Cargando…
EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework
MOTIVATION: The high-throughput chromosome conformation capture (Hi-C) technique has enabled genome-wide mapping of chromatin interactions. However, high-resolution Hi-C data requires costly, deep sequencing; therefore, it has only been achieved for a limited number of cell types. Machine learning m...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8382278/ https://www.ncbi.nlm.nih.gov/pubmed/34252966 http://dx.doi.org/10.1093/bioinformatics/btab272 |
_version_ | 1783741518836662272 |
---|---|
author | Hu, Yangyang Ma, Wenxiu |
author_facet | Hu, Yangyang Ma, Wenxiu |
author_sort | Hu, Yangyang |
collection | PubMed |
description | MOTIVATION: The high-throughput chromosome conformation capture (Hi-C) technique has enabled genome-wide mapping of chromatin interactions. However, high-resolution Hi-C data requires costly, deep sequencing; therefore, it has only been achieved for a limited number of cell types. Machine learning models based on neural networks have been developed as a remedy to this problem. RESULTS: In this work, we propose a novel method, EnHiC, for predicting high-resolution Hi-C matrices from low-resolution input data based on a generative adversarial network (GAN) framework. Inspired by non-negative matrix factorization, our model fully exploits the unique properties of Hi-C matrices and extracts rank-1 features from multi-scale low-resolution matrices to enhance the resolution. Using three human Hi-C datasets, we demonstrated that EnHiC accurately and reliably enhanced the resolution of Hi-C matrices and outperformed other GAN-based models. Moreover, EnHiC-predicted high-resolution matrices facilitated the accurate detection of topologically associated domains and fine-scale chromatin interactions. AVAILABILITY AND IMPLEMENTATION: EnHiC is publicly available at https://github.com/wmalab/EnHiC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. |
format | Online Article Text |
id | pubmed-8382278 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-83822782021-08-24 EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework Hu, Yangyang Ma, Wenxiu Bioinformatics Macromolecular Sequence, Structure, and Function MOTIVATION: The high-throughput chromosome conformation capture (Hi-C) technique has enabled genome-wide mapping of chromatin interactions. However, high-resolution Hi-C data requires costly, deep sequencing; therefore, it has only been achieved for a limited number of cell types. Machine learning models based on neural networks have been developed as a remedy to this problem. RESULTS: In this work, we propose a novel method, EnHiC, for predicting high-resolution Hi-C matrices from low-resolution input data based on a generative adversarial network (GAN) framework. Inspired by non-negative matrix factorization, our model fully exploits the unique properties of Hi-C matrices and extracts rank-1 features from multi-scale low-resolution matrices to enhance the resolution. Using three human Hi-C datasets, we demonstrated that EnHiC accurately and reliably enhanced the resolution of Hi-C matrices and outperformed other GAN-based models. Moreover, EnHiC-predicted high-resolution matrices facilitated the accurate detection of topologically associated domains and fine-scale chromatin interactions. AVAILABILITY AND IMPLEMENTATION: EnHiC is publicly available at https://github.com/wmalab/EnHiC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. Oxford University Press 2021-07-12 /pmc/articles/PMC8382278/ /pubmed/34252966 http://dx.doi.org/10.1093/bioinformatics/btab272 Text en © The Author(s) 2021. Published by Oxford University Press. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Macromolecular Sequence, Structure, and Function Hu, Yangyang Ma, Wenxiu EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework |
title | EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework |
title_full | EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework |
title_fullStr | EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework |
title_full_unstemmed | EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework |
title_short | EnHiC: learning fine-resolution Hi-C contact maps using a generative adversarial framework |
title_sort | enhic: learning fine-resolution hi-c contact maps using a generative adversarial framework |
topic | Macromolecular Sequence, Structure, and Function |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8382278/ https://www.ncbi.nlm.nih.gov/pubmed/34252966 http://dx.doi.org/10.1093/bioinformatics/btab272 |
work_keys_str_mv | AT huyangyang enhiclearningfineresolutionhiccontactmapsusingagenerativeadversarialframework AT mawenxiu enhiclearningfineresolutionhiccontactmapsusingagenerativeadversarialframework |