Jeonghyeon Kim

This paper benchmarks LLM agents in protein design tasks, finding they outperform hardcoded pipelines but underperform expert practice due to limited evaluation depth.

PRISM improves antibody language modeling by distinguishing germline and non-germline residues, achieving better binding affinity correlation and controllable generation.

AlphaFast accelerates AlphaFold 3 by using GPU-accelerated MSA construction, achieving significant speedups and cost reductions while maintaining structural accuracy.

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.