Generative Diffusion Models for Antibody Design, Docking, and Optimization

Abstract

In recent years, optimizing antibody binding affinity for biomedical applications has become increasingly important. However, traditional wet-experiment-based approaches are time-consuming and inefficient. To address this issue, we propose a diffusion model-based antibody optimization pipeline to improve binding affinity. Our approach involves two key models: AbDesign for designing antibody sequences and structures, and AbDock, a paratope-epitope docking model, used for screening designed CDRs. On an independent test set, our AbDesign demonstrates the exceptional performance of an RMSD of 2.56[A] in structure design and an amino acid recovery of 36.47% in sequence design. In a paratope-epitope docking test set, our AbDock achieves a state-of-the-art performance of DockQ 0.44, irms 2.71[A], fnat 0.40, and Lrms 6.29[A]. The effectiveness of the optimization pipeline is further experimentally validated by optimizing a flaviviruse antibody 1G5.3, resulting in a broad-spectrum antibody that demonstrates improved binding to 6 out of the nine tested flaviviruses. This research offers a general-purpose methodology to enhance antibody functionality without training on data from specific antigens.