SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model

Background: Discrimination of transcription factor binding sites (TFBS) from background sequences plays a key role in computational motif discovery. Current clustering based algorithms employ homogeneous model for problem solving, which assumes that motifs and background signals can be equivalently...

Full description

Bibliographic Details
Main Authors: Lee, Nung Kion, Wang, Dianhui
Format: Article
Language:English
Published: BioMed Central Ltd 2011
Subjects:
Online Access:http://ir.unimas.my/id/eprint/11897/
http://ir.unimas.my/id/eprint/11897/1/SOMEA_abstract.pdf
_version_ 1848837085198286848
author Lee, Nung Kion
Wang, Dianhui
author_facet Lee, Nung Kion
Wang, Dianhui
author_sort Lee, Nung Kion
building UNIMAS Institutional Repository
collection Online Access
description Background: Discrimination of transcription factor binding sites (TFBS) from background sequences plays a key role in computational motif discovery. Current clustering based algorithms employ homogeneous model for problem solving, which assumes that motifs and background signals can be equivalently characterized. This assumption has some limitations because both sequence signals have distinct properties. Results: This paper aims to develop a Self-Organizing Map (SOM) based clustering algorithm for extracting binding sites in DNA sequences. Our framework is based on a novel intra-node soft competitive procedure to achieve maximum discrimination of motifs from background signals in datasets. The intra-node competition is based on an adaptive weighting technique on two different signal models to better represent these two classes of signals. Using several real and artificial datasets, we compared our proposed method with several motif discovery tools. Compared to SOMBRERO, a state-of-the-art SOM based motif discovery tool, it is found that our algorithm can achieve significant improvements in the average precision rates (i.e., about 27%) on the real datasets without compromising its sensitivity. Our method also performed favourably comparing against other motif discovery tools. Conclusions: Motif discovery with model based clustering framework should consider the use of heterogeneous model to represent the two classes of signals in DNA sequences. Such heterogeneous model can achieve better signal discrimination compared to the homogeneous model
first_indexed 2025-11-15T06:34:03Z
format Article
id unimas-11897
institution Universiti Malaysia Sarawak
institution_category Local University
language English
last_indexed 2025-11-15T06:34:03Z
publishDate 2011
publisher BioMed Central Ltd
recordtype eprints
repository_type Digital Repository
spelling unimas-118972016-05-12T00:51:09Z http://ir.unimas.my/id/eprint/11897/ SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model Lee, Nung Kion Wang, Dianhui QA75 Electronic computers. Computer science T Technology (General) Background: Discrimination of transcription factor binding sites (TFBS) from background sequences plays a key role in computational motif discovery. Current clustering based algorithms employ homogeneous model for problem solving, which assumes that motifs and background signals can be equivalently characterized. This assumption has some limitations because both sequence signals have distinct properties. Results: This paper aims to develop a Self-Organizing Map (SOM) based clustering algorithm for extracting binding sites in DNA sequences. Our framework is based on a novel intra-node soft competitive procedure to achieve maximum discrimination of motifs from background signals in datasets. The intra-node competition is based on an adaptive weighting technique on two different signal models to better represent these two classes of signals. Using several real and artificial datasets, we compared our proposed method with several motif discovery tools. Compared to SOMBRERO, a state-of-the-art SOM based motif discovery tool, it is found that our algorithm can achieve significant improvements in the average precision rates (i.e., about 27%) on the real datasets without compromising its sensitivity. Our method also performed favourably comparing against other motif discovery tools. Conclusions: Motif discovery with model based clustering framework should consider the use of heterogeneous model to represent the two classes of signals in DNA sequences. Such heterogeneous model can achieve better signal discrimination compared to the homogeneous model BioMed Central Ltd 2011 Article PeerReviewed text en http://ir.unimas.my/id/eprint/11897/1/SOMEA_abstract.pdf Lee, Nung Kion and Wang, Dianhui (2011) SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model. BMC Bioinformatics, 12. pp. 1-10. ISSN 1471-2105 http://download.springer.com/static/pdf/502/art%253A10.1186%252F1471-2105-12-S1-S16.pdf?originUrl=http%3A%2F%2Fbmcbioinformatics.biomedcentral.com%2Farticle%2F10.1186%2F1471-2105-12-S1-S16&token2=exp=1462430179~acl=%2Fstatic%2Fpdf%2F502%2Fart%25253A10.118 DOI: 10.1186/1471-2105-12-S1-S16
spellingShingle QA75 Electronic computers. Computer science
T Technology (General)
Lee, Nung Kion
Wang, Dianhui
SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model
title SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model
title_full SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model
title_fullStr SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model
title_full_unstemmed SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model
title_short SOMEA: self-organizing map based extraction algorithm for DNA motif identification with heterogeneous model
title_sort somea: self-organizing map based extraction algorithm for dna motif identification with heterogeneous model
topic QA75 Electronic computers. Computer science
T Technology (General)
url http://ir.unimas.my/id/eprint/11897/
http://ir.unimas.my/id/eprint/11897/
http://ir.unimas.my/id/eprint/11897/
http://ir.unimas.my/id/eprint/11897/1/SOMEA_abstract.pdf