Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization

2024-10-19

International Conference on Learning Representations

AI Summary

Existing de novo antibody generation methods lack structural template constraints, resulting in unnatural sequences and suboptimal optimization. Method: We propose RADAb, a structure-guided retrieval-augmented diffusion framework that introduces a novel structure-aware retrieval mechanism and a dual-branch denoising module, jointly encoding geometric structural information and multi-scale evolutionary features. RADAb adopts a conditional diffusion paradigm to jointly model global structural context and local evolutionary signals, and employs inverse-folding conditioning for precise sequence optimization. Contribution/Results: RADAb achieves state-of-the-art performance across multiple antibody inverse-folding and affinity optimization benchmarks. It significantly improves sequence plausibility, structural fidelity, and consistency with binding affinity predictions—demonstrating superior integration of structural and evolutionary priors in generative antibody design.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Structured Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Antibodies are essential proteins responsible for immune responses in organisms, capable of specifically recognizing antigen molecules of pathogens. Recent advances in generative models have significantly enhanced rational antibody design. However, existing methods mainly create antibodies from scratch without template constraints, leading to model optimization challenges and unnatural sequences. To address these issues, we propose a retrieval-augmented diffusion framework, termed RADAb, for efficient antibody design. Our method leverages a set of structural homologous motifs that align with query structural constraints to guide the generative model in inversely optimizing antibodies according to desired design criteria. Specifically, we introduce a structure-informed retrieval mechanism that integrates these exemplar motifs with the input backbone through a novel dual-branch denoising module, utilizing both structural and evolutionary information. Additionally, we develop a conditional diffusion model that iteratively refines the optimization process by incorporating both global context and local evolutionary conditions. Our approach is agnostic to the choice of generative models. Empirical experiments demonstrate that our method achieves state-of-the-art performance in multiple antibody inverse folding and optimization tasks, offering a new perspective on biomolecular generative models.

Problem

• Designing antibodies from scratch lacks template constraints causing unnatural sequences
• Existing methods face optimization challenges without structural guidance mechanisms
• Need for structure-informed generation that aligns with query constraints

Innovation

• Retrieval-augmented diffusion framework for antibody design
• Structure-informed retrieval with dual-branch denoising module
• Conditional diffusion model with global-local evolutionary refinement