海归学者发起的公益学术平台
分享信息，整合资源
交流学术，偶尔风月
金属有机框架（MOFs）是一类由金属离子和有机配体构成的多孔材料，因其可调的孔结构和化学特性，在气体存储、分离、催化和药物输送等领域展现出巨大潜力。MOFs的多样性和设计灵活性使其在材料科学和化学工程中备受关注。然而，精确预测MOFs性能（如气体吸附）的难点在于分子力学模拟中局部电荷的准确估算。
Fig. 1 | Graph neural network training and testing.
传统方法依赖经验力场，常因其局限性影响预测精度。此外，获取高质量标记数据耗时且昂贵，限制了这些方法的实用性。为此，机器学习，尤其是图神经网络（GNN），提供了更高效的解决方案，可以从数据中学习分子的复杂关系，提升电荷估算的准确性。
Fig. 2 |QMOFv13 dataset statistics.
来自德国慕尼黑工业大学工程物理与计算系的Julija Zavadlav教授团队，提出了一种基于主动学习的GNN模型，结合Dropout蒙特卡洛方法，用于精确预测MOFs的局部电荷。研究通过设计和训练GNN模型，采用主动学习策略优化训练样本选择，显著减少了达到高准确度所需的标记数据量。模型利用Dropout蒙特卡洛技术评估预测不确定性，确保在未见过的数据上也能可靠预测。这一方法在MOFs和沸石的不同分布上展示了良好的泛化能力。
Fig. 3 | Active learning curves.
作者的研究为MOFs的分子模拟提供了高效的工具，有助于加速基于计算机的材料设计和优化。通过精确预测局部电荷，推动了新材料的开发，不仅适用于MOFs，也为其他多孔材料的研究提供了参考。该文近期发表于npj Computational Materials 10:86 2024，英文标题与摘要如下，点击左下角“阅读原文”可以自由获取论文PDF。
Active learning graph neural networks for partial charge prediction of metal-organic frameworks via dropout Monte Carlo
Stephan Thaler, Felix Mayr, Siby Thomas, Alessio Gagliardi & Julija Zavadlav
Metal-organic frameworks (MOF) are an attractive class of porous materials due to their immense design space, allowing for application-tailored properties. Properties of interest, such as gas sorption, can be predicted in silico with molecular mechanics simulations. However, the accuracy is limited by the available empirical force field and partial charge estimation scheme. In this work, we train a graph neural network for partial charge prediction via active learning based on Dropout Monte Carlo. We show that active learning significantly reduces the required amount of labeled MOFs to reach a target accuracy. The obtained model generalizes well to different distributions of MOFs and Zeolites. In addition, the uncertainty predictions of Dropout Monte Carlo enable reliable estimation of the mean absolute error for unseen MOFs. This work paves the way towards accurate molecular modeling of MOFs via next-generation potentials with machine learning predicted partial charges, supporting in-silico material design.
扩展阅读
