{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T18:28:05Z","timestamp":1786991285992,"version":"build-2736575974"},"reference-count":68,"publisher":"AIP Publishing","issue":"7","content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,21]]},"abstract":"<jats:p>Melting point (MP) is an important thermophysical property for the chemical process industry, yet accurate prediction of MP for organic compounds in the absence of experimental data remains challenging due to the complex interplay between molecular packing, intermolecular interactions, and electronic structure. Traditional group contribution and quantitative structure\u2013property relationship models, which rely primarily on static molecular descriptors, often fail to capture these critical condensed-phase effects. In this study, we present a hybrid machine learning framework that integrates cheminformatics descriptors with quantum chemical features and dynamic condensed-phase descriptors derived from molecular dynamics (MD) simulations. Using a curated subset of the DIPPR 801 database, multiple machine learning architectures, including light gradient boosting machine (LightGBM) and graph convolutional networks, were evaluated with feature sets of increasing physical fidelity. The best-performing model, based on LightGBM trained on Dragon descriptors augmented with MD and quantum chemical features, achieves a mean absolute error of 22.5\u00a0K, outperforming descriptor-only models and structure-based deep learning baselines. Shapley additive explanations interpretability analysis reveals that melting behavior is governed primarily by molecular topology, surface-area-weighted electronic descriptors, and condensed-phase interaction properties. In contrast, many isolated functional group and single molecule electronic descriptors contribute negligibly once these effects are accounted for. These results demonstrate that incorporating physics-informed, multi-scale descriptors enables more accurate and physically interpretable MP predictions.<\/jats:p>","DOI":"10.1063\/5.0342619","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T17:53:35Z","timestamp":1786989215000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning prediction of organic compound melting points informed by condensed-phase and electronic descriptors"],"prefix":"10.1063","volume":"165","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8111-6711","authenticated-orcid":false,"given":"Frank T.","family":"Mtetwa","sequence":"first","affiliation":[{"name":"Department of Chemical and Biological Engineering, Brigham Young University , Provo, Utah 84602,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8216-9990","authenticated-orcid":false,"given":"Neil F.","family":"Giles","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biological Engineering, Brigham Young University , Provo, Utah 84602,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1899-865X","authenticated-orcid":false,"given":"W. Vincent","family":"Wilding","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biological Engineering, Brigham Young University , Provo, Utah 84602,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6248-4459","authenticated-orcid":false,"suffix":"IV","given":"Thomas A.","family":"Knotts","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biological Engineering, Brigham Young University , Provo, Utah 84602,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"317","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"2026081713532854600_c1","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1023\/A:1015949907825","volume":"7","year":"1990","journal-title":"Pharm. Res."},{"key":"2026081713532854600_c2","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1002\/1520-6017(200102)90:2&lt;234::aid-jps14&gt;3.0.co;2-v","volume":"90","year":"2001","journal-title":"J.\u00a0Pharm. Sci."},{"key":"2026081713532854600_c3","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1021\/ci000338c","volume":"41","year":"2001","journal-title":"J.\u00a0Chem. Inf. Comput. Sci."},{"key":"2026081713532854600_c4","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1002\/minf.201500052","article-title":"Predicting melting points of organic molecules: Applications to aqueous solubility prediction using the general solubility equation","volume":"34","year":"2015","journal-title":"Mol. Inf."},{"key":"2026081713532854600_c5","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1080\/0031910021000059063","volume":"41","year":"2003","journal-title":"Phys. Chem. Liq."},{"key":"2026081713532854600_c6","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1080\/00986448708960487","volume":"57","year":"1987","journal-title":"Chem. Eng. Commun."},{"key":"2026081713532854600_c7","doi-asserted-by":"publisher","first-page":"1697","DOI":"10.1002\/aic.690401011","volume":"40","year":"1994","journal-title":"AIChE J."},{"key":"2026081713532854600_c8","volume-title":"The Properties of Gases and Liquids","year":"2023","edition":"6"},{"key":"2026081713532854600_c9","doi-asserted-by":"publisher","first-page":"3320","DOI":"10.1021\/ci5005288","volume":"54","year":"2014","journal-title":"J.\u00a0Chem. Inf. Model."},{"key":"2026081713532854600_c10","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1021\/ci700307p","volume":"48","year":"2008","journal-title":"J.\u00a0Chem. Inf. Model."},{"key":"2026081713532854600_c11","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1002\/minf.201400122","volume":"34","year":"2015","journal-title":"Mol. Inf."},{"key":"2026081713532854600_c12","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1039\/d0cc07384a","volume":"57","year":"2021","journal-title":"Chem. Commun."},{"key":"2026081713532854600_c13","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1080\/02678292.2023.2275293","volume":"51","year":"2024","journal-title":"Liq. Cryst."},{"key":"2026081713532854600_c14","doi-asserted-by":"publisher","first-page":"24296","DOI":"10.1021\/acsomega.5c00205","volume":"10","year":"2025","journal-title":"ACS Omega"},{"key":"2026081713532854600_c15","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1021\/ci020280x","volume":"43","year":"2003","journal-title":"J.\u00a0Chem. Inf. Comput. Sci."},{"key":"2026081713532854600_c16","doi-asserted-by":"publisher","first-page":"2412","DOI":"10.1021\/ci060149f","volume":"46","year":"2006","journal-title":"J.\u00a0Chem. Inf. Model."},{"key":"2026081713532854600_c17","volume-title":"DIPPR\u00ae Data Compilation of Pure Chemical Properties","year":"2025"},{"key":"2026081713532854600_c18","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","volume":"59","year":"2019","journal-title":"J.\u00a0Chem. Inf. Model."},{"key":"2026081713532854600_c19","doi-asserted-by":"publisher","first-page":"102616","DOI":"10.1016\/j.sbi.2023.102616","volume":"81","year":"2023","journal-title":"Curr. Opin. Struct. Biol."},{"key":"2026081713532854600_c20","first-page":"59765","article-title":"E(3)-equivariant models cannot learn chirality: Field-based molecular generation","year":"2025"},{"key":"2026081713532854600_c21","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1038\/s42004-020-00388-9","volume":"3","year":"2020","journal-title":"Commun. Chem."},{"key":"2026081713532854600_c22","doi-asserted-by":"publisher","first-page":"145301","DOI":"10.1103\/physrevlett.120.145301","volume":"120","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"2026081713532854600_c23","first-page":"27","volume-title":"Protein Simulations, Advances in Protein Chemistry","year":"2003"},{"key":"2026081713532854600_c24","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1002\/wcms.1215","volume":"5","year":"2015","journal-title":"WIREs Comput. Mol. Sci."},{"key":"2026081713532854600_c25","doi-asserted-by":"publisher","first-page":"031104","DOI":"10.1063\/1.5020808","volume":"5","year":"2018","journal-title":"Appl. Phys. Rev."},{"key":"2026081713532854600_c26","doi-asserted-by":"publisher","first-page":"4169","DOI":"10.1021\/acs.cgd.4c01753","volume":"25","year":"2025","journal-title":"Cryst. Growth Des."},{"key":"2026081713532854600_c27","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1021\/cg020039a","volume":"2","year":"2002","journal-title":"Cryst. Growth Des."},{"key":"2026081713532854600_c28","doi-asserted-by":"publisher","first-page":"2382","DOI":"10.1103\/physreve.53.2382","volume":"53","year":"1996","journal-title":"Phys. Rev. E"},{"key":"2026081713532854600_c29","doi-asserted-by":"publisher","first-page":"2495151","DOI":"10.1080\/23746149.2025.2495151","volume":"10","year":"2025","journal-title":"Adv. Phys.: X"},{"key":"2026081713532854600_c30","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1021\/acs.jced.0c00641","volume":"66","year":"2021","journal-title":"J.\u00a0Chem. Eng. Data"},{"key":"2026081713532854600_c31","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1016\/s0378-3812(98)00341-0","volume":"150\u2013151","year":"1998","journal-title":"Fluid Phase Equilib."},{"key":"2026081713532854600_c32","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","volume":"39","year":"1996","journal-title":"J.\u00a0Med. Chem."},{"key":"2026081713532854600_c33","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","volume":"50","year":"2010","journal-title":"J.\u00a0Chem. Inf. Model."},{"key":"2026081713532854600_c34","unstructured":"T. T.\n            Tanimoto\n          , \u201cAn elementary mathematical theory of classification and prediction,\u201d Internal Report (IBM Corporation, 1958)."},{"key":"2026081713532854600_c35","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","year":"1988","journal-title":"J.\u00a0Chem. Inf. Comput. Sci."},{"key":"2026081713532854600_c36","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1021\/ci00007a012","volume":"32","year":"1992","journal-title":"J.\u00a0Chem. Inf. Comput. Sci."},{"key":"2026081713532854600_c37","volume-title":"Molecular Descriptors for Chemoinformatics","year":"2009"},{"key":"2026081713532854600_c38","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.1002\/jcc.21707","volume":"32","year":"2011","journal-title":"J.\u00a0Comput. Chem."},{"key":"2026081713532854600_c39","unstructured":"G.\n            Landrum\n          , Rdkit: Open-source cheminformatics, http:\/\/www.rdkit.org, 2025 (accessed 21 June, 2025)."},{"key":"2026081713532854600_c40","unstructured":"KODE SRL, Dragon (software for molecular descriptor calculation), version 7.0.4, 2016, https:\/\/chm.kode-solutions.net."},{"key":"2026081713532854600_c41","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13321-018-0258-y","volume":"10","year":"2018","journal-title":"J.\u00a0Cheminf."},{"key":"2026081713532854600_c42","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1007\/978-1-4899-7687-1_192","volume-title":"Encyclopedia of Machine Learning and Data Mining","year":"2017"},{"key":"2026081713532854600_c43","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"2026081713532854600_c44","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1023\/a:1012487302797","volume":"46","year":"2002","journal-title":"Mach. Learn."},{"key":"2026081713532854600_c45","volume-title":"Gaussian 16 Revision C.01","year":"2016"},{"key":"2026081713532854600_c46","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1063\/1.456153","volume":"90","year":"1989","journal-title":"J.\u00a0Chem. Phys."},{"key":"2026081713532854600_c47","doi-asserted-by":"publisher","first-page":"6796","DOI":"10.1063\/1.462569","volume":"96","year":"1992","journal-title":"J.\u00a0Chem. Phys."},{"key":"2026081713532854600_c48","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1063\/1.464303","volume":"98","year":"1993","journal-title":"J.\u00a0Chem. Phys."},{"key":"2026081713532854600_c49","doi-asserted-by":"publisher","first-page":"7410","DOI":"10.1063\/1.466884","volume":"100","year":"1994","journal-title":"J.\u00a0Chem. Phys."},{"key":"2026081713532854600_c50","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/s0166-1280(96)80048-0","volume":"388","year":"1996","journal-title":"J.\u00a0Mol. Struct.: THEOCHEM"},{"key":"2026081713532854600_c51","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1016\/0009-2614(96)00917-7","volume":"260","year":"1996","journal-title":"Chem. Phys. Lett."},{"key":"2026081713532854600_c52","doi-asserted-by":"publisher","first-page":"108171","DOI":"10.1016\/j.cpc.2021.108171","volume":"271","year":"2022","journal-title":"Comput. Phys. Commun."},{"key":"2026081713532854600_c53","doi-asserted-by":"publisher","first-page":"11225","DOI":"10.1021\/ja9621760","volume":"118","year":"1996","journal-title":"J.\u00a0Am. Chem. Soc."},{"key":"2026081713532854600_c54","doi-asserted-by":"publisher","first-page":"W331","DOI":"10.1093\/nar\/gkx312","volume":"45","year":"2017","journal-title":"Nucleic Acids Res."},{"key":"2026081713532854600_c55","first-page":"3281","volume-title":"The Encyclopedia of Computational Chemistry","author":"Schleyer","year":"1998"},{"key":"2026081713532854600_c56","doi-asserted-by":"publisher","first-page":"3864","DOI":"10.1021\/acs.jpcb.7b00272","volume":"121","year":"2017","journal-title":"J.\u00a0Phys. Chem. B"},{"key":"2026081713532854600_c57","doi-asserted-by":"publisher","first-page":"2157","DOI":"10.1002\/jcc.21224","volume":"30","year":"2009","journal-title":"J.\u00a0Comput. Chem."},{"key":"2026081713532854600_c58","doi-asserted-by":"publisher","first-page":"49794","DOI":"10.1021\/acsomega.5c05503","volume":"10","year":"2025","journal-title":"ACS Omega"},{"key":"2026081713532854600_c59","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1021\/ci00005a010","volume":"32","year":"1992","journal-title":"J.\u00a0Chem. Inf. Comput. Sci."},{"key":"2026081713532854600_c60","unstructured":"G.\n            Landrum\n          , RDKit: Open-source cheminformatics, 2010, https:\/\/www.rdkit.org\/(accessed 27 November 2023)."},{"key":"2026081713532854600_c61","first-page":"3146","volume-title":"Advances In Neural Information Processing Systems","year":"2017"},{"key":"2026081713532854600_c62"},{"key":"2026081713532854600_c63","article-title":"Fast graph representation learning with PyTorch geometric","volume-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds","year":"2019"},{"key":"2026081713532854600_c64","first-page":"2623","volume-title":"The 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","year":"2019"},{"key":"2026081713532854600_c65","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in Neural Information Processing Systems 30","year":"2017"},{"key":"2026081713532854600_c66","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","year":"2020","journal-title":"Nat. Mach Intell."},{"key":"2026081713532854600_c67","doi-asserted-by":"publisher","first-page":"1902765","DOI":"10.1002\/adma.201902765","volume":"31","year":"2019","journal-title":"Adv. Mater."},{"key":"2026081713532854600_c68","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1021\/acs.jpca.9b08723","volume":"124","year":"2020","journal-title":"J.\u00a0Phys. Chem. A"}],"container-title":["The Journal of Chemical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0342619\/21108263\/074101_1_5.0342619.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0342619\/21108263\/074101_1_5.0342619.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T17:53:38Z","timestamp":1786989218000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jcp\/article\/165\/7\/074101\/3401250\/Machine-learning-prediction-of-organic-compound"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":68,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,8,21]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0342619","relation":{},"ISSN":["0021-9606","1089-7690"],"issn-type":[{"value":"0021-9606","type":"print"},{"value":"1089-7690","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8,21]]},"published":{"date-parts":[[2026,8,17]]},"article-number":"074101"}}