EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AugGCL: Multimodal graph learning for spatial transcriptomics analysis with enhanced gene and morphological data

Tengfei Ji iD, Bo Yang iD, Meng Wang, Hong Ji, Huazhe Yang, Yizhuo Liu

PLOS Computational Biology · 2026

DOI: 10.1371/journal.pcbi.1013912 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2026. Verfasst von Tengfei Ji und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Xi'an Polytechnic University, Xi'an, Shaanxi, China. Hauptthemen laut MEDLINE: Spatial Transcriptomics, Gene Expression Profiling. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Basic Research Program of Shaanxi Province, The Scientific and Technological Program of Xi’an.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatial transcriptomics enables the measurement of gene expression in intact tissues. Despite this, reconstructing anatomically accurate spatial domains remains challenging, primarily due to expression sparsity, complex tissue architecture that is characterized by sharp boundaries and long-range continuity, and weak spatial signals. Traditional pipelines typically rely on expression-driven clustering and spatial smoothing, which underperform at boundaries and in sparse regions while neglecting morphological information. To address these challenges, AugGCL is proposed, an augmented graph-convolutional learning framework that enhances spatial structure decoding and gene expression reconstruction through targeted augmentation of both gene and image data. A key component of AugGCL is neighborhood information aggregation mechanism, which integrates expression similarity and spatial proximity to construct a weighted graph and an enhanced expression matrix, addressing sparsity without sacrificing boundary clarity. Additionally, a two stream weighted graph convolutional network jointly models refined gene features and image-derived morphological information, with image-aware auxiliary reconstructions enhancing weak spatial signals and sharpening boundaries. On datasets from the human dorsolateral prefrontal cortex, breast cancer, and mouse embryo, AugGCL outperforms baseline methods across multiple metrics, showing robustness and generalization across a range of datasets. Downstream analysis validated the reliability of the method, confirming its effectiveness in cell annotation, functional enrichment, and mechanistic studies. AugGCL generates clearer spatial domains and significantly advances the application of spatial transcriptomics in tissue structure and disease research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spatial TranscriptomicsGene Expression ProfilingAnimalsHumansGraph Neural NetworksMiceComputational BiologyAlgorithmsBreast NeoplasmsFemaleImage Processing, Computer-AssistedTranscriptome

Autor:innen und Institutionen

  • School of Computer Science, Xi'an Polytechnic University, Xi'an, Shaanxi, China.

ORCID-Profile: Tengfei Ji, Bo Yang

Förderung

  • National Natural Science Foundation of China
  • Natural Science Basic Research Program of Shaanxi Province
  • The Scientific and Technological Program of Xi’an
  • Graduate Innovation Fund of Xi’an Polytechnic University

Zitieren

APA

Ji, T., Yang, B., Wang, M., Ji, H., Yang, H., & Liu, Y. (2026). AugGCL: Multimodal graph learning for spatial transcriptomics analysis with enhanced gene and morphological data. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1013912

Vancouver

Ji T, Yang B, Wang M, Ji H, Yang H, Liu Y. AugGCL: Multimodal graph learning for spatial transcriptomics analysis with enhanced gene and morphological data. PLOS Computational Biology. 2026. doi:10.1371/journal.pcbi.1013912

BibTeX
@article{Ji2026,
  author = {Ji, Tengfei and Yang, Bo and Wang, Meng and Ji, Hong and Yang, Huazhe and Liu, Yizhuo},
  title = {AugGCL: Multimodal graph learning for spatial transcriptomics analysis with enhanced gene and morphological data},
  journal = {PLOS Computational Biology},
  year = {2026},
  doi = {10.1371/journal.pcbi.1013912}
}
Kostenlos starten →