AN EFFICIENT ARTIFICIAL BEE COLONY AND FUZZY C MEANS BASED CLUSTERING GENE EXPRESSION DATA
|K.Sathishkumar1, Dr.V.Thiagarasu2, M.Ramalingam3
|Related article at Pubmed, Scholar Google|
Cluster analysis of gene expression data has proved to be a useful tool for identifying co-expressed genes as it partition a given data set into groups based on particular features. The gene microarray data are arranged based on the pattern of gene expression using various clustering algorithms and the dynamic natures of biological processes are generally unnoticed by the traditional clustering algorithms. To overcome the problems in gene expression analysis, novel algorithms for dimensionality reduction and clustering have been proposed. The dimensionality reduction of microarray gene expression data is carried out using Locality Sensitive Discriminant Analysis (LSDA). To maintain bond between the neighborhoods in locality, LSDA is used and an efficient metaheuristic optimization algorithm called Artificial Bee Colony (ABC) using Fuzzy c Means 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.