Unsupervised generative and graph representation learning for modelling cell differentiation

Abstract Using machine learning techniques to build representations from biomedical data can help us understand the latent biological mechanism of action and lead to important discoveries. Recent developments in single-cell RNA-sequencing protocols have allowed measuring gene expression for individu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ioana Bica, Helena Andrés-Terré, Ana Cvejic, Pietro Liò
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/dfe3326beb63483f91402dc5465d9cf2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dfe3326beb63483f91402dc5465d9cf2
record_format	dspace
spelling	oai:doaj.org-article:dfe3326beb63483f91402dc5465d9cf22021-12-02T17:40:46ZUnsupervised generative and graph representation learning for modelling cell differentiation10.1038/s41598-020-66166-82045-2322https://doaj.org/article/dfe3326beb63483f91402dc5465d9cf22020-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-66166-8https://doaj.org/toc/2045-2322Abstract Using machine learning techniques to build representations from biomedical data can help us understand the latent biological mechanism of action and lead to important discoveries. Recent developments in single-cell RNA-sequencing protocols have allowed measuring gene expression for individual cells in a population, thus opening up the possibility of finding answers to biomedical questions about cell differentiation. In this paper, we explore unsupervised generative neural methods, based on the variational autoencoder, that can model cell differentiation by building meaningful representations from the high dimensional and complex gene expression data. We use disentanglement methods based on information theory to improve the data representation and achieve better separation of the biological factors of variation in the gene expression data. In addition, we use a graph autoencoder consisting of graph convolutional layers to predict relationships between single-cells. Based on these models, we develop a computational framework that consists of methods for identifying the cell types in the dataset, finding driver genes for the differentiation process and obtaining a better understanding of relationships between cells. We illustrate our methods on datasets from multiple species and also from different sequencing technologies.Ioana BicaHelena Andrés-TerréAna CvejicPietro LiòNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-13 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ioana Bica Helena Andrés-Terré Ana Cvejic Pietro Liò Unsupervised generative and graph representation learning for modelling cell differentiation
description	Abstract Using machine learning techniques to build representations from biomedical data can help us understand the latent biological mechanism of action and lead to important discoveries. Recent developments in single-cell RNA-sequencing protocols have allowed measuring gene expression for individual cells in a population, thus opening up the possibility of finding answers to biomedical questions about cell differentiation. In this paper, we explore unsupervised generative neural methods, based on the variational autoencoder, that can model cell differentiation by building meaningful representations from the high dimensional and complex gene expression data. We use disentanglement methods based on information theory to improve the data representation and achieve better separation of the biological factors of variation in the gene expression data. In addition, we use a graph autoencoder consisting of graph convolutional layers to predict relationships between single-cells. Based on these models, we develop a computational framework that consists of methods for identifying the cell types in the dataset, finding driver genes for the differentiation process and obtaining a better understanding of relationships between cells. We illustrate our methods on datasets from multiple species and also from different sequencing technologies.
format	article
author	Ioana Bica Helena Andrés-Terré Ana Cvejic Pietro Liò
author_facet	Ioana Bica Helena Andrés-Terré Ana Cvejic Pietro Liò
author_sort	Ioana Bica
title	Unsupervised generative and graph representation learning for modelling cell differentiation
title_short	Unsupervised generative and graph representation learning for modelling cell differentiation
title_full	Unsupervised generative and graph representation learning for modelling cell differentiation
title_fullStr	Unsupervised generative and graph representation learning for modelling cell differentiation
title_full_unstemmed	Unsupervised generative and graph representation learning for modelling cell differentiation
title_sort	unsupervised generative and graph representation learning for modelling cell differentiation
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/dfe3326beb63483f91402dc5465d9cf2
work_keys_str_mv	AT ioanabica unsupervisedgenerativeandgraphrepresentationlearningformodellingcelldifferentiation AT helenaandresterre unsupervisedgenerativeandgraphrepresentationlearningformodellingcelldifferentiation AT anacvejic unsupervisedgenerativeandgraphrepresentationlearningformodellingcelldifferentiation AT pietrolio unsupervisedgenerativeandgraphrepresentationlearningformodellingcelldifferentiation
_version_	1718379796082196480

Unsupervised generative and graph representation learning for modelling cell differentiation

Ejemplares similares