Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design

2026-02-13

arXiv.org

AI Summary

Existing methods struggle to generalize from homochiral data of L-proteins and L-peptides to design D-peptide binders targeting L-proteins. This work proposes a chirality-aware E(3)-equivariant latent diffusion model that explicitly encodes chiral geometry through axial vector features, enabling, for the first time, cross-chirality generation of D-peptides from homochiral training data. By overcoming the fundamental limitation of conventional models in handling chirality inversion, the method outperforms current computational tools in in silico evaluations. Crucially, wet-lab experiments confirm that the designed D-peptides exhibit effective binding affinity, establishing this approach as the first AI-driven de novo D-peptide design framework validated experimentally.

Abstract

D-peptide binders targeting L-proteins have promising therapeutic potential. Despite rapid advances in machine learning-based target-conditioned peptide design, generating D-peptide binders remains largely unexplored. In this work, we show that by injecting axial features to $E(3)$-equivariant (polar) vector features,it is feasible to achieve cross-chirality generalization from homo-chiral (L--L) training data to hetero-chiral (D--L) design tasks. By implementing this method within a latent diffusion model, we achieved D-peptide binder design that not only outperforms existing tools in in silico benchmarks, but also demonstrates efficacy in wet-lab validation. To our knowledge, our approach represents the first wet-lab validated generative AI for the de novo design of D-peptide binders, offering new perspectives on handling chirality in protein design.

Problem

• cross-chirality generalization
• D-peptide design
• hetero-chiral interaction
• protein-peptide binding
• chirality

Innovation

• axial vectors
• cross-chirality generalization
• E(3)-equivariant
• D-peptide design
• latent diffusion model