Skip to Main Content
With the advent of microarray technology, there is a growing need to reliably extract biologically significant information from massive gene expression data. Clustering is one of the key steps in analyzing gene expression data by identifying groups of genes that manifest similar expression patterns. Elucidating the patterns hidden in gene expression data offers a tremendous opportunity for an enhanced understanding of proteomics. However, the large number of genes and their measurement complexity greatly increase the challenges of comprehension, interpretation and limited progress on cluster validation and identifying the number of clusters. In this paper, an intelligence based clustering algorithm is integrated with the validation techniques to assess the predictive power of the clusters. Through experimental evaluation, this approach is shown to outperform the other clustering methods greatly in terms of clustering quality, efficiency and automation. The resulting clusters offer potential insight into gene function, molecular biological processes and regulatory mechanisms.