Cargando…
GraphCpG: imputation of single-cell methylomes based on locus-aware neighboring subgraphs
MOTIVATION: Single-cell DNA methylation sequencing can assay DNA methylation at single-cell resolution. However, incomplete coverage compromises related downstream analyses, outlining the importance of imputation techniques. With a rising number of cell samples in recent large datasets, scalable and...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10516632/ https://www.ncbi.nlm.nih.gov/pubmed/37647650 http://dx.doi.org/10.1093/bioinformatics/btad533 |
_version_ | 1785109167341568000 |
---|---|
author | Deng, Yuzhong Tang, Jianxiong Zhang, Jiyang Zou, Jianxiao Zhu, Que Fan, Shicai |
author_facet | Deng, Yuzhong Tang, Jianxiong Zhang, Jiyang Zou, Jianxiao Zhu, Que Fan, Shicai |
author_sort | Deng, Yuzhong |
collection | PubMed |
description | MOTIVATION: Single-cell DNA methylation sequencing can assay DNA methylation at single-cell resolution. However, incomplete coverage compromises related downstream analyses, outlining the importance of imputation techniques. With a rising number of cell samples in recent large datasets, scalable and efficient imputation models are critical to addressing the sparsity for genome-wide analyses. RESULTS: We proposed a novel graph-based deep learning approach to impute methylation matrices based on locus-aware neighboring subgraphs with locus-aware encoding orienting on one cell type. Merely using the CpGs methylation matrix, the obtained GraphCpG outperforms previous methods on datasets containing more than hundreds of cells and achieves competitive performance on smaller datasets, with subgraphs of predicted sites visualized by retrievable bipartite graphs. Besides better imputation performance with increasing cell number, it significantly reduces computation time and demonstrates improvement in downstream analysis. AVAILABILITY AND IMPLEMENTATION: The source code is freely available at https://github.com/yuzhong-deng/graphcpg.git. |
format | Online Article Text |
id | pubmed-10516632 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-105166322023-09-23 GraphCpG: imputation of single-cell methylomes based on locus-aware neighboring subgraphs Deng, Yuzhong Tang, Jianxiong Zhang, Jiyang Zou, Jianxiao Zhu, Que Fan, Shicai Bioinformatics Original Paper MOTIVATION: Single-cell DNA methylation sequencing can assay DNA methylation at single-cell resolution. However, incomplete coverage compromises related downstream analyses, outlining the importance of imputation techniques. With a rising number of cell samples in recent large datasets, scalable and efficient imputation models are critical to addressing the sparsity for genome-wide analyses. RESULTS: We proposed a novel graph-based deep learning approach to impute methylation matrices based on locus-aware neighboring subgraphs with locus-aware encoding orienting on one cell type. Merely using the CpGs methylation matrix, the obtained GraphCpG outperforms previous methods on datasets containing more than hundreds of cells and achieves competitive performance on smaller datasets, with subgraphs of predicted sites visualized by retrievable bipartite graphs. Besides better imputation performance with increasing cell number, it significantly reduces computation time and demonstrates improvement in downstream analysis. AVAILABILITY AND IMPLEMENTATION: The source code is freely available at https://github.com/yuzhong-deng/graphcpg.git. Oxford University Press 2023-08-30 /pmc/articles/PMC10516632/ /pubmed/37647650 http://dx.doi.org/10.1093/bioinformatics/btad533 Text en © The Author(s) 2023. 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 (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 | Original Paper Deng, Yuzhong Tang, Jianxiong Zhang, Jiyang Zou, Jianxiao Zhu, Que Fan, Shicai GraphCpG: imputation of single-cell methylomes based on locus-aware neighboring subgraphs |
title | GraphCpG: imputation of single-cell methylomes based on locus-aware neighboring subgraphs |
title_full | GraphCpG: imputation of single-cell methylomes based on locus-aware neighboring subgraphs |
title_fullStr | GraphCpG: imputation of single-cell methylomes based on locus-aware neighboring subgraphs |
title_full_unstemmed | GraphCpG: imputation of single-cell methylomes based on locus-aware neighboring subgraphs |
title_short | GraphCpG: imputation of single-cell methylomes based on locus-aware neighboring subgraphs |
title_sort | graphcpg: imputation of single-cell methylomes based on locus-aware neighboring subgraphs |
topic | Original Paper |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10516632/ https://www.ncbi.nlm.nih.gov/pubmed/37647650 http://dx.doi.org/10.1093/bioinformatics/btad533 |
work_keys_str_mv | AT dengyuzhong graphcpgimputationofsinglecellmethylomesbasedonlocusawareneighboringsubgraphs AT tangjianxiong graphcpgimputationofsinglecellmethylomesbasedonlocusawareneighboringsubgraphs AT zhangjiyang graphcpgimputationofsinglecellmethylomesbasedonlocusawareneighboringsubgraphs AT zoujianxiao graphcpgimputationofsinglecellmethylomesbasedonlocusawareneighboringsubgraphs AT zhuque graphcpgimputationofsinglecellmethylomesbasedonlocusawareneighboringsubgraphs AT fanshicai graphcpgimputationofsinglecellmethylomesbasedonlocusawareneighboringsubgraphs |