Expanding Protein Language Modeling to Protein-Protein Interactions with MSA Pairformer

Summary

Protein language models have excelled at modeling individual proteins, but extending these capabilities to protein complexes remains a major challenge. MSA Pairformer, a parameter-efficient protein language model, generalizes to protein-protein interactions despite being trained exclusively on monomers, enabling accurate prediction of interface variant effects and subfamily-specific homo-oligomeric binding modes.