Skip to Main Content
Cancer is a phenotypic complexity which affects genes, proteins, pathways and regulatory networks. The research is still in progress to identify the important genes which are responsible for various types of cancer. In this context important genes refers to the gene marker which indicates change in expression or state of protein that correlates with the risk or progression of a disease, or with the susceptibility of the disease to a given treatment. However extracting these marker genes from a huge set of genes is a major problem. There are many approaches for detecting these informative genes. Most of the approaches can find a set of redundant marker genes. Motivated by this fact a multiobjective optimization method has been proposed which can find small set of non-redundant disease related genes which have high sensitivity, specificity and accuracy at the same time. In this article the optimization problem has been modeled as multiobjective problem based on the framework of particle swarm optimization. Using the real life datasets, performance of proposed algorithm has been compared with other different techniques.