide a means to identify cancer at an early stage and hence increase the chances of survival for the patients. General Terms Data Mining.