Deep learning for DNase I hypersensitive sites identification

Abstract Background The DNase I hypersensitive sites (DHSs) are associated with the cis-regulatory DNA elements. An efficient method of identifying DHSs can enhance the understanding on the accessibility of chromatin. Despite a multitude of resources available on line including experimental datasets...

Full description

Bibliographic Details
Main Authors: Chuqiao Lyu, Lei Wang, Juhua Zhang
Format: Article
Language:English
Published: BMC 2018-12-01
Series:BMC Genomics
Subjects:
Online Access:http://link.springer.com/article/10.1186/s12864-018-5283-8
id doaj-e050cb42d96945bb95d0457dd1ddfa96
record_format Article
spelling doaj-e050cb42d96945bb95d0457dd1ddfa962020-11-25T01:28:22ZengBMCBMC Genomics1471-21642018-12-0119S1015516510.1186/s12864-018-5283-8Deep learning for DNase I hypersensitive sites identificationChuqiao Lyu0Lei Wang1Juhua Zhang2School of Life Science, Beijing Institute of TechnologySchool of Life Science, Beijing Institute of TechnologySchool of Life Science, Beijing Institute of TechnologyAbstract Background The DNase I hypersensitive sites (DHSs) are associated with the cis-regulatory DNA elements. An efficient method of identifying DHSs can enhance the understanding on the accessibility of chromatin. Despite a multitude of resources available on line including experimental datasets and computational tools, the complex language of DHSs remains incompletely understood. Methods Here, we address this challenge using an approach based on a state-of-the-art machine learning method. We present a novel convolutional neural network (CNN) which combined Inception like networks with a gating mechanism for the response of multiple patterns and longterm association in DNA sequences to predict multi-scale DHSs in Arabidopsis, rice and Homo sapiens. Results Our method obtains 0.961 area under curve (AUC) on Arabidopsis, 0.969 AUC on rice and 0.918 AUC on Homo sapiens. Conclusions Our method provides an efficient and accurate way to identify multi-scale DHSs sequences by deep learning.http://link.springer.com/article/10.1186/s12864-018-5283-8DNase I hypersensitive sitesDeep learningConvolutional neural network
collection DOAJ
language English
format Article
sources DOAJ
author Chuqiao Lyu
Lei Wang
Juhua Zhang
spellingShingle Chuqiao Lyu
Lei Wang
Juhua Zhang
Deep learning for DNase I hypersensitive sites identification
BMC Genomics
DNase I hypersensitive sites
Deep learning
Convolutional neural network
author_facet Chuqiao Lyu
Lei Wang
Juhua Zhang
author_sort Chuqiao Lyu
title Deep learning for DNase I hypersensitive sites identification
title_short Deep learning for DNase I hypersensitive sites identification
title_full Deep learning for DNase I hypersensitive sites identification
title_fullStr Deep learning for DNase I hypersensitive sites identification
title_full_unstemmed Deep learning for DNase I hypersensitive sites identification
title_sort deep learning for dnase i hypersensitive sites identification
publisher BMC
series BMC Genomics
issn 1471-2164
publishDate 2018-12-01
description Abstract Background The DNase I hypersensitive sites (DHSs) are associated with the cis-regulatory DNA elements. An efficient method of identifying DHSs can enhance the understanding on the accessibility of chromatin. Despite a multitude of resources available on line including experimental datasets and computational tools, the complex language of DHSs remains incompletely understood. Methods Here, we address this challenge using an approach based on a state-of-the-art machine learning method. We present a novel convolutional neural network (CNN) which combined Inception like networks with a gating mechanism for the response of multiple patterns and longterm association in DNA sequences to predict multi-scale DHSs in Arabidopsis, rice and Homo sapiens. Results Our method obtains 0.961 area under curve (AUC) on Arabidopsis, 0.969 AUC on rice and 0.918 AUC on Homo sapiens. Conclusions Our method provides an efficient and accurate way to identify multi-scale DHSs sequences by deep learning.
topic DNase I hypersensitive sites
Deep learning
Convolutional neural network
url http://link.springer.com/article/10.1186/s12864-018-5283-8
work_keys_str_mv AT chuqiaolyu deeplearningfordnaseihypersensitivesitesidentification
AT leiwang deeplearningfordnaseihypersensitivesitesidentification
AT juhuazhang deeplearningfordnaseihypersensitivesitesidentification
_version_ 1725102194356649984