Cooperative coevolutionary multiobjective genetic programming for microarray data classification

Yang Qing, Chi Ma, Yu Zhou, Xiao Zhang, Haowen Xia

Abstract: DNA microarray data contain valuable biological information, which makes it of great importance in disease analysis and cancer diagnosis. However, the classification of microarray data is still a challenging task because of the high dimension and small sample size, especially for multiclass data accompanied by class imbalance. In this paper, we propose a cooperative coevolutionary multiobjective genetic programming (CC-MOGP) for microarray data classification. It converts a multiclass problem into a set of tractable binary problems and coevolves the corresponding population. And a cooperative coevolutionary Pareto archived evolution strategy (CC-PAES) is employed to approximate the Pareto front. During this procedure, we propose a synergy test method to assist in guiding the coevolution between populations. Experimental results on 8 multiclass microarray data show that CC-MOGP can obtain competitive prediction accuracy compared with several state-of-art evolutionary computation and traditional methods.