Cargando…

Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks

The hypo- or hyper-methylation of the human genome is one of the epigenetic features of leukemia. However, experimental approaches have only determined the methylation state of a small portion of the human genome. We developed deep learning based (stacked denoising autoencoders, or SdAs) software na...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Yiheng, Liu, Tong, Xu, Dong, Shi, Huidong, Zhang, Chaoyang, Mo, Yin-Yuan, Wang, Zheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4726425/
https://www.ncbi.nlm.nih.gov/pubmed/26797014
http://dx.doi.org/10.1038/srep19598
_version_ 1782411820099698688
author Wang, Yiheng
Liu, Tong
Xu, Dong
Shi, Huidong
Zhang, Chaoyang
Mo, Yin-Yuan
Wang, Zheng
author_facet Wang, Yiheng
Liu, Tong
Xu, Dong
Shi, Huidong
Zhang, Chaoyang
Mo, Yin-Yuan
Wang, Zheng
author_sort Wang, Yiheng
collection PubMed
description The hypo- or hyper-methylation of the human genome is one of the epigenetic features of leukemia. However, experimental approaches have only determined the methylation state of a small portion of the human genome. We developed deep learning based (stacked denoising autoencoders, or SdAs) software named “DeepMethyl” to predict the methylation state of DNA CpG dinucleotides using features inferred from three-dimensional genome topology (based on Hi-C) and DNA sequence patterns. We used the experimental data from immortalised myelogenous leukemia (K562) and healthy lymphoblastoid (GM12878) cell lines to train the learning models and assess prediction performance. We have tested various SdA architectures with different configurations of hidden layer(s) and amount of pre-training data and compared the performance of deep networks relative to support vector machines (SVMs). Using the methylation states of sequentially neighboring regions as one of the learning features, an SdA achieved a blind test accuracy of 89.7% for GM12878 and 88.6% for K562. When the methylation states of sequentially neighboring regions are unknown, the accuracies are 84.82% for GM12878 and 72.01% for K562. We also analyzed the contribution of genome topological features inferred from Hi-C. DeepMethyl can be accessed at http://dna.cs.usm.edu/deepmethyl/.
format Online
Article
Text
id pubmed-4726425
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher Nature Publishing Group
record_format MEDLINE/PubMed
spelling pubmed-47264252016-01-27 Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks Wang, Yiheng Liu, Tong Xu, Dong Shi, Huidong Zhang, Chaoyang Mo, Yin-Yuan Wang, Zheng Sci Rep Article The hypo- or hyper-methylation of the human genome is one of the epigenetic features of leukemia. However, experimental approaches have only determined the methylation state of a small portion of the human genome. We developed deep learning based (stacked denoising autoencoders, or SdAs) software named “DeepMethyl” to predict the methylation state of DNA CpG dinucleotides using features inferred from three-dimensional genome topology (based on Hi-C) and DNA sequence patterns. We used the experimental data from immortalised myelogenous leukemia (K562) and healthy lymphoblastoid (GM12878) cell lines to train the learning models and assess prediction performance. We have tested various SdA architectures with different configurations of hidden layer(s) and amount of pre-training data and compared the performance of deep networks relative to support vector machines (SVMs). Using the methylation states of sequentially neighboring regions as one of the learning features, an SdA achieved a blind test accuracy of 89.7% for GM12878 and 88.6% for K562. When the methylation states of sequentially neighboring regions are unknown, the accuracies are 84.82% for GM12878 and 72.01% for K562. We also analyzed the contribution of genome topological features inferred from Hi-C. DeepMethyl can be accessed at http://dna.cs.usm.edu/deepmethyl/. Nature Publishing Group 2016-01-22 /pmc/articles/PMC4726425/ /pubmed/26797014 http://dx.doi.org/10.1038/srep19598 Text en Copyright © 2016, Macmillan Publishers Limited http://creativecommons.org/licenses/by/4.0/ This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/
spellingShingle Article
Wang, Yiheng
Liu, Tong
Xu, Dong
Shi, Huidong
Zhang, Chaoyang
Mo, Yin-Yuan
Wang, Zheng
Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks
title Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks
title_full Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks
title_fullStr Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks
title_full_unstemmed Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks
title_short Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks
title_sort predicting dna methylation state of cpg dinucleotide using genome topological features and deep networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4726425/
https://www.ncbi.nlm.nih.gov/pubmed/26797014
http://dx.doi.org/10.1038/srep19598
work_keys_str_mv AT wangyiheng predictingdnamethylationstateofcpgdinucleotideusinggenometopologicalfeaturesanddeepnetworks
AT liutong predictingdnamethylationstateofcpgdinucleotideusinggenometopologicalfeaturesanddeepnetworks
AT xudong predictingdnamethylationstateofcpgdinucleotideusinggenometopologicalfeaturesanddeepnetworks
AT shihuidong predictingdnamethylationstateofcpgdinucleotideusinggenometopologicalfeaturesanddeepnetworks
AT zhangchaoyang predictingdnamethylationstateofcpgdinucleotideusinggenometopologicalfeaturesanddeepnetworks
AT moyinyuan predictingdnamethylationstateofcpgdinucleotideusinggenometopologicalfeaturesanddeepnetworks
AT wangzheng predictingdnamethylationstateofcpgdinucleotideusinggenometopologicalfeaturesanddeepnetworks