A New Strategy of Geometrical Biclustering for Microarray Data Analysis
MetadataShow full item record
In this paper, we present a new biclustering algorithm to provide the geometrical interpretation of similar microarray gene expression profiles. Different from standard clustering analyses, biclustering methodology can perform simultaneous classification on the row and column dimensions of a data matrix. The main object of the strategy is to reveal the submatrix, in which a subset of genes exhibits a consistent pattern over a subset of conditions. However, the search for such subsets is a computationally complex task. We propose a new algorithm, based on the Hough transform in the column-pair space to perform pattern identification. The algorithm is especially suitable for the biclustering analysis of large-scale microarray data. Our simulation studies show that the method is robust to noise and computationally efficient. Furthermore, we have applied it to a large database of gene expression profiles of multiple human organs and the resulting biclusters show clear biological meanings.
Proceedings of the Fifth Asia Pacific Bioinformatics Conference
© 2007 World Scientific. The attached file is posted here in accordance with the copyright policy of the publisher, for your personal use only. No further distribution permitted. For information about this conference please refer to the conference's website or contact the authors.