Prediction of Transcription Factor Binding Sites Using Genetic Algorithm

Identification of transcription factor binding sites (TFBS) from the upstream region of genes remains a highly important and unsolved problem particularly in higher eukaryotic genomes. In this paper, we propose a new approach to predict TFBS. This approach uses position weight matrix (PWM) to repres...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyu Chang, Wengang Zhou, Chunguang Zhou, Yanchun Liang
Format: Conference Proceeding
Language:English
Subjects:
Bioinformatics
Computer science
Educational technology
Genetic algorithms
Genomics
Hidden Markov models
Knowledge engineering
Proteins
PSSM
Pulse width modulation
Sequences
TFBS
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Identification of transcription factor binding sites (TFBS) from the upstream region of genes remains a highly important and unsolved problem particularly in higher eukaryotic genomes. In this paper, we propose a new approach to predict TFBS. This approach uses position weight matrix (PWM) to represent binding sites and uses genetic algorithm (GA) to search the best matrix. A new coding method so called multiple-variable coding is proposed in GA. We apply it on two transcription factors rebl and mgl. The result shows that this approach can find most of the known sites, which indicates that this method is very effective
DOI:10.1109/ICIEA.2006.257271