EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A masked generative graph representation learning framework empowering precise spatial domain identification

Chuyao Wang, Tongdong Zhang, Hang Sun, Zhipeng Wu, Shuo Liang, Xueting Wang, Meirong Du, Yanchun Liang, Xin Gao iD, Qi Tang, Dong Xu iD, Xiaoyue Feng iD und 2 weitere

Bioinformatics · 01.06.2026 · 42 (6)

DOI: 10.1093/bioinformatics/btag333 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 22.05.2026. Verfasst von Chuyao Wang und 13 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, College of Computer Science and Technology, Jilin Univ…. Hauptthemen laut MEDLINE: Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Planning Project of Guangdong Province, Guangdong Universities' Innovation Team.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Spatial transcriptomics (ST) enables the measurement of gene expression while preserving the spatial context of tissues. However, the sparsity of ST data leads to poor usage of gene expression and spatial information, resulting in the embeddings that are not well represented and challenging for downstream analyses. Results Here, we introduced GSG, a generative self-supervised representation learning framework for ST data that leverages a masking mechanism to learn informative representations. For spatial domain identification, GSG consistently outperformed state-of-the-art methods across benchmarking datasets, regardless of sequencing platforms. In addition, we applied GSG to an in-house human fetal heart dataset, revealing anatomically coherent spatial domains and identifying APCDD1 as an endocardial-specific marker potentially involved in congenital heart disease. Our results showcase GSG’s superiority and underscore its valuable contributions to advancing ST analysis. Availability and Implementation Our software package is available at https://github.com/keaml-Guan/GSG.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SoftwareHumansSpatial TranscriptomicsRepresentation Machine LearningGenerative Artificial Intelligence

Autor:innen und Institutionen

  • Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun, 130012, China.
  • State Key Laboratory of Cell Biology, Center for Excellence in Molecular Cell Science, Shanghai Institute of Biochemistry and Cell Biology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shangha…
  • Shanghai Key Laboratory of Maternal Fetal Medicine, Shanghai First Maternity and Infant Hospital, School of Medicine, Tongji University, Shanghai, 201204, China.
  • Zhuhai Sub Laboratory of Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Zhuhai College of Science and Technology, Zhuhai, 519041, China.
  • King Abdullah University of Science and Technology, Mathematical and Computer Science and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Saudi Arabia.
  • Department of Electrical Engineering and Computer Science, Bond Life Sciences Center, University of Missouri, Columbia, MO 65211, United States.

ORCID-Profile: Xin Gao, Dong Xu, Xiaoyue Feng, Renchu Guan

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Planning Project of Guangdong Province
  • Guangdong Universities' Innovation Team
  • Guangdong Key Disciplines
  • Guangdong Universities’ Innovation Team

Zitieren

APA

Wang, C., Zhang, T., Sun, H., Wu, Z., Liang, S., Wang, X., Du, M., Liang, Y., Gao, X., Tang, Q., Xu, D., Feng, X., Zeng, A., & Guan, R. (2026). A masked generative graph representation learning framework empowering precise spatial domain identification. Bioinformatics, 42(6). https://doi.org/10.1093/bioinformatics/btag333

Vancouver

Wang C, Zhang T, Sun H, Wu Z, Liang S, Wang X, et al. A masked generative graph representation learning framework empowering precise spatial domain identification. Bioinformatics. 2026;42(6). doi:10.1093/bioinformatics/btag333

BibTeX
@article{Wang2026,
  author = {Wang, Chuyao and Zhang, Tongdong and Sun, Hang and Wu, Zhipeng and Liang, Shuo and Wang, Xueting and Du, Meirong and Liang, Yanchun and Gao, Xin and Tang, Qi and Xu, Dong and Feng, Xiaoyue and Zeng, An and Guan, Renchu},
  title = {A masked generative graph representation learning framework empowering precise spatial domain identification},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {6},
  doi = {10.1093/bioinformatics/btag333}
}
Kostenlos starten →