Biclustering of Gene Expression Using Glowworm Swarm Optimization and Neuro-Fuzzy Discriminant Analysis

-The advent of DNA microarray technologies has revolutionized the experimental study of gene expression. Biclustering is the most popular approach of analyzing gene expression data and has indeed proven to be successful in many applications. In recent years, several biclustering methods have been suggested to identify local patterns in gene expression data. Most of these algorithms represent greedy strategies that are heuristic in nature: an approximate solution is found within reasonable time bounds. The quality of a biclustering, though, is often considered more important than the computation time required to generate it. To overcome the problems in gene expression analysis, novel algorithms for finding the coregulated clusters, dimensionality reduction and clustering have been proposed. The coregulated clusters are determined using biclustering algorithm, so it is called as coregulated biclusters. The coregulated biclusters are two or more genes which contain similarity features. The dimensionality reduction of microarray gene expression data is carried out using Neurofuzzy Discriminant Analysis (NFDA). To maintain bond between the neighborhoods in locality, NFDA is used and an efficient metaheuristic optimization algorithm called Glowworm Swarm Optimization clustering is used for clustering the gene expression based on the pattern. The experimental results shows that proposed algorithm achieve a higher clustering accuracy and takes lesser less clustering time when compared with existing algorithms.