Jinsol Yang

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

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 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 identifies and validates four kynureninases using homology searches and protein language models, with the most active one showing significant tumor reduction in mouse models.

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