Cargando…

Joint learning of multiple gene networks from single-cell gene expression data

Inferring gene networks from gene expression data is important for understanding functional organizations within cells. With the accumulation of single-cell RNA sequencing (scRNA-seq) data, it is possible to infer gene networks at single cell level. However, due to the characteristics of scRNA-seq d...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Nuosi, Yin, Fu, Ou-Yang, Le, Zhu, Zexuan, Xie, Weixin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Research Network of Computational and Structural Biotechnology 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7527714/
https://www.ncbi.nlm.nih.gov/pubmed/33033579
http://dx.doi.org/10.1016/j.csbj.2020.09.004
_version_ 1783589115577499648
author Wu, Nuosi
Yin, Fu
Ou-Yang, Le
Zhu, Zexuan
Xie, Weixin
author_facet Wu, Nuosi
Yin, Fu
Ou-Yang, Le
Zhu, Zexuan
Xie, Weixin
author_sort Wu, Nuosi
collection PubMed
description Inferring gene networks from gene expression data is important for understanding functional organizations within cells. With the accumulation of single-cell RNA sequencing (scRNA-seq) data, it is possible to infer gene networks at single cell level. However, due to the characteristics of scRNA-seq data, such as cellular heterogeneity and high sparsity caused by dropout events, traditional network inference methods may not be suitable for scRNA-seq data. In this study, we introduce a novel joint Gaussian copula graphical model (JGCGM) to jointly estimate multiple gene networks for multiple cell subgroups from scRNA-seq data. Our model can deal with non-Gaussian data with missing values, and identify the common and unique network structures of multiple cell subgroups, which is suitable for scRNA-seq data. Extensive experiments on synthetic data demonstrate that our proposed model outperforms other compared state-of-the-art network inference models. We apply our model to real scRNA-seq data sets to infer gene networks of different cell subgroups. Hub genes in the estimated gene networks are found to be biological significance.
format Online
Article
Text
id pubmed-7527714
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Research Network of Computational and Structural Biotechnology
record_format MEDLINE/PubMed
spelling pubmed-75277142020-10-07 Joint learning of multiple gene networks from single-cell gene expression data Wu, Nuosi Yin, Fu Ou-Yang, Le Zhu, Zexuan Xie, Weixin Comput Struct Biotechnol J Research Article Inferring gene networks from gene expression data is important for understanding functional organizations within cells. With the accumulation of single-cell RNA sequencing (scRNA-seq) data, it is possible to infer gene networks at single cell level. However, due to the characteristics of scRNA-seq data, such as cellular heterogeneity and high sparsity caused by dropout events, traditional network inference methods may not be suitable for scRNA-seq data. In this study, we introduce a novel joint Gaussian copula graphical model (JGCGM) to jointly estimate multiple gene networks for multiple cell subgroups from scRNA-seq data. Our model can deal with non-Gaussian data with missing values, and identify the common and unique network structures of multiple cell subgroups, which is suitable for scRNA-seq data. Extensive experiments on synthetic data demonstrate that our proposed model outperforms other compared state-of-the-art network inference models. We apply our model to real scRNA-seq data sets to infer gene networks of different cell subgroups. Hub genes in the estimated gene networks are found to be biological significance. Research Network of Computational and Structural Biotechnology 2020-09-10 /pmc/articles/PMC7527714/ /pubmed/33033579 http://dx.doi.org/10.1016/j.csbj.2020.09.004 Text en © 2020 The Author(s) http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Research Article
Wu, Nuosi
Yin, Fu
Ou-Yang, Le
Zhu, Zexuan
Xie, Weixin
Joint learning of multiple gene networks from single-cell gene expression data
title Joint learning of multiple gene networks from single-cell gene expression data
title_full Joint learning of multiple gene networks from single-cell gene expression data
title_fullStr Joint learning of multiple gene networks from single-cell gene expression data
title_full_unstemmed Joint learning of multiple gene networks from single-cell gene expression data
title_short Joint learning of multiple gene networks from single-cell gene expression data
title_sort joint learning of multiple gene networks from single-cell gene expression data
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7527714/
https://www.ncbi.nlm.nih.gov/pubmed/33033579
http://dx.doi.org/10.1016/j.csbj.2020.09.004
work_keys_str_mv AT wunuosi jointlearningofmultiplegenenetworksfromsinglecellgeneexpressiondata
AT yinfu jointlearningofmultiplegenenetworksfromsinglecellgeneexpressiondata
AT ouyangle jointlearningofmultiplegenenetworksfromsinglecellgeneexpressiondata
AT zhuzexuan jointlearningofmultiplegenenetworksfromsinglecellgeneexpressiondata
AT xieweixin jointlearningofmultiplegenenetworksfromsinglecellgeneexpressiondata