Effective clustering of microarray gene expression data using signal processing and soft computing methods

DNA microarray analysis has become the most widely used functional genomics approach in the bioinformatics field. Clustering of gene expression data is a standard exploratory technique used to identify closely related genes. Clustering is essential in the data mining process to reveal natural structures and identify interesting patterns in the underlying large number of genes and the complex of biological networks data. In this paper, an efficient technique is proposed for the precise clustering of genes from the microarray gene expression dataset. The proposed technique performs the clustering process with the aid of two phases namely, dimensionality reduction and gene clustering. The main objective of dimensionality reduction is to select the optimal number of genes from the microarray gene expression dataset. The present paper studies the capability of transform oriented signal processing techniques especially wavelet transform for dimension reduction and feature selection. These selected features are given to the K-means clustering. The method has been validated on the standard datasets. The result obtained is fast and accurate.