用分层图网络捕捉蛋白质多尺度结构，提升折叠分类性能
Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets
- 通过递归粗化与细化蛋白图，构建分层表示
- 在蛋白质折叠分类任务中显著优于基线模型
- 适合研究生物分子多尺度结构的学者使用
几何图神经网络（Geometric GNNs）和Transformer已成为学习三维蛋白结构的前沿方法。然而，其依赖消息传递机制难以捕捉调控蛋白质功能的层级相互作用，如全局结构域和远距离变构调节。本文主张网络架构应反映这一生物学层次结构。我们提出几何图U-Net，通过递归粗化与细化蛋白图，学习多尺度表示。理论上证明该设计比标准几何GNN更具表达能力。实验上，在蛋白质折叠分类任务中，几何U-Net显著优于不变性和等变性基线模型，展现出对定义蛋白质折叠的全局结构模式的学习能力。本工作为设计可学习生物分子多尺度结构的几何深度学习架构提供了理论基础。
原文摘要 · Abstract (English)
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.
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。