HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Institute for Chemical Reaction Design and Discovery : ICReDD >
Peer-reviewed Journal Articles, etc >

NMR spectrum prediction for dynamic molecules by machine learning: A case study of trefoil knot molecule

Files in This Item:
194108_1_5.0147398.pdf5.99 MBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/92421

Title: NMR spectrum prediction for dynamic molecules by machine learning: A case study of trefoil knot molecule
Authors: Tsitsvero, Mikhail Browse this author
Pirillo, Jenny Browse this author
Hijikata, Yuh Browse this author →KAKEN DB
Komatsuzaki, Tamiki Browse this author →KAKEN DB
Keywords: Density functional theory
Molecular dynamics
Artificial neural networks
Machine learning
Computational methods
Nuclear magnetic resonance spectroscopy
Covariance and correlation
Gaussian processes
Issue Date: 17-May-2023
Publisher: AIP Publishing
Journal Title: Journal of chemical physics
Volume: 158
Issue: 19
Start Page: 194108
Publisher DOI: 10.1063/5.0147398
Abstract: Nuclear magnetic resonance (NMR) spectroscopy is one of the indispensable techniques in chemistry because it enables us to obtain accurate information on the chemical, electronic, and dynamic properties of molecules. Computational simulation of the NMR spectra requires time-consuming density functional theory (DFT) calculations for an ensemble of molecular conformations. For large flexible molecules, it is considered too high-cost since it requires time-averaging of the instantaneous chemical shifts of each nuclear spin across the conformational space of molecules for NMR timescales. Here, we present a Gaussian process/deep kernel learning-based machine learning (ML) method for enabling us to predict, average in time, and analyze the instantaneous chemical shifts of conformations in the molecular dynamics trajectory. We demonstrate the use of the method by computing the averaged H-1 and C-13 chemical shifts of each nuclear spin of a trefoil knot molecule consisting of 24 para-connected benzene rings (240 atoms). By training ML model with the chemical shift data obtained from DFT calculations, we predicted chemical shifts for each conformation during dynamics. We were able to observe the merging of the time-averaged chemical shifts of each nuclear spin in a singlet H-1 NMR peak and two C-13 NMR peaks for the knot molecule, in agreement with experimental measurements. The unique feature of the presented method is the use of the learned low-dimensional deep kernel representation of local spin environments for comparing and analyzing the local chemical environment histories of spins during dynamics. It allowed us to identify two groups of protons in the knot molecule, which implies that the observed singlet H-1 NMR peak could be composed of the contributions from protons with two distinct local chemical environments.
Rights: This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Mikhail Tsitsvero, Jenny Pirillo, Yuh Hijikata, Tamiki Komatsuzaki; NMR spectrum prediction for dynamic molecules by machine learning: A case study of trefoil knot molecule. J. Chem. Phys. 15 May 2023; 158 (19): 194108. and may be found at https://doi.org/10.1063/5.0147398
Type: article
URI: http://hdl.handle.net/2115/92421
Appears in Collections:化学反応創成研究拠点:ICReDD (Institute for Chemical Reaction Design and Discovery : ICReDD) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: Mikhail Tsitsvero

Export metadata:

OAI-PMH ( junii2 , jpcoar_1.0 )

MathJax is now OFF:


 

 - Hokkaido University