Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer.
Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer.
复制标题
DOI：
10.1002/jcc.24465
复制
发表时间：
2016-10-15
影响因子：
3
通讯作者：
Popelier, Paul L. A.
中科院分区：
文献类型：
--
作者：
Davie, Stuart J.;Di Pasquale, Nicodemo;Popelier, Paul L. A.
关键词：
机器学习算法已经被证明可以以显著更少的计算成本预测接近量子化学计算精度的原子性质。然而，当试图将这些技术应用于大型系统或具有过度构象自由度的系统时，会出现困难。在这篇文章中，机器学习方法克里金被应用于预测原子内和原子间能量，以及10个水分子（十聚体）簇中心的水分子原子的静电多极矩。与以前的工作不同，其中使用分子局部框架预测小水团簇的性质，并且训练集输入（特征）基于原子指数，这里考虑了各种特征定义和坐标框架以提高预测精度。结果表明，对于一个水分子在一个十聚体的中心，没有一个单一的方法定义的功能或坐标方案是最佳的每一个属性。然而，在克里金训练集的特征定义中明确考虑第一个溶剂化壳层的结构，并将坐标框架集中在感兴趣的原子上，通常会比应用特征定义的标准方法或分子坐标框架的模型返回更好的预测。© 2016作者。计算化学杂志由Wiley Periodicals，Inc.出版。
Machine learning algorithms have been demonstrated to predict atomistic properties approaching the accuracy of quantum chemical calculations at significantly less computational cost. Difficulties arise, however, when attempting to apply these techniques to large systems, or systems possessing excessive conformational freedom. In this article, the machine learning method kriging is applied to predict both the intra‐atomic and interatomic energies, as well as the electrostatic multipole moments, of the atoms of a water molecule at the center of a 10 water molecule (decamer) cluster. Unlike previous work, where the properties of small water clusters were predicted using a molecular local frame, and where training set inputs (features) were based on atomic index, a variety of feature definitions and coordinate frames are considered here to increase prediction accuracy. It is shown that, for a water molecule at the center of a decamer, no single method of defining features or coordinate schemes is optimal for every property. However, explicitly accounting for the structure of the first solvation shell in the definition of the features of the kriging training set, and centring the coordinate frame on the atom‐of‐interest will, in general, return better predictions than models that apply the standard methods of feature definition, or a molecular coordinate frame. © 2016 The Authors. Journal of Computational Chemistry Published by Wiley Periodicals, Inc.
登录
查看更多内容
影响因子：
5.5
作者：
Fletcher, Timothy L.;Davie, Stuart J.;Popelier, Paul L. A.
通讯作者：
Popelier, Paul L. A.
影响因子：
2.8
作者：
KOCH, U;POPELIER, PLA;STONE, AJ
通讯作者：
STONE, AJ
影响因子：
4.4
作者：
Panhuis, MIH;Popelier, PLA;Angyán, JG
通讯作者：
Angyán, JG
影响因子：
2.2
作者：
Popelier, Paul L. A.
通讯作者：
Popelier, Paul L. A.
影响因子：
3
作者：
BROOKS, BR;BRUCCOLERI, RE;KARPLUS, M
通讯作者：
KARPLUS, M