Hybrid Clustering of Single-Cell Gene Expression and Spatial Information via Integrated NMF and K-Means

Advances in single cell transcriptomics have allowed us to study the identity of single cells. This has led to the discovery of new cell types and high resolution tissue maps of them. Technologies that measure multiple modalities of such data add more detail, but they also complicate data integratio...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Sooyoun Oh, Haesun Park, Xiuwei Zhang
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/5d7ec78a9dea4e1db4d2afb01d8c0e67
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5d7ec78a9dea4e1db4d2afb01d8c0e67
record_format dspace
spelling oai:doaj.org-article:5d7ec78a9dea4e1db4d2afb01d8c0e672021-11-08T06:17:24ZHybrid Clustering of Single-Cell Gene Expression and Spatial Information via Integrated NMF and K-Means1664-802110.3389/fgene.2021.763263https://doaj.org/article/5d7ec78a9dea4e1db4d2afb01d8c0e672021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fgene.2021.763263/fullhttps://doaj.org/toc/1664-8021Advances in single cell transcriptomics have allowed us to study the identity of single cells. This has led to the discovery of new cell types and high resolution tissue maps of them. Technologies that measure multiple modalities of such data add more detail, but they also complicate data integration. We offer an integrated analysis of the spatial location and gene expression profiles of cells to determine their identity. We propose scHybridNMF (single-cell Hybrid Nonnegative Matrix Factorization), which performs cell type identification by combining sparse nonnegative matrix factorization (sparse NMF) with k-means clustering to cluster high-dimensional gene expression and low-dimensional location data. We show that, under multiple scenarios, including the cases where there is a small number of genes profiled and the location data is noisy, scHybridNMF outperforms sparse NMF, k-means, and an existing method that uses a hidden Markov random field to encode cell location and gene expression data for cell type identification.Sooyoun OhHaesun ParkXiuwei ZhangFrontiers Media S.A.articlesingle cell transcriptomicsspatial locationscell identitynon-negative matrix factorizationdata integrationGeneticsQH426-470ENFrontiers in Genetics, Vol 12 (2021)
institution DOAJ
collection DOAJ
language EN
topic single cell transcriptomics
spatial locations
cell identity
non-negative matrix factorization
data integration
Genetics
QH426-470
spellingShingle single cell transcriptomics
spatial locations
cell identity
non-negative matrix factorization
data integration
Genetics
QH426-470
Sooyoun Oh
Haesun Park
Xiuwei Zhang
Hybrid Clustering of Single-Cell Gene Expression and Spatial Information via Integrated NMF and K-Means
description Advances in single cell transcriptomics have allowed us to study the identity of single cells. This has led to the discovery of new cell types and high resolution tissue maps of them. Technologies that measure multiple modalities of such data add more detail, but they also complicate data integration. We offer an integrated analysis of the spatial location and gene expression profiles of cells to determine their identity. We propose scHybridNMF (single-cell Hybrid Nonnegative Matrix Factorization), which performs cell type identification by combining sparse nonnegative matrix factorization (sparse NMF) with k-means clustering to cluster high-dimensional gene expression and low-dimensional location data. We show that, under multiple scenarios, including the cases where there is a small number of genes profiled and the location data is noisy, scHybridNMF outperforms sparse NMF, k-means, and an existing method that uses a hidden Markov random field to encode cell location and gene expression data for cell type identification.
format article
author Sooyoun Oh
Haesun Park
Xiuwei Zhang
author_facet Sooyoun Oh
Haesun Park
Xiuwei Zhang
author_sort Sooyoun Oh
title Hybrid Clustering of Single-Cell Gene Expression and Spatial Information via Integrated NMF and K-Means
title_short Hybrid Clustering of Single-Cell Gene Expression and Spatial Information via Integrated NMF and K-Means
title_full Hybrid Clustering of Single-Cell Gene Expression and Spatial Information via Integrated NMF and K-Means
title_fullStr Hybrid Clustering of Single-Cell Gene Expression and Spatial Information via Integrated NMF and K-Means
title_full_unstemmed Hybrid Clustering of Single-Cell Gene Expression and Spatial Information via Integrated NMF and K-Means
title_sort hybrid clustering of single-cell gene expression and spatial information via integrated nmf and k-means
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/5d7ec78a9dea4e1db4d2afb01d8c0e67
work_keys_str_mv AT sooyounoh hybridclusteringofsinglecellgeneexpressionandspatialinformationviaintegratednmfandkmeans
AT haesunpark hybridclusteringofsinglecellgeneexpressionandspatialinformationviaintegratednmfandkmeans
AT xiuweizhang hybridclusteringofsinglecellgeneexpressionandspatialinformationviaintegratednmfandkmeans
_version_ 1718442912196329472