Machine learning molecular dynamics for the simulation of infrared spectra.
Machine learning molecular dynamics for the simulation of infrared spectra.
复制标题
DOI：
10.1039/c7sc02267k
复制
发表时间：
2017-10-01
期刊：
影响因子：
8.4
通讯作者：
Marquetand P
中科院分区：
文献类型：
--
作者：
Gastegger M;Behler J;Marquetand P
将人工神经网络与分子动力学相结合，模拟考虑非谐性和温度效应的分子红外光谱。机器学习已经成为许多研究领域的宝贵工具。在目前的工作中，我们利用这种能力来预测高度准确的分子红外光谱，具有前所未有的计算效率。为了解释振动非谐和动力学效应-通常被传统的量子化学方法所忽略-我们将我们的机器学习策略建立在从头算分子动力学模拟的基础上。虽然这些模拟通常非常耗时，即使是小分子，但我们通过利用各种机器学习技术的力量克服了这些限制，不仅将模拟加速了几个数量级，而且还大大扩展了可以处理的系统的大小。为此，我们开发了一个分子偶极矩模型的基础上，环境依赖的神经网络电荷和联合收割机结合Behler和Parrinello的神经网络势的方法。与流行的大数据理念相反，我们能够获得非常准确的机器学习模型，用于基于数百个电子结构参考点预测红外光谱。这是通过在神经网络潜力训练期间使用分子力和引入全自动采样方案而实现的。我们展示了我们的机器学习方法的力量，通过应用它来模拟甲醇分子的红外光谱，含有多达200个原子的正构烷烃和质子化丙氨酸三肽，这同时代表了机器学习技术在模拟肽动力学方面的首次应用。在所有这些案例研究中，我们发现通过机器学习模型预测的红外光谱与相应的理论和实验光谱之间具有很好的一致性。
Artificial neural networks are combined with molecular dynamics to simulate molecular infrared spectra including anharmonicities and temperature effects. Machine learning has emerged as an invaluable tool in many research areas. In the present work, we harness this power to predict highly accurate molecular infrared spectra with unprecedented computational efficiency. To account for vibrational anharmonic and dynamical effects – typically neglected by conventional quantum chemistry approaches – we base our machine learning strategy on ab initio molecular dynamics simulations. While these simulations are usually extremely time consuming even for small molecules, we overcome these limitations by leveraging the power of a variety of machine learning techniques, not only accelerating simulations by several orders of magnitude, but also greatly extending the size of systems that can be treated. To this end, we develop a molecular dipole moment model based on environment dependent neural network charges and combine it with the neural network potential approach of Behler and Parrinello. Contrary to the prevalent big data philosophy, we are able to obtain very accurate machine learning models for the prediction of infrared spectra based on only a few hundreds of electronic structure reference points. This is made possible through the use of molecular forces during neural network potential training and the introduction of a fully automated sampling scheme. We demonstrate the power of our machine learning approach by applying it to model the infrared spectra of a methanol molecule, n-alkanes containing up to 200 atoms and the protonated alanine tripeptide, which at the same time represents the first application of machine learning techniques to simulate the dynamics of a peptide. In all of these case studies we find an excellent agreement between the infrared spectra predicted via machine learning models and the respective theoretical and experimental spectra.
登录
查看更多内容
影响因子：
3.3
作者：
Fischer, Sean A.;Ueltschi, Tyler W.;Govind, Niranjan
通讯作者：
Govind, Niranjan
影响因子：
8.6
作者：
Behler, Joerg;Parrinello, Michele
通讯作者：
Parrinello, Michele
DOI：
10.1002/wcms.1215
发表时间：
2015-03-01
影响因子：
11.4
作者：
Baker, Christopher M.
通讯作者：
Baker, Christopher M.
影响因子：
4.4
作者：
Behler, Joerg
通讯作者：
Behler, Joerg
影响因子：
3.3
作者：
Behler, Joerg
通讯作者：
Behler, Joerg