EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

scRSSL: Residual semi‐supervised learning with deep generative models to automatically identify cell types

Yanru Gao, Hongyu Duan, Fanhao Meng, Conghui Zhang, Xiyue Li, Feng Li iD

IET Systems Biology · 2025

DOI: 10.1049/syb2.12107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Systems Biology, 2025. Verfasst von Yanru Gao und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Qufu Normal University, Rizhao, China. Hauptthemen laut MEDLINE: Single-Cell Analysis, Supervised Machine Learning, Deep Learning, Computational Biology. Die Arbeit nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: the Natural Science Foundation of Rizhao, the National Natural Science Foundation of China, the Youth Foundation of Shandong Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single‐cell sequencing (scRNA‐seq) allows researchers to study cellular heterogeneity in individual cells. In single‐cell transcriptomics analysis, identifying the cell type of individual cells is a key task. At present, single‐cell datasets often face the challenges of high dimensionality, large number of samples, high sparsity and sample imbalance. The traditional methods of cell type recognition have been challenged. The authors propose a deep residual generation model based on semi‐supervised learning (scRSSL) to address these challenges. ScRSSL creatively introduces residual networks into semi‐supervised generative models. The authors take advantage of its semi‐supervised learning to solve the problem of sample imbalance. During the training of the model, the authors use a residual neural network to accomplish the inference of cell types so that local features of single‐cell data can be extracted. Because of the semi‐supervised learning approach, it can automatically and accurately predict individual cell types in datasets, even with only a small number of cell labels. Experimentally, the authors’ method has proven to have better performance compared to other methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisSupervised Machine LearningDeep LearningComputational BiologyNeural Networks, ComputerHumans

Stichwörter der Autor:innen

bioinformaticsdeep generative modeldeep learningsemi‐supervised learningsingle cell

Autor:innen und Institutionen

  • School of Computer Science, Qufu Normal University, Rizhao, China.
  • Department of Statistics and Financial Mathematics, School of Mathematics, South China University of Technology, Guangzhou, China.

ORCID-Profile: Feng Li

Förderung

  • the Natural Science Foundation of Rizhao
  • the National Natural Science Foundation of China
  • the Youth Foundation of Shandong Natural Science Foundation of China

Zitieren

APA

Gao, Y., Duan, H., Meng, F., Zhang, C., Li, X., & Li, F. (2025). scRSSL: Residual semi‐supervised learning with deep generative models to automatically identify cell types. IET Systems Biology. https://doi.org/10.1049/syb2.12107

Vancouver

Gao Y, Duan H, Meng F, Zhang C, Li X, Li F. scRSSL: Residual semi‐supervised learning with deep generative models to automatically identify cell types. IET Systems Biology. 2025. doi:10.1049/syb2.12107

BibTeX
@article{Gao2025,
  author = {Gao, Yanru and Duan, Hongyu and Meng, Fanhao and Zhang, Conghui and Li, Xiyue and Li, Feng},
  title = {scRSSL: Residual semi‐supervised learning with deep generative models to automatically identify cell types},
  journal = {IET Systems Biology},
  year = {2025},
  doi = {10.1049/syb2.12107}
}
Kostenlos starten →