用物理能量场指导语言模型，减少蛋白质设计中的结构幻觉。
Physio-DPO: Aligning Large Language Models with the Protein Energy Landscape to Eliminate Structural Hallucinations
- 基于蛋白质能量景观设计新对齐方法，引入能量差控制优化强度。
- 自洽性均方根偏差降至1.28 Å，折叠成功率提升至92.8%。
- 适合需要高稳定蛋白结构的设计任务，尤其关注生物物理合理性。
大型蛋白质语言模型在生成式蛋白质设计中展现巨大潜力，但常产生结构幻觉，即生成语言上合理却热力学不稳定的序列。现有对齐方法如直接偏好优化受限于将偏好建模为二元标签，忽略了物理能量景观的连续特性。我们提出Physio-DPO，一种融合物理先验的对齐框架，将蛋白质语言模型锚定于热力学稳定性。该方法引入幅度感知目标函数，根据天然结构与物理扰动硬负样本间的能量差动态调整优化更新。实验表明，Physio-DPO持续优于SFT、PPO和标准DPO基线，将自洽性均方根偏差降低至1.28 Å，折叠率提升至92.8%。定性分析进一步显示，Physio-DPO通过恢复疏水核心堆积和氢键网络等生物物理相互作用，有效缓解结构幻觉。
原文摘要 · Abstract (English)
Large Protein Language Models have shown strong potential for generative protein design, yet they frequently produce structural hallucinations, generating sequences with high linguistic likelihood that fold into thermodynamically unstable conformations. Existing alignment approaches such as Direct Preference Optimization are limited in this setting, as they model preferences as binary labels and ignore the continuous structure of the physical energy landscape. We propose Physio-DPO, a physics informed alignment framework that grounds protein language models in thermodynamic stability. Physio-DPO introduces a magnitude aware objective that scales optimization updates according to the energy gap between native structures and physics perturbed hard negatives. Experiments show that Physio-DPO consistently outperforms strong baselines including SFT, PPO, and standard DPO, reducing self consistency RMSD to 1.28 Å and increasing foldability to 92.8%. Qualitative analysis further demonstrates that Physio-DPO effectively mitigates structural hallucinations by recovering biophysical interactions such as hydrophobic core packing and hydrogen bond networks.
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。