A hybrid neighborhood enhanced contrastive learning and self-knowledge distillation method for scRNA-seq data clustering analysis
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag084 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Lihua Qi und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Xinjiang University, Urumqi, 830046, China. Hauptthemen laut MEDLINE: Single-Cell Analysis, RNA-Seq, Machine Learning, Computational Biology. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xinjiang Uygur Autonomous Region Key R & D program.
Abstract (Originalsprache)
Motivation Single-cell heterogeneity analysis faces significant challenges due to the high dimensionality, complexity, and noise inherent in scRNA-seq data, especially when aiming for precise cell type classification. Existing analytical methods often exhibit limited generalization ability and adaptability across different biological contexts, leading to biased identification of cell subpopulations and hindering a comprehensive understanding of diseases, therapeutic responses, and biological processes. Results To address these issues, we propose a novel method named scKD, which integrates a hybrid neighbourhood-enhanced comparative learning model with a self-knowledge distillation strategy. scKD enhances clustering accuracy and is capable of accurately identifying both major cell types and rare cell subtypes. Extensive evaluations on multiple real-world datasets demonstrate that scKD achieves superior performance in subpopulation identification, clustering stability, and robustness. These results suggest that scKD is a powerful and reliable tool for analyzing single-cell transcriptomic data, facilitating deeper insights into cellular heterogeneity. Availability All datasets used in this study are publicly available. Detailed information about all the single-cell datasets analyzed in this paper is provided in Supplementary Table 1. All datasets can be accessed at https://zenodo.org/records/15412380.The source code is available at https://github.com/A-qlh/sckd. Supplementary information Supplementary data are available at Bioinformatics online.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer Science and Technology, Xinjiang University, Urumqi, 830046, China.
- Department of Dermatology and Venereology, People's Hospital of Xinjiang Uygur Autonomous Region, Urumqi, Xinjiang 830000, China.
- Xinjiang Clinical Research Center for Dermatologic Diseases, Urumqi, Xinjiang 830000, China.
- Xinjiang Key Laboratory of Dermatology Research (XJYS1707), Urumqi, Xinjiang 830000, China.
- School of Software, Xinjiang University, Urumqi, 830046, China.
- Key Laboratory of signal detection and processing, Xinjiang University, Urumqi, 830046, China.
ORCID-Profile: Lihua Qi, Jin Gu, Cheng Chen
Förderung
- Xinjiang Uygur Autonomous Region Key R & D program
Zitieren
APA
Qi, L., Wang, P., Liu, H., Chen, C., Gu, J., & Chen, C. (2026). A hybrid neighborhood enhanced contrastive learning and self-knowledge distillation method for scRNA-seq data clustering analysis. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag084
Vancouver
Qi L, Wang P, Liu H, Chen C, Gu J, Chen C. A hybrid neighborhood enhanced contrastive learning and self-knowledge distillation method for scRNA-seq data clustering analysis. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag084
BibTeX
@article{Qi2026,
author = {Qi, Lihua and Wang, Peng and Liu, Hao and Chen, Chen and Gu, Jin and Chen, Cheng},
title = {A hybrid neighborhood enhanced contrastive learning and self-knowledge distillation method for scRNA-seq data clustering analysis},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag084}
}
EUVIMED