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

2026/02/13 by Ziyi Yang, Zitong Tian, Yinjun Jia +7 · 1 voice · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #cs.LG #q-bio.BM

paper · pdf · doi:10.48550/arxiv.2602.20176

arxiv published 2026/02/13 · arxiv updated 2026/05/29

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. Codes are available at https://github.com/YZY010418/PepMirror

Citations

• Unified all-atom molecule generation with neural fields
• UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design
• E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products
• Stereochemistry in the disorder–order continuum of protein interactions
• Full-Atom Peptide Design based on Multi-modal Flow Matching
• Target-Specific De Novo Peptide Binder Design with DiffPepBuilder
• PPFlow: Target-aware Peptide Design with Torsional Flow Matching
• A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications
• Full-Atom Peptide Design with Geometric Latent Diffusion
• De novo design of protein structure and function with RFdiffusion
• Geometry-Complete Perceptron Networks for 3D Molecular Graphs
• High-Resolution Image Synthesis with Latent Diffusion Models
• High-Resolution Image Synthesis with Latent Diffusion Models
• Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations
• Highly accurate protein structure prediction with AlphaFold
• E(n) Equivariant Graph Neural Networks
• Message Passing Networks for Molecules with Tetrahedral Chirality
• Learning from Protein Structure with Geometric Vector Perceptrons
• Finding symmetry breaking order parameters with Euclidean neural networks
• SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• An Equivariant Pretrained Transformer for Unified 3D Molecular Representation Learning

Discussions

• Yang, Tian, Jia, Zhang, Zheng, Wang, Su, He, Liu, Lan: Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design https://arxiv.org/abs/2602.20176 https://arx [bsky, 0 points, 0 comments]

Related

• D-Flow: Multi-modality Flow Matching for D-peptide Design
• Computational design of target-specific linear peptide binders with TransformerBeta
• THFlow: A Temporally Hierarchical Flow Matching Framework for 3D Peptide Design
• PPFlow: Target-aware Peptide Design with Torsional Flow Matching
• ApexGen: Simultaneous design of peptide binder sequence and structure for target proteins