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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Ziyi, Tian, Zitong, Jia, Yinjun, Zhang, Tianyi, Zheng, Jiqing, Wang, Hao, Su, Yubu, He, Juncai, Liu, Lei, Lan, Yanyan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910271152324608
author Yang, Ziyi
Tian, Zitong
Jia, Yinjun
Zhang, Tianyi
Zheng, Jiqing
Wang, Hao
Su, Yubu
He, Juncai
Liu, Lei
Lan, Yanyan
author_facet Yang, Ziyi
Tian, Zitong
Jia, Yinjun
Zhang, Tianyi
Zheng, Jiqing
Wang, Hao
Su, Yubu
He, Juncai
Liu, Lei
Lan, Yanyan
contents 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 \textit{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 \textit{de novo} design of D-peptide binders, offering new perspectives on handling chirality in protein design. Codes are available at https://github.com/YZY010418/PepMirror
format Preprint
id arxiv_https___arxiv_org_abs_2602_20176
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design
Yang, Ziyi
Tian, Zitong
Jia, Yinjun
Zhang, Tianyi
Zheng, Jiqing
Wang, Hao
Su, Yubu
He, Juncai
Liu, Lei
Lan, Yanyan
Biomolecules
Machine Learning
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 \textit{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 \textit{de novo} design of D-peptide binders, offering new perspectives on handling chirality in protein design. Codes are available at https://github.com/YZY010418/PepMirror
title Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design
topic Biomolecules
Machine Learning
url https://arxiv.org/abs/2602.20176