skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: General Protocol for the Accurate Prediction of Molecular 13C/ 1H NMR Chemical Shifts via Machine Learning Augmented DFT

Abstract

An accurate prediction of NMR chemical shifts at affordable computational cost is very important for different types of structural assignments in experimental studies. Density functional theory (DFT) and gauge-including atomic orbital (GIAO) are two of the most popular computational methods for NMR calculation, yet they often fail to resolve ambiguities in structural assignments. In this work, we present a new method that uses machine learning (ML) techniques (DFT + ML) that significantly increases the accuracy of 13C/ 1H NMR chemical shift prediction for a variety of organic molecules. The input of the generalizable DFT + ML model contains two critical parts: one is a vector providing insights into chemical environments, which can be evaluated without knowing the exact geometry of the molecule; the other one is the DFT-calculated isotropic shielding constant. The DFT + ML model was trained with a data set containing 476 13C and 270 1H experimental chemical shifts. For the DFT methods used here, the root mean square deviations (RMSDs) for the errors between predicted and experimental 13C/ 1H chemical shifts can be as small as 2.10/0.18 ppm, which is much lower than those from simple DFT (5.54/0.25 ppm), or DFT + linear regression (LR) (4.77/0.23 ppm)more » approaches. It also has a smaller maximum absolute error than two previously proposed NMR-predicting ML models. The robustness of the DFT + ML model is tested on two classes of organic molecules (TIC10 and hyacinthacines), where the correct isomers were unambiguously assigned to the experimental ones. Overall, the DFT + ML model shows promise for structural assignments in a variety of systems, including stereoisomers, that are often challenging to determine experimentally.« less

Authors:
ORCiD logo [1];  [2]; ORCiD logo [3];  [4]; ORCiD logo [2]
  1. Univ. of Wollongong, NSW (Australia)
  2. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
  3. Nankai Univ., Tianjin (China). State Key Lab. of Elemento-Organic Chemistry
  4. Guandong Lab., Guangzhou (China). Center of Chemistry and Chemical Biology
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES); National Natural Science Foundation of China (NSFC); Fundamental Research Funds of the Central Universities; Natural Science Foundation of Tianjin City
OSTI Identifier:
1668320
Report Number(s):
PNNL-SA-143566
Journal ID: ISSN 1549-9596
Grant/Contract Number:  
AC05-76RL01830; 72353; 21890722; 21702109; 11811530637; 18JCYBJC2140; 63191515; 63196021; 631915230
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Journal of Chemical Information and Modeling
Additional Journal Information:
Journal Volume: 60; Journal Issue: 8; Journal ID: ISSN 1549-9596
Publisher:
American Chemical Society
Country of Publication:
United States
Language:
English
Subject:
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; Molecular structure; molecular modeling; nuclear magnetic resonance spectroscopy; molecules; density functional theory

Citation Formats

Gao, Peng, Zhang, Jun, Peng, Qian, Zhang, Jie, and Glezakou, Vassiliki-Alexandra. General Protocol for the Accurate Prediction of Molecular 13C/1H NMR Chemical Shifts via Machine Learning Augmented DFT. United States: N. p., 2020. Web. doi:10.1021/acs.jcim.0c00388.
Gao, Peng, Zhang, Jun, Peng, Qian, Zhang, Jie, & Glezakou, Vassiliki-Alexandra. General Protocol for the Accurate Prediction of Molecular 13C/1H NMR Chemical Shifts via Machine Learning Augmented DFT. United States. https://doi.org/10.1021/acs.jcim.0c00388
Gao, Peng, Zhang, Jun, Peng, Qian, Zhang, Jie, and Glezakou, Vassiliki-Alexandra. Tue . "General Protocol for the Accurate Prediction of Molecular 13C/1H NMR Chemical Shifts via Machine Learning Augmented DFT". United States. https://doi.org/10.1021/acs.jcim.0c00388. https://www.osti.gov/servlets/purl/1668320.
@article{osti_1668320,
title = {General Protocol for the Accurate Prediction of Molecular 13C/1H NMR Chemical Shifts via Machine Learning Augmented DFT},
author = {Gao, Peng and Zhang, Jun and Peng, Qian and Zhang, Jie and Glezakou, Vassiliki-Alexandra},
abstractNote = {An accurate prediction of NMR chemical shifts at affordable computational cost is very important for different types of structural assignments in experimental studies. Density functional theory (DFT) and gauge-including atomic orbital (GIAO) are two of the most popular computational methods for NMR calculation, yet they often fail to resolve ambiguities in structural assignments. In this work, we present a new method that uses machine learning (ML) techniques (DFT + ML) that significantly increases the accuracy of 13C/1H NMR chemical shift prediction for a variety of organic molecules. The input of the generalizable DFT + ML model contains two critical parts: one is a vector providing insights into chemical environments, which can be evaluated without knowing the exact geometry of the molecule; the other one is the DFT-calculated isotropic shielding constant. The DFT + ML model was trained with a data set containing 476 13C and 270 1H experimental chemical shifts. For the DFT methods used here, the root mean square deviations (RMSDs) for the errors between predicted and experimental 13C/1H chemical shifts can be as small as 2.10/0.18 ppm, which is much lower than those from simple DFT (5.54/0.25 ppm), or DFT + linear regression (LR) (4.77/0.23 ppm) approaches. It also has a smaller maximum absolute error than two previously proposed NMR-predicting ML models. The robustness of the DFT + ML model is tested on two classes of organic molecules (TIC10 and hyacinthacines), where the correct isomers were unambiguously assigned to the experimental ones. Overall, the DFT + ML model shows promise for structural assignments in a variety of systems, including stereoisomers, that are often challenging to determine experimentally.},
doi = {10.1021/acs.jcim.0c00388},
url = {https://www.osti.gov/biblio/1668320}, journal = {Journal of Chemical Information and Modeling},
issn = {1549-9596},
number = 8,
volume = 60,
place = {United States},
year = {2020},
month = {6}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:

Works referenced in this record:

Computational Chemistry to the Rescue: Modern Toolboxes for the Assignment of Complex Molecules by GIAO NMR Calculations
journal, July 2016


Computational Prediction of 1 H and 13 C Chemical Shifts: A Useful Tool for Natural Product, Mechanistic, and Synthetic Organic Chemistry
journal, November 2011


Molecular Orbital Theory of Magnetic Shielding and Magnetic Susceptibility
journal, June 1972


An automated framework for NMR chemical shift calculations of small organic molecules
journal, October 2018


Ab Initio Methods for the Calculation of NMR Shielding and Indirect Spin−Spin Coupling Constants
journal, January 1999


Benchmarking density-functional theory calculations of NMR shielding constants and spin–rotation constants using accurate coupled-cluster calculations
journal, January 2013


Toward the Complete Prediction of the1H and13C NMR Spectra of Complex Organic Molecules by DFT Methods: Application to Natural Substances
journal, July 2006


Scaling factors for carbon NMR chemical shifts obtained from DFT B3LYP calculations
journal, January 2009


Theoretical investigation on H1 and C13 NMR chemical shifts of small alkanes and chloroalkanes
journal, October 2006


Regression Formulas for Density Functional Theory Calculated 1 H and 13 C NMR Chemical Shifts in Toluene- d 8
journal, November 2011


Towards an Accurate Prediction of Nitrogen Chemical Shifts by Density Functional Theory and Gauge‐Including Atomic Orbital
journal, November 2018


ACS Central Science Virtual Issue on Machine Learning
journal, August 2018


Learning More, with Less
journal, April 2017


Perspective: Machine learning potentials for atomistic simulations
journal, November 2016


First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed Systems
journal, August 2017


Machine Learning Force Fields: Construction, Validation, and Outlook
journal, December 2016


Machine Learning of Coarse-Grained Molecular Dynamics Force Fields
journal, April 2019


Machine learning enhanced global optimization by clustering local environments to enable bundled atomic energies
journal, October 2018


Global minimization of gold clusters by combining neural network potentials and the basin-hopping method
journal, January 2015


Neural-network-enhanced evolutionary algorithm applied to supported metal nanoparticles
journal, May 2018


Accelerating atomic structure search with cluster regularization
journal, June 2018


Disentangling Structural Confusion through Machine Learning: Structure Prediction and Polymorphism of Equiatomic Ternary Phases ABC
journal, November 2017


Chemical Pressure-Driven Enhancement of the Hydrogen Evolving Activity of Ni 2 P from Nonmetal Surface Doping Interpreted via Machine Learning
journal, March 2018


Machine Learning Directed Search for Ultraincompressible, Superhard Materials
journal, July 2018


Machine-Learning Prediction of CO Adsorption in Thiolated, Ag-Alloyed Au Nanoclusters
journal, November 2018


Accelerated Discovery of Organic Polymer Photocatalysts for Hydrogen Evolution from Water through the Integration of Experiment and Theory
journal, May 2019


Prediction of Organic Reaction Outcomes Using Machine Learning
journal, April 2017


Transferable Machine-Learning Model of the Electron Density
journal, December 2018


Deoxyfluorination with Sulfonyl Fluorides: Navigating Reaction Space with Machine Learning
journal, March 2018


A graph-convolutional neural network model for the prediction of chemical reactivity
journal, January 2019


Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
journal, July 2015


Toward More Reliable 13 C and 1 H Chemical Shift Prediction:  A Systematic Comparison of Neural-Network and Least-Squares Regression Based Approaches
journal, December 2007


Prediction of 1 H NMR Chemical Shifts Using Neural Networks
journal, January 2002


Building blocks for automated elucidation of metabolites: Machine learning methods for NMR prediction
journal, January 2008


SHIFTX2: significantly improved protein chemical shift prediction
journal, March 2011


Ab Initio Quality NMR Parameters in Solid-State Materials Using a High-Dimensional Neural-Network Representation
journal, January 2016


Chemical shifts in molecular solids by machine learning
journal, October 2018


Comparison Study on the Prediction of Multiple Molecular Properties by Various Neural Networks
journal, October 2018


Prediction of Physicochemical Parameters by Atomic Contributions
journal, August 1999


A widely applicable set of descriptors
journal, January 2000


Exploratory machine-learned theoretical chemical shifts can closely predict metabolic mixture signals
journal, January 2018


A Comparison of Density Functional Methods for the Estimation of Proton Chemical Shifts with Chemical Accuracy
journal, September 1999


SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules
journal, February 1988


Universal Solvation Model Based on Solute Electron Density and on a Continuum Model of the Solvent Defined by the Bulk Dielectric Constant and Atomic Surface Tensions
journal, May 2009

  • Marenich, Aleksandr V.; Cramer, Christopher J.; Truhlar, Donald G.
  • The Journal of Physical Chemistry B, Vol. 113, Issue 18, p. 6378-6396
  • https://doi.org/10.1021/jp810292n

Use of Solution-Phase Vibrational Frequencies in Continuum Models for the Free Energy of Solvation
journal, December 2011


Less is more: Sampling chemical space with active learning
journal, June 2018


Graphene-Based Membranes for Molecular Separation
journal, July 2015


Liquid fuels, hydrogen and chemicals from lignin A critical review
journal, May 2013


Pharmacophore Reassignment for Induction of the Immunosurveillance Cytokine TRAIL
journal, May 2014


New polyhydroxylated pyrrolizidine alkaloids from Muscari armeniacum: structural determination and biological activity
journal, January 2000