A pattern matching approach for clustering gene expression data. (1st January 2011)

• Record Type: Journal Article
• Authors: Das, Rosy; Kalita, Jugal; Bhattacharyya, Dhruba K.
• Is Part Of: International journal of data mining, modelling and management. Volume 3:Number 2(2011)
• Page Start: 130
• Page End: 149
• Publication Date: 2011-01-01
• Subjects: gene expression -- microarray -- regulation pattern -- matching -- clustering -- sub-cluster -- incremental clustering; Data mining -- Periodicals; Information science -- Periodicals; Databases -- Periodicals; 005.7
• DOI: 10.1504/IJDMMM.2011.041492
• Languages: English
• ISSNs: 1759-1163

Abstract

Identifying groups of genes with similar expression time courses is crucial in the analysis of gene expression time series data. This paper proposes a regulation-based clustering approach, PatternClus, for clustering gene expression data. The method also identifies sub-clusters based on an order preserving ranking approach. The clustering method was experimented in light of real life datasets and the proposed method has been established to perform satisfactorily. PatternClus was compared to some of the well-known clustering algorithms (k-means and hierarchical algorithm) and was found to give better results in terms of z-score measure of cluster validation. An incremental version of PatternClus is also presented here which helps in identifying clusters incrementally where the database is continuously increasing.