An Enumerative Biclustering Algorithm for DNA Microarray Data

Abstract

In a number of domains, like in DNA microarray data analysis, we need to cluster simultaneously rows (genes) and columns (conditions) of a data matrix to identify groups of constant rows with a group of columns. This kind of clustering is called biclustering. Biclustering algorithms are extensively used in DNA microarray data analysis. More effective biclustering algorithms are highly desirable and needed. We introduce a new algorithm called, Enumerative Lattice (EnumLat) for biclustering of binary microarray data. EnumLat is an algorithm adopting the approach of enumerating biclusters. This algorithm extracts all biclusters consistent good quality. The main idea of EnumLat is the construction of a new tree structure to represent adequately different biclusters discovered during the process of enumeration. This algorithm adopts the strategy of all biclusters at a time. The performance of the proposed algorithm is assessed using both synthetic and real DNA microarray data, our algorithm outperforms other biclustering algorithms for binary microarray data. Moreover, we test the biological significance using a gene annotation web tool to show that our proposed method is able to produce biologically relevant biclusters.