EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

STGNET: extending panel coverage in imaging-based spatial transcriptomics using deep generative adversarial networks

Tao Wang iD, Bingtao Wang, Han Shu iD, Peimeng Zhen iD, Jialu Hu iD, Yongtian Wang iD, Jiajie Peng iD, Xuequn Shang, Zhiyuan Wu, Bing Xiao, Jing Chen iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Tao Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Northwestern Polytechnical University, No. 1 Dongxiang Road, Chang'an District, Xi'an 710072, Shaanxi, China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Imaging-based spatial transcriptomics (ST) technologies offer unparalleled resolution for mapping gene expression within intact tissues but are fundamentally constrained by the limited size of their gene panels. This restriction hinders comprehensive biological discovery by omitting potentially crucial genes from analysis. To overcome this limitation, we introduce STGNET, a deep learning framework that extends gene panel coverage by integrating generative adversarial networks (GANs) with graph neural networks. STGNET employs a multi-stage GAN to learn the global transcriptomic distribution from single-cell RNA sequencing data, followed by a spatially aware graph convolutional network that refines imputations by modeling both physical cell proximity and transcriptional similarity. We rigorously benchmarked STGNET against seven state-of-the-art methods across nine diverse ST datasets. STGNET consistently achieved superior performance, demonstrating enhanced accuracy in gene imputation, and exceptional preservation of cellular topology. We further showcase its biological utility by accurately reconstructing developmental marker patterns in mouse embryogenesis, revealing a novel transitional cell state in breast cancer progression, and uncovering extensive, previously obscured cell–cell communication networks in the mouse brain. STGNET provides a powerful and robust solution for unlocking the full potential of targeted ST assays, thereby enabling deeper and more comprehensive spatial biology. STGNET is freely accessible at https://github.com/wuyuanwuhuii/STGNET.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGenerative Adversarial NetworksSpatial TranscriptomicsAnimalsMiceGraph Neural NetworksHumansBreast NeoplasmsGenerative Artificial IntelligenceGene Expression Profiling

Stichwörter der Autor:innen

gene panel imputationgenerative adversarial networksgraph convolutional networkimaging-based spatial transcriptomics

Autor:innen und Institutionen

  • School of Computer Science, Northwestern Polytechnical University, No. 1 Dongxiang Road, Chang'an District, Xi'an 710072, Shaanxi, China.
  • Key Laboratory of Big Data Storage and Management, Ministry of Industry and Information Technology, Northwestern Polytechnical University, No. 1 Dongxiang Road, Chang'an District, Xi'an 710072, Shaanxi, China.
  • Department of Vascular Surgery, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, No. 1 Dahua Road, Dongcheng District, Beijing 100730, China.
  • School of Automation, Northwestern Polytechnical University, No. 1 Dongxiang Road, Chang'an District, Xi'an 710072, Shaanxi, China.
  • School of Computer Science and Engineering, Xi'an University of Technology, No. 5 South Jinhua Road, Beilin District, Xi'an 710048, Shaanxi, China.

ORCID-Profile: Tao Wang, Han Shu, Peimeng Zhen, Jialu Hu, Yongtian Wang, Jiajie Peng, Jing Chen

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Wang, T., Wang, B., Shu, H., Zhen, P., Hu, J., Wang, Y., Peng, J., Shang, X., Wu, Z., Xiao, B., & Chen, J. (2026). STGNET: extending panel coverage in imaging-based spatial transcriptomics using deep generative adversarial networks. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag122

Vancouver

Wang T, Wang B, Shu H, Zhen P, Hu J, Wang Y, et al. STGNET: extending panel coverage in imaging-based spatial transcriptomics using deep generative adversarial networks. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag122

BibTeX
@article{Wang2026,
  author = {Wang, Tao and Wang, Bingtao and Shu, Han and Zhen, Peimeng and Hu, Jialu and Wang, Yongtian and Peng, Jiajie and Shang, Xuequn and Wu, Zhiyuan and Xiao, Bing and Chen, Jing},
  title = {STGNET: extending panel coverage in imaging-based spatial transcriptomics using deep generative adversarial networks},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag122}
}
Kostenlos starten →