Seongok Ryu

This paper evaluates GaluxDesign, an AI platform, for de novo antibody design, showing a 10.5% binder rate and strong performance on benchmark targets.

SHARP generates drug-like molecules using reinforcement learning with a fragment-based action space, improving synthesizability and binding affinity over existing methods.

This study designs antibodies without prior information across eight targets, achieving high precision, sensitivity, and specificity, validated by Cryo-EM and comparable to commercial antibodies.