sGDML: Constructing accurate and data efficient molecular force fields using machine learning
sGDML: Constructing accurate and data efficient molecular force fields using machine learning
复制标题
DOI：
10.1016/j.cpc.2019.02.007
复制
发表时间：
2019-07-01
影响因子：
6.3
通讯作者：
Tkatchenko, Alexandre
中科院分区：
文献类型：
--
作者：
Chmiela, Stefan;Sauceda, Huziel E.;Tkatchenko, Alexandre
我们提出了最近提出的对称梯度域机器学习（sGDML）模型的优化实现。sGDML模型能够忠实地再现具有几十个原子的分子的全局势能面（PES），这些原子来自有限数量的用户提供的参考分子构象和相关的原子力。在这里，我们介绍了一个Python软件包来重建和评估自定义sGDML力场（FF），而不需要深入了解模型的细节。用户友好的命令行界面通过模型创建的完整过程提供帮助，努力使这种新颖的机器学习方法可供广大从业者使用。我们的论文作为文档，但也包括如何重建和使用对乙酰氨基酚的PBEO+MBD FF的实际应用示例。最后，我们展示了如何将5GDML与FF仿真引擎ASE（Larsen等人，2017）和i-PI（Kapil等人，2019）运行数值实验，包括结构优化，经典和路径积分分子动力学和轻推弹性带计算。(C)2019作者（S）由爱思唯尔公司出版
We present an optimized implementation of the recently proposed symmetric gradient domain machine learning (sGDML) model. The sGDML model is able to faithfully reproduce global potential energy surfaces (PES) for molecules with a few dozen atoms from a limited number of user-provided reference molecular conformations and the associated atomic forces. Here, we introduce a Python software package to reconstruct and evaluate custom sGDML force fields (FFs), without requiring in-depth knowledge about the details of the model. A user-friendly command-line interface offers assistance through the complete process of model creation, in an effort to make this novel machine learning approach accessible to broad practitioners. Our paper serves as a documentation, but also includes a practical application example of how to reconstruct and use a PBEO+MBD FF for paracetamol. Finally, we show how to interface 5GDML with the FF simulation engines ASE (Larsen et al., 2017) and i-PI (Kapil et al., 2019) to run numerical experiments, including structure optimization, classical and path integral molecular dynamics and nudged elastic band calculations. (C) 2019 The Author(s). Published by Elsevier B.V.