用预训练图网络+令牌混合器自动提取分子构象动态特征
Using pretrained graph neural networks with token mixers as geometric featurizers for conformational dynamics
- 用自监督去噪预训练图神经网络获取通用几何特征
- 无需微调即可捕捉原子间可解释的结构关系
- 适合大分子系统分析，降低计算资源需求
在分子模拟中，识别能表征构象动态的低维特征仍具挑战，常需大量手动调参和体系特异性知识。本文提出geom2vec，利用预训练的等变图神经网络（GNNs）作为通用几何特征提取器。通过在大规模分子构象数据集上以自监督去噪目标预训练，获得可迁移的结构表示，无需进一步微调即可用于学习构象动态。我们展示如何将学习到的GNN特征与表达性强的令牌混合器结合，捕捉结构单元（令牌）间的可解释关系。关键在于，将GNN训练与下游任务解耦，使在有限计算资源下分析更大分子图（如全原子分辨率的小蛋白）成为可能。geom2vec消除了手动特征选择的需求，提升了模拟分析的鲁棒性。
原文摘要 · Abstract (English)
Identifying informative low-dimensional features that characterize dynamics in molecular simulations remains a challenge, often requiring extensive manual tuning and system-specific knowledge. Here, we introduce geom2vec, in which pretrained graph neural networks (GNNs) are used as universal geometric featurizers. By pretraining equivariant GNNs on a large dataset of molecular conformations with a self-supervised denoising objective, we obtain transferable structural representations that are useful for learning conformational dynamics without further fine-tuning. We show how the learned GNN representations can capture interpretable relationships between structural units (tokens) by combining them with expressive token mixers. Importantly, decoupling training the GNNs from training for downstream tasks enables analysis of larger molecular graphs (such as small proteins at all-atom resolution) with limited computational resources. In these ways, geom2vec eliminates the need for manual feature selection and increases the robustness of simulation analyses.
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。