Predicting Density Functional Theory-Quality Nuclear Magnetic Resonance Chemical Shifts via Δ-Machine Learning
Predicting Density Functional Theory-Quality Nuclear Magnetic Resonance Chemical Shifts via Δ-Machine Learning
复制标题
DOI：
10.1021/acs.jctc.0c00979
复制
发表时间：
2021-01-11
影响因子：
5.5
通讯作者：
Beran, Gregory J. O.
中科院分区：
文献类型：
--
作者：
Unzueta, Pablo A.;Greenwell, Chandler S.;Beran, Gregory J. O.
核磁共振化学位移的第一性原理预测在解释实验光谱中起着越来越重要的作用，但所需的密度泛函理论（DFT）计算可能是计算昂贵的。以前已经开发了用于预测一般有机分子中化学屏蔽的有前途的机器学习模型，尽管这些模型的准确性仍然低于DFT。目前的研究表明，如何更高的精度化学屏蔽可以通过获得。机器学习方法，结果是机器学习模型引入的误差仅为DFT化学位移相对于实验的预期误差的二分之一到三分之一。具体地，训练神经网络的集合以将PBE 0/6- 31 G化学屏蔽校正到PBE 0/6-311+G（2d，p）的目标水平。它可以预测H-1，C-13，15 N和O-17的化学屏蔽，均方根误差分别为0.11，0.70，1.69和2.47 ppm。同时，Delta机器学习方法比目标大基计算快1-2个数量级。它还表明，机器学习模型预测实验溶液相NMR化学位移的药物分子只有适度差的准确性比目标DFT模型。最后，还评估了基于神经网络模型集合内的变化来估计预测屏蔽中的不确定性的能力。
First-principles prediction of nuclear magnetic resonance chemical shifts plays an increasingly important role in the interpretation of experimental spectra, but the required density functional theory (DFT) calculations can be computationally expensive. Promising machine learning models for predicting chemical shieldings in general organic molecules have been developed previously, though the accuracy of those models remains below that of DFT. The present study demonstrates how much higher accuracy chemical shieldings can be obtained via the.-machine learning approach, with the result that the errors introduced by the machine learning model are only one-half to one-third the errors expected for DFT chemical shifts relative to experiment. Specifically, an ensemble of neural networks is trained to correct PBE0/6-31G chemical shieldings up to the target level of PBE0/6-311+G(2d,p). It can predict H-1, C-13, 15N, and O-17 chemical shieldings with root-mean-square errors of 0.11, 0.70, 1.69, and 2.47 ppm, respectively. At the same time, the Delta-machine learning approach is 1-2 orders of magnitude faster than the target large-basis calculations. It is also demonstrated that the machine learning model predicts experimental solution-phase NMR chemical shifts in drug molecules with only modestly worse accuracy than the target DFT model. Finally, the ability to estimate the uncertainty in the predicted shieldings based on variations within the ensemble of neural network models is also assessed.