Cargando…

D-GPM: A Deep Learning Method for Gene Promoter Methylation Inference

Whole-genome bisulfite sequencing generates a comprehensive profiling of the gene methylation levels, but is limited by a high cost. Recent studies have partitioned the genes into landmark genes and target genes and suggested that the landmark gene expression levels capture adequate information to r...

Descripción completa

Detalles Bibliográficos
Autores principales: Pan, Xingxin, Liu, Biao, Wen, Xingzhao, Liu, Yulu, Zhang, Xiuqing, Li, Shengbin, Li, Shuaicheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826513/
https://www.ncbi.nlm.nih.gov/pubmed/31615113
http://dx.doi.org/10.3390/genes10100807
_version_ 1783465106623954944
author Pan, Xingxin
Liu, Biao
Wen, Xingzhao
Liu, Yulu
Zhang, Xiuqing
Li, Shengbin
Li, Shuaicheng
author_facet Pan, Xingxin
Liu, Biao
Wen, Xingzhao
Liu, Yulu
Zhang, Xiuqing
Li, Shengbin
Li, Shuaicheng
author_sort Pan, Xingxin
collection PubMed
description Whole-genome bisulfite sequencing generates a comprehensive profiling of the gene methylation levels, but is limited by a high cost. Recent studies have partitioned the genes into landmark genes and target genes and suggested that the landmark gene expression levels capture adequate information to reconstruct the target gene expression levels. This inspired us to propose that the methylation level of the promoters in landmark genes might be adequate to reconstruct the promoter methylation level of target genes, which would eventually reduce the cost of promoter methylation profiling. Here, we propose a deep learning model called Deep-Gene Promoter Methylation (D-GPM) to predict the whole-genome promoter methylation level based on the promoter methylation profile of the landmark genes from The Cancer Genome Atlas (TCGA). D-GPM-15%-7000 × 5, the optimal architecture of D-GPM, acquires the least overall mean absolute error (MAE) and the highest overall Pearson correlation coefficient (PCC), with values of 0.0329 and 0.8186, respectively, when testing data. Additionally, the D-GPM outperforms the regression tree (RT), linear regression (LR), and the support vector machine (SVM) in 95.66%, 92.65%, and 85.49% of the target genes by virtue of its relatively lower MAE and in 98.25%, 91.00%, and 81.56% of the target genes based on its relatively higher PCC, respectively. More importantly, the D-GPM predominates in predicting 79.86% and 78.34% of the target genes according to the model distribution of the least MAE and the highest PCC, respectively.
format Online
Article
Text
id pubmed-6826513
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-68265132019-11-18 D-GPM: A Deep Learning Method for Gene Promoter Methylation Inference Pan, Xingxin Liu, Biao Wen, Xingzhao Liu, Yulu Zhang, Xiuqing Li, Shengbin Li, Shuaicheng Genes (Basel) Article Whole-genome bisulfite sequencing generates a comprehensive profiling of the gene methylation levels, but is limited by a high cost. Recent studies have partitioned the genes into landmark genes and target genes and suggested that the landmark gene expression levels capture adequate information to reconstruct the target gene expression levels. This inspired us to propose that the methylation level of the promoters in landmark genes might be adequate to reconstruct the promoter methylation level of target genes, which would eventually reduce the cost of promoter methylation profiling. Here, we propose a deep learning model called Deep-Gene Promoter Methylation (D-GPM) to predict the whole-genome promoter methylation level based on the promoter methylation profile of the landmark genes from The Cancer Genome Atlas (TCGA). D-GPM-15%-7000 × 5, the optimal architecture of D-GPM, acquires the least overall mean absolute error (MAE) and the highest overall Pearson correlation coefficient (PCC), with values of 0.0329 and 0.8186, respectively, when testing data. Additionally, the D-GPM outperforms the regression tree (RT), linear regression (LR), and the support vector machine (SVM) in 95.66%, 92.65%, and 85.49% of the target genes by virtue of its relatively lower MAE and in 98.25%, 91.00%, and 81.56% of the target genes based on its relatively higher PCC, respectively. More importantly, the D-GPM predominates in predicting 79.86% and 78.34% of the target genes according to the model distribution of the least MAE and the highest PCC, respectively. MDPI 2019-10-14 /pmc/articles/PMC6826513/ /pubmed/31615113 http://dx.doi.org/10.3390/genes10100807 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Pan, Xingxin
Liu, Biao
Wen, Xingzhao
Liu, Yulu
Zhang, Xiuqing
Li, Shengbin
Li, Shuaicheng
D-GPM: A Deep Learning Method for Gene Promoter Methylation Inference
title D-GPM: A Deep Learning Method for Gene Promoter Methylation Inference
title_full D-GPM: A Deep Learning Method for Gene Promoter Methylation Inference
title_fullStr D-GPM: A Deep Learning Method for Gene Promoter Methylation Inference
title_full_unstemmed D-GPM: A Deep Learning Method for Gene Promoter Methylation Inference
title_short D-GPM: A Deep Learning Method for Gene Promoter Methylation Inference
title_sort d-gpm: a deep learning method for gene promoter methylation inference
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6826513/
https://www.ncbi.nlm.nih.gov/pubmed/31615113
http://dx.doi.org/10.3390/genes10100807
work_keys_str_mv AT panxingxin dgpmadeeplearningmethodforgenepromotermethylationinference
AT liubiao dgpmadeeplearningmethodforgenepromotermethylationinference
AT wenxingzhao dgpmadeeplearningmethodforgenepromotermethylationinference
AT liuyulu dgpmadeeplearningmethodforgenepromotermethylationinference
AT zhangxiuqing dgpmadeeplearningmethodforgenepromotermethylationinference
AT lishengbin dgpmadeeplearningmethodforgenepromotermethylationinference
AT lishuaicheng dgpmadeeplearningmethodforgenepromotermethylationinference