
Through her research, Seul Lee aims to develop machine learning-driven automated frameworks for scientific discovery in chemistry and biology. She focuses on generative models for a variety of molecules such as organic molecules, natural products, and proteins. Specifically, she has developed molecular optimization strategies in chemical space and retrosynthetic pathway planning models for drug discovery applications. Her overarching research goal is to build drug discovery pipelines that can greatly accelerate labor-intensive real-world drug discovery problems.
Seul Lee is a third-year Ph.D. student at Graduate School of AI at KAIST advised by Professor Sung Ju Hwang. Prior to her Ph.D., she received a B.S. degree in Biological Sciences from KAIST and a M.S. degree from KAIST Graduate School. During her Ph.D. she has interned at the NVIDIA Fundamental Generative AI Research (GenAIR) team.