Structural-information guided fusion for spatial domain identification from spatial transcriptomics
Bioinformatics · 02.07.2026 · 42 (7)
DOI: 10.1093/bioinformatics/btag508 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 09.07.2026. Verfasst von Min Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710071, China. Hauptthemen laut MEDLINE: Spatial Transcriptomics, Computational Biology. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Major Project of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Motivation Accurate spatial domain identification is essential for understanding tissue organization and pathological mechanisms in spatial transcriptomics. However, existing methods mainly rely on expression profiles and spatial coordinates. Intercellular interactions are often overlooked. At the same time, preserving both local neighborhood continuity and global topological structure remains difficult. Results We propose SGFST (Structural-information Guided Fusion for spatial domain identification from Spatial Transcriptomics), a novel framework for spatial domain identification in spatial transcriptomics. SGFST integrates a spatial graph and a signal graph, and employs a dual-branch graph convolutional network with attention-based fusion to capture complementary spatial and functional information. In addition, SGFST jointly optimizes a Bayesian personalized ranking loss, a zero-inflated negative binomial loss, and a distance structural information constraint to preserve local neighborhood continuity, reconstruct expression signals, and maintain global topological consistency. Experimental results on multiple datasets demonstrate that SGFST outperforms several state-of-the-art methods in spatial domain identification. Availability and implementation The code of SGFST is available at Github (https://github.com/xkmaxidian/SGFST) and Zenodo (DOI: 10.5281/zenodo.20624899).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710071, China.
- Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, Xidian University, Xi'an, Shaanxi 710071, China.
- Shenzhen Loop Area Institute, The First Affiliated Hospital of Xi'an jiaotong University, Xi'an, Shaanxi 710061, China.
- MOE Key Laboratory of Bioinformatics, BNRIST Bioinformatics Division, Institute for Precision Medicine & Department of Automation, Tsinghua University, Beijing 100084, China.
- Fubao District, Shenzhen Loop Area Institute, Shenzhen, Guangdong 518017, China.
- Department of Radiology, School of Medicine, The Second Affiliated Hospital of South China University of Technology (Guangzhou First People's Hospital), Guangzhou 510180, China.
ORCID-Profile: Cheng Chen, Xiaoke Ma
Förderung
- National Science and Technology Major Project of China
- National Natural Science Foundation of China
Zitieren
APA
Zhang, M., Gao, P., Chen, C., Ma, X., Chen, X., & Feng, S. (2026). Structural-information guided fusion for spatial domain identification from spatial transcriptomics. Bioinformatics, 42(7). https://doi.org/10.1093/bioinformatics/btag508
Vancouver
Zhang M, Gao P, Chen C, Ma X, Chen X, Feng S. Structural-information guided fusion for spatial domain identification from spatial transcriptomics. Bioinformatics. 2026;42(7). doi:10.1093/bioinformatics/btag508
BibTeX
@article{Zhang2026,
author = {Zhang, Min and Gao, Peng and Chen, Cheng and Ma, Xiaoke and Chen, Xin and Feng, Shaoqing},
title = {Structural-information guided fusion for spatial domain identification from spatial transcriptomics},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {7},
doi = {10.1093/bioinformatics/btag508}
}
EUVIMED