EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation
Three new research papers introduce advanced AI architectures for antibody complementarity-determining region (CDR) design. ConTact and AgForce tackle the challenge of explicitly reasoning about CDR-antigen contacts, improving structural quality and epitope awareness. EvoStruct bridges protein language models with equivariant graph neural networks, addressing vocabulary collapse and enhancing sequence recovery by leveraging evolutionary data. AI
IMPACT These new models offer improved accuracy and diversity in antibody design, potentially accelerating drug discovery and therapeutic development.