Latent Retrieval Augmented Generation of Cross-Domain Protein Binders

2025-10-12

AI Summary

Designing site-specific protein binders remains challenging due to insufficient structural validity and functional fidelity of generated candidates. To address this, we propose RADiAnce—a novel framework that unifies cross-domain protein interface retrieval and conditional latent diffusion generation within a shared latent space constructed via contrastive learning, enabling knowledge-guided interface generation. Leveraging multi-source interface data, RADiAnce facilitates structure–function knowledge transfer across diverse protein families in the latent space, markedly improving geometric fidelity, interaction plausibility, and binding affinity prediction accuracy of generated binding modes. Extensive experiments demonstrate that RADiAnce outperforms existing baselines across multiple metrics—including interface RMSD, contact precision, and affinity correlation—and exhibits strong cross-domain generalization. By integrating retrieval-based prior knowledge with generative modeling in a unified latent space, RADiAnce establishes a new paradigm for rational, target-specific binder design.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Generation

Application Category

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

Abstract

Designing protein binders targeting specific sites, which requires to generate realistic and functional interaction patterns, is a fundamental challenge in drug discovery. Current structure-based generative models are limited in generating nterfaces with sufficient rationality and interpretability. In this paper, we propose Retrieval-Augmented Diffusion for Aligned interface (RADiAnce), a new framework that leverages known interfaces to guide the design of novel binders. By unifying retrieval and generation in a shared contrastive latent space, our model efficiently identifies relevant interfaces for a given binding site and seamlessly integrates them through a conditional latent diffusion generator, enabling cross-domain interface transfer. Extensive exeriments show that RADiAnce significantly outperforms baseline models across multiple metrics, including binding affinity and recovery of geometries and interactions. Additional experimental results validate cross-domain generalization, demonstrating that retrieving interfaces from diverse domains, such as peptides, antibodies, and protein fragments, enhances the generation performance of binders for other domains. Our work establishes a new paradigm for protein binder design that successfully bridges retrieval-based knowledge and generative AI, opening new possibilities for drug discovery.

Problem

• Generating realistic protein binders for drug discovery
• Improving rationality of structure-based generative models
• Enabling cross-domain interface transfer through retrieval augmentation

Innovation

• Unifies retrieval and generation in shared latent space
• Uses conditional latent diffusion for interface transfer
• Retrieves interfaces from diverse domains to enhance generation