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

Ziyi Yang, Zitong Tian, Yinjun Jia, Tianyi Zhang, Jiqing Zheng, Hao Wang, Yubu Su, Juncai He, Lei Liu, Yanyan Lan
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:146136-146169, 2026.

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 experimentally validated AI generative model for the 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

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-yang26by, title = {Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design}, author = {Yang, Ziyi and Tian, Zitong and Jia, Yinjun and Zhang, Tianyi and Zheng, Jiqing and Wang, Hao and Su, Yubu and He, Juncai and Liu, Lei and Lan, Yanyan}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {146136--146169}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/yang26by/yang26by.pdf}, url = {https://proceedings.mlr.press/v306/yang26by.html}, 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 experimentally validated AI generative model for the 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} }
Endnote
%0 Conference Paper %T Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design %A Ziyi Yang %A Zitong Tian %A Yinjun Jia %A Tianyi Zhang %A Jiqing Zheng %A Hao Wang %A Yubu Su %A Juncai He %A Lei Liu %A Yanyan Lan %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-yang26by %I PMLR %P 146136--146169 %U https://proceedings.mlr.press/v306/yang26by.html %V 306 %X 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 experimentally validated AI generative model for the 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
APA
Yang, Z., Tian, Z., Jia, Y., Zhang, T., Zheng, J., Wang, H., Su, Y., He, J., Liu, L. & Lan, Y.. (2026). Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:146136-146169 Available from https://proceedings.mlr.press/v306/yang26by.html.

Related Material