{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:04:25Z","timestamp":1789376665324,"version":"build-2803163510"},"reference-count":64,"publisher":"Wiley","issue":"24","license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Comput Chem"],"published-print":{"date-parts":[[2026,9,15]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Molecular dynamics (MD) simulations of novel molecules are essential to modern drug discovery and related fields that require large\u2010scale sampling of chemical space. However, obtaining accurate and robust force field parameters for novel molecules remains a major challenge. One approach to this problem is to perform quantum chemical calculations on a per\u2010molecule basis, but doing so on a large scale is prohibitively expensive. Here, we present a graph\u2010based machine learning framework for empirical force field assignment that scales significantly more efficiently with molecule size than quantum chemical methods, giving speedups of up to seven orders of magnitude for larger (20+ atoms) molecules. We demonstrate the utility of our framework by applying it to predict harmonic bond force constants and show that the resulting model outperforms the popular Seminario method for force constant assignment when using experimental data as benchmarks. This performance gain is likely a result of the model's intrinsic homogenization effect, which counteracts the noise in the training data. Moreover, our framework overcomes several challenges in translating first\u2010principles calculations to classical MD force field parameters, producing parameters with better transferability and interpretability compared to previous models of this class.<\/jats:p>","DOI":"10.1002\/jcc.70508","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:18:59Z","timestamp":1789373939000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Graph\u2010Based Machine Learning Framework to Assign Empirical Interaction Parameters for Novel Molecules"],"prefix":"10.1002","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2818-8980","authenticated-orcid":false,"given":"Yao","family":"Fu","sequence":"first","affiliation":[{"name":"Australian Institute for Bioengineering and Nanotechnology, The University of Queensland  St Lucia Queensland Australia"},{"name":"ARC Centre of Excellence in Quantum Biotechnology The University of Queensland  St Lucia Queensland Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Stroet","sequence":"additional","affiliation":[{"name":"ARC Centre of Excellence in Quantum Biotechnology The University of Queensland  St Lucia Queensland Australia"},{"name":"School of Chemistry and Molecular Biosciences The University of Queensland  St Lucia Queensland Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8764-1585","authenticated-orcid":false,"given":"Megan L.","family":"O'Mara","sequence":"additional","affiliation":[{"name":"Australian Institute for Bioengineering and Nanotechnology, The University of Queensland  St Lucia Queensland Australia"},{"name":"ARC Centre of Excellence in Quantum Biotechnology The University of Queensland  St Lucia Queensland Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"issue":"7","key":"e_1_2_10_2_1","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1007\/s00249-011-0700-9","article-title":"Definition and Testing of the GROMOS Force\u2010Field Versions 54A7 and 54B7","volume":"40","author":"Schmid N.","year":"2011","journal-title":"European Biophysics Journal"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.9b00591"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1021\/jp973084f"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1021\/ja9621760"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.3c00148"},{"issue":"23","key":"e_1_2_10_7_1","doi-asserted-by":"crossref","first-page":"13055","DOI":"10.1039\/D1CP00215E","article-title":"Evaluation of Nine Condensed\u2010Phase Force Fields of the GROMOS, CHARMM, OPLS, AMBER, and OpenFF Families Against Experimental Cross\u2010Solvation Free Energies","volume":"23","author":"Kashefolgheta S.","year":"2021","journal-title":"Physical Chemistry Chemical Physics"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.5b01684"},{"issue":"4","key":"e_1_2_10_9_1","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1002\/jcc.21367","article-title":"CHARMM General Force Field: A Force Field for Drug\u2010Like Molecules Compatible With the CHARMM All\u2010Atom Additive Biological Force Fields","volume":"31","author":"Vanommeslaeghe K.","year":"2010","journal-title":"Journal of Computational Chemistry"},{"issue":"9","key":"e_1_2_10_10_1","doi-asserted-by":"crossref","first-page":"1157","DOI":"10.1002\/jcc.20035","article-title":"Development and Testing of a General Amber Force Field","volume":"25","author":"Wang J.","year":"2004","journal-title":"Journal of Computational Chemistry"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1021\/ct4003477"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1021\/ct200196m"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cplett.2005.02.109"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1021\/jp410975s"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpcc.5b08554"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097\u2010461X(1996)60:7<1271::AID\u2010QUA8>3.0.CO;2\u2010W"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.7b00785"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.1c00195"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0004997"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.8b00768"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.3c00427"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.22937"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.21523"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1021\/ct500573f"},{"issue":"11","key":"e_1_2_10_25_1","doi-asserted-by":"crossref","first-page":"3736","DOI":"10.1039\/c3cp44179b","article-title":"Joyce and Ulysses: Integrated and User\u2010Friendly Tools for the Parameterization of Intramolecular Force Fields From Quantum Mechanical Data","volume":"15","author":"Barone V.","year":"2013","journal-title":"Physical Chemistry Chemical Physics"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.10190"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1021\/ct700113h"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c01444"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.8b00767"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.23877"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.58"},{"issue":"41","key":"e_1_2_10_32_1","doi-asserted-by":"crossref","first-page":"12016","DOI":"10.1039\/D2SC02739A","article-title":"End\u2010to\u2010End Differentiable Construction of Molecular Mechanics Force Fields","volume":"13","author":"Wang Y.","year":"2022","journal-title":"Chemical Science"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1039\/d4sc05465b"},{"key":"e_1_2_10_34_1","doi-asserted-by":"crossref","DOI":"10.1063\/5.0237876","article-title":"On the Design Space Between Molecular Mechanics and Machine Learning Force Fields","volume":"12","author":"Wang Y.","year":"2025","journal-title":"Applied Physics Reviews"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aav6490"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1039\/C6SC05720A"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010022\u201029939\u20105"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.0c00121"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrev.0c00868"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010020\u201020427\u20102"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010023\u201036329\u2010y"},{"key":"e_1_2_10_42_1","doi-asserted-by":"crossref","first-page":"11423","DOI":"10.52202\/068431-0830","article-title":"MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields","volume":"35","author":"Batatia I.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_43_1","first-page":"1263","article-title":"Neural Message Passing for Quantum Chemistry","volume":"70","author":"Gilmer J.","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.9b00181"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.5019779"},{"key":"e_1_2_10_46_1","unstructured":"T. K.Rusch M. M.Bronstein andS.Mishra \u201cA Survey on Oversmoothing in Graph Neural Networks \u201dpreprint arXiv March 20 2023 https:\/\/doi.org\/10.48550\/arXiv.2303.10993."},{"key":"e_1_2_10_47_1","volume-title":"Advances in Neural Information Processing Systems","author":"Hamilton W.","year":"2017"},{"key":"e_1_2_10_48_1","unstructured":"T. N.KipfandM.Welling \u201cSemi\u2010Supervised Classification With Graph Convolutional Networks \u201dpreprint arXiv September 9 2016 https:\/\/doi.org\/10.48550\/arXiv.1609.02907."},{"key":"e_1_2_10_49_1","unstructured":"K.Xu W.Hu J.Leskovec andS.Jegelka \u201cHow Powerful Are Graph Neural Networks? \u201dpreprint arXiv October 1 2018 https:\/\/doi.org\/10.48550\/arXiv.1810.00826."},{"issue":"8","key":"e_1_2_10_50_1","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short\u2010Term Memory","volume":"9","author":"Hochreiter S.","year":"1997","journal-title":"Neural Computation"},{"key":"e_1_2_10_51_1","unstructured":"R. L.Murphy B.Srinivasan V.Rao andB.Ribeiro \u201cJanossy Pooling: Learning Deep Permutation\u2010Invariant Functions for Variable\u2010Size Inputs \u201dpreprint arXiv November 5 2018 https:\/\/doi.org\/10.48550\/arXiv.1811.01900."},{"key":"e_1_2_10_52_1","volume-title":"CRC Handbook of Chemistry and Physics","author":"Rumble J.","year":"2017"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/0009\u20102614"},{"issue":"11","key":"e_1_2_10_54_1","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1002\/jcc.540141112","article-title":"General Atomic and Molecular Electronic Structure System","volume":"14","author":"Schmidt M. W.","year":"1993","journal-title":"Journal of Computational Chemistry"},{"key":"e_1_2_10_55_1","unstructured":"D. P.Kingma \u201cAdam: A Method for Stochastic Optimization \u201dpreprint arXiv December 22 2014 https:\/\/doi.org\/10.48550\/arXiv.1412.6980."},{"key":"e_1_2_10_56_1","unstructured":"S.Mitchell M.O'Sullivan andI.Dunning \u201cPuLP: A Linear Programming Toolkit for Python \u201d2011 https:\/\/api.semanticscholar.org\/CorpusID:14277904."},{"key":"e_1_2_10_57_1","doi-asserted-by":"publisher","DOI":"10.1021\/ja00315a051"},{"key":"e_1_2_10_58_1","doi-asserted-by":"publisher","DOI":"10.1021\/ja00214a001"},{"issue":"5","key":"e_1_2_10_59_1","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1021\/je000236i","article-title":"The NIST Chemistry WebBook: A Chemical Data Resource on the Internet","volume":"46","author":"Linstrom P. J.","year":"2001","journal-title":"Journal of Chemical & Engineering Data"},{"key":"e_1_2_10_60_1","volume-title":"Tables of Spectral Data for Structure Determination of Organic Compounds","author":"Pretsch E.","year":"2013"},{"issue":"2","key":"e_1_2_10_61_1","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1016\/j.drudis.2019.12.001","article-title":"Targeting CDK2 in Cancer: Challenges and Opportunities for Therapy","volume":"25","author":"Tadesse S.","year":"2020","journal-title":"Drug Discovery Today"},{"key":"e_1_2_10_62_1","doi-asserted-by":"publisher","DOI":"10.1021\/jm0311442"},{"key":"e_1_2_10_63_1","doi-asserted-by":"publisher","DOI":"10.1038\/nsb842"},{"key":"e_1_2_10_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtbi.2013.05.014"},{"key":"e_1_2_10_65_1","doi-asserted-by":"publisher","DOI":"10.1021\/jp960976r"}],"container-title":["Journal of Computational Chemistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jcc.70508","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jcc.70508","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jcc.70508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:19:07Z","timestamp":1789373947000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jcc.70508"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,14]]},"references-count":64,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2026,9,15]]}},"alternative-id":["10.1002\/jcc.70508"],"URL":"https:\/\/doi.org\/10.1002\/jcc.70508","archive":["Portico"],"relation":{},"ISSN":["0192-8651","1096-987X"],"issn-type":[{"value":"0192-8651","type":"print"},{"value":"1096-987X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,14]]},"assertion":[{"value":"2026-05-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70508"}}