EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

An unsupervised method for spatial transcriptomics analysis based on adversarial autoencoder

Wei Lan, Guohang He, Lingzhi Zhu, Ruiqing Zheng, Min Li, Yi Pan

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag070 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Wei Lan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Guangxi Key Laboratory of Multimedia Communications and Networks Technology, School of Computer, Electronic and Information, Guangxi University, No. …. Hauptthemen laut MEDLINE: Spatial Transcriptomics, Unsupervised Machine Learning, Gene Expression Profiling, Transcriptome. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Natural Science Foundation of Guangxi Zhuang Autonomous Region of China, National Natural Science Foundation of China, Guangxi Bagui Youth Talent Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatial transcriptomics (ST) offers unprecedented opportunities to decode the spatial organization of gene expression, yet the inherent noise and complexity of ST data pose substantial challenges for accurate analysis. Here, we present DACN, a unified framework that integrates an improved adversarial autoencoder (AAE) with a graph convolutional network (GCN) to robustly analyze ST data across varying resolutions and throughputs. DACN employs a hybrid encoder that couples multi-head attention with residual connections to capture fine-grained local expression patterns while retaining critical global information. The hybrid encoder and generator jointly construct the AAE module, which denoises expression profiles and learns stable latent representations. The GCN component further exploits spatial neighborhood relationships to refine these embeddings. Across multiple ST datasets with varying resolutions, DACN consistently outperforms existing methods in accuracy and robustness. All code and datasets are publicly available at https://github.com/lanbiolab/DACN.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spatial TranscriptomicsUnsupervised Machine LearningGene Expression ProfilingTranscriptomeAutoencoderGraph Neural NetworksAlgorithmsHumans

Stichwörter der Autor:innen

adversarial autoencoderdeep learningspatial domainspatial transcriptomics

Autor:innen und Institutionen

  • Guangxi Key Laboratory of Multimedia Communications and Networks Technology, School of Computer, Electronic and Information, Guangxi University, No. 100 Daxue Road, Nanning, Guangxi 530004, China.
  • School of Computer and Information Science, Hunan Institute of Technology, No. 18 Henghua Road, Hengyang, Hunan 421002, China.
  • Hunan Provincial Key laboratory on Bioinformatics, School of Computer Science and Engineering, Central South University, No. 932 Lushan South Road, Changsha, Hunan 410083, China.
  • Faculty of Computer Science and Control Engineering, Shenzhen Institute of Advanced Technology, No. 1 Gongchang Road, Shenzhen, Guangdong 518055, China.

Förderung

  • Natural Science Foundation of Guangxi Zhuang Autonomous Region of China
  • National Natural Science Foundation of China
  • Guangxi Bagui Youth Talent Program
  • Guangxi Key Laboratory of Eye Health
  • 2025 Guangxi Education Department Graduate Innovation Project
  • Natural Science Foundation of Hunan Province
  • Hunan Intelligent Rehabilitation Robot and Auxiliary Equipment Engineering Technology Research Center
  • Project of Guangxi Health Commission Eye and Related Diseases Artificial Intelligence Screen Technology Key Laboratory

Zitieren

APA

Lan, W., He, G., Zhu, L., Zheng, R., Li, M., & Pan, Y. (2026). An unsupervised method for spatial transcriptomics analysis based on adversarial autoencoder. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag070

Vancouver

Lan W, He G, Zhu L, Zheng R, Li M, Pan Y. An unsupervised method for spatial transcriptomics analysis based on adversarial autoencoder. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag070

BibTeX
@article{Lan2026,
  author = {Lan, Wei and He, Guohang and Zhu, Lingzhi and Zheng, Ruiqing and Li, Min and Pan, Yi},
  title = {An unsupervised method for spatial transcriptomics analysis based on adversarial autoencoder},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag070}
}
Kostenlos starten →