ABOPD：通过策略蒸馏进行抗体CDR设计
ABOPD: Antibody CDR Design via On-Policy Distillation
浏览论文内容
中文总结 AI 辅助
研究针对抗体CDR设计，提出基于策略蒸馏的ABOPD框架，利用天然几何结构监督模型去噪轨迹，提升了RAbD CDR-H3生成的结构恢复，降低均方根偏差，优于其他控制方法，为高保真蛋白质设计开辟道路。
中文摘要 AI 辅助
抗体是重要的治疗分子，其互补决定区（CDR）构成主要抗原识别界面。近期蛋白质生成模型在生物分子设计中有广泛能力，但下游目标的训练后策略有限。标准去噪训练基于扰动天然结构得到的噪声状态，递归生成则通过模型生成的中间状态。对于像CDR-H3这样的灵活抗体CDR环，这种不匹配会使主链偏差沿去噪轨迹积累并损害面向抗原的环几何形状。我们引入ABOPD，一个基于策略蒸馏的抗体设计框架，在训练期间利用特权天然几何结构监督沿模型自身去噪轨迹访问的状态。通过这种细粒度结构监督，ABOPD显著改善了RAbD CDR-H3生成的结构恢复，将均方根偏差降低了0.42 Å（从2.37 Å降至1.95 Å），优于监督微调及离线蒸馏控制，为更高保真蛋白质设计提供了途径。
英文摘要
Antibodies are essential therapeutic molecules, and their complementarity-determining regions (CDRs) form the primary antigen-recognition interface. Recent protein generative models have demonstrated broad capabilities in biomolecular design, yet post-training strategies for downstream objectives remain limited. Standard denoising training operates on noisy states obtained by perturbing native structures, whereas recursive generation proceeds through model-generated intermediate states. For flexible antibody CDR loops such as CDR-H3, this mismatch can allow backbone deviations to accumulate along the denoising trajectory and compromise antigen-facing loop geometry. We introduce ABOPD, an antibody design framework based on on-policy distillation that leverages privileged native geometry during training to supervise states visited along the model's own denoising trajectories. With this fine-grained structural supervision, ABOPD substantially improves structural recovery on RAbD CDR-H3 generation, reducing RMSD by 0.42 Å (from 2.37 Å to 1.95 Å) and outperforming supervised fine-tuning and offline distillation controls, offering a path to higher-fidelity protein design.
