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

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.

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.

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).

Oxford University Press (OUP)

Briefings in Bioinformatics


Additional Links

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