Biclustering Gene Expression Data based on a High Dimensional Geometric Method
MetadataShow full item record
In gene expression data, a bicluster is a subset of genes exhibiting a consistent pattern over a subset of the conditions. In this paper, we propose a new method to detect biclusters in gene expression data. Our approach is based on the high dimensional geometric property of biclusters and it avoids dependence on specific patterns, which degrade many available biclustering algorithms. Furthermore, we illustrate that a bilclustering algorithm can be decomposed into two independent steps and this not only helps to build up a hierarchical structure but also provides a coarse-to-fine mechanism and overcome the effect of the inherent noise in gene expression data. The simulated experiments demonstrate that our algorithm is very promising.
Proceedings of the Fourth International Conference on Machine Learning and Cybernetics
© 2005 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.