Yan Kai

I am an AI × Omics researcher in drug discovery and development. I am currently a Principal Scientist at Bristol Myers Squibb, where I focus on integrating AI with large-scale biological data to accelerate the discovery of protein degraders (e.g., molecular glues and PROTACs) and induced-proximity therapeutics (e.g., RIPTACs).

My work spans the full drug discovery pipeline—from target identification and validation to lead optimization and clinical development. I am particularly interested in the following questions:

• How can we model multi-modal, noisy, and heterogeneous biological data across scales to better understand disease biology and drug response?
• How can AI be used to design novel therapeutics with desired molecular and pharmacological properties?
• How can large language models and AI agents accelerate drug discovery, from target identification and hypothesis generation to patient stratification and clinical trial design?

To address these challenges, I develop and apply AI/ML methods to large-scale biological datasets, including genomics, transcriptomics, proteomics, and CRISPR screens. I also build AI agents that support decision-making across drug discovery and development.

Previously, I completed my research fellowship training at Harvard Medical School and Dana-Farber Cancer Institute, working with Dr. Stuart Orkin and Dr. Guo-Cheng Yuan. I received my Ph.D. from George Washington University (with Dr. Weiqun Peng and Alexandros Tzatsos).