Real-time prediction of 1 H and 13 C chemical shifts with DFT accuracy using a 3D graph neural network

Guan, Yanfei; Shree Sowndarya, S. V.; Gallegos, Liliana C.; St. John, Peter C.; Paton, Robert S.

doi:10.1039/D1SC03343C

Title: Real-time prediction of ¹ H and ¹³ C chemical shifts with DFT accuracy using a 3D graph neural network

Journal Article · Wed Sep 22 00:00:00 EDT 2021 · Chemical Science

DOI:https://doi.org/10.1039/D1SC03343C· OSTI ID:1812410

^[1];

^[2];

^[1]

Department of Chemistry, Colorado State University, Fort Collins, CO, 80523, USA
Biosciences Center, National Renewable Energy Laboratory, Golden, CO 80401, USA

Nuclear magnetic resonance (NMR) is one of the primary techniques used to elucidate the chemical structure, bonding, stereochemistry, and conformation of organic compounds. The distinct chemical shifts in an NMR spectrum depend upon each atom's local chemical environment and are influenced by both through-bond and through-space interactions with other atoms and functional groups. The in silico prediction of NMR chemical shifts using quantum mechanical (QM) calculations is now commonplace in aiding organic structural assignment since spectra can be computed for several candidate structures and then compared with experimental values to find the best possible match. However, the computational demands of calculating multiple structural- and stereo-isomers, each of which may typically exist as an ensemble of rapidly-interconverting conformations, are expensive. Additionally, the QM predictions themselves may lack sufficient accuracy to identify a correct structure. In this work, we address both of these shortcomings by developing a rapid machine learning (ML) protocol to predict ¹H and ¹³C chemical shifts through an efficient graph neural network (GNN) using 3D structures as input. Transfer learning with experimental data is used to improve the final prediction accuracy of a model trained using QM calculations. When tested on the CHESHIRE dataset, the proposed model predicts observed ¹³C chemical shifts with comparable accuracy to the best-performing DFT functionals (1.5 ppm) in around 1/6000 of the CPU time. An automated prediction webserver and graphical interface are accessible online at http://nova.chem.colostate.edu/cascade/. We further demonstrate the model in three applications: first, we use the model to decide the correct organic structure from candidates through experimental spectra, including complex stereoisomers; second, we automatically detect and revise incorrect chemical shift assignments in a popular NMR database, the NMRShiftDB; and third, we use NMR chemical shifts as descriptors for determination of the sites of electrophilic aromatic substitution.

View Journal Article

Cite

Export

Save

Research Organization:: National Renewable Energy Lab. (NREL), Golden, CO (United States)

Sponsoring Organization:: USDOE Advanced Research Projects Agency - Energy (ARPA-E)

Grant/Contract Number:: AC36-08GO28308

OSTI ID:: 1812410

Alternate ID(s):: OSTI ID: 1822396

Report Number(s):: NREL/JA-2700-80593; CSHCBM

Journal Information:: Chemical Science, Journal Name: Chemical Science Vol. 12 Journal Issue: 36; ISSN 2041-6520

Publisher:: Royal Society of Chemistry (RSC)Copyright Statement

Country of Publication:: United Kingdom

Language:: English

References (71)

NMReDATA, a standard to report the NMR assignment and parameters of organic compounds Pupier, Marion; Nuzillard, Jean-Marc; Wist, Julien Magnetic Resonance in Chemistry, Vol. 56, Issue 8 https://doi.org/10.1002/mrc.4737	journal	May 2018
NMRShiftDBConstructing a Free Chemical Information System with Open-Source Components Steinbeck, Christoph; Krause, Stefan; Kuhn, Stefan Journal of Chemical Information and Computer Sciences, Vol. 43, Issue 6 https://doi.org/10.1021/ci0341363	journal	November 2003
Crystal Structure Prediction via Deep Learning Ryan, Kevin; Lengyel, Jeff; Shatruk, Michael Journal of the American Chemical Society, Vol. 140, Issue 32 https://doi.org/10.1021/jacs.8b03913	journal	June 2018
MoleculeNet: a benchmark for molecular machine learning Wu, Zhenqin; Ramsundar, Bharath; Feinberg, Evan N. Chemical Science, Vol. 9, Issue 2 https://doi.org/10.1039/C7SC02664A	journal	January 2018
Predicting NMR Spectra by Computational Methods: Structure Revision of Hexacyclinol Rychnovsky, Scott D. Organic Letters, Vol. 8, Issue 13 https://doi.org/10.1021/ol0611346	journal	June 2006
Addressing the Stereochemistry of Complex Organic Molecules by Density Functional Theory-NMR: Vannusal B in Retrospective Saielli, Giacomo; Nicolaou, K. C.; Ortiz, Adrian Journal of the American Chemical Society, Vol. 133, Issue 15 https://doi.org/10.1021/ja201108a	journal	April 2011
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost Smith, J. S.; Isayev, O.; Roitberg, A. E. Chemical Science, Vol. 8, Issue 4 https://doi.org/10.1039/C6SC05720A	journal	January 2017
The value of universally available raw NMR data for transparency, reproducibility, and integrity in natural product research McAlpine, James B.; Chen, Shao-Nong; Kutateladze, Andrei Natural Product Reports, Vol. 36, Issue 1 https://doi.org/10.1039/C7NP00064B	journal	January 2019
Assigning the Stereochemistry of Pairs of Diastereoisomers Using GIAO NMR Shift Calculation Smith, Steven G.; Goodman, Jonathan M. The Journal of Organic Chemistry, Vol. 74, Issue 12 https://doi.org/10.1021/jo900408d	journal	June 2009
Better Informed Distance Geometry: Using What We Know To Improve Conformation Generation Riniker, Sereina; Landrum, Gregory A. Journal of Chemical Information and Modeling, Vol. 55, Issue 12 https://doi.org/10.1021/acs.jcim.5b00654	journal	November 2015
Beyond DP4: an Improved Probability for the Stereochemical Assignment of Isomeric Compounds using Quantum Chemical Calculations of NMR Shifts Grimblat, Nicolás; Zanardi, María M.; Sarotti, Ariel M. The Journal of Organic Chemistry, Vol. 80, Issue 24 https://doi.org/10.1021/acs.joc.5b02396	journal	December 2015
Doubling the power of DP4 for computational structure elucidation Ermanis, K.; Parkes, K. E. B.; Agback, T. Organic & Biomolecular Chemistry, Vol. 15, Issue 42 https://doi.org/10.1039/C7OB01379E	journal	January 2017
A computer program for the prediction of 13-C-NMR chemical shifts of organic compounds Fürst, Andràs; Pretsch, Ernö Analytica Chimica Acta, Vol. 229 https://doi.org/10.1016/S0003-2670(00)85105-3	journal	January 1990
Toward More Reliable ¹³ C and ¹ H Chemical Shift Prediction: A Systematic Comparison of Neural-Network and Least-Squares Regression Based Approaches Smurnyy, Yegor D.; Blinov, Kirill A.; Churanova, Tatiana S. Journal of Chemical Information and Modeling, Vol. 48, Issue 1 https://doi.org/10.1021/ci700256n	journal	December 2007
A Multi-standard Approach for GIAO ¹³ C NMR Calculations Sarotti, Ariel M.; Pellegrinet, Silvina C. The Journal of Organic Chemistry, Vol. 74, Issue 19 https://doi.org/10.1021/jo901234h	journal	October 2009
Assigning Stereochemistry to Single Diastereoisomers by GIAO NMR Calculation: The DP4 Probability Smith, Steven G.; Goodman, Jonathan M. Journal of the American Chemical Society, Vol. 132, Issue 37 https://doi.org/10.1021/ja105035r	journal	September 2010
On representing chemical environments Bartók, Albert P.; Kondor, Risi; Csányi, Gábor Physical Review B, Vol. 87, Issue 18 https://doi.org/10.1103/PhysRevB.87.184115	journal	May 2013
Message-passing neural networks for high-throughput polymer screening St. John, Peter C.; Phillips, Caleb; Kemper, Travis W. The Journal of Chemical Physics, Vol. 150, Issue 23 https://doi.org/10.1063/1.5099132	journal	June 2019
IMPRESSION – prediction of NMR parameters for 3-dimensional chemical structures using machine learning with near quantum chemical accuracy Gerrard, Will; Bratholm, Lars A.; Packer, Martin J. Chemical Science, Vol. 11, Issue 2 https://doi.org/10.1039/C9SC03854J	journal	January 2020
Demonstrating the Transferability and the Descriptive Power of Sketch-Map Ceriotti, Michele; Tribello, Gareth A.; Parrinello, Michele Journal of Chemical Theory and Computation, Vol. 9, Issue 3 https://doi.org/10.1021/ct3010563	journal	February 2013
Prediction of ¹ H NMR Chemical Shifts Using Neural Networks Aires-de-Sousa, João; Hemmer, Markus C.; Gasteiger, Johann Analytical Chemistry, Vol. 74, Issue 1 https://doi.org/10.1021/ac010737m	journal	January 2002
SchNet – A deep learning architecture for molecules and materials Schütt, K. T.; Sauceda, H. E.; Kindermans, P. -J. The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5019779	journal	June 2018
The M06 suite of density functionals for main group thermochemistry, thermochemical kinetics, noncovalent interactions, excited states, and transition elements: two new functionals and systematic testing of four M06-class functionals and 12 other functionals Zhao, Yan; Truhlar, Donald G. Theoretical Chemistry Accounts, Vol. 120, Issue 1-3 https://doi.org/10.1007/s00214-007-0310-x	journal	July 2007
Hose — a novel substructure code Bremser, W. Analytica Chimica Acta, Vol. 103, Issue 4 https://doi.org/10.1016/S0003-2670(01)83100-7	journal	December 1978
Importance of Engineered and Learned Molecular Representations in Predicting Organic Reactivity, Selectivity, and Chemical Properties Gallegos, Liliana C.; Luchini, Guilian; St. John, Peter C. Accounts of Chemical Research, Vol. 54, Issue 4 https://doi.org/10.1021/acs.accounts.0c00745	journal	February 2021
Walking in the woods with quantum chemistry – applications of quantum chemical calculations in natural products research Tantillo, Dean J. Natural Product Reports, Vol. 30, Issue 8 https://doi.org/10.1039/c3np70028c	journal	January 2013
Transferable Machine-Learning Model of the Electron Density Grisafi, Andrea; Fabrizio, Alberto; Meyer, Benjamin ACS Central Science, Vol. 5, Issue 1 https://doi.org/10.1021/acscentsci.8b00551	journal	December 2018
Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties von Lilienfeld, O. Anatole; Ramakrishnan, Raghunathan; Rupp, Matthias International Journal of Quantum Chemistry, Vol. 115, Issue 16 https://doi.org/10.1002/qua.24912	journal	April 2015
Merck molecular force field. I. Basis, form, scope, parameterization, and performance of MMFF94 Halgren, Thomas A. Journal of Computational Chemistry, Vol. 17, Issue 5-6 https://doi.org/10.1002/(SICI)1096-987X(199604)17:5/6<490::AID-JCC1>3.0.CO;2-P	journal	April 1996
Use of ¹³ C NMR Chemical Shift as QSAR/QSPR Descriptor Verma, Rajeshwar P.; Hansch, Corwin Chemical Reviews, Vol. 111, Issue 4 https://doi.org/10.1021/cr100125d	journal	March 2011
Fast and accurate prediction of the regioselectivity of electrophilic aromatic substitution reactions Kromann, Jimmy C.; Jensen, Jan H.; Kruszyk, Monika Chemical Science, Vol. 9, Issue 3 https://doi.org/10.1039/C7SC04156J	journal	January 2018
Exchange functionals with improved long-range behavior and adiabatic connection methods without adjustable parameters: The mPW and mPW1PW models Adamo, Carlo; Barone, Vincenzo The Journal of Chemical Physics, Vol. 108, Issue 2 https://doi.org/10.1063/1.475428	journal	January 1998
Determination of Relative Configuration in Organic Compounds by NMR Spectroscopy and Computational Methods Bifulco, Giuseppe; Dambruoso, Paolo; Gomez-Paloma, Luigi Chemical Reviews, Vol. 107, Issue 9 https://doi.org/10.1021/cr030733c	journal	September 2007
Using Neural Networks for 13C NMR Chemical Shift Prediction–Comparison with Traditional Methods Meiler, Jens; Maier, Walter; Will, Martin Journal of Magnetic Resonance, Vol. 157, Issue 2 https://doi.org/10.1006/jmre.2002.2599	journal	August 2002
A Predictive Tool for Electrophilic Aromatic Substitutions Using Machine Learning Tomberg, Anna; Johansson, Magnus J.; Norrby, Per-Ola The Journal of Organic Chemistry, Vol. 84, Issue 8 https://doi.org/10.1021/acs.joc.8b02270	journal	October 2018
Using ¹ H and ¹³ C NMR chemical shifts to determine cyclic peptide conformations: a combined molecular dynamics and quantum mechanics approach Nguyen, Q. Nhu N.; Schwochert, Joshua; Tantillo, Dean J. Physical Chemistry Chemical Physics, Vol. 20, Issue 20 https://doi.org/10.1039/C8CP01616J	journal	January 2018
Rapid prediction of NMR spectral properties with quantified uncertainty Jonas, Eric; Kuhn, Stefan Journal of Cheminformatics, Vol. 11, Issue 1 https://doi.org/10.1186/s13321-019-0374-3	journal	August 2019
Regio-selectivity prediction with a machine-learned reaction representation and on-the-fly quantum mechanical descriptors Guan, Yanfei; Coley, Connor W.; Wu, Haoyang Chemical Science, Vol. 12, Issue 6 https://doi.org/10.1039/D0SC04823B	journal	January 2021
Building blocks for automated elucidation of metabolites: Machine learning methods for NMR prediction Kuhn, Stefan; Egert, Bjorn; Neumann, Steffen BMC Bioinformatics, Vol. 9, Issue 1 https://doi.org/10.1186/1471-2105-9-400	journal	January 2008
Efficient implementation of the gauge-independent atomic orbital method for NMR chemical shift calculations Wolinski, Krzysztof; Hinton, James F.; Pulay, Peter Journal of the American Chemical Society, Vol. 112, Issue 23 https://doi.org/10.1021/ja00179a005	journal	November 1990
Atom-centered symmetry functions for constructing high-dimensional neural network potentials Behler, Jörg The Journal of Chemical Physics, Vol. 134, Issue 7 https://doi.org/10.1063/1.3553717	journal	February 2011
Machine Learning for Quantum Mechanical Properties of Atoms in Molecules Rupp, Matthias; Ramakrishnan, Raghunathan; von Lilienfeld, O. Anatole The Journal of Physical Chemistry Letters, Vol. 6, Issue 16 https://doi.org/10.1021/acs.jpclett.5b01456	journal	July 2015
Carbon-13 NMR Chemical Shift: A Descriptor for Electronic Structure and Reactivity of Organometallic Compounds Gordon, Christopher P.; Raynaud, Christophe; Andersen, Richard A. Accounts of Chemical Research, Vol. 52, Issue 8 https://doi.org/10.1021/acs.accounts.9b00225	journal	July 2019
Application of the Multi-standard Methodology for Calculating ¹ H NMR Chemical Shifts Sarotti, Ariel M.; Pellegrinet, Silvina C. The Journal of Organic Chemistry, Vol. 77, Issue 14 https://doi.org/10.1021/jo3008447	journal	July 2012
Molecular graph convolutions: moving beyond fingerprints Kearnes, Steven; McCloskey, Kevin; Berndl, Marc Journal of Computer-Aided Molecular Design, Vol. 30, Issue 8 https://doi.org/10.1007/s10822-016-9938-8	journal	August 2016
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert Physical Review Letters, Vol. 108, Issue 5 https://doi.org/10.1103/PhysRevLett.108.058301	journal	January 2012
GFN2-xTB—An Accurate and Broadly Parametrized Self-Consistent Tight-Binding Quantum Chemical Method with Multipole Electrostatics and Density-Dependent Dispersion Contributions Bannwarth, Christoph; Ehlert, Sebastian; Grimme, Stefan Journal of Chemical Theory and Computation, Vol. 15, Issue 3 https://doi.org/10.1021/acs.jctc.8b01176	journal	January 2019
Resolving Transition Metal Chemical Space: Feature Selection for Machine Learning and Structure–Property Relationships Janet, Jon Paul; Kulik, Heather J. The Journal of Physical Chemistry A, Vol. 121, Issue 46 https://doi.org/10.1021/acs.jpca.7b08750	journal	November 2017
Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning Smith, Justin S.; Nebgen, Benjamin T.; Zubatyuk, Roman Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-10827-4	journal	July 2019
Reinvestigation of a robotically revealed reaction Sader, Jonathan K.; Wulff, Jeremy E. Nature, Vol. 570, Issue 7762 https://doi.org/10.1038/s41586-019-1176-5	journal	June 2019
DP4-AI automated NMR data analysis: straight from spectrometer to structure Howarth, Alexander; Ermanis, Kristaps; Goodman, Jonathan M. Chemical Science, Vol. 11, Issue 17 https://doi.org/10.1039/D0SC00442A	journal	January 2020
Analyzing Learned Molecular Representations for Property Prediction Yang, Kevin; Swanson, Kyle; Jin, Wengong Journal of Chemical Information and Modeling, Vol. 59, Issue 8 https://doi.org/10.1021/acs.jcim.9b00237	journal	July 2019
The Correct Structure of Aquatolide—Experimental Validation of a Theoretically-Predicted Structural Revision Lodewyk, Michael W.; Soldi, Cristian; Jones, Paul B. Journal of the American Chemical Society, Vol. 134, Issue 45 https://doi.org/10.1021/ja3089394	journal	November 2012
Machine learning unifies the modeling of materials and molecules Bartók, Albert P.; De, Sandip; Poelking, Carl Science Advances, Vol. 3, Issue 12 https://doi.org/10.1126/sciadv.1701816	journal	December 2017
Bypassing the Kohn-Sham equations with machine learning Brockherde, Felix; Vogt, Leslie; Li, Li Nature Communications, Vol. 8, Issue 1 https://doi.org/10.1038/s41467-017-00839-3	journal	October 2017
PotentialNet for Molecular Property Prediction Feinberg, Evan N.; Sur, Debnil; Wu, Zhenqin ACS Central Science, Vol. 4, Issue 11 https://doi.org/10.1021/acscentsci.8b00507	journal	November 2018
Synergy of synthesis, computation and NMR reveals correct baulamycin structures Wu, Jingjing; Lorenzo, Paula; Zhong, Siying Nature, Vol. 547, Issue 7664 https://doi.org/10.1038/nature23265	journal	July 2017
Quantum chemical calculations for over 200,000 organic radical species and 40,000 associated closed-shell molecules St. John, Peter C.; Guan, Yanfei; Kim, Yeonjoon Scientific Data, Vol. 7, Issue 1 https://doi.org/10.1038/s41597-020-00588-x	journal	July 2020
Neural Message Passing for NMR Chemical Shift Prediction Kwon, Youngchun; Lee, Dongseon; Choi, Youn-Suk Journal of Chemical Information and Modeling, Vol. 60, Issue 4 https://doi.org/10.1021/acs.jcim.0c00195	journal	April 2020
Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations Behler, Jörg Physical Chemistry Chemical Physics, Vol. 13, Issue 40 https://doi.org/10.1039/c1cp21668f	journal	January 2011
Computational Prediction of ¹ H and ¹³ C Chemical Shifts: A Useful Tool for Natural Product, Mechanistic, and Synthetic Organic Chemistry Lodewyk, Michael W.; Siebert, Matthew R.; Tantillo, Dean J. Chemical Reviews, Vol. 112, Issue 3 https://doi.org/10.1021/cr200106v	journal	November 2011
Chemical shifts in molecular solids by machine learning Paruzzo, Federico M.; Hofstetter, Albert; Musil, Félix Nature Communications, Vol. 9, Issue 1 https://doi.org/10.1038/s41467-018-06972-x	journal	October 2018
A Survey on Transfer Learning Pan, Sinno Jialin; Yang, Qiang IEEE Transactions on Knowledge and Data Engineering, Vol. 22, Issue 10 https://doi.org/10.1109/TKDE.2009.191	journal	October 2010
Performance Validation of Neural Network Based ¹³ C NMR Prediction Using a Publicly Available Data Source Blinov, K. A.; Smurnyy, Y. D.; Elyashberg, M. E. Journal of Chemical Information and Modeling, Vol. 48, Issue 3 https://doi.org/10.1021/ci700363r	journal	February 2008
Can Two Molecules Have the Same NMR Spectrum? Hexacyclinol Revisited Saielli, Giacomo; Bagno, Alessandro Organic Letters, Vol. 11, Issue 6 https://doi.org/10.1021/ol900164a	journal	February 2009
Quantum-chemical insights from deep tensor neural networks Schütt, Kristof T.; Arbabzadah, Farhad; Chmiela, Stefan Nature Communications, Vol. 8, Issue 1 https://doi.org/10.1038/ncomms13890	journal	January 2017
Total Synthesis of (−)-Himalensine A Shi, Heyao; Michaelides, Iacovos N.; Darses, Benjamin Journal of the American Chemical Society, Vol. 139, Issue 49 https://doi.org/10.1021/jacs.7b10956	journal	November 2017
A Synthesis of Echinopine B Michels, Theo D.; Dowling, Matthew S.; Vanderwal, Christopher D. Angewandte Chemie International Edition, Vol. 51, Issue 30 https://doi.org/10.1002/anie.201203147	journal	June 2012
Stereostructure Assignment of Flexible Five-Membered Rings by GIAO ¹³ C NMR Calculations: Prediction of the Stereochemistry of Elatenyne Smith, Steven G.; Paton, Robert S.; Burton, Jonathan W. The Journal of Organic Chemistry, Vol. 73, Issue 11 https://doi.org/10.1021/jo8003138	journal	May 2008
Development of a ¹³ C NMR Chemical Shift Prediction Procedure Using B3LYP/cc-pVDZ and Empirically Derived Systematic Error Correction Terms: A Computational Small Molecule Structure Elucidation Method Xin, Dongyue; Sader, C. Avery; Chaudhary, Om The Journal of Organic Chemistry, Vol. 82, Issue 10 https://doi.org/10.1021/acs.joc.7b00321	journal	April 2017

Similar Records

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

Journal Article · Tue Jun 30 00:00:00 EDT 2020 · Journal of Chemical Information and Modeling · OSTI ID:1812410

Gao, Peng; Zhang, Jun; Peng, Qian; +2 more

Machine Learning Full NMR Chemical Shift Tensors of Silicon Oxides with Equivariant Graph Neural Networks

Journal Article · Thu Mar 02 00:00:00 EST 2023 · Journal of Physical Chemistry. A, Molecules, Spectroscopy, Kinetics, Environment, and General Theory · OSTI ID:1812410

Venetos, Maxwell C.; Wen, Mingjian; Persson, Kristin A.

Applying Crystallography and ¹⁹ F NMR to investigate dynamics and partner protein interactions in a long chain Flavodoxin

Journal Article · Fri May 13 00:00:00 EDT 2022 · FASEB Journal · OSTI ID:1812410

Khan, Sharique; Ansari, Ahmadullah; Miller, Anne‐Frances

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
cheminformatics
machine learning
NMR

Title: Real-time prediction of 1 H and 13 C chemical shifts with DFT accuracy using a 3D graph neural network

Citation Formats

References (71)

Similar Records

Related Subjects

Title: Real-time prediction of ¹ H and ¹³ C chemical shifts with DFT accuracy using a 3D graph neural network