Haotian Cui, Ph.D.

prof_pic.jpg

I am a researcher specializing in machine learning, genomics, and drug discovery. I currently work as a Senior AI Scientist at Xaira Therapeutics. My work focuses on developing self-driving labs powered by agents, and large-scale pretrained models to enable biological insights and therapeutic discoveries. I am passionate about building foundation models for single-cell omics and molecular biology, integrating AI with experimental pipelines to accelerate biomedical breakthroughs.

I completed my Ph.D. in Computer Science at University of Toronto (2019-2024) under Prof. Bo Wang, where I pioneered scGPT, one of the first generative foundation models for single-cell multi-omics. I also led the development of LUMI-lab, an AI-driven autonomous lab for mRNA therapeutics.

Research Interests: Self-Driving Lab, Foundation Model, Machine Learning, Genomics, Drug Discovery

selected publications

  1. Cell
    LUMI-lab: a Foundation Model-Driven Autonomous Platform Enabling Discovery of New Ionizable Lipid Designs for mRNA Delivery
    Y. Xu*, H. Cui*, K. Pang, G. Li, F. Gong, B. Wang, and B. Li
    Cell. Fully self-driving lab for active-learning experiments on lipid design. , 2026
    DOI HTML Video
  2. Nature Methods
    scGPT: toward building a foundation model for single-cell multi-omics using generative AI
    H. Cui*, C. Wang*, H. Maan, K. Pang, F. Luo, N. Duan, and B. Wang
    Nature Methods. Pioneering single-cell foundation model with generative pretraining. , 2024
    DOI HTML
  3. Nature
    Towards Multimodal Foundation Models in Molecular Cell Biology
    H. Cui, A. Tejada-Lapuerta, M. Brbić, J. Saez-Rodriguez, S. Cristea, H. Goodarzi, M. Lotfollahi, F.J. Theis, and B. Wang
    Nature. Perspective on multimodal foundation models across the central dogma. , 2025
    DOI HTML
  4. bioRxiv
    scGPT-spatial: Continual Pretraining of Single-Cell Foundation Model for Spatial Transcriptomics
    C.X. Wang*, H. Cui*, A.H. Zhang, R. Xie, H. Goodarzi, and B. Wang
    bioRxiv, 2025
  5. bioRxiv
    MethylGPT: a foundation model for the DNA methylome
    K. Ying*, J. Song*, H. Cui*, Y. Zhang, S. Li, X. Chen, H. Liu, A. Eames, D.L. McCartney, R.E. Marioni, and J.R. Poganik
    bioRxiv, 2024
  6. Nature Communications
    AGILE platform: a deep learning powered approach to accelerate LNP development for mRNA delivery
    Y. Xu*, S. Ma*, H. Cui*, J. Chen, S. Xu, F. Gong, A. Golubovic, M. Zhou, K.C. Wang, A. Varley, and R.X.Z. Lu
    Nature Communications, 2024
  7. Genome Biology
    DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics
    H. Cui*, H. Maan*, M.C. Vladoiu, J. Zhang, M.D. Taylor, and B. Wang
    Genome Biology, 2024
  8. EMNLP 2022
    CodeExp: Explanatory Code Document Generation
    H. Cui, C. Wang, J. Huang, J.P. Inala, T. Mytkowicz, B. Wang, J. Gao, and N. Duan
    In Findings of the Association for Computational Linguistics: EMNLP 2022, Dec 2022
  9. bioRxiv
    scFormer: a universal representation learning approach for single-cell data using transformers
    H. Cui*, C. Wang*, H. Maan, N. Duan, and B. Wang
    bioRxiv, Dec 2022
  10. ICML 2022
    A Deep Learning Framework for Estimating Cell-specific Kinetic Rates of RNA Velocity
    H. Cui*, H. Maan*, M.D. Taylor, and B. Wang
    In The 2022 ICML Workshop on Computational Biology, Dec 2022
  11. Nature Biomedical Engineering
    Stretchable ultrasonic arrays for the three-dimensional mapping of the modulus of deep tissue
    H. Hu, Y. Ma, X. Gao, D. Song, M. Li, H. Huang, X. Qian, R. Wu, K. Shi, H. Ding, M. Lin, X. Chen, W. Zhao, B. Qi, S. Zhou, R. Chen, Y. Gu, Y. Chen, Y. Lei, C. Wang, C. Wang, Y. Tong, H. Cui, A. Abdal, Y. Zhu, X. Tian, Z. Chen, C. Lu, X. Yang, J. Mu, Z. Lou, M. Eghtedari, Q. Zhou, A. Oberai, and S. Xu
    Nature Biomedical Engineering, Dec 2023
  12. DaSH 2022
    Execution-based Evaluation for Data Science Code Generation Models
    J. Huang, C. Wang, J. Zhang, C. Yan, H. Cui, J.P. Inala, C. Clement, N. Duan, and J. Gao
    In DaSH 2022, Dec 2022