多尺度蛋白质结构建模与几何图U-网络
Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets
AI总结：
本文提出几何图U-网络，通过递归粗化和细化蛋白质图，实现多尺度结构建模，显著提升蛋白质折叠分类性能。
摘要：
几何图神经网络（GNNs）和Transformer已成为从3D蛋白质结构中学习的最新技术。然而，它们依赖于消息传递，限制了捕捉支配蛋白质功能的层次相互作用，如全局领域和远距离别构调节。在本工作中，我们主张网络架构本身应反映这种生物层次结构。我们引入了几何图U-网络，一种新的模型，通过递归粗化和细化蛋白质图来学习多尺度表示。我们证明这种层次设计在理论上比标准几何GNNs更具表现力。在蛋白质折叠分类任务中，几何U-网络显著优于不变和等变基线，展示了其学习定义蛋白质折叠的全局结构模式的能力。我们的工作为设计能够学习生物分子多尺度结构的几何深度学习架构提供了原则性基础。
英文摘要：
Geometric Graph Neural Networks (GNNs) and Transformers have become state-of-the-art for learning from 3D protein structures. However, their reliance on message passing prevents them from capturing the hierarchical interactions that govern protein function, such as global domains and long-range allosteric regulation. In this work, we argue that the network architecture itself should mirror this biological hierarchy. We introduce Geometric Graph U-Nets, a new class of models that learn multi-scale representations by recursively coarsening and refining the protein graph. We prove that this hierarchical design can theoretically more expressive than standard Geometric GNNs. Empirically, on the task of protein fold classification, Geometric U-Nets substantially outperform invariant and equivariant baselines, demonstrating their ability to learn the global structural patterns that define protein folds. Our work provides a principled foundation for designing geometric deep learning architectures that can learn the multi-scale structure of biomolecules.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
