A new hybrid evolutionary biclustring algorithm based on transposed virtual error

Abstract

Microarray technology in the last decade has been widely applied to detect correlated biomarkers in biological processes. Due to the need for analyzing massive amounts of generated data in this technology, computational intelligence approaches are used increasingly in this field. Biclustering algorithms are one of the most important of these techniques in microarray analysis. Two aspects of search mechanisms and biologists' desired patterns are the most essential issues in the design and evaluation of these algorithms. Different patterns can be achieved by considering different metrics. In this paper, Transposed Virtual Error (VET) is used as main metric. Also a hybrid evolutionary algorithm is proposed based on Evo-Bexpa algorithm which is introduced with VET. The proposed method is developed based on Genetic Algorithm (GA) used in Evo-Bexpa and Asexual Reproduction Optimization (ARO). The results indicate that underlying algorithm against Evo-Bexpa is more efficient in finding biclusters.