Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design
This work addresses the challenge of designing therapeutic D-peptide binders for L-proteins, offering a novel generative AI approach with wet-lab validation, which is not incremental as it represents the first such validated method for this task.
The paper tackled the problem of designing D-peptide binders for L-proteins, which is underexplored in machine learning, by achieving cross-chirality generalization from L--L training data to D--L tasks, resulting in D-peptide binder designs that outperformed existing tools in benchmarks and demonstrated efficacy in wet-lab validation.
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.