{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T13:00:07Z","timestamp":1790600407399,"version":"4.1.0"},"reference-count":34,"publisher":"American Chemical Society (ACS)","issue":"9","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2025ZD0121802"],"award-info":[{"award-number":["2025ZD0121802"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Organoboron compounds are widely used across pharmaceuticals and materials science, where 11B NMR spectroscopy serves as a valuable tool for structural characterization. However, severe spectral line broadening induced by the quadrupolar nature of the boron nucleus often causes signal overlap, making it exceptionally difficult to experimentally resolve chemically inequivalent sites in complex multiboron architectures. While traditional density functional theory can resolve these ambiguities, it faces prohibitive computational bottlenecks, whereas data-driven alternatives remain constrained by the scarcity of high-quality data sets. Herein, we report a manually verified, solvent-annotated 11B NMR data set constructed via a large language model (LLM)-assisted workflow. Interpretable machine learning identifies a strong correlation between the BCUT2D_MRLOW descriptor and the boron hybridization. Integrating these ML-derived features as prior knowledge, we developed a prior-guided Graph Transformer for accurate atom-level chemical shift prediction. Notably, the model provides a form of virtual spectral resolution, enabling the discrimination of chemically inequivalent boron sites that are difficult to resolve experimentally. We further deploy the framework as an open-access Web tool to support the rapid structural analysis of organoboron compounds.<\/jats:p>","DOI":"10.1021\/jacsau.6c00935","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T22:01:16Z","timestamp":1786744876000},"page":"5254-5263","source":"Crossref","is-referenced-by-count":0,"title":["Resolving Chemically\nInequivalent 11B NMR\nSites via Interpretable Hybrid Machine Learning"],"prefix":"10.1021","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3831-4357","authenticated-orcid":true,"given":"Penghui","family":"Li","sequence":"first","affiliation":[{"name":"Wuhan University , , , ,","place":["Wuhan, Hubei, China, 430072"]},{"name":"Shanghai Innovation Institute , ,","place":["Shanghai, China, 200230"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Gao","sequence":"additional","affiliation":[{"name":"Wuhan University , , , ,","place":["Wuhan, Hubei, China, 430072"]},{"name":"Shanghai Artificial Intelligence Laboratory , ,","place":["Shanghai, China, 200232"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University , , , ,","place":["Wuhan, Hubei, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute , ,","place":["Shanghai, China, 200230"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhisen","family":"Wei","sequence":"additional","affiliation":[{"name":"Wuhan University , , , ,","place":["Wuhan, Hubei, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2179-4634","authenticated-orcid":true,"given":"Guoyin","family":"Yin","sequence":"additional","affiliation":[{"name":"Wuhan University , , , ,","place":["Wuhan, Hubei, China, 430072"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6756-6154","authenticated-orcid":true,"given":"Yuqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute , ,","place":["Shanghai, China, 200230"]},{"name":"Shanghai Artificial Intelligence Laboratory , ,","place":["Shanghai, China, 200232"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"key":"2026092808093560900_cit1","doi-asserted-by":"publisher","first-page":"3060","DOI":"10.1039\/d3sc06864a","article-title":"Boryls,\ntheir compounds and reactivity: a structure\nand bonding perspective","volume":"15","author":"Guo","year":"2024","journal-title":"Chem. Sci."},{"key":"2026092808093560900_cit2","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1021\/jacsau.1c00129","article-title":"Recent advances in the construction\nof fluorinated organoboron compounds","volume":"2","author":"Ma","year":"2022","journal-title":"JACS Au"},{"key":"2026092808093560900_cit3","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1126\/science.abn9124","article-title":"Modular access to substituted cyclohexanes\nwith kinetic stereocontrol","volume":"376","author":"Li","year":"2022","journal-title":"Science"},{"key":"2026092808093560900_cit4","doi-asserted-by":"publisher","first-page":"1768","DOI":"10.1038\/s41557-025-01903-y","article-title":"Head\u2013tail carboboration\nof multisubstituted\nalkenes enabled by chain recognition","volume":"17","author":"Kong","year":"2025","journal-title":"Nat. Chem."},{"key":"2026092808093560900_cit5","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1039\/C3CS60197H","article-title":"Selection\nof boron reagents for Suzuki\u2013Miyaura\ncoupling","volume":"43","author":"Lennox","year":"2014","journal-title":"Chem. Soc. Rev."},{"key":"2026092808093560900_cit6","doi-asserted-by":"publisher","first-page":"264","DOI":"10.3390\/ph15030264","article-title":"The boron advantage: the evolution\nand diversification of boron\u2019s applications in medicinal chemistry","volume":"15","author":"Messner","year":"2022","journal-title":"Pharmaceuticals"},{"key":"2026092808093560900_cit7","doi-asserted-by":"publisher","first-page":"5995","DOI":"10.1039\/D5CS00147A","article-title":"BN-embedded aromatic\nhydrocarbons: synthesis, functionalization\nand applications","volume":"54","author":"Feng","year":"2025","journal-title":"Chem. Soc. Rev."},{"key":"2026092808093560900_cit8","doi-asserted-by":"publisher","first-page":"15074","DOI":"10.1002\/anie.201507770","article-title":"In situ solid-state\ngeneration of (BN)2-pyrenes and electroluminescent devices","volume":"54","author":"Wang","year":"2015","journal-title":"Angew. Chem., Int. Ed."},{"key":"2026092808093560900_cit9","doi-asserted-by":"publisher","first-page":"12945","DOI":"10.1002\/ange.202103488","article-title":"Syntheses and physical properties\nof cationic BN-embedded polycyclic aromatic hydrocarbons","volume":"133","author":"Gotoh","year":"2021","journal-title":"Angew. Chem."},{"key":"2026092808093560900_cit10","doi-asserted-by":"publisher","first-page":"13562","DOI":"10.1021\/jacs.8b08197","article-title":"Four-step synthesis of B2N2-embedded\ncorannulene","volume":"140","author":"Nakatsuka","year":"2018","journal-title":"J. Am. Chem. Soc."},{"key":"2026092808093560900_cit11","doi-asserted-by":"publisher","first-page":"8020","DOI":"10.1021\/acs.joc.8b00859","article-title":"An accessible method\nfor DFT calculation\nof 11B NMR shifts of organoboron compounds","volume":"83","author":"Rzepa","year":"2018","journal-title":"J. Org. Chem."},{"key":"2026092808093560900_cit12","doi-asserted-by":"publisher","first-page":"12385","DOI":"10.1021\/acsomega.9b01566","article-title":"11B NMR\nchemical shift predictions via density functional theory and gauge-including\natomic orbital approach: applications to structural elucidations of\nboron-containing molecules","volume":"4","author":"Gao","year":"2019","journal-title":"ACS Omega"},{"key":"2026092808093560900_cit13","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1021\/acs.jcim.5c02506","article-title":"Solvent matters:\nbridging theory and experiment in\nquantum-mechanical NMR structural elucidation","volume":"66","author":"Corte\u0301s","year":"2026","journal-title":"J. Chem. Inf. Model."},{"key":"2026092808093560900_cit14","doi-asserted-by":"publisher","first-page":"3569","DOI":"10.1038\/s41467-023-39283-x","article-title":"Reaction performance\nprediction with an extrapolative and interpretable graph model based\non chemical knowledge","volume":"14","author":"Li","year":"2023","journal-title":"Nat. Commun."},{"key":"2026092808093560900_cit15","doi-asserted-by":"publisher","DOI":"10.1002\/anie.202518560","article-title":"Data-driven modeling of N,N\u2019-dioxide\/metal-catalyzed\nasymmetric\nMichael additions","volume":"65","author":"Tang","year":"2025","journal-title":"Angew. Chem., Int. Ed."},{"key":"2026092808093560900_cit16","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1038\/s41570-022-00416-3","article-title":"Extending\nmachine learning beyond interatomic potentials\nfor predicting molecular properties","volume":"6","author":"Fedik","year":"2022","journal-title":"Nat. Rev.\nChem."},{"key":"2026092808093560900_cit17","doi-asserted-by":"publisher","first-page":"16109","DOI":"10.1021\/jacs.3c04538","article-title":"Chemical shift-dependent\ninteraction maps in molecular\nsolids","volume":"145","author":"Cordova","year":"2023","journal-title":"J. Am. Chem. Soc."},{"key":"2026092808093560900_cit18","doi-asserted-by":"publisher","first-page":"12012","DOI":"10.1039\/d1sc03343c","article-title":"Real-time\nprediction of 1H and 13C chemical shifts with\nDFT accuracy using a 3D graph neural network","volume":"12","author":"Guan","year":"2021","journal-title":"Chem. Sci."},{"key":"2026092808093560900_cit19","doi-asserted-by":"publisher","first-page":"107795","DOI":"10.1016\/j.jmr.2024.107795","article-title":"Chemical shift prediction\nin 13C NMR spectroscopy\nusing ensembles of message passing neural networks (MPNNs)","volume":"368","author":"Williamson","year":"2024","journal-title":"J. Magn. Reson."},{"key":"2026092808093560900_cit20","doi-asserted-by":"publisher","first-page":"5250","DOI":"10.1021\/acs.jctc.4c00422","article-title":"Accurate prediction\nof NMR chemical shifts: integrating DFT calculations with three-dimensional\ngraph neural networks","volume":"20","author":"Han","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026092808093560900_cit21","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1038\/s43588-025-00783-z","article-title":"Toward\na unified benchmark and framework for deep learning-based prediction\nof nuclear magnetic resonance chemical shifts","volume":"5","author":"Xu","year":"2025","journal-title":"Nat. Comput. Sci."},{"key":"2026092808093560900_cit22","doi-asserted-by":"publisher","first-page":"100043","DOI":"10.1016\/j.aichem.2024.100043","article-title":"Prediction of 19F NMR\nchemical shift by\nmachine learning","volume":"2","author":"Li","year":"2024","journal-title":"Artif. Intell. Chem."},{"key":"2026092808093560900_cit23","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1186\/s13321-023-00792-y","article-title":"Ilm-NMR-P31: an open-access 31P nuclear\nmagnetic resonance database and data-driven prediction\nof 31P NMR shifts","volume":"15","author":"Hack","year":"2023","journal-title":"J. Cheminf."},{"key":"2026092808093560900_cit24","doi-asserted-by":"publisher","first-page":"9472","DOI":"10.1039\/D3CP00253E","article-title":"Accurate prediction\nof 11B NMR chemical shift of BODIPYs via machine learning","volume":"25","author":"Ksenofontov","year":"2023","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2026092808093560900_cit25","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1021\/accountsmr.1c00244","article-title":"Interpretable and\nexplainable machine learning for materials science and chemistry","volume":"3","author":"Oviedo","year":"2022","journal-title":"Acc. Mater. Res."},{"key":"2026092808093560900_cit26","doi-asserted-by":"publisher","first-page":"2149","DOI":"10.1021\/acs.jctc.2c01235","article-title":"A perspective on\nexplanations of molecular prediction models","volume":"19","author":"Wellawatte","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"2026092808093560900_cit27","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1038\/s42004-025-01455-9","article-title":"TransPeakNet for solvent-aware 2D NMR prediction via multi-task pre-training\nand unsupervised learning","volume":"8","author":"Li","year":"2025","journal-title":"Commun. Chem."},{"key":"2026092808093560900_cit28","unstructured":"Lundberg, S. M.; Lee, S.-I.\n          A unified approach\nto interpreting model predictions.  NIPS\u201917:\nProceedings of the 31st International Conference on Neural Information\nProcessing Systems, 2017; Vol. 30."},{"key":"2026092808093560900_cit29","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1186\/s13321-024-00927-9","article-title":"GT-NMR: a\nnovel graph transformer-based approach for accurate prediction of\nNMR chemical shifts","volume":"16","author":"Chen","year":"2024","journal-title":"J. Cheminf."},{"key":"2026092808093560900_cit30","unstructured":"Satorras, V. G.; Hoogeboom, E.; Welling, M.\n          Proceedings\nof the 38th\nInternational Conference on Machine Learning; PMLR, 2021; pp 9323\u20139332; Vol. 139."},{"key":"2026092808093560900_cit31","unstructured":"Schu\u0308tt, K.; Unke, O.; Gastegger, M.\n          Proceedings of the 38th\nInternational Conference on Machine Learning; PMLR, 2021; pp 9377\u20139388l Vol. 139."},{"key":"2026092808093560900_cit32","doi-asserted-by":"crossref","unstructured":"Batatia, I.; Kova\u0301cs, D. P.; Simm, G. N. C.; Ortner, C.; Csa\u0301nyi, G.\n          Advances in Neural Information\nProcessing Systems; Curran Associates, Inc., 2022; pp 11423\u201311436; Vol. 35.","DOI":"10.52202\/068431-0830"},{"key":"2026092808093560900_cit33","doi-asserted-by":"publisher","first-page":"1954","DOI":"10.1038\/s41597-025-06245-5","article-title":"NMRexp: A database of 3.3 million experimental NMR spectra","volume":"12","author":"Wang","year":"2025","journal-title":"Sci. Data"},{"key":"2026092808093560900_cit34","doi-asserted-by":"publisher","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries\nof molecular representation for drug discovery\nwith the graph attention mechanism","volume":"63","author":"Xiong","year":"2020","journal-title":"J. Med.\nChem."}],"container-title":["JACS Au"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/jacsau.6c00935","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jaaucr\/article-pdf\/6\/9\/5254\/66573798\/jacsau.6c00935.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jaaucr\/article-pdf\/6\/9\/5254\/66573798\/jacsau.6c00935.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T12:27:12Z","timestamp":1790598432000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jaaucr\/article\/6\/9\/5254\/5257205\/Resolving-Chemically-Inequivalent-11B-NMR-Sites"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":34,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,8,14]]},"published-print":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1021\/jacsau.6c00935","relation":{},"ISSN":["2691-3704"],"issn-type":[{"value":"2691-3704","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]}}}