Kim Lab published in Science magazine for their approach combining the 3D structure of the protein backbone with large language models based on amino acid sequence.

Biochemistry Professor Peter S. Kim, Assistant Professor of Chemical Engineering and Stanford Data Science faculty Brian Hie, and members from Kim Lab co-led research on a new machine learning-based method for designing antibody drugs. The method was shown to improve a once FDA-approved SARS-CoV-2 antibody that had been discontinued due to ineffectiveness.

https://news.stanford.edu/stories/2024/07/new-ai-approach-to-faster-more-accurately-predict-improved-antibody-drugs