Bioinformatics Advance Access originally published online on March 29, 2005
Bioinformatics 2005 21(11):2657-2666; doi:10.1093/bioinformatics/bti410
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Identification of transcription factor binding sites with variable-order Bayesian networks
1Department of Industrial Engineering, Tel-Aviv University Tel-Aviv, 69978, Israel
2Institute of Plant Genetics and Crop Plant Research, (IPK) 06466 Gatersleben, Germany
3Institute of Computer Science, University Halle 06099 Halle (Saale), Germany
4Department of Information Systems Engineering, Ben-Gurion University Beer-Sheva, 84105, Israel
*To whom correspondence should be addressed.
Motivation: We propose a new class of variable-order Bayesian network (VOBN) models for the identification of transcription factor binding sites (TFBSs). The proposed models generalize the widely used position weight matrix (PWM) models, Markov models and Bayesian network models. In contrast to these models, where for each position a fixed subset of the remaining positions is used to model dependencies, in VOBN models, these subsets may vary based on the specific nucleotides observed, which are called the context. This flexibility turns out to be of advantage for the classification and analysis of TFBSs, as statistical dependencies between nucleotides in different TFBS positions (not necessarily adjacent) may be taken into account efficiently—in a position-specific and context-specific manner.
Results: We apply the VOBN model to a set of 238 experimentally verified sigma-70 binding sites in Escherichia coli. We find that the VOBN model can distinguish these 238 sites from a set of 472 intergenic ‘non-promoter’ sequences with a higher accuracy than fixed-order Markov models or Bayesian trees. We use a replicated stratified-holdout experiment having a fixed true-negative rate of 99.9%. We find that for a foreground inhomogeneous VOBN model of order 1 and a background homogeneous variable-order Markov (VOM) model of order 5, the obtained mean true-positive (TP) rate is 47.56%. In comparison, the best TP rate for the conventional models is 44.39%, obtained from a foreground PWM model and a background 2nd-order Markov model. As the standard deviation of the estimated TP rate is 
0.01%, this improvement is highly significant.
Availability: All datasets are available upon request from the authors. A web server for utilizing the VOBN and VOM models is available at http://www.eng.tau.ac.il/~bengal/
Contact: bengal{at}eng.tau.ac.il
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  E. Wingender The TRANSFAC project as an example of framework technology that supports the analysis of genomic regulation Brief Bioinform, April 24, 2008; (2008) bbn016v1. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 A. Vandenbon, Y. Miyamoto, N. Takimoto, T. Kusakabe, and K. Nakai Markov Chain-based Promoter Structure Modeling for Tissue-specific Expression Pattern Prediction DNA Res, February 7, 2008; (2008) dsm034v1. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 T. S. Rani, S. D. Bhavani, and R. S. Bapi Analysis of E.coli promoter recognition problem in dinucleotide feature space Bioinformatics, March 1, 2007; 23(5): 582 - 588. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 J. Grau, I. Ben-Gal, S. Posch, and I. Grosse VOMBAT: prediction of transcription factor binding sites using variable order Bayesian trees. Nucleic Acids Res., July 1, 2006; 34(Web Server issue): W529 - W533. [Abstract] [Full Text] [PDF]
|
|