Gene specific co-regulation discovery: an improved approach
Zhang, Ji, Liu, Qing and Xu, Kai ORCID: https://orcid.org/0000-0003-2242-5440
(2009)
Gene specific co-regulation discovery: an improved approach.
In:
Computational Science – ICCS 2009 : 9th International Conference Baton Rouge, LA, USA, May 25-27, 2009 Proceedings, Part I.
Allen, Gabrielle, Nabrzyski, Jarosław, Seidel, Edward and Albada, Geert Dick van, eds.
Computational Science – ICCS 2009
(5544)
.
Springer, Berlin, pp. 838-847.
ISBN 9783642019692.
[Book Section]
(doi:10.1007/978-3-642-01970-8_84)
Abstract
Discovering gene co-regulatory relationships is a new but important research problem in DNA microarray data analysis. The problem of gene specific co-regulation discovery is to, for a particular gene of interest, called the target gene, identify its strongly co-regulated genes and the condition subsets where such strong gene co-regulations are observed. The study on this problem can contribute to a better understanding and characterization of the target gene. The existing method, using the genetic algorithm (GA), is slow due to its expensive fitness evaluation and long individual representation. In this paper, we propose an improved method for finding gene specific co-regulations. Compared with the current method, our method features a notably improved efficiency. We employ kNN Search Table to substantially speed up fitness evaluation in the GA. We also propose a more compact representation scheme for encoding individuals in the GA, which contributes to faster crossover and mutation operations. Experimental results with a real-life gene microarray data set demonstrate the improved efficiency of our technique compared with the current method.
Item Type: | Book Section |
---|---|
Research Areas: | A. > School of Science and Technology > Computer Science |
Item ID: | 11145 |
Useful Links: | |
Depositing User: | Teddy ~ |
Date Deposited: | 03 Jul 2013 13:07 |
Last Modified: | 13 Oct 2016 14:27 |
URI: | https://eprints.mdx.ac.uk/id/eprint/11145 |
Actions (login required)
![]() |
View Item |
Statistics
Additional statistics are available via IRStats2.