EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Topology-Feature Disentangled Deep Clustering Method for scRNA-seq Based on Graph-to-MLP Distillation

Xilai Gao, Hao Liu, Yang Zhao, Xiaoyi Lv, Xiangwei Zhao, Cheng Chen

Bioinformatics · 13.11.2026

DOI: 10.1093/bioinformatics/btag827 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 13.11.2026. Verfasst von Xilai Gao und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Software, Xinjiang University, Urumqi 830046, China. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Graph neural networks (GNNs), owing to their ability to model topological relationships between cells, have gradually emerged as a mainstream approach in the clustering analysis of single-cell RNA sequencing (scRNA-seq) data. However, their practical application still faces the following challenges: (1) excessive smoothing undermines cellular heterogeneity; (2) pre-constructed graphs introduce end-to-end dependencies; (3) large-scale cellular graph computations are computationally intensive. Results To fully utilise the expression profiles and topological information contained within scRNA-seq data and overcome these limitations, this paper proposes a Graph-to-MLP (G2M) knowledge distillation method incorporating AdaBoost principles, and builds upon this to develop a graph-disentangled single-cell clustering framework—scAdaG2M. This framework utilises a GNN teacher model to learn higher-order topological relationships and local neighbourhood structures between cells on a cellular graph, whilst multiple lightweight MLP student models perform feature learning in an ungraphed setting. By combining this with an AdaBoost-style dynamic reweighting strategy, the framework enhances the model’s ability to characterise cells that are difficult to distinguish, cells with blurred boundaries, and potentially rare cell populations, thereby mitigating the dilution of cellular heterogeneity caused by over-smoothing. At the same time, this framework effectively decouples graph-based modelling from graph-free reasoning, reduces the end-to-end reliance on pre-constructed graphs, and significantly reduces the computational overhead associated with large-scale cellular graphs. 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. The source code is available at https://github.com/gxl1110/scAdaG2M and https://doi.org/10.5281/zenodo.21512950. Supplementary information Supplementary data are available at Bioinformatics online.

Autor:innen und Institutionen

  • School of Software, Xinjiang University, Urumqi 830046, China.
  • School of Computer Science and Technology, Xinjiang University, Urumqi 830046, China.
  • People's Hospital of Xinjiang Uyghur Autonomous Region, Urumqi 830001, China.
  • State Key Laboratory of Digital Medical Engineering, School of Biological Science & Medical Engineering, Southeast University, Nanjing 211189, China.
  • Xinjiang Key Laboratory of Cardiovascular Homeostasis and Regeneration Research, Urumqi 830046, China.
  • MOE Key Laboratory of Bioinformatics, BNRIST Bioinformatics Division, Institute for Precision Medicine & Department of Automation, Tsinghua University, Beijing 100084, China.

Zitieren

APA

Gao, X., Liu, H., Zhao, Y., Lv, X., Zhao, X., & Chen, C. (2026). A Topology-Feature Disentangled Deep Clustering Method for scRNA-seq Based on Graph-to-MLP Distillation. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag827

Vancouver

Gao X, Liu H, Zhao Y, Lv X, Zhao X, Chen C. A Topology-Feature Disentangled Deep Clustering Method for scRNA-seq Based on Graph-to-MLP Distillation. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag827

BibTeX
@article{Gao2026,
  author = {Gao, Xilai and Liu, Hao and Zhao, Yang and Lv, Xiaoyi and Zhao, Xiangwei and Chen, Cheng},
  title = {A Topology-Feature Disentangled Deep Clustering Method for scRNA-seq Based on Graph-to-MLP Distillation},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag827}
}
Kostenlos starten →