Cargando…
Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome
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 i...
Autores principales: | , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8529514/ https://www.ncbi.nlm.nih.gov/pubmed/34712916 http://dx.doi.org/10.1016/j.isci.2021.103200 |
_version_ | 1784586486942793728 |
---|---|
author | Shen, Hongru Li, Yang Feng, Mengyao Shen, Xilin Wu, Dan Zhang, Chao Yang, Yichen Yang, Meng Hu, Jiani Liu, Jilei Wang, Wei Zhang, Qiang Song, Fangfang Yang, Jilong Chen, Kexin Li, Xiangchun |
author_facet | Shen, Hongru Li, Yang Feng, Mengyao Shen, Xilin Wu, Dan Zhang, Chao Yang, Yichen Yang, Meng Hu, Jiani Liu, Jilei Wang, Wei Zhang, Qiang Song, Fangfang Yang, Jilong Chen, Kexin Li, Xiangchun |
author_sort | Shen, Hongru |
collection | PubMed |
description | 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 | Online Article Text |
id | pubmed-8529514 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-85295142021-10-27 Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome Shen, Hongru Li, Yang Feng, Mengyao Shen, Xilin Wu, Dan Zhang, Chao Yang, Yichen Yang, Meng Hu, Jiani Liu, Jilei Wang, Wei Zhang, Qiang Song, Fangfang Yang, Jilong Chen, Kexin Li, Xiangchun iScience Article 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. Elsevier 2021-10-02 /pmc/articles/PMC8529514/ /pubmed/34712916 http://dx.doi.org/10.1016/j.isci.2021.103200 Text en © 2021 The Authors https://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 | Article Shen, Hongru Li, Yang Feng, Mengyao Shen, Xilin Wu, Dan Zhang, Chao Yang, Yichen Yang, Meng Hu, Jiani Liu, Jilei Wang, Wei Zhang, Qiang Song, Fangfang Yang, Jilong Chen, Kexin Li, Xiangchun Miscell: An efficient self-supervised learning approach for dissecting single-cell transcriptome |
title | 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_short | 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 |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8529514/ https://www.ncbi.nlm.nih.gov/pubmed/34712916 http://dx.doi.org/10.1016/j.isci.2021.103200 |
work_keys_str_mv | AT shenhongru miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT liyang miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT fengmengyao miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT shenxilin miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT wudan miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT zhangchao miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT yangyichen miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT yangmeng miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT hujiani miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT liujilei miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT wangwei miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT zhangqiang miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT songfangfang miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT yangjilong miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT chenkexin miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome AT lixiangchun miscellanefficientselfsupervisedlearningapproachfordissectingsinglecelltranscriptome |