BiRange:An Efficient Framework for Biclustering of Gene Expression Data Using Range Bipartite Graph

Biclustering is a vital data mining tool which is commonly employed on microarray data sets for analysis task in bioinformatics research and medical applications. There has been extensive research on biclustering of gene expression data arising from microarray experiment. This technique is an important analysis tool in gene expression measurement, when some genes have multiple functions and experimental conditions are diverse. In this paper, we introduce a new framework for biclustering of gene expression data. The basis of this framework is the construction of a range bipartite graph for the representation of 2-dimensional gene expression data. We have constructed this range bipartite graph by partitioning the set of experimental conditions into two disjoint sets. The key benefit of this representation is that, it leads to a compact representation of all similar value ranges between experimental conditions. Based on this problem formulation, an efficient algorithm is proposed that searches for constrained maximal cliques in this range bipartite graph, in order to extract a set of biclusters. Our technique is scalable to practical gene expression data and can produce different types of biclusters amid noise. The experimental evaluation of this technique also reveals its accuracy and effectiveness with respect to noise handling and execution time in comparison to other similar techniques.