Discover gene specific local co-regulations from time-course gene expression data

Zhang, Ji and Gao, Qigang and Wang, Hai (2008) Discover gene specific local co-regulations from time-course gene expression data. Journal of Scientific Programming, 16 (1). pp. 31-47. ISSN 1058-9244

[img]
Preview
Text (Accepted Version)
Zhang_Gao_Hai_SP_v16n1_AV.pdf

Download (235Kb)

Abstract

[Abstract]: Discovering gene co-regulatory relationships is one of most important research in DNA microarray data analysis. The problem of gene specific co-regulation discovery is to, for a particular gene of interest (called target gene), identify the condition subsets where strong gene co-regulations of the target gene are observed and its co-regulated genes in these condition subsets. The co-regulations are local in the sense that they occur in some subsets of full experimental conditions. The study on this problem can contribute to better understanding and characterizing the target gene during the biological activity involved. In this paper, we propose an innovative method for finding gene specific co-regulations using genetic algorithm (GA). A sliding window is used to delimit the allowed length of conditions in which gene co-regulations occur and an \textit{ad hoc} GA, called the progressive GA, is performed in each window position to find those condition subsets having high fitness. It is called progressive because the initial population for the GA in a window position inherits the top-ranked individuals obtained in its preceding window position, enabling the GA to achieve a better accuracy than the non-progressive algorithm. kNN Lookup Table is utilized to substantially speed up fitness evaluation in the GA. Experimental results with a real-life gene expression data demonstrate the efficiency and effectiveness of our technique in discovering gene specific co-regulations.


Statistics for USQ ePrint 5619
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Author's version deposited in accordance with the copyright policy of the publisher.
Depositing User: Dr Ji Zhang
Faculty / Department / School: Historic - Faculty of Sciences - Department of Maths and Computing
Date Deposited: 23 Sep 2009 02:53
Last Modified: 29 Aug 2014 04:29
Uncontrolled Keywords: genes; gene co-regulatory relationships; gene specific co-regulation
Fields of Research (FOR2008): 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
Identification Number or DOI: doi: 10.3233/SPR-2008-0243
URI: http://eprints.usq.edu.au/id/eprint/5619

Actions (login required)

View Item Archive Repository Staff Only