EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AddaGCN: Spatial transcriptomics deconvolution using graph convolutional networks with adversarial discriminative domain adaptation

Shuzhen Ding, Zhou Yu, Jingsi Ming iD

PLOS Computational Biology · 05.08.2026 · 22 (8) · e1014609

DOI: 10.1371/journal.pcbi.1014609 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 05.08.2026. Verfasst von Shuzhen Ding und 2 weiteren Autor:innen. Beteiligte Einrichtung: KLATASDS-MOE, School of Statistics, East China Normal University, Shanghai, China. Hauptthemen laut MEDLINE: Spatial Transcriptomics. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China, National Natural Science Foundation of China, Shanghai Key Program of Computational Biology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancement of spatial transcriptomics has substantially improved our understanding of the spatial architecture and gene expression heterogeneity within tissues. However, many spatial transcriptomics techniques can not reach single-cell resolution, instead measuring gene expression profiles from mixtures of potentially heterogeneous cell types. Here we propose AddaGCN, a robust deconvolution method to infer cell type composition from spatial transcriptomic data. AddaGCN leverages graph convolutional networks to incorporate spatial information and adopts an adversarial discriminative domain adaptation approach to mitigate batch effects between spatial and single-cell reference data. Comprehensive analyses of real data generated by diverse technology platforms demonstrate AddaGCN’s superior performance and robustness in cell-type deconvolution compared to other methods. These analyses further reveal AddaGCN’s potential to uncover spatiotemporal changes during tissue development and to characterize the tumor microenvironment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spatial TranscriptomicsGraph Neural NetworksComputational BiologyHumansAlgorithmsTranscriptomeAnimalsGene Expression ProfilingTumor Microenvironment

Autor:innen und Institutionen

  • KLATASDS-MOE, School of Statistics, East China Normal University, Shanghai, China.
  • College of Mathematics and Systems Sciences, Xinjiang University, Urumqi, China.
  • Academy of Statistics and Interdisciplinary Sciences, East China Normal University, Shanghai, China.

ORCID-Profile: Jingsi Ming

Förderung

  • Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China
  • National Natural Science Foundation of China
  • Shanghai Key Program of Computational Biology
  • Shanghai Pilot Program for Basic Research

Zitieren

APA

Ding, S., Yu, Z., & Ming, J. (2026). AddaGCN: Spatial transcriptomics deconvolution using graph convolutional networks with adversarial discriminative domain adaptation. PLOS Computational Biology, 22(8), e1014609. https://doi.org/10.1371/journal.pcbi.1014609

Vancouver

Ding S, Yu Z, Ming J. AddaGCN: Spatial transcriptomics deconvolution using graph convolutional networks with adversarial discriminative domain adaptation. PLOS Computational Biology. 2026;22(8):e1014609. doi:10.1371/journal.pcbi.1014609

BibTeX
@article{Ding2026,
  author = {Ding, Shuzhen and Yu, Zhou and Ming, Jingsi},
  title = {AddaGCN: Spatial transcriptomics deconvolution using graph convolutional networks with adversarial discriminative domain adaptation},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {8},
  pages = {e1014609},
  doi = {10.1371/journal.pcbi.1014609}
}
Kostenlos starten →