EUVIMEDEUVIMED entdecken
Crossref

ScCCL: Single-Cell Data Clustering Based on Self-Supervised Contrastive Learning

Linlin Du, Rui Han, Bo Liu, Yadong Wang, Junyi Li

IEEE/ACM Transactions on Computational Biology and Bioinformatics · 01.05.2023 · 20 (3) · 2233-2241

DOI: 10.1109/tcbb.2023.3241129 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE/ACM Transactions on Computational Biology and Bioinformatics, erschienen am 01.05.2023. Verfasst von Linlin Du und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Gene Expression Profiling, Algorithms. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Key R&D Program of China, Shenzhen Science and Technology University Stable Support Program, Shenzhen Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The growing maturity of single-cell RNA-sequencing (scRNA-seq) technology allows us to explore the heterogeneity of tissues, organisms, and complex diseases at cellular level. In single-cell data analysis, clustering calculation is very important. However, the high dimensionality of scRNA-seq data, the ever-increasing number of cells, and the unavoidable technical noise bring great challenges to clustering calculations. Motivated by the good performance of contrastive learning in multiple domains, we propose ScCCL, a novel self-supervised contrastive learning method for clustering of scRNA-seq data. ScCCL first randomly masks the gene expression of each cell twice and adds a small amount of Gaussian noise, and then uses the momentum encoder structure to extract features from the enhanced data. Contrastive learning is then applied in the instance-level contrastive learning module and the cluster-level contrastive learning module, respectively. After training, a representation model that can efficiently extract high-order embeddings of single cells is obtained. We selected two evaluation metrics, ARI and NMI, to conduct experiments on multiple public datasets. The results show that ScCCL improves the clustering effect compared with the benchmark algorithms. Notably, since ScCCL does not depend on a specific type of data, it can also be helpful in clustering analysis of single-cell multi-omics data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene Expression ProfilingAlgorithmsSequence Analysis, RNACluster AnalysisSingle-Cell Analysis

Förderung

  • National Key R&D Program of China
  • Shenzhen Science and Technology University Stable Support Program
  • Shenzhen Science and Technology Program
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies

Zitieren

APA

Du, L., Han, R., Liu, B., Wang, Y., & Li, J. (2023). ScCCL: Single-Cell Data Clustering Based on Self-Supervised Contrastive Learning. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 20(3), 2233-2241. https://doi.org/10.1109/tcbb.2023.3241129

Vancouver

Du L, Han R, Liu B, Wang Y, Li J. ScCCL: Single-Cell Data Clustering Based on Self-Supervised Contrastive Learning. IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2023;20(3):2233-2241. doi:10.1109/tcbb.2023.3241129

BibTeX
@article{Du2023,
  author = {Du, Linlin and Han, Rui and Liu, Bo and Wang, Yadong and Li, Junyi},
  title = {ScCCL: Single-Cell Data Clustering Based on Self-Supervised Contrastive Learning},
  journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},
  year = {2023},
  volume = {20},
  number = {3},
  pages = {2233--2241},
  doi = {10.1109/tcbb.2023.3241129}
}
Kostenlos starten →