Chaok Seok

G-screen provides a scalable virtual screening method that combines flexible ligand alignment with protein-aware pharmacophore analysis to efficiently filter large chemical libraries.

ProMiSE evaluates protein multi-state prediction models using a curated dataset of biological conformational changes, revealing limitations in capturing functionally relevant dynamics.

T-SCAPE predicts T-cell immunogenicity using a multi-domain deep learning framework, achieving high accuracy in predicting T-cell activation and antibody-induced ADA potential.

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

This paper introduces MotifGen, a deep learning model that predicts molecular interaction motifs from receptor structures, enabling peptide binder design and small-molecule binding site prediction.

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.

The paper introduces DENOISer, a deep neural network that improves scoring accuracy in model docking by incorporating physical knowledge, outperforming existing tools on benchmark sets.

This study shows that accurate antibody loop structure prediction enables the design of target-specific antibodies without prior structural templates.