EUVIMEDEUVIMED entdecken
Open Access

Cross‐Propagative Graph Learning Reveals Spatial Tissue Domains in Multi‐Modal Spatial Transcriptomics

Yin Guo iD, Songyan Liu, Zixuan Zhang, Shuqin Zhang, Limin Li

Small Methods · 2026-08 · 10 (15)

DOI: 10.1002/smtd.70851 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Small Methods, online erschienen am 12.07.2026. Verfasst von Yin Guo und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, Shannxi, China. Hauptthemen laut MEDLINE: Spatial Transcriptomics, Gene Expression Profiling, Transcriptome. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatial transcriptomics enables in situ characterization of tissue organization by jointly profiling gene expression profiles and spatial coordinates, with histological images as complementary contextual information. However, effectively integrating these heterogeneous modalities remains challenging due to differences in statistical properties and structural patterns. We propose st‐Xprop, a cross‐propagative graph network with dual‐graph embedding coupling for spatial domain identification. st‐Xprop constructs modality‐specific graphs for gene expression and histological features, and performs alternating cross‐modal propagation to explicitly model inter‐modal heterogeneity while enabling complementary information exchange. Through dual‐graph embedding coupling, the framework progressively learns a unified low‐dimensional representation that integrates multi‐modal signals and preserves spatial coherence. Evaluations on multiple real spatial transcriptomics datasets demonstrate that st‐Xprop consistently improves clustering accuracy and robustness, particularly in weak‐signal or structurally complex regions, yielding spatial domains that are more stable and biologically meaningful.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spatial TranscriptomicsGene Expression ProfilingTranscriptomeAlgorithmsGraph Neural NetworksHumansAnimalsClustering Algorithms

Stichwörter der Autor:innen

cross‐propagative learninghistology imagespatial domain identificationspatial transcriptomics

Autor:innen und Institutionen

  • School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, Shannxi, China.
  • School of Mathematical Sciences, Fudan University, Shanghai, China.

ORCID-Profile: Yin Guo

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Commission of Shanghai Municipality

Zitieren

APA

Guo, Y., Liu, S., Zhang, Z., Zhang, S., & Li, L. (2026). Cross‐Propagative Graph Learning Reveals Spatial Tissue Domains in Multi‐Modal Spatial Transcriptomics. Small Methods, 10(15). https://doi.org/10.1002/smtd.70851

Vancouver

Guo Y, Liu S, Zhang Z, Zhang S, Li L. Cross‐Propagative Graph Learning Reveals Spatial Tissue Domains in Multi‐Modal Spatial Transcriptomics. Small Methods. 2026;10(15). doi:10.1002/smtd.70851

BibTeX
@article{Guo2026,
  author = {Guo, Yin and Liu, Songyan and Zhang, Zixuan and Zhang, Shuqin and Li, Limin},
  title = {Cross‐Propagative Graph Learning Reveals Spatial Tissue Domains in Multi‐Modal Spatial Transcriptomics},
  journal = {Small Methods},
  year = {2026},
  volume = {10},
  number = {15},
  doi = {10.1002/smtd.70851}
}
Kostenlos starten →