A New Systematic Computational Approach to Predicting Target Genes of Transcription Factors.
From: Plant Biology Division, the Samuel Robert Noble Foundation, Ardmore, OK 73401, USA.
Nucleic acids research
- Publish Date: 2007
- ISSN: 1362-4962
- Volume: 35
- Issue: 13
- Pages: 4433-40
- Medium: Internet
- Language: English
- Citation (JAMA): Dai Xinbin, He Ji, Zhao Xuechun, et al. A New Systematic Computational Approach to Predicting Target Genes of Transcription Factors.. Nucleic Acids Res. 2007;35:4433-40
Abstract
Identifying transcription factor target genes (TFTGs) is a vital step towards understanding regulatory mechanisms of gene expression. Methods for the de novo identification of TFTGs are generally based on screening for novel DNA binding sites. However, experimental screening of new binding sites is a technically challenging, laborious and time-consuming task, while computational methods still lack accuracy. We propose a novel systematic computational approach for predicting TFTGs directly on a genome scale. Utilizing gene co-expression data, we modeled the prediction problem as a ‘yes’ or ‘no’ classification task by converting biological sequences into novel reverse-complementary position-sensitive n-gram profiles and implemented the classifiers with support vector machines. Our approach does not necessarily predict new DNA binding sites, which other studies have shown to be difficult and inaccurate. We applied the proposed approach to predict auxin-response factor target genes from published Arabidopsis thaliana co-expression data and obtained satisfactory results. Using ten-fold cross validations, the area under curve value of the receiver operating characteristic reaches around 0.73.
Mesh Headings (Keywords): Algorithms, Arabidopsis, Artificial Intelligence, Binding Sites, Computational Biology, Gene Expression, Genomics, Promoter Regions (Genetics), Transcription Factors
Check for Full Text / PubMed Unique Identifier (PMID): 17576669
This abstract is part of PubMed, a service of the U.S. National Library of Medicine. PubMed includes more than 17 million citations from MEDLINE and other life science journals for biomedical articles. See Copyright and Disclaimers.
Linked medical terms appearing on this page are added by Healia to help readers find more information and are not part of the original PubMed document.
The data herein was last updated on July 8th, 2008 and may not reflect the most current and accurate data available from NLM.