{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T21:16:07Z","timestamp":1771535767154,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T00:00:00Z","timestamp":1771459200000},"content-version":"vor","delay-in-days":22,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"crossref","award":["RS-2023-00225125"],"award-info":[{"award-number":["RS-2023-00225125"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"crossref","award":["RS-2025\u201300519428"],"award-info":[{"award-number":["RS-2025\u201300519428"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","award":["RS-2023-KH136924"],"award-info":[{"award-number":["RS-2023-KH136924"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Environment","award":["National Institute of Chemical Safety"],"award-info":[{"award-number":["National Institute of Chemical Safety"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"abstract":"<jats:sec>\n                    <jats:title>Abstract<\/jats:title>\n                    <jats:p>\n                      The rapid proliferation of chemical substances presents significant challenges in assessing their safety\u2013critical physicochemical properties. This study presents an integrated approach using Graph Neural Networks (GNNs) to predict three crucial properties for chemical safety assessment: Heat of Combustion (HoC), Vapor Pressure (VP), and Flashpoint. Leveraging comprehensive datasets of 4780, 3573, and 14,696 compounds respectively, we developed a unified prediction model that outperforms existing approaches. Our model achieves mean absolute errors of 126\u00a0J\/mol (R\n                      <jats:sup>2<\/jats:sup>\n                      \u2009=\u20090.993) for HoC, 0.617 log units (R\n                      <jats:sup>2<\/jats:sup>\n                      \u2009=\u20090.898) for VP, and 14.42\u00a0\u00b0C (R\n                      <jats:sup>2<\/jats:sup>\n                      \u2009=\u20090.839) for Flashpoint, representing notable improvements over conventional methods. Through detailed analysis, we identified and addressed a specific challenge in predicting HoC for cyclic compounds by implementing a hybrid approach combining DFT calculations and Random Forest modeling. This specialized treatment expanded our cyclic compound dataset from 12 to 55 compounds and achieved an R\n                      <jats:sup>2<\/jats:sup>\n                      of 0.918 for these traditionally challenging structures. The model was integrated into a real-time prediction system using Flask, allowing users to input chemical structures through SMILES notation or direct drawing. The system includes features for comparing predictions with experimental data and benchmarking against common industrial chemicals (acetone, n-hexane, and n-decane), enhancing its practical utility in emergency response scenarios. Our approach provides a robust, unified solution for predicting multiple safety\u2013critical properties simultaneously, addressing a crucial need in chemical safety assessment and emergency response planning.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Scientific contribution<\/jats:title>\n                    <jats:p>Overall, this study provides an integrated framework that deploys three GNN-based prediction models within a common architecture and a real-time prediction system. For cyclic compounds, which exhibit systematic prediction challenges under the GNN framework, we incorporate a targeted alternative modeling strategy to improve predictive reliability, thereby enhancing the practical applicability of machine-learning approaches to chemical safety assessment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13321-026-01151-3","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T05:03:58Z","timestamp":1769576638000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Advancing chemical safety prediction: an integrated GNN framework with DFT-augmented cyclic compound solution"],"prefix":"10.1186","volume":"18","author":[{"given":"Seul","family":"Lee","sequence":"first","affiliation":[]},{"given":"Jooyeon","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Unghwi","family":"Yoon","sequence":"additional","affiliation":[]},{"given":"Jahyun","family":"Koo","sequence":"additional","affiliation":[]},{"given":"Young Wook","family":"Yoon","sequence":"additional","affiliation":[]},{"given":"Yoonjae","family":"Cho","sequence":"additional","affiliation":[]},{"given":"Seung-Ryul","family":"Hwang","sequence":"additional","affiliation":[]},{"given":"Keunhong","family":"Jeong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"1151_CR1","unstructured":"United States Environmental Protection Agency (2024) Studies & Cost Estimates. https:\/\/www.epa.gov\/system\/files\/documents\/2024-05\/studies-cost-estimates-2024.pdf"},{"key":"1151_CR2","doi-asserted-by":"publisher","unstructured":"Devito M, Farrell P, Hagiwara S, Harrill A, Krewski D, Paoli G, Thomas R (2024) Value of information case study: human health and economic trade-offs associated with the timeliness, uncertainty, and costs of the draft EPA transcriptomic assessment product (ETAP). U.S. Environmental Protection Agency: Washington, DC. https:\/\/doi.org\/10.23645\/epacomptox.26093572","DOI":"10.23645\/epacomptox.26093572"},{"issue":"11","key":"1151_CR3","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1002\/ajim.20613","volume":"51","author":"AM Nicol","year":"2008","unstructured":"Nicol AM, Hurrell AC, Wahyuni D, McDowall W, Chu W (2008) Accuracy, comprehensibility, and use of material safety data sheets: a review. Am J Ind Med 51(11):861\u2013876. https:\/\/doi.org\/10.1002\/ajim.20613","journal-title":"Am J Ind Med"},{"key":"1151_CR4","unstructured":"Commission Regulation (EU) 2020\/878 of 18 June 2020 amending Annex II to Regulation (EC) No 1907\/2006 of the European Parliament and of the Council concerning the Registration, Evaluation, Authorisation and Restriction of Chemicals (REACH)"},{"key":"1151_CR5","unstructured":"U.S. Chemical Safety Board. (2016) West Fertilizer Explosion and Fire. https:\/\/www.csb.gov\/west-fertilizer-explosion-and-fire-\/. Accessed 3 Feb 2025"},{"issue":"38","key":"1151_CR6","doi-asserted-by":"publisher","first-page":"8305","DOI":"10.1021\/acs.jpca.9b04771","volume":"123","author":"KK Yalamanchi","year":"2019","unstructured":"Yalamanchi KK, van Oudenhoven VCO, Tutino F, Monge-Palacios M, Alshehri A, Gao X, Sarathy SM (2019) Predicting standard enthalpy of formation of hydrocarbons using machine learning. J Phys Chem A 123(38):8305\u20138313. https:\/\/doi.org\/10.1021\/acs.jpca.9b04771","journal-title":"J Phys Chem A"},{"issue":"28","key":"1151_CR7","doi-asserted-by":"publisher","first-page":"13281","DOI":"10.1021\/acs.energyfuels.4c04517","volume":"39","author":"CE \u00dcst\u00fcn","year":"2025","unstructured":"\u00dcst\u00fcn CE, Karao\u011flan ME, Y\u0131ld\u0131z AA, Y\u0131lmaz A (2025) Machine learning applications for predicting fuel ignition and flame properties: current status and future perspectives. Energy Fuels 39(28):13281\u201313314. https:\/\/doi.org\/10.1021\/acs.energyfuels.4c04517","journal-title":"Energy Fuels"},{"key":"1151_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.wasman.2025.115111","volume":"207","author":"K Lin","year":"2025","unstructured":"Lin K, Liao B, Chen X, Chen C, Lei W, Zhou X (2025) Interpretable machine learning for predicting key hazardous properties of chemicals. Waste Manag 207:115111. https:\/\/doi.org\/10.1016\/j.wasman.2025.115111","journal-title":"Waste Manag"},{"issue":"5","key":"1151_CR9","doi-asserted-by":"publisher","DOI":"10.1002\/cem.3586","volume":"38","author":"K Jeong","year":"2024","unstructured":"Jeong K, Nam JH, Lee S, Koo J, Lee J, Yu D, Jo S, Kim J (2024) Prediction of flash point of materials using Bayesian kernel machine regression based on Gaussian processes with LASSO-like spike-and-slab hyperprior. J Chemom 38(5):e3586. https:\/\/doi.org\/10.1002\/cem.3586","journal-title":"J Chemom"},{"issue":"11","key":"1151_CR10","doi-asserted-by":"publisher","DOI":"10.3390\/pr10112384","volume":"10","author":"A Abdul Jameel","year":"2022","unstructured":"Abdul Jameel A, Al-Muslem A, Ahmad N, Alquaity A, Zahid U, Ahmed U (2022) Predicting enthalpy of combustion using machine learning. Processes 10(11):2384. https:\/\/doi.org\/10.3390\/pr10112384","journal-title":"Processes"},{"issue":"2","key":"1151_CR11","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1016\/j.jlp.2009.01.002","volume":"22","author":"HY Cao","year":"2009","unstructured":"Cao HY, Jiang JC, Pan Y, Wang R, Cui Y (2009) Prediction of the net heat of combustion of organic compounds based on atom-type electrotopological state indices. J Loss Prev Process Ind 22(2):222\u2013227","journal-title":"J Loss Prev Process Ind"},{"key":"1151_CR12","doi-asserted-by":"publisher","first-page":"1900101","DOI":"10.1002\/minf.201900101","volume":"39","author":"X Sun","year":"2020","unstructured":"Sun X, Krakauer NJ, Politowicz A, Chen W-T, Li Q, Li Z, Shao X, Sunaryo A, Shen M, Wang J, Morgan D (2020) Assessing graph-based deep learning models for predicting flash point. Mol Inf 39:1900101","journal-title":"Mol Inf"},{"key":"1151_CR13","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1002\/aic.17721","volume":"68","author":"Y Xu","year":"2022","unstructured":"Xu Y, Huang X, Li C, Wei Z, Wang M (2022) Predicting structure-dependent properties directly from the three dimensional molecular images. AIChE J 68:8","journal-title":"AIChE J"},{"issue":"4","key":"1151_CR14","first-page":"297","volume":"39","author":"HR Mirshahvalad","year":"2020","unstructured":"Mirshahvalad HR, Ghasemiasl R, Raufi N, Dirin M (2020) A neural networks model for accurate prediction of the flash point of chemical compounds. Iran J Chem Chem Eng 39(4):297\u2013304","journal-title":"Iran J Chem Chem Eng"},{"key":"1151_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaecs.2025.100341","volume":"23","author":"Z Chen","year":"2025","unstructured":"Chen Z, Vom Lehn F, Pitsch H, Cai L (2025) Design of novel high-performance fuels with artificial intelligence: Case study for spark-ignition engine applications. Appl Energ Combust Sci 23:100341. https:\/\/doi.org\/10.1016\/j.jaecs.2025.100341","journal-title":"Appl Energ Combust Sci"},{"key":"1151_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtice.2024.105926","author":"YH Lin","year":"2024","unstructured":"Lin YH, Liang HH, Lin ST, Li YP (2024) Advancing vapor pressure prediction: a machine learning approach with directed message passing neural networks. J Taiwan Inst Chem Eng. https:\/\/doi.org\/10.1016\/j.jtice.2024.105926","journal-title":"J Taiwan Inst Chem Eng"},{"key":"1151_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ces.2023.119623","volume":"286","author":"VV Santana","year":"2024","unstructured":"Santana VV, Rebello CM, Queiroz LP, Ribeiro AM, Shardt N, Nogueira IBR (2024) PUFFIN: a path-unifying feed-forward interfaced network for vapor pressure prediction. Chem Eng Sci 286:119623","journal-title":"Chem Eng Sci"},{"key":"1151_CR18","first-page":"1263","volume":"70","author":"J Gilmer","year":"2017","unstructured":"Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE (2017) Neural message passing for Quantum chemistry. Int Conf Mach Learn 70:1263\u20131272","journal-title":"Int Conf Mach Learn"},{"issue":"2","key":"1151_CR19","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","volume":"9","author":"Z Wu","year":"2017","unstructured":"Wu Z, Ramsundar B, Feinberg EN, Gomes J, Geniesse C, Pappu AS, Leswing K, Pande V (2017) MoleculeNet: a benchmark for molecular machine learning. Chem Sci 9(2):513\u2013530","journal-title":"Chem Sci"},{"issue":"6","key":"1151_CR20","doi-asserted-by":"publisher","first-page":"3098","DOI":"10.1103\/physreva.38.3098","volume":"38","author":"AD Becke","year":"1988","unstructured":"Becke AD (1988) Density-functional exchange-energy approximation with correct asymptotic behavior. Phys Rev A 38(6):3098\u20133100. https:\/\/doi.org\/10.1103\/physreva.38.3098","journal-title":"Phys Rev A"},{"issue":"2","key":"1151_CR21","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1103\/physrevb.37.785","volume":"37","author":"C Lee","year":"2018","unstructured":"Lee C, Yang W, Parr RG (2018) Development of the Colle-Salvetti correlation-energy formula into a functional of the electron density. Phys Rev B Condens Matter 37(2):785\u2013789. https:\/\/doi.org\/10.1103\/physrevb.37.785","journal-title":"Phys Rev B Condens Matter"},{"issue":"1\u20133","key":"1151_CR22","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/s00214-007-0310-x.","volume":"120","author":"Y Zhao","year":"2008","unstructured":"Zhao Y, Truhlar DG (2008) 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. Theor Chem Acc 120(1\u20133):215\u2013241. https:\/\/doi.org\/10.1007\/s00214-007-0310-x.","journal-title":"Theor Chem Acc"},{"issue":"18","key":"1151_CR23","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/PhysRevLett.77.3865","volume":"77","author":"JP Perdew","year":"1996","unstructured":"Perdew JP, Burke K, Ernzerhof M (1996) Generalized gradient approximation made simple. Phys Rev Lett 77(18):3865\u20133868. https:\/\/doi.org\/10.1103\/PhysRevLett.77.3865","journal-title":"Phys Rev Lett"},{"issue":"7","key":"1151_CR24","doi-asserted-by":"publisher","first-page":"3265","DOI":"10.1063\/1.447079","volume":"80","author":"MJ Frisch","year":"1984","unstructured":"Frisch MJ, Pople JA, Binkley JS (1984) Self-consistent molecular orbital methods 25. supplementary functions for gaussian basis sets. J Chem Phys 80(7):3265\u20133269. https:\/\/doi.org\/10.1063\/1.447079","journal-title":"J Chem Phys"},{"issue":"9","key":"1151_CR25","doi-asserted-by":"publisher","first-page":"6796","DOI":"10.1063\/1.462569","volume":"96","author":"RA Kendall","year":"1992","unstructured":"Kendall RA, Dunning TH, Harrison RJ (1992) Electron affinities of the first-row atoms revisited. systematic basis sets and wave functions. J Chem Phys 96(9):6796\u20136806. https:\/\/doi.org\/10.1063\/1.462569","journal-title":"J Chem Phys"},{"issue":"2","key":"1151_CR26","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1063\/1.464303","volume":"98","author":"DE Woon","year":"1993","unstructured":"Woon DE, Dunning TH (1993) Gaussian basis sets for use in correlated molecular calculations. III. The atoms aluminum through argon. J Chem Phys 98(2):1358\u20131371. https:\/\/doi.org\/10.1063\/1.464303","journal-title":"J Chem Phys"},{"issue":"10","key":"1151_CR27","doi-asserted-by":"publisher","first-page":"7410","DOI":"10.1063\/1.466884","volume":"100","author":"KA Peterson","year":"1994","unstructured":"Peterson KA, Woon DE, Dunning TH (1994) Benchmark calculations with correlated molecular wave functions. IV. The classical barrier height of the H+H2\u2192H2+H reaction. J Chem Phys 100(10):7410\u20137415. https:\/\/doi.org\/10.1063\/1.466884","journal-title":"J Chem Phys"},{"key":"1151_CR28","doi-asserted-by":"crossref","unstructured":"Wilson AK, Van Mourik T, Dunning TH (1996) Gaussian basis sets for use in correlated molecular calculations. VI. Sextuple zeta correlation consistent basis sets for boron through neon. J Mol Struct THEOCHEM. Vol. 388. http:\/\/www.emsl.pnl.gov:2080\/forms\/basisform.html","DOI":"10.1016\/S0166-1280(96)80048-0"},{"key":"1151_CR29","volume-title":"Gaussian16","author":"MJ Frisch","year":"2016","unstructured":"Frisch MJ et al (2016) Gaussian16. Gaussian Inc, Wallingford CT"},{"key":"1151_CR30","volume-title":"Gaussian view 6","author":"R Dennington","year":"2016","unstructured":"Dennington R et al (2016) Gaussian view 6. Semichem Inc, Shawnee Mission"},{"issue":"5","key":"1151_CR31","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1002\/jcc.22885","volume":"33","author":"T Lu","year":"2012","unstructured":"Lu T, Chen F (2012) Multiwfn: a multifunctional wavefunction analyzer. J Comput Chem 33(5):580\u2013592. https:\/\/doi.org\/10.1002\/jcc.22885","journal-title":"J Comput Chem"},{"key":"1151_CR32","doi-asserted-by":"publisher","DOI":"10.1063\/5.0216272","author":"T Lu","year":"2024","unstructured":"Lu T (2024) A comprehensive electron wavefunction analysis toolbox for chemists, Multiwfn. J Chem Phys. https:\/\/doi.org\/10.1063\/5.0216272","journal-title":"J Chem Phys"},{"key":"1151_CR33","volume-title":"Quantitative treatments of solute\/solvent interactions","author":"JS Murray","year":"1994","unstructured":"Murray JS, Politzer P (1994) Quantitative treatments of solute\/solvent interactions. Elsevier, Amsterdam"},{"issue":"5","key":"1151_CR34","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1080\/002689797171030","volume":"91","author":"P Politzer","year":"1997","unstructured":"Politzer P, Murray JS, Edward Grice ME, Desalvo M, Miller E (1997) Calculation of heats of sublimation and solid phase heats of formation. Mol Phys 91(5):923\u2013928. https:\/\/doi.org\/10.1080\/002689797171030","journal-title":"Mol Phys"},{"key":"1151_CR35","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1002\/qua.20709","volume":"105","author":"P Politzer","year":"2005","unstructured":"Politzer P, Ma Y, Lane P, Concha MC (2005) <article-title update=\"added\">Computational prediction of standard gas, liquid, and solid\u2010phase heats of formation and heats of vaporization and sublimation. Int J Quantum Chem 105:341\u2013347. https:\/\/doi.org\/10.1002\/qua.20709","journal-title":"Int J Quantum Chem"},{"key":"1151_CR36","unstructured":"Mallard WG, Linstrom PJ. NIST chemistry webbook, NIST standard reference database No. 69. http:\/\/webbook.nist.gov"},{"issue":"3","key":"1151_CR37","doi-asserted-by":"publisher","first-page":"589","DOI":"10.2307\/2335441","volume":"68","author":"B Efron","year":"1981","unstructured":"Efron B (1981) Nonparametric estimates of standard error: the jackknife, the bootstrap and other methods. Biometrika 68(3):589\u2013599. https:\/\/doi.org\/10.2307\/2335441","journal-title":"Biometrika"},{"key":"1151_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.fuel.2021.122712","volume":"313","author":"J Liu","year":"2022","unstructured":"Liu J, Gong S, Li H, Liu G (2022) Molecular graph-based deep learning method for predicting multiple physical properties of alternative fuel components. Fuel 313:122712. https:\/\/doi.org\/10.1016\/j.fuel.2021.122712","journal-title":"Fuel"},{"key":"1151_CR39","doi-asserted-by":"publisher","first-page":"3900","DOI":"10.1021\/ef200795j","volume":"25","author":"DA Saldana","year":"2011","unstructured":"Saldana DA, Starck L, Mougin P, Rousseau B, Pidol L, Jeuland N, Creton B (2011) Flash point and cetane number predictions for fuel compounds using quantitative structure property relationship (QSPR) methods. Energ Fuel 25:3900\u20133908. https:\/\/doi.org\/10.1021\/ef200795j","journal-title":"Energ Fuel"},{"issue":"4","key":"1151_CR40","first-page":"97","volume":"34","author":"A Tarjomannejad","year":"2015","unstructured":"Tarjomannejad A (2015) Prediction of the liquid vapor pressure using the artificial neural network-group contribution method. Iran J Chem Chem Eng 34(4):97\u2013111","journal-title":"Iran J Chem Chem Eng"},{"issue":"9","key":"1151_CR41","doi-asserted-by":"publisher","first-page":"1156","DOI":"10.1021\/acsestair.4c00113","volume":"1","author":"N Hyttinen","year":"2024","unstructured":"Hyttinen N, Li L, Hallquist M, Wu C (2024) Machine learning model to predict saturation vapor pressures of atmospheric aerosol constituents. ACS ES&T Air 1(9):1156\u20131163","journal-title":"ACS ES&T Air"},{"issue":"2","key":"1151_CR42","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1021\/ci970289c","volume":"38","author":"C Liang","year":"1998","unstructured":"Liang C, Gallagher DA (1998) QSPR prediction of vapor pressure from solely theoretically-derived descriptors. J Chem Inf Comput Sci 38(2):321\u2013324","journal-title":"J Chem Inf Comput Sci"},{"key":"1151_CR43","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1038\/s43246-022-00315-6","volume":"3","author":"P Reiser","year":"2022","unstructured":"Reiser P, Neubert M, Eberhard A et al (2022) Graph neural networks for materials science and chemistry. Commun Mater 3:93","journal-title":"Commun Mater"},{"key":"1151_CR44","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13321-020-00479-8","volume":"13","author":"D Jiang","year":"2021","unstructured":"Jiang D, Wu Z, Hsieh CY et al (2021) Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models. J Cheminform 13:12","journal-title":"J Cheminform"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-026-01151-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01151-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01151-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T20:48:01Z","timestamp":1771534081000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13321-026-01151-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1151"],"URL":"https:\/\/doi.org\/10.1186\/s13321-026-01151-3","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,28]]},"assertion":[{"value":"18 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"28"}}