Jing Zhang, Ph.D.

Our lab develops AI and computational genomics methods to understand gene regulation, cellular states, and tissue organization in human disease. We build models for single-cell and spatial omics, integrate functional and regulatory genomics, and connect disease-associated molecular programs to perturbation and therapeutic discovery. We apply these approaches across complex disease, including psychiatric, neurodegenerative, substance-use, HIV-associated, and other human disease settings.

1. 01AI & Machine Learning for Single-Cell and Spatial Genomics
2. 02Gene Regulation & Functional Genomics
3. 03Human Disease Genomics
4. 04AI-Guided Perturbation & Therapeutic Discovery

• Identifying Combinatorial Regulatory Genes for Cell Fate Decision via Reparameterizable Subset Explanations

  Junhao Liu, Pengpeng Zhang, Martin Renqiang Min, Jing Zhang

  KDD · 2025

  • AI/ML for Single-Cell & Spatial
  • Perturbation / Therapeutic Discovery

  • Paper: Identifying Combinatorial Regulatory Genes for Cell Fate Decision via Reparameterizable Subset Explanations

• Single-cell genomics and regulatory networks for 388 human brains

  Prashant S. Emani, Jason J. Liu, Declan Clarke, et al.

  Science · 2024

  • Gene Regulation
  • Human Disease Genomics

  • Paper: Single-cell genomics and regulatory networks for 388 human brains

• DeepVelo: Single-cell transcriptomic deep velocity field learning with neural ordinary differential equations

  Zhanlin Chen, William C. King, Aheyon Hwang, Mark Gerstein, Jing Zhang

  Science Advances · 2022

  • AI/ML for Single-Cell & Spatial
  • Perturbation / Therapeutic Discovery

  • Paper: DeepVelo: Single-cell transcriptomic deep velocity field learning with neural ordinary differential equations

• DIRECT-NET: An efficient method to discover cis-regulatory elements and construct regulatory networks from single-cell multiomics data

  Lihua Zhang, Jing Zhang, Qing Nie

  Science Advances · 2022

  • AI/ML for Single-Cell & Spatial
  • Gene Regulation

  • Paper: DIRECT-NET: An efficient method to discover cis-regulatory elements and construct regulatory networks from single-cell multiomics data