Keynote Speaker

Sun Kim

Director of Bioinformatics Institute
Professor at Seoul National University

Website: https://bhi-kimlab.github.io/members/sun_kim.html


AI Technologies for Target-Driven Small Molecule Drug Discovery and Development

Abstract:
Target-driven small molecule drug discovery is inherently multidisciplinary, requiring close collaboration among medicinal chemists, biologists, and clinical scientists. With the rapid advancement of artificial intelligence, leveraging AI tools has become standard practice in modern drug development. When successfully implemented, the ultimate breakthrough of AI lies in its ability to dissolve traditional disciplinary silos, seamlessly integrating chemistry, biology, and medicine into a unified workflow.
    Achieving this ambitious goal requires advanced AI technologies capable of effectively navigating the vast, interconnected chemistry-biology-medicine (Che-Bio-Med) space. In this talk, I will share our research insights and practical experiences addressing this challenge at AIGENDRUG Co. Ltd. and Seoul National University.
     From a computer science perspective, this problem must be evaluated through three interconnected pillars: data availability, objective functions (endpoints), and model architectures. While data is critical for constructing deep learning embedding spaces, data availability must always be contextualized by the specific clinical endpoints we aim to predict. Although patients represent the ultimate endpoint, clinical data remains severely limited—a bottleneck that standalone AI tools cannot solve in isolation.
     Consequently, we must orchestrate an ensemble of specialized AI tools structured around these endpoints. While numerous foundation models already exist to define individual chemistry, biology, and medicine spaces, the true challenge lies in configuring these models to navigate across spaces. Specifically, we must determine the optimal regions and search directions within complex embedding spaces.
     To solve this, we incorporate a "Human-in-the-Loop" (HITL) strategy. By integrating expert human feedback, we can iteratively refine AI models at each stage of the Che-Bio-Med navigation process using small volumes of proprietary assay data. Throughout this presentation, we will introduce our suite of AI tools and demonstrate how they orchestrate this multi-stage, iterative navigation across the chemistry, biology, and medicine layers.

Biography:
Sun Kim is Professor in the School of Computer Science and Engineering, Adjunct Professor of Biological Sciences, and Director of Bioinformatics Institute (2011-2021) at Seoul National University and Founder/CEO of AIGENDRUG Co. Ltd. He is a member of National Academy of Engineering Korea; a Division Chair (2024-2026) and Advisor (2026-2028) of Korea Presidential Committee on Artificial Intelligence (2024-2026). Until recently, he was President of MOGAM Institute of Biomedical Research (2022-2024). Before joining SNU, he was Chair of Faculty Division C; Director of Center for Bioinformatics Research, an Associate Professor in School of Informatics and Computing at Indiana University (IU) Bloomington. Prior to joining IU in 2001, he worked at DuPont Central Research from 1998 to 2001, and at the University of Illinois at Urbana-Champaign from 1997 to 1998. Sun Kim received B.S and M.S and Ph.D in Computer Science from Seoul National University, KAIST and the University of Iowa, respectively.