{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T12:01:55Z","timestamp":1775736115297,"version":"3.50.1"},"reference-count":85,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["191948804"],"award-info":[{"award-number":["191948804"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["466417970"],"award-info":[{"award-number":["466417970"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007210","name":"RWTH Aachen University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007210","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurate prediction of toluene\/water partition coefficients of neutral species is crucial in drug discovery and separation processes; however, data-driven modeling of these coefficients remains challenging due to limited available experimental data. To address the limitation of available data, we apply multi-fidelity learning approaches leveraging a quantum chemical dataset (low fidelity) of approximately 9000 entries generated by COSMO-RS and an experimental dataset (high fidelity) of about 250 entries collected from the literature. We explore the\n                    <jats:italic>transfer learning<\/jats:italic>\n                    ,\n                    <jats:italic>feature-augmented learning<\/jats:italic>\n                    , and\n                    <jats:italic>multi-target learning<\/jats:italic>\n                    approaches in combination with graph neural networks, validating them on two external datasets: one with molecules similar to training data (EXT-Zamora) and one with more challenging molecules (EXT-SAMPL9). Our results show that\n                    <jats:italic>multi-target learning<\/jats:italic>\n                    significantly improves predictive accuracy, achieving a root-mean-square error of 0.44\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$$\\log {P}$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:mrow>\n                            <mml:mo>log<\/mml:mo>\n                            <mml:mi>P<\/mml:mi>\n                          <\/mml:mrow>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    units for the EXT-Zamora, compared to a root-mean-square error of 0.63\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$$\\log {P}$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:mrow>\n                            <mml:mo>log<\/mml:mo>\n                            <mml:mi>P<\/mml:mi>\n                          <\/mml:mrow>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    units for single-task models. For the EXT-SAMPL9 dataset,\n                    <jats:italic>multi-target learning<\/jats:italic>\n                    achieves a root-mean-square error of 1.02\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$$\\log {P}$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:mrow>\n                            <mml:mo>log<\/mml:mo>\n                            <mml:mi>P<\/mml:mi>\n                          <\/mml:mrow>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    units, indicating reasonable performance even for more complex molecular structures. These findings highlight the potential of multi-fidelity learning approaches that leverage quantum chemical data to improve toluene\/water partition coefficient predictions and address challenges posed by limited experimental data. We expect the applicability of the methods used beyond just toluene\/water partition coefficients.\n                  <\/jats:p>","DOI":"10.1186\/s13321-025-01057-6","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T08:47:59Z","timestamp":1754642879000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-fidelity graph neural networks for predicting toluene\/water partition coefficients"],"prefix":"10.1186","volume":"17","author":[{"given":"Thomas","family":"Nevolianis","sequence":"first","affiliation":[]},{"given":"Jan G.","family":"Rittig","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Mitsos","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Leonhard","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,8]]},"reference":[{"issue":"1","key":"1057_CR1","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1023\/a:1008741731244","volume":"19","author":"B Testa","year":"2000","unstructured":"Testa B, Crivori P, Reist M, Carrupt P-A (2000) The influence of lipophilicity on the pharmacokinetic behavior of drugs: concepts and examples. Perspect Drug Discov Des 19(1):179\u2013211. https:\/\/doi.org\/10.1023\/a:1008741731244","journal-title":"Perspect Drug Discov Des"},{"issue":"2","key":"1057_CR2","doi-asserted-by":"publisher","first-page":"127","DOI":"10.2174\/1389557053402765","volume":"5","author":"G Klopman","year":"2005","unstructured":"Klopman G, Zhu H (2005) Recent methodologies for the estimation of n-octanol\/water partition coefficients and their use in the prediction of membrane transport properties of drugs. Mini-Rev Med Chem 5(2):127\u2013133. https:\/\/doi.org\/10.2174\/1389557053402765","journal-title":"Mini-Rev Med Chem"},{"issue":"3","key":"1057_CR3","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1002\/jps.21494","volume":"98","author":"R Mannhold","year":"2009","unstructured":"Mannhold R, Poda GI, Ostermann C, Tetko IV (2009) Calculation of molecular lipophilicity: state-of-the-art and comparison of logp methods on more than 96,000 compounds. J Pharm Sci 98(3):861\u2013893. https:\/\/doi.org\/10.1002\/jps.21494","journal-title":"J Pharm Sci"},{"key":"1057_CR4","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.ejps.2015.05.008","volume":"76","author":"A Andr\u00e9s","year":"2015","unstructured":"Andr\u00e9s A, Ros\u00e9s M, R\u00e0fols C, Bosch E, Espinosa S, Segarra V, Huerta JM (2015) Setup and validation of shake-flask procedures for the determination of partition coefficients (logd) from low drug amounts. Eur J Pharm Sci 76:181\u2013191. https:\/\/doi.org\/10.1016\/j.ejps.2015.05.008","journal-title":"Eur J Pharm Sci"},{"key":"1057_CR5","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1016\/S0098-1354(99)00300-2","volume":"23","author":"M Hostrup","year":"1999","unstructured":"Hostrup M, Harper PM, Gani R (1999) Design of environmentally benign processes: integration of solvent design and separation process synthesis. Comput Chem Eng 23:1395\u20131414. https:\/\/doi.org\/10.1016\/S0098-1354(99)00300-2","journal-title":"Comput Chem Eng"},{"key":"1057_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.fluid.2022.113540","volume":"561","author":"FC Paes","year":"2022","unstructured":"Paes FC, Privat R, Jaubert J-N, Sirjean B (2022) A comparative study of cosmo-based and equation-of-state approaches for the prediction of solvation energies based on the compsol databank. Fluid Phase Equilib 561:113540. https:\/\/doi.org\/10.1016\/j.fluid.2022.113540","journal-title":"Fluid Phase Equilib"},{"issue":"10","key":"1057_CR7","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1517\/17460441.2012.714363","volume":"7","author":"JA Arnott","year":"2012","unstructured":"Arnott JA, Planey SL (2012) The influence of lipophilicity in drug discovery and design. Expert Opin Drug Discov 7(10):863\u2013875. https:\/\/doi.org\/10.1517\/17460441.2012.714363","journal-title":"Expert Opin Drug Discov"},{"issue":"15","key":"1057_CR8","doi-asserted-by":"publisher","first-page":"6401","DOI":"10.1021\/acs.jmedchem.8b00077","volume":"61","author":"TW Johnson","year":"2018","unstructured":"Johnson TW, Gallego RA, Edwards MP (2018) Lipophilic efficiency as an important metric in drug design. J Med Chem 61(15):6401\u20136420. https:\/\/doi.org\/10.1021\/acs.jmedchem.8b00077","journal-title":"J Med Chem"},{"key":"1057_CR9","unstructured":"Dunn WJ, Block JH, Pearlman RS (1986) Partition coefficient: determination and estimation. Pergamon Press, New York . Published in cooperation with the American Pharmaceutical Association, Academy of Pharmaceutical Sciences"},{"key":"1057_CR10","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1385\/1-59259-955-9:269","volume-title":"Purification by solvent extraction using partition coefficient","author":"H Otsuka","year":"2005","unstructured":"Otsuka H (2005) Purification by solvent extraction using partition coefficient. Humana Press, Totowa, pp 269\u2013273. https:\/\/doi.org\/10.1385\/1-59259-955-9:269"},{"issue":"3","key":"1057_CR11","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1002\/cite.202200144","volume":"95","author":"L Polte","year":"2022","unstructured":"Polte L, Ra\u00dfpe-Lange L, Latz F, Jupke A, Leonhard K (2022) Cosmo-camped-solvent design for an extraction distillation considering molecular, process, equipment, and economic optimization. Chem Ing Tec 95(3):416\u2013426. https:\/\/doi.org\/10.1002\/cite.202200144","journal-title":"Chem Ing Tec"},{"issue":"9","key":"1057_CR12","doi-asserted-by":"publisher","first-page":"3269","DOI":"10.1021\/jm048980b","volume":"48","author":"G Caron","year":"2005","unstructured":"Caron G, Ermondi G (2005) lculating virtual log P in the alkane\/water system (log P Nalk) and its derived parameters \u0394log P Noct-alk and log D pHalk. J Med Chem 48(9):3269\u20133279. https:\/\/doi.org\/10.1021\/jm048980b","journal-title":"J Med Chem"},{"issue":"17","key":"1057_CR13","doi-asserted-by":"publisher","first-page":"2669","DOI":"10.1002\/cmdc.202100306","volume":"16","author":"L David","year":"2021","unstructured":"David L, Wenlock M, Barton P, Ritz\u00e9n A (2021) Prediction of chameleonic efficiency. ChemMedChem 16(17):2669\u20132685. https:\/\/doi.org\/10.1002\/cmdc.202100306","journal-title":"ChemMedChem"},{"issue":"7","key":"1057_CR14","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1021\/j100007a062","volume":"99","author":"A Klamt","year":"1995","unstructured":"Klamt A (1995) Conductor-like screening model for real solvents: a new approach to the quantitative calculation of solvation phenomena. J Phys Chem 99(7):2224\u20132235. https:\/\/doi.org\/10.1021\/j100007a062","journal-title":"J Phys Chem"},{"issue":"26","key":"1057_CR15","doi-asserted-by":"publisher","first-page":"5074","DOI":"10.1021\/jp980017s","volume":"102","author":"A Klamt","year":"1998","unstructured":"Klamt A, Jonas V, B\u00fcrger T, Lohrenz JC (1998) Refinement and parametrization of COSMO-RS. J Phys Chem A 102(26):5074\u20135085. https:\/\/doi.org\/10.1021\/jp980017s","journal-title":"J Phys Chem A"},{"issue":"1","key":"1057_CR16","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1021\/ci990427t","volume":"40","author":"JA Platts","year":"1999","unstructured":"Platts JA, Abraham MH, Butina D, Hersey A (1999) Estimation of molecular linear free energy relationship descriptors by a group contribution approach. 2. Prediction of partition coefficients. J Chem Inf Comput Sci 40(1):71\u201380. https:\/\/doi.org\/10.1021\/ci990427t","journal-title":"J Chem Inf Comput Sci"},{"key":"1057_CR17","doi-asserted-by":"publisher","first-page":"7099","DOI":"10.1021\/jp000091m","volume":"104","author":"S-T Lin","year":"2000","unstructured":"Lin S-T, Sandler SI (2000) Multipole corrections to account for structure and proximity effects in group contribution methods: octanol-water partition coefficients. J Phys Chem A 104:7099\u20137105. https:\/\/doi.org\/10.1021\/jp000091m","journal-title":"J Phys Chem A"},{"key":"1057_CR18","doi-asserted-by":"crossref","unstructured":"Buggert M, Cadena C, Mokrushina L, Smirnova I, Maginn EJ, Arlt W (2009) COSMO-RS calculations of partition coefficients: different tools for conformation search. Chem Eng Technol 32:977\u2013986. https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1002\/ceat.200800654","DOI":"10.1002\/ceat.200800654"},{"key":"1057_CR19","doi-asserted-by":"publisher","first-page":"11478","DOI":"10.1021\/ie501669z","volume":"53","author":"C Loschen","year":"2014","unstructured":"Loschen C, Klamt A (2014) Prediction of solubilities and partition coefficients in polymers using COSMO-RS. Ind Eng Chem Res 53:11478\u201311487. https:\/\/doi.org\/10.1021\/ie501669z","journal-title":"Ind Eng Chem Res"},{"key":"1057_CR20","doi-asserted-by":"crossref","unstructured":"Ince A, Carstensen H-H, Reyniers M-F, Marin GB (2015) First-principles based group additivity values for thermochemical properties of substituted aromatic compounds. AIChE J 61:3858\u20133870. https:\/\/aiche.onlinelibrary.wiley.com\/doi\/abs\/10.1002\/aic.15008","DOI":"10.1002\/aic.15008"},{"issue":"8","key":"1057_CR21","doi-asserted-by":"publisher","first-page":"4015","DOI":"10.1021\/acs.jctc.6b00449","volume":"12","author":"CC Bannan","year":"2016","unstructured":"Bannan CC, Calabr\u00f3 G, Kyu DY, Mobley DL (2016) Calculating partition coefficients of small molecules in octanol\/water and cyclohexane\/water. J Chem Theory Comput 12(8):4015\u20134024. https:\/\/doi.org\/10.1021\/acs.jctc.6b00449","journal-title":"J Chem Theory Comput"},{"key":"1057_CR22","doi-asserted-by":"crossref","unstructured":"M\u00fcller S, Nevolianis T, Garcia-Rat\u00e9s M, Riplinger C, Leonhard K, Smirnova I (2024) Predicting solvation free energies for neutral molecules in any solvent with openCOSMO-RS . https:\/\/arxiv.org\/abs\/2407.03434","DOI":"10.1016\/j.fluid.2024.114250"},{"key":"1057_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.fluid.2024.114250","volume":"589","author":"S M\u00fcller","year":"2025","unstructured":"M\u00fcller S, Nevolianis T, Garcia-Rat\u00e9s M, Riplinger C, Leonhard K, Smirnova I (2025) Predicting solvation free energies for neutral molecules in any solvent with openCOSMO-RS. Fluid Phase Equilib 589:114250. https:\/\/doi.org\/10.1016\/j.fluid.2024.114250","journal-title":"Fluid Phase Equilib"},{"key":"1057_CR24","doi-asserted-by":"publisher","unstructured":"Amezcua M, Mobley DL, Bergazin TD (2023) samplchallenges\/SAMPL9: 0.8. Zenodo . https:\/\/doi.org\/10.5281\/ZENODO.7644720","DOI":"10.5281\/ZENODO.7644720"},{"key":"1057_CR25","doi-asserted-by":"publisher","first-page":"31683","DOI":"10.1039\/D3CP04077A","volume":"25","author":"T Nevolianis","year":"2023","unstructured":"Nevolianis T, Ahmed RA, Hellweg A, Diedenhofen M, Leonhard K (2023) Blind prediction of toluene\/water partition coefficients using COSMO-RS: results from the sampl9 challenge. Phys Chem Chem Phys 25:31683\u201331691. https:\/\/doi.org\/10.1039\/D3CP04077A","journal-title":"Phys Chem Chem Phys"},{"issue":"36","key":"1057_CR26","doi-asserted-by":"publisher","first-page":"11809","DOI":"10.1021\/ie301611w","volume":"51","author":"Z Xue","year":"2012","unstructured":"Xue Z, Mu T, Gmehling J (2012) Comparison of the a priori COSMO-RS models and group contribution methods: Original unifac, modified unifac(do), and modified unifac(do) consortium. Ind Eng Chem Res 51(36):11809\u201311817. https:\/\/doi.org\/10.1021\/ie301611w","journal-title":"Ind Eng Chem Res"},{"issue":"35","key":"1057_CR27","doi-asserted-by":"publisher","first-page":"9868","DOI":"10.1021\/acs.iecr.7b01360","volume":"56","author":"R Fingerhut","year":"2017","unstructured":"Fingerhut R, Chen W-L, Schedemann A, Cordes W, Rarey J, Hsieh C-M, Vrabec J, Lin S-T (2017) Comprehensive assessment of cosmo-sac models for predictions of fluid-phase equilibria. Ind Eng Chem Res 56(35):9868\u20139884. https:\/\/doi.org\/10.1021\/acs.iecr.7b01360","journal-title":"Ind Eng Chem Res"},{"key":"1057_CR28","doi-asserted-by":"crossref","unstructured":"Klamt A (2018) The cosmo and COSMO-RS solvation models. Wiley Interdiscip Rev Comput Mol Sci 8(1):1338. https:\/\/wires.onlinelibrary.wiley.com\/doi\/abs\/10.1002\/wcms.1338","DOI":"10.1002\/wcms.1338"},{"key":"1057_CR29","unstructured":"Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE (2017) Neural message passing for quantum chemistry. In: Precup D, Teh YW (eds.) Proceedings of the 34th international conference on machine learning. proceedings of machine learning research, vol. 70, pp 1263\u20131272. PMLR. https:\/\/proceedings.mlr.press\/v70\/gilmer17a.html"},{"issue":"9","key":"1057_CR30","doi-asserted-by":"publisher","first-page":"11395","DOI":"10.1021\/acs.energyfuels.0c01533","volume":"34","author":"AM Schweidtmann","year":"2020","unstructured":"Schweidtmann AM, Rittig JG, K\u00f6nig A, Grohe M, Mitsos A, Dahmen M (2020) Graph neural networks for prediction of fuel ignition quality. Energy Fuels 34(9):11395\u201311407. https:\/\/doi.org\/10.1021\/acs.energyfuels.0c01533","journal-title":"Energy Fuels"},{"key":"1057_CR31","unstructured":"Rong Y, Bian Y, Xu T, Xie W, Wei Y, Huang W, Huang J (2020) Self-supervised graph transformer on large-scale molecular data. In: Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H (eds.) Advances in Neural Information Processing Systems, vol. 33. Curran Associates, Inc., pp 12559\u201312571. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/94aef38441efa3380a3bed3faf1f9d5d-Paper.pdf"},{"key":"1057_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cej.2021.129307","volume":"418","author":"FH Vermeire","year":"2021","unstructured":"Vermeire FH (2021) Transfer learning for solvation free energies: from quantum chemistry to experiments. Chem Eng J 418:129307. https:\/\/doi.org\/10.1016\/j.cej.2021.129307","journal-title":"Chem Eng J"},{"issue":"6","key":"1057_CR33","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1039\/d2dd00058j","volume":"1","author":"B Winter","year":"2022","unstructured":"Winter B, Winter C, Schilling J, Bardow A (2022) A smile is all you need: predicting limiting activity coefficients from smiles with natural language processing. Digital Discov 1(6):859\u2013869. https:\/\/doi.org\/10.1039\/d2dd00058j","journal-title":"Digital Discov"},{"issue":"3","key":"1057_CR34","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1039\/d1dd00037c","volume":"1","author":"EI Sanchez Medina","year":"2022","unstructured":"Sanchez Medina EI, Linke S, Stoll M, Sundmacher K (2022) Graph neural networks for the prediction of infinite dilution activity coefficients. Digital Discov 1(3):216\u2013225. https:\/\/doi.org\/10.1039\/d1dd00037c","journal-title":"Digital Discov"},{"key":"1057_CR35","unstructured":"Felton KC, Ben-Safar H, Lapkin AA (2021) Deepgamma : A deep learning model for activity coeff\u00efcient prediction. In: 1st annual AAAI workshop on AI to accelerate science and engineering"},{"key":"1057_CR36","doi-asserted-by":"publisher","unstructured":"Rittig JG, Gao Q, Dahmen M, Mitsos A, Schweidtmann AM (2023) Graph neural networks for the prediction of molecular structure\u2013property relationships. In: Zhang D, Del R\u00edo Chanona EA (eds) Machine learning and hybrid modelling for reaction engineering. Royal Society of Chemistry, pp 159\u2013181. https:\/\/doi.org\/10.1039\/BK9781837670178-00159","DOI":"10.1039\/BK9781837670178-00159"},{"key":"1057_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ces.2023.119358","volume":"282","author":"G Sun","year":"2023","unstructured":"Sun G, Zhao Z, Sun S, Ma Y, Li H, Gao X (2023) Vapor-liquid phase equilibria behavior prediction of binary mixtures using machine learning. Chem Eng Sci 282:119358. https:\/\/doi.org\/10.1016\/j.ces.2023.119358","journal-title":"Chem Eng Sci"},{"key":"1057_CR38","doi-asserted-by":"publisher","DOI":"10.1039\/D3CP01428B","author":"WJ Zamora","year":"2023","unstructured":"Zamora WJ, Viayna A, Pinheiro S, Curutchet C, Bisbal L, Ruiz R, R\u00e0fols C, Luque FJ (2023) Prediction of toluene\/water partition coefficients in the sampl9 blind challenge: assessment of machine learning and ief-pcm\/mst continuum solvation models. Phys Chem Chem Phys. https:\/\/doi.org\/10.1039\/D3CP01428B","journal-title":"Phys Chem Chem Phys"},{"issue":"4","key":"1057_CR39","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.1039\/d1sc05677h","volume":"13","author":"KP Greenman","year":"2022","unstructured":"Greenman KP, Green WH, G\u00f3mez-Bombarelli R (2022) Multi-fidelity prediction of molecular optical peaks with deep learning. Chem Sci 13(4):1152\u20131162. https:\/\/doi.org\/10.1039\/d1sc05677h","journal-title":"Chem Sci"},{"key":"1057_CR40","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00947-9","author":"C Fare","year":"2022","unstructured":"Fare C, Fenner P, Benatan M, Varsi A, Pyzer-Knapp EO (2022) A multi-fidelity machine learning approach to high throughput materials screening. NPJ Comput Mater. https:\/\/doi.org\/10.1038\/s41524-022-00947-9","journal-title":"NPJ Comput Mater"},{"key":"1057_CR41","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45566-8","author":"D Buterez","year":"2024","unstructured":"Buterez D, Janet JP, Kiddle SJ, Oglic D, Li\u00f3 P (2024) Transfer learning with graph neural networks for improved molecular property prediction in the multi-fidelity setting. Nat Commun. https:\/\/doi.org\/10.1038\/s41467-024-45566-8","journal-title":"Nat Commun"},{"key":"1057_CR42","doi-asserted-by":"crossref","unstructured":"Qian E, Chaudhuri A, Kang D, Sella V (2024) Multifidelity linear regression for scientific machine learning from scarce data. arXiv preprint arXiv:2403.08627","DOI":"10.3934\/fods.2024049"},{"key":"1057_CR43","unstructured":"Cheng J-P, Yang J-D, Xue X-S, Ji P, Li X, Wang Z (2023) iBonD Website. http:\/\/ibond.nankai.edu.cn\/"},{"issue":"5","key":"1057_CR44","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1021\/ci2004658","volume":"52","author":"J-P Ebejer","year":"2012","unstructured":"Ebejer J-P, Morris GM, Deane CM (2012) Freely available conformer generation methods: how good are they? J Chem Inf Model 52(5):1146\u20131158. https:\/\/doi.org\/10.1021\/ci2004658","journal-title":"J Chem Inf Model"},{"key":"1057_CR45","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3732262","author":"G Landrum","year":"2020","unstructured":"Landrum G, Tosco P, Kelley B, Sriniker A, Dalke A, Vianello R, Cole B, Codrea V, Bain D, Halvorsen T, W\u00f3jcikowski M, Pahl A, Shadnia H, Jones M, Turk S, Vaucher A, Schwaller P, Johnson D, Fuller P, Saconne M (2020) rdkit\/rdkit: 2020\/03\/1 (Q1 2020) release. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.3732262","journal-title":"Zenodo"},{"issue":"3","key":"1057_CR46","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1021\/acs.jctc.8b01176","volume":"15","author":"C Bannwarth","year":"2019","unstructured":"Bannwarth C, Ehlert S, Grimme S (2019) Gfn2-xtb-an accurate and broadly parametrized self-consistent tight-binding quantum chemical method with multipole electrostatics and density-dependent dispersion contributions. J Chem Theory Comput 15(3):1652\u20131671. https:\/\/doi.org\/10.1021\/acs.jctc.8b01176. (PMID: 30741547)","journal-title":"J Chem Theory Comput"},{"key":"1057_CR47","unstructured":"Dassault Syst\u00e8mes: BIOVIA COSMOconf 2023 (2023). https:\/\/www.3ds.com"},{"key":"1057_CR48","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 38:3098\u20133100. https:\/\/doi.org\/10.1103\/PhysRevA.38.3098","journal-title":"Phys Rev A"},{"key":"1057_CR49","doi-asserted-by":"publisher","first-page":"8822","DOI":"10.1103\/PhysRevB.33.8822","volume":"33","author":"JP Perdew","year":"1986","unstructured":"Perdew JP (1986) Density-functional approximation for the correlation energy of the inhomogeneous electron gas. Phys Rev B 33:8822\u20138824. https:\/\/doi.org\/10.1103\/PhysRevB.33.8822","journal-title":"Phys Rev B"},{"issue":"13","key":"1057_CR50","doi-asserted-by":"publisher","DOI":"10.1063\/1.3484283","volume":"133","author":"D Rappoport","year":"2010","unstructured":"Rappoport D, Furche F (2010) Property-optimized gaussian basis sets for molecular response calculations. J Chem Phys 133(13):134105. https:\/\/doi.org\/10.1063\/1.3484283","journal-title":"J Chem Phys"},{"key":"1057_CR51","unstructured":"Dassault Syst\u00e8mes: BIOVIA COSMOtherm 2023 (2023). https:\/\/www.3ds.com"},{"key":"1057_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejps.2021.106066","volume":"168","author":"R Ruiz","year":"2022","unstructured":"Ruiz R, Zamora WJ, R\u00e0fols C, Bosch E (2022) Molecular characteristics of several drugs evaluated from solvent\/water partition measurements: solvation parameters and intramolecular hydrogen bond indicator. Eur J Pharm Sci 168:106066. https:\/\/doi.org\/10.1016\/j.ejps.2021.106066","journal-title":"Eur J Pharm Sci"},{"key":"1057_CR53","doi-asserted-by":"publisher","unstructured":"Letcher TM (2007) Development and applications in solubility. Royal Society of Chemistry. https:\/\/doi.org\/10.1039\/9781847557681","DOI":"10.1039\/9781847557681"},{"issue":"4","key":"1057_CR54","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/s10822-019-00271-3","volume":"34","author":"M I\u015f\u0131k","year":"2019","unstructured":"I\u015f\u0131k M, Levorse D, Mobley DL, Rhodes T, Chodera JD (2019) Octanol-water partition coefficient measurements for the sampl6 blind prediction challenge. J Comput Aided Mol Des 34(4):405\u2013420. https:\/\/doi.org\/10.1007\/s10822-019-00271-3","journal-title":"J Comput Aided Mol Des"},{"issue":"2","key":"1057_CR55","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1002\/aic.690480220","volume":"48","author":"F Eckert","year":"2002","unstructured":"Eckert F, Klamt A (2002) Fast solvent screening via quantum chemistry: COSMO-RS approach. AIChE J 48(2):369\u2013385. https:\/\/doi.org\/10.1002\/aic.690480220","journal-title":"AIChE J"},{"issue":"1","key":"1057_CR56","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/S0378-3812(00)00357-5.00530","volume":"172","author":"A Klamt","year":"2000","unstructured":"Klamt A, Eckert F (2000) COSMO-RS: a novel and efficient method for the a priori prediction of thermophysical data of liquids. Fluid Phase Equilibr 172(1):43\u201372. https:\/\/doi.org\/10.1016\/S0378-3812(00)00357-5.00530","journal-title":"Fluid Phase Equilibr"},{"issue":"10","key":"1057_CR57","doi-asserted-by":"publisher","first-page":"2332","DOI":"10.1002\/aic.690481023.00070","volume":"48","author":"A Klamt","year":"2002","unstructured":"Klamt A, Krooshof GJP, Taylor R (2002) COSMOSPACE: alternative to conventional activity-coefficient models. AIChE J 48(10):2332\u20132349. https:\/\/doi.org\/10.1002\/aic.690481023.00070","journal-title":"AIChE J"},{"issue":"4","key":"1057_CR58","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/s10822-019-00259-z","volume":"34","author":"C Loschen","year":"2020","unstructured":"Loschen C, Reinisch J, Klamt A (2020) COSMO-RS based predictions for the sampl6 logp challenge. J Comput Aided Mol Des 34(4):385\u2013392. https:\/\/doi.org\/10.1007\/s10822-019-00259-z","journal-title":"J Comput Aided Mol Des"},{"issue":"7","key":"1057_CR59","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1007\/s10822-021-00395-5","volume":"35","author":"J Warnau","year":"2021","unstructured":"Warnau J, Wichmann K, Reinisch J (2021) COSMO-RS predictions of logp in the sampl7 blind challenge. J Comput Aided Mol Des 35(7):813\u2013818. https:\/\/doi.org\/10.1007\/s10822-021-00395-5","journal-title":"J Comput Aided Mol Des"},{"key":"1057_CR60","doi-asserted-by":"publisher","unstructured":"Lipinski CA, Lombardo F, Dominy BW, Feeney PJ (2001) Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings1pii of original article: S0169-409x(96)00423-1. the article was originally published in advanced drug delivery reviews 23 (1997) 3-25.1. Advanced Drug Delivery Reviews 46(1), 3\u201326 https:\/\/doi.org\/10.1016\/S0169-409X(00)00129-0 . Special issue dedicated to Dr. Eric Tomlinson, Advanced Drug Delivery Reviews, A Selection of the Most Highly Cited Articles, 1991-1998","DOI":"10.1016\/S0169-409X(00)00129-0"},{"issue":"8","key":"1057_CR61","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1021\/acs.jcim.6b00601","volume":"57","author":"CW Coley","year":"2017","unstructured":"Coley CW, Barzilay R, Green WH, Jaakkola TS, Jensen KF (2017) Convolutional embedding of attributed molecular graphs for physical property prediction. J Chem Inf Model 57(8):1757\u20131772. https:\/\/doi.org\/10.1021\/acs.jcim.6b00601","journal-title":"J Chem Inf Model"},{"key":"1057_CR62","doi-asserted-by":"publisher","DOI":"10.1016\/j.colsurfa.2024.134133","volume":"694","author":"C Brozos","year":"2004","unstructured":"Brozos C, Rittig JG, Bhattacharya S, Akanny E, Kohlmann C, Mitsos A (2004) Graph neural networks for surfactant multi-property prediction. Colloids Surf A 694:134133. https:\/\/doi.org\/10.1016\/j.colsurfa.2024.134133","journal-title":"Colloids Surf A"},{"key":"1057_CR63","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2023.108153","volume":"171","author":"JG Rittig","year":"2023","unstructured":"Rittig JG, Ben Hicham K, Schweidtmann AM, Dahmen M, Mitsos A (2023) Graph neural networks for temperature-dependent activity coefficient prediction of solutes in ionic liquids. Comput Chem Eng 171:108153. https:\/\/doi.org\/10.1016\/j.compchemeng.2023.108153","journal-title":"Comput Chem Eng"},{"issue":"1","key":"1057_CR64","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1039\/d2dd00045h","volume":"2","author":"S Qin","year":"2023","unstructured":"Qin S, Jiang S, Li J, Balaprakash P, Lehn RCV, Zavala VM (2023) Capturing molecular interactions in graph neural networks: a case study in multi-component phase equilibrium. Digital Discov 2(1):138\u2013151. https:\/\/doi.org\/10.1039\/d2dd00045h","journal-title":"Digital Discov"},{"issue":"1","key":"1057_CR65","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, Torresi L, Zhou C, Shao C, Metni H, van Hoesel C, Schopmans H, Sommer T, Friederich P (2022) Graph neural networks for materials science and chemistry. Commun Mater 3(1):93. https:\/\/doi.org\/10.1038\/s43246-022-00315-6","journal-title":"Commun Mater"},{"key":"1057_CR66","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2023.108202","volume":"172","author":"AM Schweidtmann","year":"2023","unstructured":"Schweidtmann AM, Rittig JG, Weber JM, Grohe M, Dahmen M, Leonhard K, Mitsos A (2023) Physical pooling functions in graph neural networks for molecular property prediction. Comput Chem Eng 172:108202. https:\/\/doi.org\/10.1016\/j.compchemeng.2023.108202","journal-title":"Comput Chem Eng"},{"issue":"1","key":"1057_CR67","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","volume":"64","author":"E Heid","year":"2023","unstructured":"Heid E, Greenman KP, Chung Y, Li S-C, Graff DE, Vermeire FH, Wu H, Green WH, McGill CJ (2023) Chemprop: a machine learning package for chemical property prediction. J Chem Inf Model 64(1):9\u201317. https:\/\/doi.org\/10.1021\/acs.jcim.3c01250","journal-title":"J Chem Inf Model"},{"issue":"10","key":"1057_CR68","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345\u20131359. https:\/\/doi.org\/10.1109\/TKDE.2009.191","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1057_CR69","doi-asserted-by":"publisher","unstructured":"Handbook of research on machine learning applications and trends: algorithms, methods, and techniques. IGI Global (2010). https:\/\/doi.org\/10.4018\/978-1-60566-766-9","DOI":"10.4018\/978-1-60566-766-9"},{"key":"1057_CR70","unstructured":"Ruder S (2017) An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 arXiv"},{"key":"1057_CR71","unstructured":"Zhang Y, Yang Q (2017) A survey on multi-task learning. arXiv preprint arXiv:1707.08114 . arXiv"},{"key":"1057_CR72","doi-asserted-by":"publisher","first-page":"1752","DOI":"10.1039\/D3DD00103B","volume":"2","author":"JG Rittig","year":"2023","unstructured":"Rittig JG, Felton KC, Lapkin AA, Mitsos A (2023) Gibbs-duhem-informed neural networks for binary activity coefficient prediction. Digital Discov 2:1752\u20131767. https:\/\/doi.org\/10.1039\/D3DD00103B","journal-title":"Digital Discov"},{"key":"1057_CR73","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1039\/D2DD00142J","volume":"2","author":"EI Sanchez Medina","year":"2023","unstructured":"Sanchez Medina EI, Linke S, Stoll M, Sundmacher K (2023) Gibbs-helmholtz graph neural network: capturing the temperature dependency of activity coefficients at infinite dilution. Digital Discov 2:781\u2013798. https:\/\/doi.org\/10.1039\/D2DD00142J","journal-title":"Digital Discov"},{"key":"1057_CR74","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c01103","author":"Y Chung","year":"2022","unstructured":"Chung Y, Vermeire FH, Wu H, Walker PJ, Abraham MH, Green WH (2022) Group contribution and machine learning approaches to predict Abraham solute parameters, solvation free energy, and solvation enthalpy. J Chem Inf Model. https:\/\/doi.org\/10.1021\/acs.jcim.1c01103","journal-title":"J Chem Inf Model"},{"issue":"20","key":"1057_CR75","doi-asserted-by":"publisher","first-page":"7130","DOI":"10.1021\/acs.iecr.2c00326","volume":"61","author":"PJ Walker","year":"2022","unstructured":"Walker PJ, Yew H-W, Riedemann A (2022) Clapeyron.jl: an extensible, open-source fluid thermodynamics toolkit. Ind Eng Chem Res 61(20):7130\u20137153. https:\/\/doi.org\/10.1021\/acs.iecr.2c00326","journal-title":"Ind Eng Chem Res"},{"key":"1057_CR76","doi-asserted-by":"publisher","unstructured":"Bell C, Yoel seimen cintronej, Yu T, Alex Matthias A, Vasilyev A., Volpatto D, Felton K, RoryKurek Keskitalo T, Shimwell J CalebBell\/thermo: 0.4.2. https:\/\/doi.org\/10.5281\/zenodo.15036476","DOI":"10.5281\/zenodo.15036476"},{"issue":"6","key":"1057_CR77","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1002\/aic.690210607","volume":"21","author":"A Fredenslund","year":"1975","unstructured":"Fredenslund A, Jones RL, Prausnitz JM (1975) Group-contribution estimation of activity coefficients in nonideal liquid mixtures. AIChE J 21(6):1086\u20131099. https:\/\/doi.org\/10.1002\/aic.690210607","journal-title":"AIChE J"},{"key":"1057_CR78","unstructured":"Gmehling J, Tiegs D, Medina A, Soares M, Bastos J, Alessi P, Kikic I, Schiller M, Menke J (2008) Dechema chemistry data series, volume ix activity coefficients at infinite dilution. DECHEMA Chemistry Data Series 9. ISBN: 978-3-89746-107-9. https:\/\/dechema.de\/Analysis+_+Consulting\/Chemistry+Data+Series\/Volume+IX.html"},{"issue":"5","key":"1057_CR79","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1021\/je000236i","volume":"46","author":"PJ Linstrom","year":"2001","unstructured":"Linstrom PJ, Mallard WG (2001) The NIST chemistry webbook: a chemical data resource on the internet. J Chem Eng Data 46(5):1059\u20131063. https:\/\/doi.org\/10.1021\/je000236i","journal-title":"J Chem Eng Data"},{"issue":"21","key":"1057_CR80","doi-asserted-by":"publisher","first-page":"3762","DOI":"10.1021\/jp980230o","volume":"102","author":"AK Ghose","year":"1998","unstructured":"Ghose AK, Viswanadhan VN, Wendoloski JJ (1998) Prediction of hydrophobic (lipophilic) properties of small organic molecules using fragmental methods: an analysis of alogp and clogp methods. J Phys Chem A 102(21):3762\u20133772. https:\/\/doi.org\/10.1021\/jp980230o","journal-title":"J Phys Chem A"},{"key":"1057_CR81","unstructured":"Dassault Syst\u00e8mes: BIOVIA COSMOconf 2022 (2022). https:\/\/www.3ds.com"},{"key":"1057_CR82","unstructured":"Dassault Syst\u00e8mes: BIOVIA COSMOtherm 2022 (2022). https:\/\/www.3ds.com"},{"key":"1057_CR83","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.4c04670","author":"S-C Li","year":"2024","unstructured":"Li S-C, Wu H, Menon A, Spiekermann KA, Li Y-P, Green WH (2024) When do quantum mechanical descriptors help graph neural networks to predict chemical properties? J Am Chem Soc. https:\/\/doi.org\/10.1021\/jacs.4c04670","journal-title":"J Am Chem Soc"},{"key":"1057_CR84","doi-asserted-by":"crossref","unstructured":"Rittig JG, Mitsos A (2024) Thermodynamics-consistent graph neural networks. arXiv preprint arXiv:2407.18372 . arXiv","DOI":"10.1039\/D4SC04554H"},{"key":"1057_CR85","doi-asserted-by":"crossref","unstructured":"Specht T, Nagda M, Fellenz S, Mandt S, Hasse H, Jirasek F (2024) Hanna: Hard-constraint neural network for consistent activity coefficient prediction. arXiv preprint arXiv:2407.18011","DOI":"10.1039\/D4SC05115G"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01057-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-025-01057-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01057-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T08:48:11Z","timestamp":1754642891000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-025-01057-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,8]]},"references-count":85,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1057"],"URL":"https:\/\/doi.org\/10.1186\/s13321-025-01057-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2024-3t818","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,8]]},"assertion":[{"value":"13 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2025","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":"123"}}