Self-supervised contrastive learning for integrative single cell RNA-seq data analysis

Abstract
We present a novel self-supervised Contrastive LEArning framework for single-cell ribonucleic acid (RNA)-sequencing (CLEAR) data representation and the downstream analysis. Compared with current methods, CLEAR overcomes the heterogeneity of the experimental data with a specifically designed representation learning task and thus can handle batch effects and dropout events simultaneously. It achieves superior performance on a broad range of fundamental tasks, including clustering, visualization, dropout correction, batch effect removal, and pseudo-time inference. The proposed method successfully identifies and illustrates inflammatory-related mechanisms in a COVID-19 disease study with 43 695 single cells from peripheral blood mononuclear cells.

Citation
Han, W., Cheng, Y., Chen, J., Zhong, H., Hu, Z., Chen, S., Zong, L., Hong, L., Chan, T.-F., King, I., Gao, X., & Li, Y. (2022). Self-supervised contrastive learning for integrative single cell RNA-seq data analysis. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbac377

Acknowledgements
We are thankful to all members of the SFB group for kind discussions. King Abdullah University of Science and Technology FCC/1/1976-44-01, FCC/1/1976-45-01, REI/1/4742-01-01, REI/1/5202-01-01, and REI/1/4940-01-01; Chinese University of Hong Kong (4937025, 4937026, 5501517 and 5501329).

Publisher
Oxford University Press (OUP)

Journal
Briefings in Bioinformatics

DOI
10.1093/bib/bbac377

Additional Links
https://academic.oup.com/bib/advance-article/doi/10.1093/bib/bbac377/6695268

Relations
Is Supplemented By:
  • [Software]
    Title: ml4bio/CLEAR: CLEAR: Self-supervised contrastive learning for integrative single-cell RNA-seq data analysis. Publication Date: 2021-06-27. github: ml4bio/CLEAR Handle: 10754/681610

Permanent link to this record