EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

m2ST: dual multi-scale graph clustering for spatially resolved transcriptomics

Wei Zhang iD, Ziqi Zhang, Hailong Yang, Te Zhang, Shu Jiang, Ning Qiao, Zhaohong Deng iD, Xiaoyong Pan iD, Hong-Bin Shen iD, Dong-Jun Yu iD, Shitong Wang

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf221 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Wei Zhang und 10 weiteren Autor:innen. Beteiligte Einrichtung: The School of Artificial Intelligence and Computer Science, Nantong University, Nantong, 226019, China. Hauptthemen laut MEDLINE: Gene Expression Profiling, Transcriptome, Computational Biology, Software. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Six Talent Peaks Project in Jiangsu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Spatial clustering is a key analytical technique for exploring spatial transcriptomics data. Recent graph neural network-based methods have shown promise in spatial clustering but face notable challenges. One significant issue is that analyzing the functions and complex mechanisms of organisms from a single scale is difficult and most methods focus exclusively on the single-scale representation of transcriptomic data, potentially limiting the discriminative power of extracted features for spatial domain clustering. Furthermore, classical clustering algorithms are often applied directly to latent representation, making it a worthwhile endeavor to explore a tailored clustering method to further improve the accuracy of spatial domain annotation. Results To address these limitations, we propose m2ST, a novel dual multi-scale graph clustering method. m2ST first uses a multi-scale masked graph autoencoder to extract representations across different scales from spatial transcriptomic data. To effectively compress and distill meaningful knowledge embedded in the data, m2ST introduces a random masking mechanism for node features and uses a scaled cosine error as the loss function. Additionally, we introduce a tailored multi-scale clustering framework that integrates scale-common and scale-specific information exploration into the clustering process, achieving more robust annotation performance. Shannon entropy is finally utilized to dynamically adjust the importance of different scales. Extensive experiments on multiple spatial transcriptomic datasets demonstrate the superior performance of m2ST compared to existing methods. Availability and implementation https://github.com/BBKing49/m2ST.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene Expression ProfilingTranscriptomeComputational BiologySoftwareCluster AnalysisAlgorithms

Autor:innen und Institutionen

  • The School of Artificial Intelligence and Computer Science, Nantong University, Nantong, 226019, China.
  • The School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, China.
  • The Lab for Uncertainty in Data and Decision Making (LUCID), School of Computer Science, University of Nottingham, Nottingham, NG81BB, United Kingdom.
  • Department of Automation, Shanghai Jiao Tong University, Shanghai, 200240, China.
  • School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China.

ORCID-Profile: Wei Zhang, Zhaohong Deng, Xiaoyong Pan, Hong-Bin Shen, Dong-Jun Yu

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Six Talent Peaks Project in Jiangsu Province
  • General Program of the Natural Science Research of Higher Education of Jiangsu Province
  • China Scholarship Council

Zitieren

APA

Zhang, W., Zhang, Z., Yang, H., Zhang, T., Jiang, S., Qiao, N., Deng, Z., Pan, X., Shen, H. B., Yu, D. J., & Wang, S. (2025). m2ST: dual multi-scale graph clustering for spatially resolved transcriptomics. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf221

Vancouver

Zhang W, Zhang Z, Yang H, Zhang T, Jiang S, Qiao N, et al. m2ST: dual multi-scale graph clustering for spatially resolved transcriptomics. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf221

BibTeX
@article{Zhang2025,
  author = {Zhang, Wei and Zhang, Ziqi and Yang, Hailong and Zhang, Te and Jiang, Shu and Qiao, Ning and Deng, Zhaohong and Pan, Xiaoyong and Shen, Hong-Bin and Yu, Dong-Jun and Wang, Shitong},
  title = {m2ST: dual multi-scale graph clustering for spatially resolved transcriptomics},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf221}
}
Kostenlos starten →