QUT QUT ePrints

SVM Based Prediction of Bacterial Transcription Start Sites

Gordon, James J. and Towsey, Michael W. (2005) SVM Based Prediction of Bacterial Transcription Start Sites . In Proceedings Proceedings 6th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL’05) 3578, pages pp. 448-453, Brisbane, Australia.

Full text available as:
PDF (Author-version) - Requires Adobe Acrobat Reader or other PDF viewer.

Abstract

Identifying bacterial promoters is the key to understanding gene expression. Promoters lie in tightly constrained positions relative to the transcription start site (TSS). Knowing the TSS position, one can predict promoter positions to within a few base pairs, and vice versa. As a route to promoter identification, we formally address the problem of TSS prediction, drawing on the RegulonDB database of known (mapped) Escherichia coli TSS locations. The accepted method of finding promoters (and therefore TSSs) is to use position weight matrices (PWMs). We use an alternative approach based on sup-port vector machines (SVMs). In particular, we quantify performance of several SVM models versus a PWM approach, using area under the detection-error tradeoff (DET) curve as a performance metric. SVM models are shown to out-perform the PWM at TSS prediction, and to substantially reduce numbers of false positives, which are the bane of this problem.

Item Type:Conference Paper
Status:Published
Keywords:Support Vector Machines, Bacterial Promoters
Subjects:230000 Mathematical Sciences > 239900 Other Mathematical Sciences > 239901 Biological Mathematics
280000 Information, Computing and Communication Sciences > 280200 Artificial Intelligence and Signal and Image Processing > 280207 Pattern Recognition
280000 Information, Computing and Communication Sciences > 280200 Artificial Intelligence and Signal and Image Processing > 280213 Other Artificial Intelligence
ID Code:7600
Deposited By:Towsey, Michael W.
Deposited On:11 May 2007
Alternative Locations:http://dx.doi.org/10.1007/11508069_58
Copyright Owner:Copyright 2005 Springer
Copyright Statement:This is the author-version of the work. Conference proceedings published, by Springer Verlag, will be available via SpringerLink. http://www.springer.de/comp/lncs/ Lecture Notes in Computer Science