Latent Retrieval Augmented Generation of Cross-Domain Protein Binders
This addresses the problem of insufficient rationality and interpretability in protein binder design for drug discovery, establishing a new paradigm that bridges retrieval-based knowledge and generative AI.
The paper tackled the challenge of designing realistic and functional protein binders by proposing RADiAnce, a framework that leverages known interfaces to guide novel binder generation, resulting in significant outperformance over baselines in metrics like binding affinity and geometry recovery.
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.