Cover Image

DeepFinder : An integration of feature-based and deep learning approach for DNA motif discovery

We propose an improved solution to the three-stage DNA motif prediction approach. The three-stage approach uses only a subset of input sequences for initial motif prediction, and the initial motifs obtained are employed for site detection in the remaining input subset of non-overlaps. The currently...

Full description

Saved in:
Bibliographic Details
Main Authors: Nung, Kion Lee, Farah Liyana, Azizan, Yu, Shiong Wong, Norshafarina, Omar
Format: Article
Language:English
Published: Taylor and Francis Ltd. 2018
Subjects:
H Social Sciences (General)
QH426 Genetics
Online Access:http://ir.unimas.my/id/eprint/19914/1/DeepFinder.pdf
http://ir.unimas.my/id/eprint/19914/
https://www.tandfonline.com/doi/full/10.1080/13102818.2018.1438209
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimas.ir.19914
record_format eprints
spelling my.unimas.ir.199142021-04-28T22:33:41Z http://ir.unimas.my/id/eprint/19914/ DeepFinder : An integration of feature-based and deep learning approach for DNA motif discovery Nung, Kion Lee Farah Liyana, Azizan Yu, Shiong Wong Norshafarina, Omar H Social Sciences (General) QH426 Genetics We propose an improved solution to the three-stage DNA motif prediction approach. The three-stage approach uses only a subset of input sequences for initial motif prediction, and the initial motifs obtained are employed for site detection in the remaining input subset of non-overlaps. The currently available solution is not robust because motifs obtained from the initial subset are represented as a position weight matrices, which results in high false positives. Our approach, called DeepFinder, employs deep learning neural networks with features associated with binding sites to construct a motif model. Furthermore, multiple prediction tools are used in the initial motif prediction process to obtain a higher number of positive hits. Our features are engineered from the context of binding sites, which are assumed to be enriched with specificity information of sites recognized by transcription factor proteins. DeepFinder is evaluated using several performance metrics on ten chromatin immunoprecipitation (ChIP) datasets. The results show marked improvement of our solution in comparison with the existing solution. This indicates the effectiveness and potential of our proposed DeepFinder for large-scale motif analysis. © 2018 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. Taylor and Francis Ltd. 2018-02-01 Article PeerReviewed text en http://ir.unimas.my/id/eprint/19914/1/DeepFinder.pdf Nung, Kion Lee and Farah Liyana, Azizan and Yu, Shiong Wong and Norshafarina, Omar (2018) DeepFinder : An integration of feature-based and deep learning approach for DNA motif discovery. Biotechnology and Biotechnological Equipment, 32 (3). pp. 1-10. ISSN 1310-2818 https://www.tandfonline.com/doi/full/10.1080/13102818.2018.1438209 DOI: 10.1080/13102818.2018.1438209
institution Universiti Malaysia Sarawak
building Centre for Academic Information Services (CAIS)
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Sarawak
content_source UNIMAS Institutional Repository
url_provider http://ir.unimas.my/
language English
topic H Social Sciences (General)
QH426 Genetics
spellingShingle H Social Sciences (General)
QH426 Genetics
Nung, Kion Lee
Farah Liyana, Azizan
Yu, Shiong Wong
Norshafarina, Omar
DeepFinder : An integration of feature-based and deep learning approach for DNA motif discovery
description We propose an improved solution to the three-stage DNA motif prediction approach. The three-stage approach uses only a subset of input sequences for initial motif prediction, and the initial motifs obtained are employed for site detection in the remaining input subset of non-overlaps. The currently available solution is not robust because motifs obtained from the initial subset are represented as a position weight matrices, which results in high false positives. Our approach, called DeepFinder, employs deep learning neural networks with features associated with binding sites to construct a motif model. Furthermore, multiple prediction tools are used in the initial motif prediction process to obtain a higher number of positive hits. Our features are engineered from the context of binding sites, which are assumed to be enriched with specificity information of sites recognized by transcription factor proteins. DeepFinder is evaluated using several performance metrics on ten chromatin immunoprecipitation (ChIP) datasets. The results show marked improvement of our solution in comparison with the existing solution. This indicates the effectiveness and potential of our proposed DeepFinder for large-scale motif analysis. © 2018 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
format Article
author Nung, Kion Lee
Farah Liyana, Azizan
Yu, Shiong Wong
Norshafarina, Omar
author_facet Nung, Kion Lee
Farah Liyana, Azizan
Yu, Shiong Wong
Norshafarina, Omar
author_sort Nung, Kion Lee
title DeepFinder : An integration of feature-based and deep learning approach for DNA motif discovery
title_short DeepFinder : An integration of feature-based and deep learning approach for DNA motif discovery
title_full DeepFinder : An integration of feature-based and deep learning approach for DNA motif discovery
title_fullStr DeepFinder : An integration of feature-based and deep learning approach for DNA motif discovery
title_full_unstemmed DeepFinder : An integration of feature-based and deep learning approach for DNA motif discovery
title_sort deepfinder : an integration of feature-based and deep learning approach for dna motif discovery
publisher Taylor and Francis Ltd.
publishDate 2018
url http://ir.unimas.my/id/eprint/19914/1/DeepFinder.pdf
http://ir.unimas.my/id/eprint/19914/
https://www.tandfonline.com/doi/full/10.1080/13102818.2018.1438209
_version_ 1698700771741138944
score 13.211869

Similar Items