Abstract: In this lecture, Dr. Deng will highlight several exciting applications of AI and digital twins for precision medicine and discuss some of the major challenges in implementing AI and digital twins for healthcare and medicine in the coming years.

Abstract: Randomized controlled trials (RCTs) remain the gold standard for evaluating the efficacy and safety of medical interventions. However, they are time-consuming and expensive to conduct. We propose a multi-agent framework where a team of AI agents, each focused on a specific task, collaborate to streamline workflows in clinical trials. The talk will highlight our recent work on leveraging this framework to infer and accelerate trial design by deriving real-world evidence from real-world data in the pre-trial stage. The future opportunities and challenges associated with this framework will also be discussed. 

Abstract: The discovery of new drug candidates is challenged by the vastness of chemical space and the inefficiency of traditional approaches. Generative machine learning models provide new opportunities by enabling the automated design of novel molecules. This talk will review genAI methods across three main directions: 1D SMILES-based language models, 2D graph-based generation, and diffusion models for 3D molecular structures. While SMILES and graph methods support efficient and valid molecular design, diffusion approaches improve the accuracy and stability of 3D generation. We will highlight recent progress from our group, including knowledge-infused hierarchical modeling, real-time feedback in SMILES generation, and an annealing-based diffusion framework for 3D structures. Together, these developments illustrate the potential of generative AI to accelerate drug discovery and deliver novel, synthesizable candidates.