Among these, D-peptides are resistant to proteolysis, exhibit greater in vivo stability, and are easier to synthesize. Despite advances in deep learning for peptide discovery, the scarcity of natural D-protein data limits the transfer of existing generative models to the D-peptide chemical space. We propose D-Flow, a full-atom flow-based framework for de novo D-peptide design. Conditioned on receptor binding, D-Flow uses structural representations incorporating backbone frames, side-chain angles, and discrete amino acid types. A mirror-image algorithm is implemented to address the lack of training data for D-proteins by converting the chirality of L-receptors. Furthermore, we enhance D-Flow's capacity by integrating protein language models (PLMs) with structural awareness through a lightweight structural adapter that injects structural representations into PLM embeddings. This enables D-Flow to learn conformational priors in the D-peptide chemical space and to accommodate the chiral selectivity of binding sites, thereby mitigating the scarcity of D-peptide data. A two-stage training pipeline and a control toolkit enable D-Flow to transition from general protein design to targeted binder design while preserving pre-training knowledge. Results on the PepMerge benchmark show D-Flow's effectiveness. D-peptides generated by D-Flow align more closely with native sequences and structures, with sequence identity improving by 10.2% over the best baseline, and the top affinity score reaching 24.31%. Overall, D-Flow shows potential for D-peptide design, facilitating the development of bioorthogonal and stable molecular tools and diagnostics. Code is available at https://github.com/smiles724/PeptideDesign.

翻译：其中，D-肽具有抗蛋白酶水解、体内稳定性更高且更易合成的优势。尽管深度学习在肽发现领域取得进展，但天然D-蛋白数据的稀缺性限制了现有生成模型向D-肽化学空间的迁移。我们提出D-Flow——一种全原子流框架，用于从头设计D-肽。基于受体结合条件，D-Flow采用包含主链框架、侧链角度与离散氨基酸类型的结构表征。通过镜像算法将L-受体手性转换，以解决D-蛋白训练数据缺失问题。此外，我们通过轻量级结构适配器将结构表征注入蛋白语言模型（PLMs）嵌入，增强D-Flow的结构感知能力。这使D-Flow既能学习D-肽化学空间中的构象先验，又能容纳结合位点的手性选择性，从而缓解D-肽数据稀缺问题。两阶段训练流程与调控工具包使D-Flow能从通用蛋白设计过渡至靶向结合物设计，同时保留预训练知识。在PepMerge基准测试中的结果表明了D-Flow的有效性。D-Flow生成的D-肽更接近天然序列与结构，其序列一致性较最优基线提升10.2%，最高亲和力分数达24.31%。总体而言，D-Flow在D-肽设计中展现出潜力，可推动生物正交、稳定分子工具及诊断技术的发展。代码已开源：https://github.com/smiles724/PeptideDesign。