Electrostatic Embedding of Machine Learning Potentials.

Electrostatic Embedding of Machine Learning Potentials.
复制标题

DOI:
10.1021/acs.jctc.2c00914
复制
发表时间:
2023-03-28
影响因子:
5.5
通讯作者:
Zinovjev, Kirill
Zinovjev, Kirill
中科院分区:
化学1区
文献类型:
--
作者:
Zinovjev, Kirill

文献摘要

参考文献

相似文献

这项工作提出了一种静电嵌入方案的变体,该方案允许在真空中嵌入在分子系统上训练的任意机器学习势。该方案基于电子密度和极化率的物理激励模型,从而在不依赖于穷尽训练集的情况下产生通用模型。该方案只需要在真空单点QM计算中提供训练密度和分子偶极极化率。作为例子,该方案被应用于使用仅有445个参考原子环境的高斯过程回归来建立QM7数据集的嵌入模型。该模型在SARS-CoV-2与PF-00835231的酶复合体上进行了测试,与显式密度泛函/密度泛函理论计算相比,预测的嵌入能量均方根值为2千卡/摩尔。
This work presents a variant of an electrostatic embedding scheme that allows the embedding of arbitrary machine learned potentials trained on molecular systems in vacuo. The scheme is based on physically motivated models of electronic density and polarizability, resulting in a generic model without relying on an exhaustive training set. The scheme only requires in vacuo single point QM calculations to provide training densities and molecular dipolar polarizabilities. As an example, the scheme is applied to create an embedding model for the QM7 data set using Gaussian Process Regression with only 445 reference atomic environments. The model was tested on the SARS-CoV-2 protease complex with PF-00835231, resulting in a predicted embedding energy RMSE of 2 kcal/mol, compared to explicit DFT/MM calculations.
DOI: 10.1103/physrevb.87.184115
发表时间: 2013-05-28
期刊: PHYSICAL REVIEW B
影响因子: 3.7
作者:
Bartok, Albert P.;Kondor, Risi;Csanyi, Gabor
通讯作者: Csanyi, Gabor
DOI: 10.1021/acs.jctc.1c00565
发表时间: 2021-09-14
影响因子: 5.5
作者:
Pan, Xiaoliang;Yang, Junjie;Van, Richard;Epifanovsky, Evgeny;Ho, Junming;Huang, Jing;Pu, Jingzhi;Mei, Ye;Nam, Kwangho;Shao, Yihan
通讯作者: Shao, Yihan
DOI: 10.1021/acs.jctc.5b00099
发表时间: 2015-05-01
影响因子: 5.5
作者:
Ramakrishnan, Raghunathan;Dral, Pavlo O.;von Lilienfeld, O. Anatole
通讯作者: von Lilienfeld, O. Anatole
DOI: 10.1021/ct401096t
发表时间: 2014-04-01
影响因子: 5.5
作者:
Lipparini, Filippo;Lagardere, Louis;Piquemal, Jean-Philip
通讯作者: Piquemal, Jean-Philip
DOI: 10.1103/physrevb.71.235333
发表时间: 2005-06-01
期刊: PHYSICAL REVIEW B
影响因子: 3.7
作者:
Mayer, A
通讯作者: Mayer, A