Relation-Aware Equivariant Graph Networks for Epitope-Unknown Antibody Design and Specificity Optimization

TL;DR

This paper introduces RAAD, a relation-aware graph network framework that dynamically models antigen-antibody interactions, improving CDR design and specificity optimization for antibody development.

Contribution

The paper presents a novel relation-aware graph network framework for dynamic modeling of antigen-antibody interactions, enhancing CDR design and specificity during antibody optimization.

Findings

RAAD outperforms existing methods in antibody modeling and generation.

The framework effectively improves antibody specificity and structural accuracy.

Extensive experiments validate RAAD's robustness across various CDR types and input contexts.

Abstract

Antibodies are Y-shaped proteins that protect the host by binding to specific antigens, and their binding is mainly determined by the Complementary Determining Regions (CDRs) in the antibody. Despite the great progress made in CDR design, existing computational methods still encounter several challenges: 1) poor capability of modeling complex CDRs with long sequences due to insufficient contextual information; 2) conditioned on pre-given antigenic epitopes and their static interaction with the target antibody; 3) neglect of specificity during antibody optimization leads to non-specific antibodies. In this paper, we take into account a variety of node features, edge features, and edge relations to include more contextual and geometric information. We propose a novel Relation-Aware Antibody Design (RAAD) framework, which dynamically models antigen-antibody interactions for co-designing the sequences and structures of antigen-specific CDRs. Furthermore, we propose a new evaluation metric to better measure antibody specificity and develop a contrasting specificity-enhancing constraint to optimize the specificity of antibodies. Extensive experiments have demonstrated the superior capability of RAAD in terms of antibody modeling, generation, and optimization across different CDR types, sequence lengths, pre-training strategies, and input contexts.