A Machine Learning Model of Chemical Shifts for Chemically and Structurally Diverse Molecular Solids.


Journal

The journal of physical chemistry. C, Nanomaterials and interfaces
ISSN: 1932-7447
Titre abrégé: J Phys Chem C Nanomater Interfaces
Pays: United States
ID NLM: 101299949

Informations de publication

Date de publication:
06 Oct 2022
Historique:
received: 03 06 2022
revised: 24 08 2022
entrez: 14 10 2022
pubmed: 15 10 2022
medline: 15 10 2022
Statut: ppublish

Résumé

Nuclear magnetic resonance (NMR) chemical shifts are a direct probe of local atomic environments and can be used to determine the structure of solid materials. However, the substantial computational cost required to predict accurate chemical shifts is a key bottleneck for NMR crystallography. We recently introduced ShiftML, a machine-learning model of chemical shifts in molecular solids, trained on minimum-energy geometries of materials composed of C, H, N, O, and S that provides rapid chemical shift predictions with density functional theory (DFT) accuracy. Here, we extend the capabilities of ShiftML to predict chemical shifts for both finite temperature structures and more chemically diverse compounds, while retaining the same speed and accuracy. For a benchmark set of 13 molecular solids, we find a root-mean-squared error of 0.47 ppm with respect to experiment for

Identifiants

pubmed: 36237276
doi: 10.1021/acs.jpcc.2c03854
pmc: PMC9549463
doi:

Types de publication

Journal Article

Langues

eng

Pagination

16710-16720

Informations de copyright

© 2022 The Authors. Published by American Chemical Society.

Déclaration de conflit d'intérêts

The authors declare no competing financial interest.

Références

Int J Mol Sci. 2020 Jul 11;21(14):
pubmed: 32664570
J Comput Chem. 2006 Nov 30;27(15):1787-99
pubmed: 16955487
J Phys Condens Matter. 2017 Oct 24;29(46):465901
pubmed: 29064822
Phys Chem Chem Phys. 2006 Aug 7;8(29):3418-22
pubmed: 16855720
J Phys Chem Lett. 2019 Aug 15;10(16):4558-4565
pubmed: 31305081
Phys Chem Chem Phys. 2019 Nov 14;21(42):23385-23400
pubmed: 31631196
Chem Commun (Camb). 2012 Nov 14;48(88):10844-6
pubmed: 23023334
Mol Pharm. 2018 Apr 2;15(4):1476-1487
pubmed: 29490140
J Chem Phys. 2021 Sep 14;155(10):104106
pubmed: 34525832
J Phys Condens Matter. 2009 Sep 30;21(39):395502
pubmed: 21832390
J Chem Phys. 2021 Feb 21;154(7):074102
pubmed: 33607885
Acc Chem Res. 2013 Sep 17;46(9):2008-17
pubmed: 23537227
Chem Sci. 2021 Jul 9;12(32):10802-10809
pubmed: 34476061
Nat Rev Methods Primers. 2021;1:
pubmed: 34368784
J Chem Phys. 2021 Mar 21;154(11):114109
pubmed: 33752353
J Chem Theory Comput. 2021 Feb 9;17(2):826-840
pubmed: 33428408
Nat Commun. 2021 May 20;12(1):2964
pubmed: 34016980
Cryst Growth Des. 2016 Nov 2;16(11):6479-6493
pubmed: 27829821
J Biomol NMR. 2003 May;26(1):25-37
pubmed: 12766400
J Chem Theory Comput. 2012 Apr 10;7(4):931-948
pubmed: 23204947
Magn Reson Chem. 2007 Dec;45 Suppl 1:S174-86
pubmed: 18157842
Chemphyschem. 2020 Sep 15;21(18):2075-2083
pubmed: 32691463
J Am Chem Soc. 2013 Nov 20;135(46):17501-7
pubmed: 24168679
Phys Chem Chem Phys. 2016 Aug 21;18(31):21686-709
pubmed: 27431490
J Chem Theory Comput. 2019 Feb 12;15(2):906-915
pubmed: 30605342
Nat Commun. 2018 Oct 29;9(1):4501
pubmed: 30374021
Nat Chem. 2017 Sep;9(9):890-895
pubmed: 28837175
Prog Nucl Magn Reson Spectrosc. 2020 Jun - Aug;118-119:10-53
pubmed: 32883448
J Phys Chem Lett. 2021 Aug 19;12(32):7701-7707
pubmed: 34355903
Acta Crystallogr B Struct Sci Cryst Eng Mater. 2016 Apr;72(Pt 2):171-9
pubmed: 27048719
J Phys Chem B. 2017 Aug 31;121(34):8132-8141
pubmed: 28762740
Phys Chem Chem Phys. 2019 Jul 10;21(27):14992-15000
pubmed: 31237586
Chem Commun (Camb). 2016 May 10;52(40):6685-8
pubmed: 27115483
Proc Natl Acad Sci U S A. 2022 Jan 25;119(4):
pubmed: 35058365
Sci Adv. 2021 Nov 26;7(48):eabk2341
pubmed: 34826232
Phys Rev Lett. 2009 Jan 16;102(2):020601
pubmed: 19257259
Chem Sci. 2019 Nov 20;11(2):508-515
pubmed: 32190270
J Am Chem Soc. 2022 Apr 27;144(16):7215-7223
pubmed: 35416661
Chem Sci. 2021 Aug 9;12(36):12012-12026
pubmed: 34667567
Magn Reson Chem. 2004 May;42(5):445-52
pubmed: 15095380
Phys Rev Lett. 1996 Oct 28;77(18):3865-3868
pubmed: 10062328
Magn Reson Chem. 2020 Jun;58(6):512-519
pubmed: 31912547
J Comput Chem. 2009 Apr 30;30(6):934-9
pubmed: 18785153
J Am Chem Soc. 2021 Jan 27;143(3):1529-1538
pubmed: 33442979
Phys Chem Chem Phys. 2013 Jun 7;15(21):8069-80
pubmed: 23503809
IEEE Trans Image Process. 1997;6(9):1305-15
pubmed: 18283019
J Chem Theory Comput. 2013 Aug 13;9(8):3806-15
pubmed: 26584127

Auteurs

Manuel Cordova (M)

Laboratory of Magnetic Resonance, Institute of Chemical Sciences and Engineering, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.
National Centre for Computational Design and Discovery of Novel Materials MARVEL, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.

Edgar A Engel (EA)

Theory of Condensed Matter Group, Cavendish Laboratory, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K.

Artur Stefaniuk (A)

Laboratory of Magnetic Resonance, Institute of Chemical Sciences and Engineering, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.

Federico Paruzzo (F)

Laboratory of Magnetic Resonance, Institute of Chemical Sciences and Engineering, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.

Albert Hofstetter (A)

Laboratory of Magnetic Resonance, Institute of Chemical Sciences and Engineering, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.

Michele Ceriotti (M)

National Centre for Computational Design and Discovery of Novel Materials MARVEL, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.
Laboratory of Computational Science and Modelling, Institute of Materials, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.

Lyndon Emsley (L)

Laboratory of Magnetic Resonance, Institute of Chemical Sciences and Engineering, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.
National Centre for Computational Design and Discovery of Novel Materials MARVEL, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.

Classifications MeSH