Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design
This addresses the challenge of antibody design for therapeutic applications, offering a novel co-design approach that could improve efficiency and effectiveness in drug development.
The paper tackles the problem of designing antibody complementarity-determining regions (CDRs) with enhanced binding specificity or neutralization capabilities by co-designing sequence and 3D structure as graphs, achieving superior log-likelihood and outperforming previous baselines in neutralizing SARS-CoV-2.
Antibodies are versatile proteins that bind to pathogens like viruses and stimulate the adaptive immune system. The specificity of antibody binding is determined by complementarity-determining regions (CDRs) at the tips of these Y-shaped proteins. In this paper, we propose a generative model to automatically design the CDRs of antibodies with enhanced binding specificity or neutralization capabilities. Previous generative approaches formulate protein design as a structure-conditioned sequence generation task, assuming the desired 3D structure is given a priori. In contrast, we propose to co-design the sequence and 3D structure of CDRs as graphs. Our model unravels a sequence autoregressively while iteratively refining its predicted global structure. The inferred structure in turn guides subsequent residue choices. For efficiency, we model the conditional dependence between residues inside and outside of a CDR in a coarse-grained manner. Our method achieves superior log-likelihood on the test set and outperforms previous baselines in designing antibodies capable of neutralizing the SARS-CoV-2 virus.