Accurate reconstruction of spatial cell-type maps and characterization of domain-specific functions based on a gene-aware heterogeneous network
Genome Research · 2026
DOI: 10.1101/gr.282246.126 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genome Research, 2026. Verfasst von Zilin Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710126, China. Hauptthemen laut MEDLINE: Gene Regulatory Networks, Transcriptome. Die Arbeit nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Basic Research Program of Shaanxi Province, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Spatial transcriptomic (ST) profiles gene expression with spatial context, but most platforms capture multicellular spots containing mixed cell types, making accurate deconvolution essential. Existing reference-based methods using scRNA-seq often ignore spatial dependency and gene-level contribution, yielding fragmented maps and limited insight into domain-specific programs. Here, we propose a gene-aware heterogeneous graph attention network called STGnet for ST deconvolution and functional annotation. Leveraging a hybrid pseudospot generation strategy that captures realistic spatially enriched cell-type patterns, STGnet accurately integrates spatial adjacency, transcriptional similarity, and gene–spot associations within a unified heterogeneous network. Attention weights highlight domain-specific genes for interpretable domain annotation. Importantly, STGnet can characterize spatially ordered functional programs across domains that may be associated with disease progression. These insights may facilitate the discovery of spatial disease mechanisms and improve understanding of pathological tissue organization. Experiments on simulated and real data sets show that STGnet achieves the best overall performance compared with state-of-the-art methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710126, China.
- School of Management, Xi'an Polytechnic University, Xi'an, Shaanxi 710048, China; lyu@xidian.edu.cn zhao_chenguang@outlook.com 20170914@xpu.edu.cn.
- Department of Rehabilitation Medicine, Xijing Hospital, Fourth Military Medical University, Xi'an, Shaanxi 710032, China lyu@xidian.edu.cn zhao_chenguang@outlook.com 20170914@xpu.edu.cn.
- School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi 710126, China; lyu@xidian.edu.cn zhao_chenguang@outlook.com 20170914@xpu.edu.cn.
Förderung
- National Natural Science Foundation of China
- Natural Science Basic Research Program of Shaanxi Province
- Fundamental Research Funds for the Central Universities
- Xidian University Specially Funded Project for Interdisciplinary Exploration
Zitieren
APA
Li, Z., Huang, Z., Li, Y., Zhao, C., & Yu, L. (2026). Accurate reconstruction of spatial cell-type maps and characterization of domain-specific functions based on a gene-aware heterogeneous network. Genome Research. https://doi.org/10.1101/gr.282246.126
Vancouver
Li Z, Huang Z, Li Y, Zhao C, Yu L. Accurate reconstruction of spatial cell-type maps and characterization of domain-specific functions based on a gene-aware heterogeneous network. Genome Research. 2026. doi:10.1101/gr.282246.126
BibTeX
@article{Li2026,
author = {Li, Zilin and Huang, Zhaoyang and Li, Yan and Zhao, Chenguang and Yu, Liang},
title = {Accurate reconstruction of spatial cell-type maps and characterization of domain-specific functions based on a gene-aware heterogeneous network},
journal = {Genome Research},
year = {2026},
doi = {10.1101/gr.282246.126}
}
EUVIMED