A deep learning model for predicting transcription factor binding location at single nucleotide resolution

Sirajul Salekin, Jianqiu Michelle Zhang, Yufei Huang

Research output: ResearchConference contribution

Abstract

Transcriptional regulation by transcription factors (TFs) plays a pivotal role in controlling the gene expression. However, understanding the mechanism through which the transcription factors regulate the gene expression is a challenging task. This is primarily hindered by the low specificity in identifying transcription factor binding sites (TFBS). The emergence of the ChIP-exonuclease (ChIP-exo) method enables the detection of TFBS at single nucleotide sensitivity, providing us an opportunity to study the detailed mechanisms of TF regulation. Nevertheless, there is still a lack of computational tools that can also provide single base pair (bp) resolution prediction of TFBS. In this paper, we propose DeepSNR, a Deep Learning algorithm for Single Nucleotide Resolution prediction of transcription factor binding site. Our proposed method is inspired by the similarity between predicting the specific binding location from input nucleotide sequence and image segmentation. Particularly, we adopted the deconvolution network (deconvNet); a deep learning model designed for image segmentation, and developed a TFBS specific deconvNet architecture constructed on top of 'DeepBind'. We trained a deconvNet for predicting CTCF binding sites using the data from ChIP-exo experiments. The proposed algorithm achieved median precision and recall of 87% and 77% respectively, significantly outperforming motif search based algorithms such as MatInspector.

LanguageEnglish (US)
Title of host publication2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages57-60
Number of pages4
ISBN (Electronic)9781509041794
DOIs
StatePublished - Apr 11 2017
Event4th IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017 - Orlando, United States
Duration: Feb 16 2017Feb 19 2017

Other

Other4th IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017
CountryUnited States
CityOrlando
Period2/16/172/19/17

Fingerprint

Transcription factors
Nucleotides
Deep learning
Transcription Factors
Learning
Binding sites
Binding Sites
Deconvolution
Image segmentation
Gene expression
Gene Expression
Network architecture
Learning algorithms
Experiments
Exonucleases
Base Pairing

ASJC Scopus subject areas

  • Health Informatics
  • Computer Science Applications
  • Biomedical Engineering

Cite this

Salekin, S., Zhang, J. M., & Huang, Y. (2017). A deep learning model for predicting transcription factor binding location at single nucleotide resolution. In 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017 (pp. 57-60). [7897204] Institute of Electrical and Electronics Engineers Inc.. DOI: 10.1109/BHI.2017.7897204

A deep learning model for predicting transcription factor binding location at single nucleotide resolution. / Salekin, Sirajul; Zhang, Jianqiu Michelle; Huang, Yufei.

2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 57-60 7897204.

Research output: ResearchConference contribution

Salekin, S, Zhang, JM & Huang, Y 2017, A deep learning model for predicting transcription factor binding location at single nucleotide resolution. in 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017., 7897204, Institute of Electrical and Electronics Engineers Inc., pp. 57-60, 4th IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017, Orlando, United States, 2/16/17. DOI: 10.1109/BHI.2017.7897204
Salekin S, Zhang JM, Huang Y. A deep learning model for predicting transcription factor binding location at single nucleotide resolution. In 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017. Institute of Electrical and Electronics Engineers Inc.2017. p. 57-60. 7897204. Available from, DOI: 10.1109/BHI.2017.7897204
Salekin, Sirajul ; Zhang, Jianqiu Michelle ; Huang, Yufei. / A deep learning model for predicting transcription factor binding location at single nucleotide resolution. 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 57-60
@inbook{9571c256b853479da43fddf743a48ef9,
title = "A deep learning model for predicting transcription factor binding location at single nucleotide resolution",
abstract = "Transcriptional regulation by transcription factors (TFs) plays a pivotal role in controlling the gene expression. However, understanding the mechanism through which the transcription factors regulate the gene expression is a challenging task. This is primarily hindered by the low specificity in identifying transcription factor binding sites (TFBS). The emergence of the ChIP-exonuclease (ChIP-exo) method enables the detection of TFBS at single nucleotide sensitivity, providing us an opportunity to study the detailed mechanisms of TF regulation. Nevertheless, there is still a lack of computational tools that can also provide single base pair (bp) resolution prediction of TFBS. In this paper, we propose DeepSNR, a Deep Learning algorithm for Single Nucleotide Resolution prediction of transcription factor binding site. Our proposed method is inspired by the similarity between predicting the specific binding location from input nucleotide sequence and image segmentation. Particularly, we adopted the deconvolution network (deconvNet); a deep learning model designed for image segmentation, and developed a TFBS specific deconvNet architecture constructed on top of 'DeepBind'. We trained a deconvNet for predicting CTCF binding sites using the data from ChIP-exo experiments. The proposed algorithm achieved median precision and recall of 87% and 77% respectively, significantly outperforming motif search based algorithms such as MatInspector.",
author = "Sirajul Salekin and Zhang, {Jianqiu Michelle} and Yufei Huang",
year = "2017",
month = "4",
doi = "10.1109/BHI.2017.7897204",
pages = "57--60",
booktitle = "2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - CHAP

T1 - A deep learning model for predicting transcription factor binding location at single nucleotide resolution

AU - Salekin,Sirajul

AU - Zhang,Jianqiu Michelle

AU - Huang,Yufei

PY - 2017/4/11

Y1 - 2017/4/11

N2 - Transcriptional regulation by transcription factors (TFs) plays a pivotal role in controlling the gene expression. However, understanding the mechanism through which the transcription factors regulate the gene expression is a challenging task. This is primarily hindered by the low specificity in identifying transcription factor binding sites (TFBS). The emergence of the ChIP-exonuclease (ChIP-exo) method enables the detection of TFBS at single nucleotide sensitivity, providing us an opportunity to study the detailed mechanisms of TF regulation. Nevertheless, there is still a lack of computational tools that can also provide single base pair (bp) resolution prediction of TFBS. In this paper, we propose DeepSNR, a Deep Learning algorithm for Single Nucleotide Resolution prediction of transcription factor binding site. Our proposed method is inspired by the similarity between predicting the specific binding location from input nucleotide sequence and image segmentation. Particularly, we adopted the deconvolution network (deconvNet); a deep learning model designed for image segmentation, and developed a TFBS specific deconvNet architecture constructed on top of 'DeepBind'. We trained a deconvNet for predicting CTCF binding sites using the data from ChIP-exo experiments. The proposed algorithm achieved median precision and recall of 87% and 77% respectively, significantly outperforming motif search based algorithms such as MatInspector.

AB - Transcriptional regulation by transcription factors (TFs) plays a pivotal role in controlling the gene expression. However, understanding the mechanism through which the transcription factors regulate the gene expression is a challenging task. This is primarily hindered by the low specificity in identifying transcription factor binding sites (TFBS). The emergence of the ChIP-exonuclease (ChIP-exo) method enables the detection of TFBS at single nucleotide sensitivity, providing us an opportunity to study the detailed mechanisms of TF regulation. Nevertheless, there is still a lack of computational tools that can also provide single base pair (bp) resolution prediction of TFBS. In this paper, we propose DeepSNR, a Deep Learning algorithm for Single Nucleotide Resolution prediction of transcription factor binding site. Our proposed method is inspired by the similarity between predicting the specific binding location from input nucleotide sequence and image segmentation. Particularly, we adopted the deconvolution network (deconvNet); a deep learning model designed for image segmentation, and developed a TFBS specific deconvNet architecture constructed on top of 'DeepBind'. We trained a deconvNet for predicting CTCF binding sites using the data from ChIP-exo experiments. The proposed algorithm achieved median precision and recall of 87% and 77% respectively, significantly outperforming motif search based algorithms such as MatInspector.

UR - http://www.scopus.com/inward/record.url?scp=85018403951&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018403951&partnerID=8YFLogxK

U2 - 10.1109/BHI.2017.7897204

DO - 10.1109/BHI.2017.7897204

M3 - Conference contribution

SP - 57

EP - 60

BT - 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -