Rapid prediction of NMR spectral properties with quantified uncertainty

Abstract Accurate calculation of specific spectral properties for NMR is an important step for molecular structure elucidation. Here we report the development of a novel machine learning technique for accurately predicting chemical shifts of both $${^1\mathrm{H}}$$ 1H and $${^{13}\mathrm{C}}$$ 13C...

Full description

Bibliographic Details
Main Authors:	Eric Jonas, Stefan Kuhn
Format:	Article
Language:	English
Published:	BMC 2019-08-01
Series:	Journal of Cheminformatics
Subjects:	NMR Machine learning DFT
Online Access:	http://link.springer.com/article/10.1186/s13321-019-0374-3

id	doaj-10d6431d09b34bcdac535200f976ad8a
record_format	Article
spelling	doaj-10d6431d09b34bcdac535200f976ad8a2020-11-25T03:10:22ZengBMCJournal of Cheminformatics1758-29462019-08-011111710.1186/s13321-019-0374-3Rapid prediction of NMR spectral properties with quantified uncertaintyEric Jonas0Stefan Kuhn1Department of Computer Science, University of ChicagoSchool of Computer Science and InformaticsAbstract Accurate calculation of specific spectral properties for NMR is an important step for molecular structure elucidation. Here we report the development of a novel machine learning technique for accurately predicting chemical shifts of both $${^1\mathrm{H}}$$ 1H and $${^{13}\mathrm{C}}$$ 13C nuclei which exceeds DFT-accessible accuracy for $${^{13}\mathrm{C}}$$ 13C and $${^1\mathrm{H}}$$ 1H for a subset of nuclei, while being orders of magnitude more performant. Our method produces estimates of uncertainty, allowing for robust and confident predictions, and suggests future avenues for improved performance.http://link.springer.com/article/10.1186/s13321-019-0374-3NMRMachine learningDFT
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Eric Jonas Stefan Kuhn
spellingShingle	Eric Jonas Stefan Kuhn Rapid prediction of NMR spectral properties with quantified uncertainty Journal of Cheminformatics NMR Machine learning DFT
author_facet	Eric Jonas Stefan Kuhn
author_sort	Eric Jonas
title	Rapid prediction of NMR spectral properties with quantified uncertainty
title_short	Rapid prediction of NMR spectral properties with quantified uncertainty
title_full	Rapid prediction of NMR spectral properties with quantified uncertainty
title_fullStr	Rapid prediction of NMR spectral properties with quantified uncertainty
title_full_unstemmed	Rapid prediction of NMR spectral properties with quantified uncertainty
title_sort	rapid prediction of nmr spectral properties with quantified uncertainty
publisher	BMC
series	Journal of Cheminformatics
issn	1758-2946
publishDate	2019-08-01
description	Abstract Accurate calculation of specific spectral properties for NMR is an important step for molecular structure elucidation. Here we report the development of a novel machine learning technique for accurately predicting chemical shifts of both $${^1\mathrm{H}}$$ 1H and $${^{13}\mathrm{C}}$$ 13C nuclei which exceeds DFT-accessible accuracy for $${^{13}\mathrm{C}}$$ 13C and $${^1\mathrm{H}}$$ 1H for a subset of nuclei, while being orders of magnitude more performant. Our method produces estimates of uncertainty, allowing for robust and confident predictions, and suggests future avenues for improved performance.
topic	NMR Machine learning DFT
url	http://link.springer.com/article/10.1186/s13321-019-0374-3
work_keys_str_mv	AT ericjonas rapidpredictionofnmrspectralpropertieswithquantifieduncertainty AT stefankuhn rapidpredictionofnmrspectralpropertieswithquantifieduncertainty
_version_	1724659009808498688

Rapid prediction of NMR spectral properties with quantified uncertainty

Similar Items