Accurate Single-Cell Clustering through Ensemble Similarity Learning

Single-cell sequencing provides novel means to interpret the transcriptomic profiles of individual cells. To obtain in-depth analysis of single-cell sequencing, it requires effective computational methods to accurately predict single-cell clusters because single-cell sequencing techniques only provi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyundoo Jeong, Sungtae Shin, Hong-Gi Yeom
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	single-cell RNA sequencing zero-inflated noise reduction ensemble similarity estimation correspondence network visualization and clustering imputation Genetics QH426-470
Acceso en línea:	https://doaj.org/article/81efa5a7ee3344549d181b43bcc5a857
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:81efa5a7ee3344549d181b43bcc5a857
record_format	dspace
spelling	oai:doaj.org-article:81efa5a7ee3344549d181b43bcc5a8572021-11-25T17:40:34ZAccurate Single-Cell Clustering through Ensemble Similarity Learning10.3390/genes121116702073-4425https://doaj.org/article/81efa5a7ee3344549d181b43bcc5a8572021-10-01T00:00:00Zhttps://www.mdpi.com/2073-4425/12/11/1670https://doaj.org/toc/2073-4425Single-cell sequencing provides novel means to interpret the transcriptomic profiles of individual cells. To obtain in-depth analysis of single-cell sequencing, it requires effective computational methods to accurately predict single-cell clusters because single-cell sequencing techniques only provide the transcriptomic profiles of each cell. Although an accurate estimation of the cell-to-cell similarity is an essential first step to derive reliable single-cell clustering results, it is challenging to obtain the accurate similarity measurement because it highly depends on a selection of genes for similarity evaluations and the optimal set of genes for the accurate similarity estimation is typically unknown. Moreover, due to technical limitations, single-cell sequencing includes a larger number of artificial zeros, and the technical noise makes it difficult to develop effective single-cell clustering algorithms. Here, we describe a novel single-cell clustering algorithm that can accurately predict single-cell clusters in large-scale single-cell sequencing by effectively reducing the zero-inflated noise and accurately estimating the cell-to-cell similarities. First, we construct an ensemble similarity network based on different similarity estimates, and reduce the artificial noise using a random walk with restart framework. Finally, starting from a larger number small size but highly consistent clusters, we iteratively merge a pair of clusters with the maximum similarities until it reaches the predicted number of clusters. Extensive performance evaluation shows that the proposed single-cell clustering algorithm can yield the accurate single-cell clustering results and it can help deciphering the key messages underlying complex biological mechanisms.Hyundoo JeongSungtae ShinHong-Gi YeomMDPI AGarticlesingle-cell RNA sequencingzero-inflated noise reductionensemble similarity estimationcorrespondence networkvisualization and clusteringimputationGeneticsQH426-470ENGenes, Vol 12, Iss 1670, p 1670 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	single-cell RNA sequencing zero-inflated noise reduction ensemble similarity estimation correspondence network visualization and clustering imputation Genetics QH426-470
spellingShingle	single-cell RNA sequencing zero-inflated noise reduction ensemble similarity estimation correspondence network visualization and clustering imputation Genetics QH426-470 Hyundoo Jeong Sungtae Shin Hong-Gi Yeom Accurate Single-Cell Clustering through Ensemble Similarity Learning
description	Single-cell sequencing provides novel means to interpret the transcriptomic profiles of individual cells. To obtain in-depth analysis of single-cell sequencing, it requires effective computational methods to accurately predict single-cell clusters because single-cell sequencing techniques only provide the transcriptomic profiles of each cell. Although an accurate estimation of the cell-to-cell similarity is an essential first step to derive reliable single-cell clustering results, it is challenging to obtain the accurate similarity measurement because it highly depends on a selection of genes for similarity evaluations and the optimal set of genes for the accurate similarity estimation is typically unknown. Moreover, due to technical limitations, single-cell sequencing includes a larger number of artificial zeros, and the technical noise makes it difficult to develop effective single-cell clustering algorithms. Here, we describe a novel single-cell clustering algorithm that can accurately predict single-cell clusters in large-scale single-cell sequencing by effectively reducing the zero-inflated noise and accurately estimating the cell-to-cell similarities. First, we construct an ensemble similarity network based on different similarity estimates, and reduce the artificial noise using a random walk with restart framework. Finally, starting from a larger number small size but highly consistent clusters, we iteratively merge a pair of clusters with the maximum similarities until it reaches the predicted number of clusters. Extensive performance evaluation shows that the proposed single-cell clustering algorithm can yield the accurate single-cell clustering results and it can help deciphering the key messages underlying complex biological mechanisms.
format	article
author	Hyundoo Jeong Sungtae Shin Hong-Gi Yeom
author_facet	Hyundoo Jeong Sungtae Shin Hong-Gi Yeom
author_sort	Hyundoo Jeong
title	Accurate Single-Cell Clustering through Ensemble Similarity Learning
title_short	Accurate Single-Cell Clustering through Ensemble Similarity Learning
title_full	Accurate Single-Cell Clustering through Ensemble Similarity Learning
title_fullStr	Accurate Single-Cell Clustering through Ensemble Similarity Learning
title_full_unstemmed	Accurate Single-Cell Clustering through Ensemble Similarity Learning
title_sort	accurate single-cell clustering through ensemble similarity learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/81efa5a7ee3344549d181b43bcc5a857
work_keys_str_mv	AT hyundoojeong accuratesinglecellclusteringthroughensemblesimilaritylearning AT sungtaeshin accuratesinglecellclusteringthroughensemblesimilaritylearning AT honggiyeom accuratesinglecellclusteringthroughensemblesimilaritylearning
_version_	1718412114397233152

Accurate Single-Cell Clustering through Ensemble Similarity Learning

Ejemplares similares