Chenchen Han

Evolla, a protein-language model, improves functional inference and discovers novel proteins through natural language queries and benchmarking.

Pairing each residue with its Foldseek 3D-structure token and pre-training an ESM-2-sized model on about 40 million AlphaFold2 structures beat ESM-2 and structure-based baselines on variant-effect and function tasks.

This paper introduces a diffusion model-based pipeline for antibody design and optimization, achieving high performance in structure and sequence design and docking, validated by improved binding to flaviviruses.