用自监督结构约束提升抗体结合区生成精度
ABOPD: Antibody CDR Design via On-Policy Distillation
- 训练时用原始结构引导模型自身生成路径，实时修正构象偏差
- 在RAbD数据集上使CDR-H3结构误差降低0.42埃（2.37→1.95Å）
- 适合抗体药物设计、高精度蛋白生成方向的研究者
抗体是重要的治疗分子，其互补决定区（CDRs）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展现出广泛能力，但针对下游目标的后训练策略仍有限。标准去噪训练依赖对天然结构扰动得到的噪声状态，而递归生成则通过模型生成的中间状态进行。对于如CDR-H3这类灵活的抗体环区，这种不匹配会导致主链偏差沿去噪轨迹累积，影响抗原面向的环结构几何。我们提出ABOPD，一种基于策略内蒸馏的抗体设计框架，利用训练期间的特权天然几何信息，监督模型自身去噪轨迹中经过的状态。通过这种细粒度结构监督，ABOPD在RAbD CDR-H3生成任务中显著提升结构恢复能力，将均方根偏差（RMSD）降低0.42 Å（从2.37 Å降至1.95 Å），优于有监督微调和离线蒸馏对照组，为更高保真度的蛋白质设计提供新路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。