dyAb: Flow Matching for Flexible Antibody Design with AlphaFold-driven Pre-binding Antigen
This work addresses the challenge of designing therapeutic antibodies by accounting for dynamic antigen conformations, which is incremental as it builds on existing computational methods with specific enhancements.
The paper tackled the problem of antibody design by addressing overlooked conformational changes in antigens during binding, introducing dyAb which incorporates AlphaFold2-driven predictions and flow matching techniques to model pre-binding antigen structures, resulting in significant outperformance over existing models in experiments.
The development of therapeutic antibodies heavily relies on accurate predictions of how antigens will interact with antibodies. Existing computational methods in antibody design often overlook crucial conformational changes that antigens undergo during the binding process, significantly impacting the reliability of the resulting antibodies. To bridge this gap, we introduce dyAb, a flexible framework that incorporates AlphaFold2-driven predictions to model pre-binding antigen structures and specifically addresses the dynamic nature of antigen conformation changes. Our dyAb model leverages a unique combination of coarse-grained interface alignment and fine-grained flow matching techniques to simulate the interaction dynamics and structural evolution of the antigen-antibody complex, providing a realistic representation of the binding process. Extensive experiments show that dyAb significantly outperforms existing models in antibody design involving changing antigen conformations. These results highlight dyAb's potential to streamline the design process for therapeutic antibodies, promising more efficient development cycles and improved outcomes in clinical applications.