SpaSEG: unsupervised deep learning for multi-task analysis of spatially resolved transcriptomics.

Journal: Genome biology
Published Date: Jul 29, 2025

Abstract

Spatially resolved transcriptomics (SRT) for characterizing spatial cellular heterogeneities in tissue environments requires systematic analytical approaches to elucidate gene expression variations within their physiological context. Here, we introduce SpaSEG, an unsupervised deep learning model utilizing convolutional neural networks for multiple SRT analysis tasks. Extensive evaluations across diverse SRT datasets generated by various platforms demonstrate SpaSEG's superior robustness and efficiency compared to existing methods. In the application analysis of invasive ductal carcinoma, SpaSEG successfully unravels intratumoral heterogeneity and delivers insights into immunoregulatory mechanisms. These results highlight SpaSEG's substantial potential for exploring tissue architectures and pathological biology.

Authors

  • Yong Bai
    Intensive Care Unit, Hubei University of Medicine, Renmin Hospital, Shiyan, Hubei, China.
  • Xiangyu Guo
    College of Foreign Languages, Zhengzhou University of Technology, Zhengzhou, Henan, China.
  • Keyin Liu
    BGI Research, Shenzhen, 518083, China.
  • Bingjie Zheng
    Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA.
  • Yilin Wei
    School of Biology and Biological Engineering, South China University of Technology, Guangzhou 510006, China; BGI Research, Shenzhen 518083, China.
  • Yingyue Wang
    BGI Research, Shenzhen, 518083, China.
  • Wenxi Zhang
    BGI Research, Shenzhen, 518083, China.
  • Qiuhong Luo
    BGI Research, Shenzhen, 518083, China.
  • Jianhua Yin
  • Liang Wu
    Clinical and Research Center of AIDS, Beijing Ditan Hospital, Capital Medical University, Beijing, China.
  • Yuxiang Li
    BGI Research, Shenzhen 518083, China.
  • Yong Zhang
    Outpatient Department of Hepatitis, The Sixth Affiliated People's Hospital of Dalian Medical University, Dalian, Liaoning, China.
  • Ao Chen
    BGI Research, Shenzhen 518083, China.
  • Xiangdong Wang
    Department of Pulmonary and Critical Care Medicine, The Second Hospital of Fujian Medical University, Quanzhou, Fujian Province, China. Xiangdong.wang@clintransmed.org.
  • Xun Xu
    BGI-Shenzhen, Shenzhen 518083, China.
  • Chuanyu Liu
    State Key Laboratory of Genome and Multi-Omics Technologies, BGI Research, Shenzhen, 518083, China. liuchuanyu@genomics.cn.
  • Xin Jin
    Department of Hepatic Surgery, Fudan University Shanghai Cancer Center, Shanghai Medical College, Fudan University, Shanghai, China.

Keywords

External Resources

Popular Topics
Recent Journals