로고 로고

AI-driven Discovery of Targeted Protein Degraders — CRBN-based Molecular Glue Degraders

To secure world-leading AI-driven molecular glue degrader (MGD) design technology that controls undruggable disease targets beyond the reach of conventional small molecules,

to secure world-leading AI-driven molecular glue degrader (MGD) design technology,
to pioneer a closed-loop drug-discovery paradigm connecting AI prediction with experimental validation, and
to become a global hub that delivers first-in-class therapeutics through university–government research institute (GRI) convergence.

KEYWORDKeyword

Drug Discovery AI for Science Generative AI Agentic AI Foundation Models

OBJECTIVE Objective

The project strengthens national strategic competitiveness in AI–bio convergence and advanced biotechnology, and creates convergent drug-discovery outcomes—together with a foundation for follow-up non-clinical research
and technology transfer—that neither a university nor a GRI could achieve alone.

INTRODUCTION Director's Message





I am Professor Woo Youn Kim of the Department of Chemistry at KAIST,

leading this research project. Building on artificial intelligence and computational chemistry, we aim to design new protein degraders capable of controlling difficult, undruggable disease targets.

By integrating the predictive power of AI with the experimental and validation capabilities of government research institutes into a single closed loop, we will cultivate both first-in-class therapeutics that genuinely benefit human health and the next generation of drug-discovery talent.

We sincerely appreciate your interest and support.



IMPACT Impact

By securing a first-in-class IPF drug candidate and a CRBN-based MGD discovery AI workflow, the project connects directly to follow-up non-clinical research, joint research, technology transfer, and commercialization.

The resulting AI workflow serves as a general-purpose platform extensible to other diseases and targets, raising national drug-discovery productivity, while the GRI–university collaboration model and dual-mentorship-based talent development foster a sustainable research ecosystem in AI–bio convergence.

TALENT Ideal Talent

Convergent researchers who combine deep understanding of AI algorithms with chemistry and biology domain knowledge in drug discovery, who validate and iterate AI predictions through experiments, and who formulate and test their own hypotheses.

We cultivate next-generation drug-discovery leaders with the autonomy and responsibility to critically review AI reasoning and decide what to accept or reject, and who grow within GRI–university collaboration and global academic–industrial networks.

FACULTY Faculty