Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus

Yan Zhang, Lin An, Jie Xu, Bo Zhang, W. Jim Zheng, Ming Hu, Jijun Tang, Feng Yue

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Although Hi-C technology is one of the most popular tools for studying 3D genome organization, due to sequencing cost, the resolution of most Hi-C datasets are coarse and cannot be used to link distal regulatory elements to their target genes. Here we develop HiCPlus, a computational approach based on deep convolutional neural network, to infer high-resolution Hi-C interaction matrices from low-resolution Hi-C data. We demonstrate that HiCPlus can impute interaction matrices highly similar to the original ones, while only using 1/16 of the original sequencing reads. We show that the models learned from one cell type can be applied to make predictions in other cell or tissue types. Our work not only provides a computational framework to enhance Hi-C data resolution but also reveals features underlying the formation of 3D chromatin interactions.

Original languageEnglish (US)
Article number750
JournalNature communications
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2018

Fingerprint

sequencing
Genes
Neural networks
Chromatin
chromatin
genome
interactions
Genome
Tissue
matrices
Technology
cells
Costs and Cost Analysis
genes
costs
Costs
high resolution
predictions
Datasets

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Physics and Astronomy(all)

Cite this

Zhang, Y., An, L., Xu, J., Zhang, B., Zheng, W. J., Hu, M., ... Yue, F. (2018). Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus. Nature communications, 9(1), [750]. https://doi.org/10.1038/s41467-018-03113-2
Zhang, Yan ; An, Lin ; Xu, Jie ; Zhang, Bo ; Zheng, W. Jim ; Hu, Ming ; Tang, Jijun ; Yue, Feng. / Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus. In: Nature communications. 2018 ; Vol. 9, No. 1.
@article{de7cffe4d6884cc4a3966b688c1f5cc2,
title = "Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus",
abstract = "Although Hi-C technology is one of the most popular tools for studying 3D genome organization, due to sequencing cost, the resolution of most Hi-C datasets are coarse and cannot be used to link distal regulatory elements to their target genes. Here we develop HiCPlus, a computational approach based on deep convolutional neural network, to infer high-resolution Hi-C interaction matrices from low-resolution Hi-C data. We demonstrate that HiCPlus can impute interaction matrices highly similar to the original ones, while only using 1/16 of the original sequencing reads. We show that the models learned from one cell type can be applied to make predictions in other cell or tissue types. Our work not only provides a computational framework to enhance Hi-C data resolution but also reveals features underlying the formation of 3D chromatin interactions.",
author = "Yan Zhang and Lin An and Jie Xu and Bo Zhang and Zheng, {W. Jim} and Ming Hu and Jijun Tang and Feng Yue",
year = "2018",
month = "12",
day = "1",
doi = "10.1038/s41467-018-03113-2",
language = "English (US)",
volume = "9",
journal = "Nature Communications",
issn = "2041-1723",
publisher = "Nature Publishing Group",
number = "1",

}

Zhang, Y, An, L, Xu, J, Zhang, B, Zheng, WJ, Hu, M, Tang, J & Yue, F 2018, 'Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus', Nature communications, vol. 9, no. 1, 750. https://doi.org/10.1038/s41467-018-03113-2

Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus. / Zhang, Yan; An, Lin; Xu, Jie; Zhang, Bo; Zheng, W. Jim; Hu, Ming; Tang, Jijun; Yue, Feng.

In: Nature communications, Vol. 9, No. 1, 750, 01.12.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus

AU - Zhang, Yan

AU - An, Lin

AU - Xu, Jie

AU - Zhang, Bo

AU - Zheng, W. Jim

AU - Hu, Ming

AU - Tang, Jijun

AU - Yue, Feng

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Although Hi-C technology is one of the most popular tools for studying 3D genome organization, due to sequencing cost, the resolution of most Hi-C datasets are coarse and cannot be used to link distal regulatory elements to their target genes. Here we develop HiCPlus, a computational approach based on deep convolutional neural network, to infer high-resolution Hi-C interaction matrices from low-resolution Hi-C data. We demonstrate that HiCPlus can impute interaction matrices highly similar to the original ones, while only using 1/16 of the original sequencing reads. We show that the models learned from one cell type can be applied to make predictions in other cell or tissue types. Our work not only provides a computational framework to enhance Hi-C data resolution but also reveals features underlying the formation of 3D chromatin interactions.

AB - Although Hi-C technology is one of the most popular tools for studying 3D genome organization, due to sequencing cost, the resolution of most Hi-C datasets are coarse and cannot be used to link distal regulatory elements to their target genes. Here we develop HiCPlus, a computational approach based on deep convolutional neural network, to infer high-resolution Hi-C interaction matrices from low-resolution Hi-C data. We demonstrate that HiCPlus can impute interaction matrices highly similar to the original ones, while only using 1/16 of the original sequencing reads. We show that the models learned from one cell type can be applied to make predictions in other cell or tissue types. Our work not only provides a computational framework to enhance Hi-C data resolution but also reveals features underlying the formation of 3D chromatin interactions.

UR - http://www.scopus.com/inward/record.url?scp=85042362175&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042362175&partnerID=8YFLogxK

U2 - 10.1038/s41467-018-03113-2

DO - 10.1038/s41467-018-03113-2

M3 - Article

C2 - 29467363

AN - SCOPUS:85042362175

VL - 9

JO - Nature Communications

JF - Nature Communications

SN - 2041-1723

IS - 1

M1 - 750

ER -