Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome

Summary: We developed Miscell, a self-supervised learning approach with deep neural network as latent feature encoder for mining information from single-cell transcriptomes. We demonstrated the capability of Miscell with canonical single-cell analysis tasks including delineation of single-cell clust...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hongru Shen, Yang Li, Mengyao Feng, Xilin Shen, Dan Wu, Chao Zhang, Yichen Yang, Meng Yang, Jiani Hu, Jilei Liu, Wei Wang, Qiang Zhang, Fangfang Song, Jilong Yang, Kexin Chen, Xiangchun Li
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Biological sciences Neural networks Transcriptomics Science Q
Acceso en línea:	https://doaj.org/article/ae5873effb654cd6beaee306458de941
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ae5873effb654cd6beaee306458de941
record_format	dspace
spelling	oai:doaj.org-article:ae5873effb654cd6beaee306458de9412021-11-20T05:08:18ZMiscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome2589-004210.1016/j.isci.2021.103200https://doaj.org/article/ae5873effb654cd6beaee306458de9412021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2589004221011688https://doaj.org/toc/2589-0042Summary: We developed Miscell, a self-supervised learning approach with deep neural network as latent feature encoder for mining information from single-cell transcriptomes. We demonstrated the capability of Miscell with canonical single-cell analysis tasks including delineation of single-cell clusters and identification of cluster-specific marker genes. We evaluated Miscell along with three state-of-the-art methods on three heterogeneous datasets. Miscell achieved at least comparable or better performance than the other methods by significant margin on a variety of clustering metrics such as adjusted rand index, normalized mutual information, and V-measure score. Miscell can identify cell-type specific markers by quantifying the influence of genes on cell clusters via deep learning approach.Hongru ShenYang LiMengyao FengXilin ShenDan WuChao ZhangYichen YangMeng YangJiani HuJilei LiuWei WangQiang ZhangFangfang SongJilong YangKexin ChenXiangchun LiElsevierarticleBiological sciencesNeural networksTranscriptomicsScienceQENiScience, Vol 24, Iss 11, Pp 103200- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biological sciences Neural networks Transcriptomics Science Q
spellingShingle	Biological sciences Neural networks Transcriptomics Science Q Hongru Shen Yang Li Mengyao Feng Xilin Shen Dan Wu Chao Zhang Yichen Yang Meng Yang Jiani Hu Jilei Liu Wei Wang Qiang Zhang Fangfang Song Jilong Yang Kexin Chen Xiangchun Li Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome
description	Summary: We developed Miscell, a self-supervised learning approach with deep neural network as latent feature encoder for mining information from single-cell transcriptomes. We demonstrated the capability of Miscell with canonical single-cell analysis tasks including delineation of single-cell clusters and identification of cluster-specific marker genes. We evaluated Miscell along with three state-of-the-art methods on three heterogeneous datasets. Miscell achieved at least comparable or better performance than the other methods by significant margin on a variety of clustering metrics such as adjusted rand index, normalized mutual information, and V-measure score. Miscell can identify cell-type specific markers by quantifying the influence of genes on cell clusters via deep learning approach.
format	article
author	Hongru Shen Yang Li Mengyao Feng Xilin Shen Dan Wu Chao Zhang Yichen Yang Meng Yang Jiani Hu Jilei Liu Wei Wang Qiang Zhang Fangfang Song Jilong Yang Kexin Chen Xiangchun Li
author_facet	Hongru Shen Yang Li Mengyao Feng Xilin Shen Dan Wu Chao Zhang Yichen Yang Meng Yang Jiani Hu Jilei Liu Wei Wang Qiang Zhang Fangfang Song Jilong Yang Kexin Chen Xiangchun Li
author_sort	Hongru Shen
title	Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome
title_short	Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome
title_full	Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome
title_fullStr	Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome
title_full_unstemmed	Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome
title_sort	miscell: an efficient self-supervised learning approach for dissecting single-cell transcriptome
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/ae5873effb654cd6beaee306458de941
work_keys_str_mv	AT hongrushen miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT yangli miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT mengyaofeng miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT xilinshen miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT danwu miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT chaozhang miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT yichenyang miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT mengyang miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT jianihu miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT jileiliu miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT weiwang miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT qiangzhang miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT fangfangsong miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT jilongyang miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT kexinchen miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT xiangchunli miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome
_version_	1718419561124986880

Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome

Ejemplares similares