用扭转角扩散生成蛋白骨架，确保几何准确且结构紧凑。
Torsion-Space Diffusion for Protein Backbone Generation with Geometric Refinement
- 在扭转角空间生成骨架，天然满足键长键角约束
- 键长准确率100%，半径均方根误差降至18.6%
- 适合需要高精度蛋白结构生成的研究者
设计新蛋白质结构是计算生物学的基础，有助于治疗分子发现和酶工程。现有基于扩散的生成模型通常在笛卡尔坐标空间中运行，加噪会破坏键长、键角等严格几何约束，常生成物理无效结构。为此，我们提出一种扭转角扩散模型，通过去噪扭转角生成蛋白骨架，从构建上保证局部几何正确性。采用可微分正向运动学模块重建3D坐标，固定主链键长为3.8埃；再通过约束后处理优化全局紧凑性，以半径均方根（Rg）校正为目标，不违反键约束。标准PDB蛋白实验表明，该方法实现100%键长准确率，Rg误差由基线的70%降低至18.6%。整体框架结合扭转角扩散与几何精修，生成物理有效且结构紧凑的蛋白骨架，为全原子蛋白生成提供了可行路径。
原文摘要 · Abstract (English)
Designing new protein structures is fundamental to computational biology, enabling advances in therapeutic molecule discovery and enzyme engineering. Existing diffusion-based generative models typically operate in Cartesian coordinate space, where adding noise disrupts strict geometric constraints such as fixed bond lengths and angles, often producing physically invalid structures. To address this limitation, we propose a Torsion-Space Diffusion Model that generates protein backbones by denoising torsion angles, ensuring perfect local geometry by construction. A differentiable forward-kinematics module reconstructs 3D coordinates with fixed 3.8 Angstrom backbone bond lengths while a constrained post-processing refinement optimizes global compactness via Radius of Gyration (Rg) correction, without violating bond constraints. Experiments on standard PDB proteins demonstrate 100% bond-length accuracy and significantly improved structural compactness, reducing Rg error from 70% to 18.6% compared to Cartesian diffusion baselines. Overall, this hybrid torsion-diffusion plus geometric-refinement framework generates physically valid and compact protein backbones, providing a promising path toward full-atom protein generation.
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。