{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T01:22:21Z","timestamp":1790644941399,"version":"4.1.0"},"reference-count":54,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T00:00:00Z","timestamp":1716076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Institute of Health","award":["U24 AT010811"],"award-info":[{"award-number":["U24 AT010811"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Metabolites"],"abstract":"<jats:p>NMR is widely considered the gold standard for organic compound structure determination. As such, NMR is routinely used in organic compound identification, drug metabolite characterization, natural product discovery, and the deconvolution of metabolite mixtures in biofluids (metabolomics and exposomics). In many cases, compound identification by NMR is achieved by matching measured NMR spectra to experimentally collected NMR spectral reference libraries. Unfortunately, the number of available experimental NMR reference spectra, especially for metabolomics, medical diagnostics, or drug-related studies, is quite small. This experimental gap could be filled by predicting NMR chemical shifts for known compounds using computational methods such as machine learning (ML). Here, we describe how a deep learning algorithm that is trained on a high-quality, \u201csolvent-aware\u201d experimental dataset can be used to predict 1H chemical shifts more accurately than any other known method. The new program, called PROSPRE (PROton Shift PREdictor) can accurately (mean absolute error of &lt;0.10 ppm) predict 1H chemical shifts in water (at neutral pH), chloroform, dimethyl sulfoxide, and methanol from a user-submitted chemical structure. PROSPRE (pronounced \u201cprosper\u201d) has also been used to predict 1H chemical shifts for &gt;600,000 molecules in many popular metabolomic, drug, and natural product databases.<\/jats:p>","DOI":"10.3390\/metabo14050290","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T06:31:58Z","timestamp":1716186718000},"page":"290","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Accurate Prediction of 1H NMR Chemical Shifts of Small Molecules Using Machine Learning"],"prefix":"10.3390","volume":"14","author":[{"given":"Tanvir","family":"Sajed","sequence":"first","affiliation":[{"name":"Department of Biological Sciences, University of Alberta, Edmonton, AB T6G 2E9, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zinat","family":"Sayeeda","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, University of Alberta, Edmonton, AB T6G 2E9, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian L.","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, University of Alberta, Edmonton, AB T6G 2E9, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Berjanskii","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, University of Alberta, Edmonton, AB T6G 2E9, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, AB T6G 2E8, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9204-1963","authenticated-orcid":false,"given":"Vasuk","family":"Gautam","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, University of Alberta, Edmonton, AB T6G 2E9, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3207-2434","authenticated-orcid":false,"given":"David S.","family":"Wishart","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, University of Alberta, Edmonton, AB T6G 2E9, Canada"},{"name":"Department of Computing Science, University of Alberta, Edmonton, AB T6G 2E8, Canada"},{"name":"Department of Laboratory Medicine and Pathology, University of Alberta, Edmonton, AB T6G 2B7, Canada"},{"name":"Faculty of Pharmacy and Pharmaceutical Sciences, University of Alberta, Edmonton, AB T6G 2H7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,5,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.pnmrs.2021.08.001","article-title":"NMR spectroscopy of wastewater: A review, case study, and future potential","volume":"126\u2013127","author":"Anaraki","year":"2021","journal-title":"Prog. Nucl. Magn. Reson. Spectrosc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.coesh.2020.01.008","article-title":"The use of nuclear magnetic resonance (NMR) and mass spectrometry (MS)\u2013based metabolomics in environmental exposure assessment","volume":"15","author":"Labine","year":"2020","journal-title":"Curr. Opin. Environ. Sci. Health"},{"key":"ref_3","first-page":"549","article-title":"Environmental Metabolomics: NMR Techniques","volume":"Volume 2","author":"Harris","year":"2013","journal-title":"eMagRes"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Shi, L., and Zhang, N. (2021). Applications of solution NMR in drug discovery. Molecules, 26.","DOI":"10.3390\/molecules26030576"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Bruzzone, C., Conde, R., Embade, N., Mato, J.M., and Millet, O. (2023). Metabolomics as a powerful tool for diagnostic, prognostic and drug intervention analysis in COVID-19. Front. Mol. Biosci., 10.","DOI":"10.3389\/fmolb.2023.1111482"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1044","DOI":"10.1021\/acs.jnatprod.0c01076","article-title":"Development of an NMR-based platform for the direct structural annotation of complex natural products mixtures","volume":"84","author":"Egan","year":"2021","journal-title":"J. Nat. Prod."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"480","DOI":"10.1002\/em.21777","article-title":"Measuring the exposome: A powerful basis for evaluating environmental exposures and cancer risk","volume":"54","author":"Wild","year":"2013","journal-title":"Environ. Mol. Mutagen."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"9108","DOI":"10.1038\/s41598-017-09203-3","article-title":"Serum and urine (1)H NMR-based metabolomics in the diagnosis of selected thyroid diseases","volume":"7","author":"Wojtowicz","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"D622","DOI":"10.1093\/nar\/gkab1062","article-title":"HMDB 5.0: The Human Metabolome Database for 2022","volume":"50","author":"Wishart","year":"2022","journal-title":"Nucleic Acids Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/978-1-0716-0270-6_14","article-title":"BioMagResBank (BMRB) as a resource for structural biology","volume":"2112","author":"Romero","year":"2020","journal-title":"Methods Mol. Biol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1021\/ci0341363","article-title":"NMRShiftDB\u2014Constructing a free chemical information system with open-source components","volume":"43","author":"Steinbeck","year":"2003","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"35","DOI":"10.5571\/syntheng.4.35","article-title":"Development and release of a spectral database for organic compounds\u2014Key to the continual services and success of a large-scale database","volume":"4","author":"Saito","year":"2011","journal-title":"Synthesiology"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"D665","DOI":"10.1093\/nar\/gkab1052","article-title":"NP-MRD: The Natural Products Magnetic Resonance Database","volume":"50","author":"Wishart","year":"2022","journal-title":"Nucleic Acids Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"D1265","DOI":"10.1093\/nar\/gkad976","article-title":"DrugBank 6.0: The DrugBank knowledgebase for 2024","volume":"52","author":"Knox","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lokhov, P.G., Maslov, D.L., Kharibin, O.N., Balashova, E.E., and Archakov, A.I. (2017). Label-free data standardization for clinical metabolomics. BioData Min., 10.","DOI":"10.1186\/s13040-017-0132-x"},{"key":"ref_16","unstructured":"Nu\u00f1ez, J.R., Colby, S.M., Thomas, D.G., Tfaily, M.M., Tolic, N., Ulrich, E.M., Sobus, J.R., Metz, T.O., Teeguarden, J.G., and Renslow, R.S. (2018). Advancing standards-free methods for the identification of small molecules in complex samples. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1002\/mrc.5234","article-title":"Prediction of chemical shift in NMR: A review","volume":"60","author":"Jonas","year":"2021","journal-title":"Magn. Reson. Chem."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5121","DOI":"10.1021\/ja01552a031","article-title":"Nuclear magnetic resonance spectra of steroids","volume":"80","author":"Shoolery","year":"1958","journal-title":"J. Am. Chem. Soc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3977","DOI":"10.1021\/ja01620a009","article-title":"The electron withdrawal power of substituent groups","volume":"77","author":"Dailey","year":"1955","journal-title":"J. Am. Chem. Soc."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1021\/ci00046a010","article-title":"CSEARCH: A computer program for identification of organic compounds and fully automated assignment of carbon-13 nuclear magnetic resonance spectra","volume":"25","author":"Kalchhauser","year":"1985","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/S0003-2670(01)83100-7","article-title":"Hose\u2014A novel substructure code","volume":"103","author":"Bremser","year":"1978","journal-title":"Anal. Chim. Acta"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"7323","DOI":"10.1021\/acsomega.9b00488","article-title":"Stereo-aware extension of HOSE codes","volume":"4","author":"Kuhn","year":"2019","journal-title":"ACS Omega"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1002\/(SICI)1096-987X(19990115)20:1<91::AID-JCC10>3.0.CO;2-C","article-title":"The DFT route to NMR chemical shifts","volume":"20","author":"Kaupp","year":"1999","journal-title":"J. Comput. Chem."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"12012","DOI":"10.1039\/D1SC03343C","article-title":"Real-time prediction of 1H and 13C chemical shifts with DFT accuracy using a 3D graph neural network","volume":"12","author":"Guan","year":"2021","journal-title":"Chem. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1021\/cr200106v","article-title":"Computational prediction of 1H and 13C chemical shifts: A useful tool for natural product, mechanistic, and synthetic organic chemistry","volume":"112","author":"Lodewyk","year":"2012","journal-title":"Chem. Rev."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci00010a023","article-title":"Application of recurrent neural networks in chemistry. Prediction and classification of carbon-13 NMR chemical shifts in a series of monosubstituted benzenes","volume":"32","author":"Kvasnicka","year":"1992","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1021\/ci000021c","article-title":"Fast determination of 13C NMR chemical shifts using artificial neural networks","volume":"40","author":"Meiler","year":"2000","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1021\/ac010737m","article-title":"Prediction of 1H NMR chemical shifts using neural networks","volume":"74","author":"Hemmer","year":"2002","journal-title":"Anal. Chem."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1021\/ci034228s","article-title":"Structure-based predictions of 1H NMR chemical shifts using feed-forward neural networks","volume":"44","author":"Binev","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/s13321-019-0374-3","article-title":"Rapid prediction of NMR spectral properties with quantified uncertainty","volume":"11","author":"Jonas","year":"2019","journal-title":"J. Cheminform."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1218","DOI":"10.1063\/1.1730877","article-title":"On the nature of solvent effects in the proton resonance spectra of unsaturated ring compounds. I. Substituted benzenes","volume":"32","author":"Schaefer","year":"1960","journal-title":"J. Chem. Phys."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1829","DOI":"10.1139\/v67-295","article-title":"Studies of the solvent effect on the chemical shifts in n.m.r. spectroscopy. II. Solutions of succinic anhydride, maleic anhydride, and the N-substituted imides","volume":"45","author":"Matsuo","year":"1967","journal-title":"Can. J. Chem."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"7512","DOI":"10.1021\/jo971176v","article-title":"NMR chemical shifts of common laboratory solvents as trace impurities","volume":"62","author":"Gottlieb","year":"1997","journal-title":"J. Org. Chem."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/BF00211777","article-title":"1H, 13C and 15N chemical shift referencing in biomolecular NMR","volume":"6","author":"Wishart","year":"1995","journal-title":"J. Biomol. NMR"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"10646","DOI":"10.1021\/acs.analchem.8b02660","article-title":"Applications of parametrized NMR spin systems of small molecules","volume":"90","author":"Dashti","year":"2018","journal-title":"Anal. Chem."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/S0076-6879(94)39014-2","article-title":"Chemical shifts as a tool for structure determination","volume":"239","author":"Wishart","year":"1994","journal-title":"Methods Enzymol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"170073","DOI":"10.1038\/sdata.2017.73","article-title":"Unique identifiers for small molecules enable rigorous labeling of their atoms","volume":"4","author":"Dashti","year":"2017","journal-title":"Sci. Data"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"13180","DOI":"10.1021\/ja906709t","article-title":"MestRe Nova","volume":"131","author":"Willcott","year":"2009","journal-title":"J. Am. Chem. Soc."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Friebolin, H. (2005). Basic One-and Two-Dimensional NMR Spectroscopy, Wiley-VCH. [4th ed.].","DOI":"10.1055\/s-2005-867116"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2895","DOI":"10.1021\/ol0611346","article-title":"Predicting NMR spectra by computational methods: Structure revision of hexacyclinol","volume":"8","author":"Rychnovsky","year":"2006","journal-title":"Org. Lett."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"18550","DOI":"10.1021\/ja3089394","article-title":"The correct structure of aquatolide\u2014Experimental validation of a theoretically-predicted structural revision","volume":"134","author":"Lodewyk","year":"2012","journal-title":"J. Am. Chem. Soc."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"107105","DOI":"10.1016\/j.jmr.2021.107105","article-title":"Magnetic susceptibility measurement by NMR: 2. The magnetic susceptibility of NMR solvents and their chemical shifts","volume":"335","author":"Hoffman","year":"2022","journal-title":"J. Magn. Reson."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"D611","DOI":"10.1093\/nar\/gkac868","article-title":"MiMeDB: The Human Microbial Metabolome Database","volume":"51","author":"Wishart","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"D495","DOI":"10.1093\/nar\/gkv1060","article-title":"ECMDB 2.0: A richer resource for understanding the biochemistry of E. coli","volume":"44","author":"Sajed","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"D440","DOI":"10.1093\/nar\/gkw1058","article-title":"YMDB 2.0: A significantly expanded version of the yeast metabolome database","volume":"45","author":"Marcu","year":"2017","journal-title":"Nucleic Acids Res."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1186\/s12302-022-00680-6","article-title":"The NORMAN Suspect List Exchange (NORMAN-SLE): Facilitating European and worldwide collaboration on suspect screening in high resolution mass spectrometry","volume":"34","author":"Aalizadeh","year":"2022","journal-title":"Environ. Sci. Eur."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"18326","DOI":"10.1021\/acs.analchem.3c02413","article-title":"Deep learning-enabled MS\/MS spectrum prediction facilitates automated identification of novel psychoactive substances","volume":"95","author":"Wang","year":"2023","journal-title":"Anal. Chem."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.copbio.2016.07.006","article-title":"Knowns and unknowns in metabolomics identified by multidimensional NMR and hybrid MS\/NMR methods","volume":"43","author":"Bingol","year":"2017","journal-title":"Curr. Opin. Biotechnol."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1021\/ci9902696","article-title":"JChem: Java applets and modules supporting chemical database handling from web browsers","volume":"40","author":"Csizmadia","year":"2000","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/s13321-016-0160-4","article-title":"Jmol SMILES and Jmol SMARTS: Specifications and applications","volume":"8","author":"Hanson","year":"2016","journal-title":"J. Cheminform."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1002\/bmb.2006.494034042644","article-title":"Biomolecules in the computer: Jmol to the rescue","volume":"34","year":"2006","journal-title":"Biochem. Mol. Biol. Educ."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1186\/s13321-016-0174-y","article-title":"ClassyFire: Automated chemical classification with a comprehensive, computable taxonomy","volume":"8","author":"Eisner","year":"2016","journal-title":"J. Cheminform."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"2044","DOI":"10.1021\/acs.jcim.0c00025","article-title":"Improving conformer generation for small rings and macrocycles based on distance geometry and experimental torsional-angle preferences","volume":"60","author":"Wang","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/1758-2946-3-33","article-title":"Open Babel: An open chemical toolbox","volume":"3","author":"Banck","year":"2011","journal-title":"J. Cheminform."}],"container-title":["Metabolites"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-1989\/14\/5\/290\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:44:55Z","timestamp":1760107495000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-1989\/14\/5\/290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,19]]},"references-count":54,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["metabo14050290"],"URL":"https:\/\/doi.org\/10.3390\/metabo14050290","relation":{},"ISSN":["2218-1989"],"issn-type":[{"value":"2218-1989","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,19]]}}}