CISE Seminar: Byung-Jun Yoon, Professor, Electrical and Computer Engineering, Texas A&M University

Accelerating Molecular Design and Discovery Through Uncertainty-Aware AI

Molecular design and discovery have traditionally been labor-intensive and time-consuming endeavors. Although the development of quantitative structure–activity relationship (QSAR) models has significantly accelerated drug discovery by enabling predictive modeling of molecular properties, direct optimization within the vast and high-dimensional molecular/chemical space remains a formidable challenge. High-throughput virtual screening (HTVS) has proven to be a valuable tool, but its application to large-scale molecular libraries often incurs prohibitive computational costs. Furthermore, conventional HTVS pipelines frequently rely on expert-driven heuristics, which can limit their overall efficiency and predictive accuracy. In this talk, we will discuss how AI-driven strategies can be harnessed to address these challenges, enabling smarter design and faster discovery. We will explore recent advances in generative AI models for multi-objective molecular design and examine how AI-based methods can enhance the design and execution of HTVS campaigns. Special emphasis will be placed on the role of uncertainty-aware modeling, which facilitates robust and data-efficient decision-making in the presence of complex and noisy molecular landscapes. By integrating techniques such as uncertainty quantification, active learning, and optimal experimental design, these AI-driven strategies not only accelerate discovery but also improve the reliability of outcomes in real-world settings that are often resource-constrained and data-scarce.

Dr. Byung-Jun Yoon received the B.S. degree from the Seoul National University and the M.S. and Ph.D. degrees from the California Institute of Technology, all in Electrical Engineering. Since 2008, he has been with the Department of Electrical and Computer Engineering, Texas A&M University, where he is currently a Professor. Dr. Yoon holds a joint appointment at Brookhaven National Laboratory, where he is a Scientist in Computing and Data Sciences (CDS), Applied Mathematics Department. He received the NSF CAREER Award, Best Paper Awards at the 9th Asia Pacific Bioinformatics Conference and the 12th Annual MCBIOS Conference, and the SLATE Teaching Excellence Award from the Texas A&M University. Dr. Yoon’s main research interests lie in AI for Science, objective-based uncertainty quantification, optimal experimental design, and decision-making under uncertainty. He is actively working on the development of these methods and their application to various scientific domains, including life science

Faculty Host: Yannis Paschalidis

Student Host: Ilker Isik