EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

STransfer: a transfer learning-enhanced graph convolutional network for clustering spatial transcriptomics data

Chaojie Wang iD, Xin Yu

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Chaojie Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematical Sciences, Jiangsu University, Zhenjiang, Jiangsu 212013, China. Hauptthemen laut MEDLINE: Software, Computational Biology. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Research General Project of Jiangsu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Capturing spatial structure is fundamental to the analysis of spatial transcriptomics data. However, most existing methods focus on clustering within individual tissue slices and often ignore the high inter-slice similarity inherent in multi-slice datasets. Results To address this limitation, we propose STransfer, a novel transfer learning framework that combines graph convolutional networks (GCNs) with positive pointwise mutual information (PPMI) to model both local and global spatial dependencies. An attention-based module is introduced to fuse features from multiple graphs into unified node representations, facilitating the learning of low-dimensional embeddings that jointly encode gene expression and spatial context. By transferring knowledge from labeled slices to adjacent unlabeled ones, STransfer significantly enhances clustering accuracy while reducing manual annotation costs. Extensive experiments demonstrate that STransfer consistently outperforms state-of-the-art methods in both spatial modeling and cross-slice transfer performance. Availability and implementation The code for STransfer has been uploaded to GitHub: https://github.com/Saki-JSU/Publications/tree/main/STransfer.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SoftwareComputational BiologyTransfer Machine LearningGraph Neural NetworksSpatial TranscriptomicsClustering AlgorithmsCluster Analysis

Autor:innen und Institutionen

  • School of Mathematical Sciences, Jiangsu University, Zhenjiang, Jiangsu 212013, China.
  • School of Finance & Economics, Jiangsu University, Zhenjiang, Jiangsu 212013, China.

ORCID-Profile: Chaojie Wang

Förderung

  • National Natural Science Foundation of China
  • Natural Science Research General Project of Jiangsu Province

Zitieren

APA

Wang, C., & Yu, X. (2026). STransfer: a transfer learning-enhanced graph convolutional network for clustering spatial transcriptomics data. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag049

Vancouver

Wang C, Yu X. STransfer: a transfer learning-enhanced graph convolutional network for clustering spatial transcriptomics data. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag049

BibTeX
@article{Wang2026,
  author = {Wang, Chaojie and Yu, Xin},
  title = {STransfer: a transfer learning-enhanced graph convolutional network for clustering spatial transcriptomics data},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag049}
}
Kostenlos starten →