Welcome to my webpage!

I'm a

I am on the academic job market in the 2025 Fall cycle. Please feel free to reach out if you think I could be a good fit!


Hi, I am Siyu, currently a 3rd-year postdoctoral fellow in the Department of Biomedical Data Science at Stanford University, where I am co-advised by Dr. James Zou and Dr. Stephen Quake.


My research focuses on the intersection of AI and biomedicine, where I mainly develop generative AI models for learning and predicting spatiotemporal dynamics of the cells in both healthy and diseased states.


I earned my PhD in Biomedical Engineering from Columbia University, where I am co-advised by Dr. Kam Leong and Dr. Elham Azizi. I hold a Bachelor's degree in Physics from Xi'an Jiaotong Unversity in China.


  • Postdoc, Biomedical Data Science, Stanford University, 2023 -
  • PhD, Biomedical Engineering, Columbia University, 2018 - 2023
  • BS, Physics with honors, Xian Jiaotong University, 2013 - 2017

    • Research Interests: Generative AI for single-cell and spatial biology | Precision medicine | Regenerative medicine AI for science | Agentic and Quantum AI for healthcare | Cancer immunology

    Research


    1. Statistical machine learning of cellular spatial dynamics in complex tissues

    I am interested in generative models such as probabilistic graphical models and graph neural network that learns reliable genetic relationship between cells in tissue space through precisely designing cell state parameters. These models disentangle tissue complexity, and uncovers the tissue architecture associated with disease progression and the relative therapeutic responses.

    Related Paper:
  • He, S.*†, Bieniosek, M., Song, D., Zhou, J., Chidester, B., Wu, Z., Boen, J., Sharma†, P., Trevino, A.†, Zou, J.† Learning single-cell spatial context through integrated spatial multiomics with CORAL. In revision at Nature Genetics (2025). [CODE] [Paper]

  • He, S.*† Encoding spatial tumour dynamics with Starfysh. Nature Reviews Cancer (2024). [Paper]

  • He, S.*, Jin, Y.*, Nazaret, A.* et al. Starfysh integrates spatial transcriptomic and histologic data to reveal heterogeneous tumor–immune hubs. Nature Biotechnology (2024). [CODE] [Paper]

  • He, S.*, C. Xu*, S. Chauhan, YH. Lao, Y. Xiao, M. Willner, S. McElroy, R. Tomer, Y. Jin, S. Rao, J. Gogos, E. Azizi, B. Xu†, K.W. Leong†. Mapping morphological malformation to genetic dysfunction in blood vessel organoids. bioRxiv. [Paper]

  • He, S.*, YH. Lao*, S. Shankar, R. Kunes, R. Berris, W. Jiang, J. Lee, S. Hingtgen, E. Azizi, K. W. Leong. Topological defects induced by MSC-cancer interaction correlate with cancer cell apoptosis. In preparation.

    • 2. Generative AI for in silico screening in regenerative and precision medicine

    I am interested in generative models such as diffusion model to learn and predict the cell states through high-throughput omics data.

    Related Paper:
  • He, S.*, Zhu, Y.*, Tavakol, D.*, Ye, H., Lao, Y., Zhu, Z., Xu, C., Chauhan, S., Garty, G., Tomer, R., Vunjak-Novakovic, G., Zou, J.†, Azizi, E.†, Leong, K†. Squidiff: Predicting cellular development and responses to perturbations using a diffusion model. Nature Methods (2025). [CODE] [Paper] [Cover News]

  • He, S.*, Leong, K†. Predicting cellular responses with conditional diffusion models. Nature Methods (2025). [Paper]

  • Xu, C.*, He, S.*, Zhu, Y., Crasto, G., Chen, C., Clay, M., Lao, Y., Leong, K. Vascular Organoid Generation from Human-Induced Pluripotent Stem Cells. JoVE (2024). [Paper]

  • He, S.*, Y. Zhu, S. Chauhan, D. N. Tavakol, J. H. Lee, R. B. Berris, C. Xu, J. H. Lee, C. Lee, S. Cai, S. McElroy, G. Vunjak-Novakovic, R. Tomer, E. Azizi, B. Xu, YH. Lao and K. W. Leong. Human vascular organoids with a mosaic AKT1 mutation recapitulate Proteus syndrome. bioRxiv (2024). [Paper]

    • 3. Virtual cell foundation model

    I am interested in virtual cell foundation models for biological discovery.

    Related Paper:
  • Stephen R Quake, The Tabula Sapiens Consortium (I am the major contributor on sex-specific features). Tabula Sapiens reveals transcription factor expression, senescence effects, and sex-specific features in cell types from 28 human organs and tissues. bioRxiv. In revision (2024). [Paper]
    • To see all publications >> click here

    Selected News

    • [2026-01] Squidiff has been featured on the cover of Nature Methods [Cover News]
    • [2025-09] Glad to be selected to attend the Rising Stars in EECS Workshop! Looking forward to seeing everyone in Boston!

    • [2025-09] Glad to be selected to attend the Rising Stars in Data Science Workshop! Looking forward to seeing everyone there this November!

    • [2025-08] I am excited to receive the Katharine McCormick Postdoctoral Fellowship!

    • [2025-04] Gave a talk about CORAL at Computational Spatial Biology seminar hosted by Nathan Levy and Justin Hong, thanks for the invitation! [Youtube]

    • [2025-03] Hornored to be interviewed by the Cognitive Revolution, and share our work Squidiff and CORAL. [the Cognitive Revolution Podcast] [Youtube]

    • [2025-04] Invited talk at Department of Pharmaceutical Science at University at Buffalo, hosted by Prof. Sima Lao. Thanks for the invitation and I enjoyed the discussion a lot!

    • [2024-10] I am excited to share my phd experience at Columbia BME Blaze. [Columbia BME Blaze]

    • [2024-09] I am excited to receive the Stellar Abstract Award at [Harvard PQG 2024].

    • [2024-05] We shared our story of developing Starfysh on Nature Biotech podcast. [From bench to podcast]

    • [2024-03] Starfysh is on the news including [Columbia IICD new] [Columbia BME news] [Columbia News]

    • [2022-03] I am on the spotlight in woman's history month: [Columbia IICD spotlight]

    Siyu He

    Postdoc fellow,

    Department of Biomedical Data Science

    School of Medicine, Stanford

    siyuhe@stanford.edu