{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:50:11Z","timestamp":1791910211078,"version":"4.3.4"},"reference-count":80,"publisher":"American Chemical Society (ACS)","issue":"19","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/100006112","name":"Microsoft Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006112","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018992","name":"Fonds der Chemischen Industrie","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018992","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Quantum Delta"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Recent machine-learning models have shown that implicit solvation based on continuum solvation models can be learned efficiently with graph neural networks. However, previous studies have focused almost exclusively on neutral or only weakly charged molecules, leaving the strongly charged regime essentially unexplored. Here, we systematically investigate which model architectures and architectural components are required to predict solvation energies and corresponding forces for molecules with total charges ranging from \u22125 to +5. Using reference data generated from the conductor-like screening model for realistic solvation (COSMO-RS) for water, acetonitrile, and cyclohexane, we show that an explicit and robust treatment of molecular charge is essential for reliable performance across charge states. At the same time, highly charged systems prove easier to learn than neutral and singly charged ones, whose solvation energies depend more strongly on subtle structural effects. Finally, we demonstrate that the machine-learning models enable stable solvent-aware geometry optimization and can be used for efficient conformational sampling in solution.<\/jats:p>","DOI":"10.1021\/acs.jctc.6c00804","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T15:06:28Z","timestamp":1790694388000},"page":"10022-10035","source":"Crossref","is-referenced-by-count":0,"title":["Can Machine Learning Predict Solvation Effects on\nEnergies and Geometries of Highly Charged Molecules?"],"prefix":"10.1021","volume":"22","author":[{"given":"Dario","family":"Baum","sequence":"first","affiliation":[{"name":"Vrije Universiteit Amsterdam , , De Boelelaan 1108 , ,","place":["Amsterdam, The Netherlands, 1081 HZ"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7748-6243","authenticated-orcid":true,"given":"Lucas","family":"Visscher","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam , , De Boelelaan 1108 , ,","place":["Amsterdam, The Netherlands, 1081 HZ"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1895-2037","authenticated-orcid":true,"given":"Amber","family":"Pausch","sequence":"additional","affiliation":[{"name":"University of Mu\u0308nster, Organisch-Chemisches Institut and Center for Multiscale Theory and Computation , Corrensstra\u00dfe 36 , ,","place":["Mu\u0308nster, Germany, 48149"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"2026101310071758000_cit1","doi-asserted-by":"publisher","first-page":"2999","DOI":"10.1021\/cr9904009","article-title":"Quantum Mechanical Continuum Solvation\nModels","volume":"105","author":"Tomasi","year":"2005","journal-title":"Chem. Rev."},{"key":"2026101310071758000_cit2","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1519","article-title":"Dielectric\ncontinuum methods for quantum chemistry","volume":"11","author":"Herbert","year":"2021","journal-title":"WIREs\nComput. Mol. Sci."},{"key":"2026101310071758000_cit3","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.1021\/cr960149m","article-title":"Implicit solvation\nmodels: equilibria, structure, spectra,\nand dynamics","volume":"99","author":"Cramer","year":"1999","journal-title":"Chem. Rev."},{"key":"2026101310071758000_cit4","doi-asserted-by":"publisher","first-page":"5644","DOI":"10.1039\/D2CC07079K","article-title":"Continuum vs. atomistic\napproaches to computational\nspectroscopy of solvated systems","volume":"59","author":"Giovannini","year":"2023","journal-title":"Chem. Commun."},{"key":"2026101310071758000_cit5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0301-4622(98)00226-9","article-title":"Implicit solvent models","volume":"78","author":"Roux","year":"1999","journal-title":"Biophys.\nChem."},{"key":"2026101310071758000_cit6","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.ejmech.2014.08.064","article-title":"Implicit solvent methods\nfor free energy estimation","volume":"91","author":"Decherchi","year":"2015","journal-title":"Eur. J. Med. Chem."},{"key":"2026101310071758000_cit7","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.sbi.2008.01.003","article-title":"Recent advances\nin implicit solvent-based\nmethods for biomolecular simulations","volume":"18","author":"Chen","year":"2008","journal-title":"Curr.\nOpin. Struct. Biol."},{"key":"2026101310071758000_cit8","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.cplett.2007.02.012","article-title":"An efficient\nstatistically converged average configuration for solvent effects","volume":"437","author":"Coutinho","year":"2007","journal-title":"Chem. Phys. Lett."},{"key":"2026101310071758000_cit9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50418-6","article-title":"Modelling chemical\nprocesses in explicit\nsolvents with machine learning potentials","volume":"15","author":"Zhang","year":"2024","journal-title":"Nat.\nCommun."},{"key":"2026101310071758000_cit10","doi-asserted-by":"publisher","first-page":"6654","DOI":"10.1073\/pnas.0500193102","article-title":"Ab initio\nmolecular dynamics: Concepts,\nrecent developments, and future trends","volume":"102","author":"Iftimie","year":"2005","journal-title":"Proc.\nNatl. Acad. Sci. U.S.A."},{"key":"2026101310071758000_cit11","doi-asserted-by":"publisher","first-page":"13333","DOI":"10.1021\/jp021625h","article-title":"Ab Initio QM\/MM Simulation with Proper\nSampling: \u201cFirst Principle\u201d Calculations of the Free\nEnergy of the Autodissociation of Water in Aqueous Solution","volume":"106","author":"S\u030ctrajbl","year":"2002","journal-title":"J. Phys. Chem. B"},{"key":"2026101310071758000_cit12","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1039\/P29930000799","article-title":"COSMO: a new approach to dielectric\nscreening in solvents with explicit expressions for the screening\nenergy and its gradient","volume":"2","author":"Klamt","year":"1993","journal-title":"J. Chem. Soc., Perkin\nTrans. 2"},{"key":"2026101310071758000_cit13","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/0301-0104(81)85090-2","article-title":"Electrostatic interaction of a solute\nwith a continuum. A direct utilizaion of AB initio molecular potentials\nfor the prevision of solvent effects","volume":"55","author":"Miertus\u030c","year":"1981","journal-title":"Chem.\nPhys."},{"key":"2026101310071758000_cit14","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1002\/wcms.1086","article-title":"Polarizable\ncontinuum model","volume":"2","author":"Mennucci","year":"2012","journal-title":"WIREs Comput. Mol. Sci."},{"key":"2026101310071758000_cit15","doi-asserted-by":"publisher","first-page":"1995","DOI":"10.1021\/jp9716997","article-title":"Quantum Calculation\nof Molecular Energies and Energy Gradients in\nSolution by a Conductor Solvent Model","volume":"102","author":"Barone","year":"1998","journal-title":"J. Phys.\nChem. A"},{"key":"2026101310071758000_cit16","doi-asserted-by":"publisher","DOI":"10.1063\/1.3359469","article-title":"Continuous surface\ncharge polarizable continuum models\nof solvation. I. General formalism","volume":"132","author":"Scalmani","year":"2010","journal-title":"J. Chem.\nPhys."},{"key":"2026101310071758000_cit17","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1021\/j100007a062","article-title":"Conductor-like\nScreening Model for Real Solvents: A New Approach to the Quantitative\nCalculation of Solvation Phenomena","volume":"99","author":"Klamt","year":"1995","journal-title":"J. Phys.\nChem. A"},{"key":"2026101310071758000_cit18","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1338","article-title":"The COSMO\nand COSMO-RS solvation models","volume":"8","author":"Klamt","year":"2018","journal-title":"WIREs Comput.\nMol. Sci."},{"key":"2026101310071758000_cit19","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.fluid.2010.02.002","article-title":"COSMO-RS as a tool\nfor property prediction of IL mixtures\u2013A\nreview","volume":"294","author":"Diedenhofen","year":"2010","journal-title":"Fluid Phase Equilib."},{"key":"2026101310071758000_cit20","doi-asserted-by":"publisher","first-page":"4806","DOI":"10.1021\/acs.jcim.9b00659","article-title":"Benchmarking\nDifferent QM Levels for Usage with COSMO-RS","volume":"59","author":"Reinisch","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"2026101310071758000_cit21","doi-asserted-by":"publisher","first-page":"11851","DOI":"10.1021\/acs.iecr.0c00449","article-title":"Extensive Evaluation of Performance\nof the COSMO-RS\nApproach in Capturing Liquid-Liquid Equilibria of Binary Mixtures\nof Ionic Liquids with Molecular Compounds","volume":"59","author":"Paduszyn\u0301ski","year":"2020","journal-title":"Ind.\nEng. Chem. Res."},{"key":"2026101310071758000_cit22","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemosphere.2023.140195","article-title":"COSMO-RS solute partition ratios\nfor solvent mixtures\nof unknown composition: Henry\u2019s law constants as descriptors\nfor mixture sigma profiles","volume":"344","author":"Celsie","year":"2023","journal-title":"Chemosphere"},{"key":"2026101310071758000_cit23","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1080\/00268970903313667","article-title":"Towards a first principles prediction\nof pK a: COSMO-RS and the cluster-continuum approach","volume":"108","author":"Eckert","year":"2010","journal-title":"Mol. Phys."},{"key":"2026101310071758000_cit24","doi-asserted-by":"publisher","first-page":"3169","DOI":"10.1021\/acs.jctc.4c00052","article-title":"Consistent\nAnalytical Second Derivatives of the Kohn-Sham DFT Energy in the Framework\nof the Conductor-Like Screening Model through Gaussian Charge Distributions","volume":"20","author":"Pausch","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit25","doi-asserted-by":"publisher","first-page":"6155","DOI":"10.1021\/acs.jpca.5c02873","article-title":"Gradients of Ground and Excited States\nfor CC2 and\nADC(2) in Polarizable Continuum and Atomistic Embeddings within a\nGeneralized PTED Coupling Scheme","volume":"129","author":"Ha\u0308ttig","year":"2025","journal-title":"J. Phys. Chem.\nA"},{"key":"2026101310071758000_cit26","doi-asserted-by":"publisher","first-page":"2235","DOI":"10.1021\/jp056016z","article-title":"Calculation of solvent shifts on electronic g-tensors with the conductor-like\nscreening model (COSMO) and its self-consistent generalization to\nreal solvents (direct COSMO-RS)","volume":"110","author":"Sinnecker","year":"2006","journal-title":"J. Phys. Chem.\nA"},{"key":"2026101310071758000_cit27","doi-asserted-by":"publisher","first-page":"1304","DOI":"10.1002\/jcc.22961","article-title":"Thermodynamics of chemical\nreactions with COSMO-RS:\nThe extreme case of charge separation or recombination","volume":"33","author":"Deglmann","year":"2012","journal-title":"J. Comput. Chem."},{"key":"2026101310071758000_cit28","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1021\/ct5008857","article-title":"Validation of the Direct-COSMO-RS\nSolvent Model for Diels-Alder Reactions in Aqueous Solution","volume":"11","author":"Theilacker","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit29","doi-asserted-by":"publisher","first-page":"22976","DOI":"10.1039\/D5SC06406F","article-title":"A diverse and chemically relevant\nsolvation model benchmark set with flexible molecules and conformer\nensembles","volume":"16","author":"Wittmann","year":"2025","journal-title":"Chem. Sci."},{"key":"2026101310071758000_cit30","doi-asserted-by":"publisher","first-page":"5439","DOI":"10.1021\/jp511158y","article-title":"Calculation\nof Solvation Free Energies with DCOSMO-RS","volume":"119","author":"Klamt","year":"2015","journal-title":"J.\nPhys. Chem. A"},{"key":"2026101310071758000_cit31","doi-asserted-by":"publisher","first-page":"3913","DOI":"10.1039\/D2SC06696C","article-title":"Neural network potentials\nfor accelerated metadynamics of oxygen reduction kinetics at Au-water\ninterfaces","volume":"14","author":"Yang","year":"2023","journal-title":"Chem. Sci."},{"key":"2026101310071758000_cit32","doi-asserted-by":"publisher","DOI":"10.1063\/1.4996819","article-title":"High-dimensional neural network potentials\nfor solvation: The case of protonated water clusters in helium","volume":"148","author":"Schran","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2026101310071758000_cit33","doi-asserted-by":"publisher","first-page":"10350","DOI":"10.1021\/acs.jctc.4c01201","article-title":"Capturing\ndichotomic solvent behavior in solute-solvent reactions with neural\nnetwork potentials","volume":"20","author":"Ce\u0301lerse","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit34","doi-asserted-by":"publisher","first-page":"9932","DOI":"10.1021\/acs.jpclett.4c02224","article-title":"Unveiling the role\nof solvent in solution phase chemical reactions using deep potential-based\nenhanced sampling simulations","volume":"15","author":"Anmol","year":"2024","journal-title":"J. Phys. Chem.\nLett."},{"key":"2026101310071758000_cit35","doi-asserted-by":"publisher","DOI":"10.1063\/5.0098330","article-title":"Automated workflow for computation of redox potentials, acidity constants,\nand solvation free energies accelerated by machine learning","volume":"157","author":"Wang","year":"2022","journal-title":"J. Chem. Phys."},{"key":"2026101310071758000_cit36","doi-asserted-by":"publisher","first-page":"2410","DOI":"10.1039\/D3SC05353A","article-title":"Machine learning\nfrom quantum chemistry to predict\nexperimental solvent effects on reaction rates","volume":"15","author":"Chung","year":"2024","journal-title":"Chem. Sci."},{"key":"2026101310071758000_cit37","doi-asserted-by":"publisher","DOI":"10.1063\/5.0147027","article-title":"Implicit solvent\napproach based on generalized Born\nand transferable graph neural networks for molecular dynamics simulations","volume":"158","author":"Katzberger","year":"2023","journal-title":"J. Chem. Phys."},{"key":"2026101310071758000_cit38","article-title":"FieldSchNet:\nDeep learning of molecular systems with\nelectrostatics","volume":"154","author":"Gastegger","year":"2021","journal-title":"J. Chem. Phys."},{"key":"2026101310071758000_cit39","doi-asserted-by":"publisher","first-page":"2830","DOI":"10.1016\/j.bpj.2024.02.029","article-title":"Calculation of solvation force in\nmolecular dynamics simulation by deep-learning method","volume":"123","author":"Liao","year":"2024","journal-title":"Biophys. J."},{"key":"2026101310071758000_cit40","doi-asserted-by":"publisher","first-page":"4565","DOI":"10.1039\/D2RA08180F","article-title":"Machine learning based implicit solvent\nmodel for aqueous-solution\nalanine dipeptide molecular dynamics simulations","volume":"13","author":"Yao","year":"2023","journal-title":"RSC Adv."},{"key":"2026101310071758000_cit41","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/978-3-031-72381-0_5","article-title":"Leveraging Quantum\nMechanical Properties to Predict Solvent Effects on Large Drug-like\nMolecules","volume-title":"Lecture Notes in Computer Science","author":"Hilfiker","year":"2025"},{"key":"2026101310071758000_cit42","doi-asserted-by":"publisher","first-page":"11473","DOI":"10.1039\/D1SC02742E","article-title":"Machine learning of solvent effects\non molecular spectra and reactions","volume":"12","author":"Gastegger","year":"2021","journal-title":"Chem. Sci."},{"key":"2026101310071758000_cit43","doi-asserted-by":"publisher","first-page":"13264","DOI":"10.1021\/jacs.4c17622","article-title":"Rapid access\nto small molecule conformational ensembles in organic solvents enabled\nby graph neural network-based implicit solvent model","volume":"147","author":"Katzberger","year":"2025","journal-title":"J. Am. Chem. Soc."},{"key":"2026101310071758000_cit44","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1021\/acs.jctc.3c00984","article-title":"Developing\nan implicit solvation machine learning model for molecular simulations\nof ionic media","volume":"20","author":"Coste","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit45","doi-asserted-by":"publisher","first-page":"10142","DOI":"10.1021\/acs.chemrev.0c01111","article-title":"Machine learning force\nfields","volume":"121","author":"Unke","year":"2021","journal-title":"Chem. Rev."},{"key":"2026101310071758000_cit46","doi-asserted-by":"publisher","first-page":"10037","DOI":"10.1021\/acs.chemrev.0c00868","article-title":"Four generations\nof high-dimensional neural network potentials","volume":"121","author":"Behler","year":"2021","journal-title":"Chem. Rev."},{"key":"2026101310071758000_cit47","doi-asserted-by":"publisher","first-page":"7450","DOI":"10.1021\/acs.jctc.5c00728","article-title":"Transferring knowledge from MM to\nQM: A graph neural network-based implicit solvent model for small\norganic molecules","volume":"21","author":"Katzberger","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit48","doi-asserted-by":"publisher","DOI":"10.1063\/5.0235189","article-title":"Predicting\nsolvation free energies\nwith an implicit solvent machine learning potential","volume":"161","author":"Ro\u0308cken","year":"2024","journal-title":"J. Chem. Phys."},{"key":"2026101310071758000_cit49","doi-asserted-by":"publisher","first-page":"2087","DOI":"10.1021\/acs.jctc.5b00099","article-title":"Big data\nmeets quantum chemistry approximations: the \u0394-machine learning\napproach","volume":"11","author":"Ramakrishnan","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit50","doi-asserted-by":"publisher","first-page":"9710","DOI":"10.1021\/acs.jctc.5c01193","article-title":"End-to-End\nModeling of Reaction Field Energy Using\nData-Driven Geometric Graph Neural Networks","volume":"21","author":"Wu","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit51","doi-asserted-by":"publisher","first-page":"8583","DOI":"10.1021\/acs.jctc.4c00794","article-title":"Nutmeg\nand SPICE:\nModels and data for biomolecular machine learning","volume":"20","author":"Eastman","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit52","doi-asserted-by":"publisher","first-page":"5215","DOI":"10.1021\/acs.jctc.3c01411","article-title":"The determination of\nfree energy of hydration of water ions from first principles","volume":"20","author":"Butin","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit53","doi-asserted-by":"publisher","first-page":"1840","DOI":"10.1021\/acs.jcim.2c00260","article-title":"Accurate prediction\nof aqueous free solvation energies\nusing 3D atomic feature-based graph neural network with transfer learning","volume":"62","author":"Zhang","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026101310071758000_cit54","doi-asserted-by":"publisher","first-page":"4820","DOI":"10.1021\/acs.jctc.4c00116","article-title":"Solvation free energies from machine\nlearning molecular\ndynamics","volume":"20","author":"Bonnet","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit55","doi-asserted-by":"publisher","first-page":"8920","DOI":"10.1039\/D0CC03512B","article-title":"Active learning\nand neural network potentials accelerate molecular screening of ether-based\nsolvate ionic liquids","volume":"56","author":"Wang","year":"2020","journal-title":"Chem. Commun."},{"key":"2026101310071758000_cit56","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2407877121","article-title":"The role of the water contact layer\non hydration and transport at solid\/liquid interfaces","volume":"121","author":"Ga\u0308ding","year":"2024","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"2026101310071758000_cit57","doi-asserted-by":"publisher","first-page":"7216","DOI":"10.1021\/acs.jpcb.5c01669","article-title":"Machine Learning\nwith Physically Inspired Descriptors to Predict Solvation Free Energies\nof Neutral and Ionic Solutes in Aqueous and Nonaqueous Solvents","volume":"129","author":"Jia","year":"2025","journal-title":"J. Phys. Chem. B"},{"key":"2026101310071758000_cit58","doi-asserted-by":"publisher","first-page":"10794","DOI":"10.1039\/D4SC02432J","article-title":"A general graph neural network based\nimplicit solvation\nmodel for organic molecules in water","volume":"15","author":"Katzberger","year":"2024","journal-title":"Chem.\nSci."},{"key":"2026101310071758000_cit59","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1002\/wcms.81","article-title":"The ORCA program\nsystem","volume":"2","author":"Neese","year":"2012","journal-title":"WIREs Comput. Mol. Sci."},{"key":"2026101310071758000_cit60","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.70019","article-title":"Software Update:\nThe ORCA Program SystemVersion 6.0","volume":"15","author":"Neese","year":"2025","journal-title":"WIREs Comput.\nMol. Sci."},{"key":"2026101310071758000_cit61","unstructured":"Nayal, K.; Cho, I.; Gao, N.; Zheng, P.; Isayev, O.\n          Training datasets for AIMNet2(2025) machine-learned\nneural network potential. 202510.1184\/R1\/31141138.v1."},{"key":"2026101310071758000_cit62","doi-asserted-by":"publisher","first-page":"2819","DOI":"10.1073\/pnas.1521570113","article-title":"Long-ranged\ncontributions to solvation free energies\nfrom theory and short-ranged models","volume":"113","author":"Remsing","year":"2016","journal-title":"Proc. Natl.\nAcad. Sci. U.S.A."},{"key":"2026101310071758000_cit63","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1002\/qua.24901","article-title":"An overview\nof continuum models for nonequilibrium solvation: Popular theories\nand new challenge","volume":"115","author":"Li","year":"2015","journal-title":"Int. J. Quantum Chem."},{"key":"2026101310071758000_cit64","doi-asserted-by":"publisher","DOI":"10.1063\/1.4952647","article-title":"\u03c9B97M-V: A combinatorially optimized,\nrange-separated hybrid, meta-GGA density functional with VV10 nonlocal\ncorrelation","volume":"144","author":"Mardirossian","year":"2016","journal-title":"J. Chem. Phys."},{"key":"2026101310071758000_cit65","doi-asserted-by":"publisher","DOI":"10.1063\/1.3382344","article-title":"A consistent and accurate\nab initio parametrization of Density Functional dispersion correction\n(DFT-D) for the 94 elements H-Pu","volume":"132","author":"Grimme","year":"2010","journal-title":"J. Chem. Phys."},{"key":"2026101310071758000_cit66","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1002\/jcc.21759","article-title":"Effect of the damping function in\ndispersion corrected density functional theory","volume":"32","author":"Grimme","year":"2011","journal-title":"J. Comput. Chem."},{"key":"2026101310071758000_cit67","doi-asserted-by":"publisher","first-page":"3297","DOI":"10.1039\/b508541a","article-title":"Balanced basis sets of split valence, triple zeta valence\nand quadruple zeta valence quality for H to Rn: Design and assessment\nof accuracy","volume":"7","author":"Weigend","year":"2005","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2026101310071758000_cit68","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.chemphys.2008.10.036","article-title":"Efficient, approximate\nand parallel Hartree-Fock and hybrid DFT calculations. A chain-of-spheres\u2019\nalgorithm for the Hartree-Fock exchange","volume":"356","author":"Neese","year":"2009","journal-title":"Chem.\nPhys."},{"key":"2026101310071758000_cit69","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1039\/b515623h","article-title":"Accurate Coulomb-fitting\nbasis sets for H to Rn","volume":"8","author":"Weigend","year":"2006","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2026101310071758000_cit70","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/BF00549096","article-title":"Bonded-atom\nfragments for describing molecular charge densities","volume":"44","author":"Hirshfeld","year":"1977","journal-title":"Theor. Chim. Acta"},{"key":"2026101310071758000_cit71","doi-asserted-by":"publisher","first-page":"6127","DOI":"10.1021\/ja00172a038","article-title":"Semianalytical\ntreatment of solvation for molecular mechanics and dynamics","volume":"112","author":"Still","year":"1990","journal-title":"J. Am. Chem. Soc."},{"key":"2026101310071758000_cit72","doi-asserted-by":"publisher","first-page":"2462","DOI":"10.1021\/acs.jpclett.3c03551","article-title":"Improving\nQuantum Chemical Solvation Models by Dynamic Radii Adjustment for\nContinuum Solvation (DRACO)","volume":"15","author":"Plett","year":"2024","journal-title":"J. Phys. Chem.\nLett."},{"key":"2026101310071758000_cit73","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27504-0","article-title":"SpookyNet: Learning force fields\nwith electronic degrees of freedom and nonlocal effects","volume":"12","author":"Unke","year":"2021","journal-title":"Nat. Commun."},{"key":"2026101310071758000_cit74","unstructured":"Ba, J. L.; Kiros, J. R.; Hinton, G. E.\n          Layer normalization. 2016, arXiv:1607.06450v1. arXiv.org e-Print archive. https:\/\/doi.org\/10.48550\/arXiv.1607.06450."},{"key":"2026101310071758000_cit75","doi-asserted-by":"publisher","first-page":"5457","DOI":"10.1021\/acs.jcim.2c01013","article-title":"Explainable\nsolvation free energy\nprediction combining graph neural networks with chemical intuition","volume":"62","author":"Low","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026101310071758000_cit76","doi-asserted-by":"publisher","DOI":"10.1063\/5.0059915","article-title":"Machine learning implicit solvation\nfor molecular dynamics","volume":"155","author":"Chen","year":"2021","journal-title":"J. Chem. Phys."},{"key":"2026101310071758000_cit77","doi-asserted-by":"publisher","first-page":"8340","DOI":"10.1021\/acs.jctc.3c00858","article-title":"Predicting\nsolvation free energies using electronegativity-equalization atomic\ncharges and a dense neural network: A generalized-Born approach","volume":"19","author":"Vyboishchikov","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"2026101310071758000_cit78","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.70104","article-title":"Atomic\nNeural Network for Calculation of Solvation Free Energies in Organic\nSolvents","volume":"46","author":"Vyboishchikov","year":"2025","journal-title":"J. Comput. Chem."},{"key":"2026101310071758000_cit79","doi-asserted-by":"publisher","first-page":"8306","DOI":"10.1039\/C9SC02452B","article-title":"Delfos: deep learning model for prediction of solvation free energies\nin generic organic solvents","volume":"10","author":"Lim","year":"2019","journal-title":"Chem. Sci."},{"key":"2026101310071758000_cit80","unstructured":"Paszke, A.; Gross, S.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L.; et al. In  Pytorch: An Imperative\nStyle, High-performance\nDeep Learning Library, Advances in Neural Information Processing\nSystems; NeurIPS Proceedings, 2019."}],"container-title":["Journal of Chemical Theory and Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jctc.6c00804","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jctcce\/article-pdf\/doi\/10.1021\/acs.jctc.6c00804\/68693217\/acs.jctc.6c00804.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jctcce\/article-pdf\/doi\/10.1021\/acs.jctc.6c00804\/68693217\/acs.jctc.6c00804.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:11:24Z","timestamp":1791907884000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jctcce\/article\/22\/19\/10022\/5441205\/Can-Machine-Learning-Predict-Solvation-Effects-on"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":80,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,9,29]]},"published-print":{"date-parts":[[2026,10,13]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jctc.6c00804","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.15002484\/v1","asserted-by":"object"}]},"ISSN":["1549-9618","1549-9626"],"issn-type":[{"value":"1549-9618","type":"print"},{"value":"1549-9626","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]}}}