{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T14:07:22Z","timestamp":1790086042021,"version":"4.0.1"},"reference-count":76,"publisher":"American Chemical Society (ACS)","issue":"18","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f?r Forschung, Technologie und Raumfahrt","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101162908"],"award-info":[{"award-number":["101162908"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001655","name":"Deutscher Akademischer Austauschdienst","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001655","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012650","name":"Technische Universit?t Wien Bibliothek","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012650","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002428","name":"Austrian Science Fund","doi-asserted-by":"publisher","award":["10.55776\/ESP1292125"],"award-info":[{"award-number":["10.55776\/ESP1292125"]}],"id":[{"id":"10.13039\/501100002428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Machine-learned interatomic potentials (MLIPs) have become an increasingly important tool for molecular dynamics (MD) simulations, enabling near quantum-mechanical accuracy at significantly reduced computational cost. Recent studies indicate that the Graph Atomic Cluster Expansion (GRACE) neural network architecture delivers strong performance in materials chemistry. In this work, we assess the GRACE architecture for the prediction of potential energy surfaces for organic molecules and introduce GRACE-OFF (GRACE Organic Force Field). GRACE models of varying depth (one-layer and two-layer) and size (small, medium, large) are trained on the SPICE v2.0 data set. We validate the resulting models using a variety of benchmarks. These include single-point energy and force predictions, torsional energy profiles, condensed phase properties of organic liquids and water (thermodynamic properties, self-diffusion coefficients, radial distribution functions, and temperature-dependent water density), as well as the stability of biomolecular MD simulations for gas-phase Ala15 and solvated crambin. For the single-molecule benchmarks (single point energies and forces, torsional energy profiles), the one-layer models showed only mediocre performance, whereas the two-layer models outperformed the MACE-OFF models to which we compare. For the condensed phase properties, the two-layer models gave consistently better results than the MACE-OFF family of MLIPs. For water and hexane, the GRACE-OFF models also beat the much more expensive small UMA\/OMol25 (S) model. The two-layer GRACE-OFF models accurately reproduce experimental water radial distribution functions and predict water densities in close agreement with experimental data over a temperature range from 270 to 330 K. Benchmarks demonstrate that GRACE-OFF achieves higher MD performance than comparable MACE-OFF models in both single and double precision. This establishes GRACE-OFF as an accurate and computationally efficient foundation potential for routine simulations of organic liquids and biomolecular systems.<\/jats:p>","DOI":"10.1021\/acs.jctc.6c01169","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T20:19:11Z","timestamp":1788466751000},"page":"9274-9289","source":"Crossref","is-referenced-by-count":0,"title":["GRACE-OFF: A Machine-Learned\nInteratomic Potential\nfor Organic Liquids Using the GRACE Architecture"],"prefix":"10.1021","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9131-9435","authenticated-orcid":true,"given":"Anna Katharina","family":"Picha","sequence":"first","affiliation":[{"name":"University of Vienna , , ,","place":["Vienna, Austria, 1090"]},{"name":"University of Vienna , , ,","place":["Vienna, Austria, 1090"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0172-863X","authenticated-orcid":true,"given":"Johannes","family":"Karwounopoulos","sequence":"additional","affiliation":[{"name":"TU Wien , , ,","place":["Vienna, Austria, A-1060"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0219-5801","authenticated-orcid":true,"given":"Linus C.","family":"Erhard","sequence":"additional","affiliation":[{"name":"TU Wien , , ,","place":["Vienna, Austria, A-1060"]},{"name":"Ruhr-University Bochum , , ,","place":["Bochum, Germany, 44780"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2793-6656","authenticated-orcid":true,"given":"Stefan","family":"Boresch","sequence":"additional","affiliation":[{"name":"University of Vienna , , ,","place":["Vienna, Austria, 1090"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8404-6596","authenticated-orcid":true,"given":"Esther","family":"Heid","sequence":"additional","affiliation":[{"name":"TU Wien , , ,","place":["Vienna, Austria, A-1060"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"2026092209062561400_cit1","doi-asserted-by":"publisher","first-page":"3419","DOI":"10.1021\/acs.jpclett.3c03405","article-title":"Numerical Accuracy\nMatters: Applications of Machine\nLearned Potential Energy Surfaces","volume":"15","author":"Ka\u0308ser","year":"2024","journal-title":"J. Phys.\nChem. Lett."},{"key":"2026092209062561400_cit2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0237876","article-title":"On the\ndesign space between molecular mechanics and machine learning force\nfields","volume":"12","author":"Wang","year":"2025","journal-title":"Appl. Phys. Rev."},{"key":"2026092209062561400_cit3","unstructured":"Weber, J. L.; Guha, R. D.; Agarwal, G.; Wei, Y.; et al.\n          Efficient Long-Range\nMachine Learning Force Fields for Liquid and Materials Properties. 2025."},{"key":"2026092209062561400_cit4","doi-asserted-by":"publisher","first-page":"5373","DOI":"10.1021\/acs.jcim.2c00817","article-title":"Auto3D: Automatic Generation\nof the Low-Energy 3D Structures with ANI Neural Network Potentials","volume":"62","author":"Liu","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026092209062561400_cit5","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aav6490","article-title":"Accurate and transferable\nmultitask prediction of chemical properties with an atoms-in-molecules\nneural network","volume":"5","author":"Zubatyuk","year":"2019","journal-title":"Sci. Adv."},{"key":"2026092209062561400_cit6","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-025-01542-4","article-title":"Understanding\nphase transitions of \u03b1-quartz under dynamic\ncompression conditions by machine-learning driven atomistic simulations","volume":"11","author":"Erhard","year":"2025","journal-title":"npj Comput. Mater."},{"key":"2026092209062561400_cit7","doi-asserted-by":"publisher","first-page":"2719","DOI":"10.1021\/acs.jctc.3c01274","article-title":"Reweighting\nfrom Molecular Mechanics Force Fields to the ANI-2x Neural Network\nPotential","volume":"20","author":"Tkaczyk","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209062561400_cit8","doi-asserted-by":"publisher","first-page":"6693","DOI":"10.1021\/acs.jpcb.4c01417","article-title":"Insights and Challenges\nin Correcting Force Field Based Solvation Free Energies Using a Neural\nNetwork Potential","volume":"128","author":"Karwounopoulos","year":"2024","journal-title":"J. Phys. Chem. B"},{"key":"2026092209062561400_cit9","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1021\/acs.jcim.3c02031","article-title":"Enhancing Protein-Ligand Binding Affinity Predictions\nUsing Neural Network Potentials","volume":"64","author":"Sabane\u0301s Zariquiey","year":"2024","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026092209062561400_cit10","doi-asserted-by":"publisher","first-page":"12080","DOI":"10.1021\/acs.jpclett.5c02980","article-title":"Architecture-Independent\nAbsolute Solvation Free Energy Calculations with Neural Network Potentials","volume":"16","author":"Picha","year":"2025","journal-title":"J. Phys. Chem. Lett."},{"key":"2026092209062561400_cit11","doi-asserted-by":"publisher","first-page":"4928","DOI":"10.1021\/jacs.5c10940","article-title":"Computing\nSolvation Free Energies of Small Molecules with Experimental Accuracy","volume":"148","author":"Harry Moore","year":"2026","journal-title":"J. Am. Chem. Soc."},{"key":"2026092209062561400_cit12","doi-asserted-by":"publisher","first-page":"7558","DOI":"10.1021\/acs.jctc.6c00824","article-title":"Dual-Coordinate Relative Free Energy Simulations Using\nMachine-Learned Interatomic Potentials","volume":"22","author":"Picha","year":"2026","journal-title":"J. Chem.\nTheory Comput."},{"key":"2026092209062561400_cit13","doi-asserted-by":"publisher","first-page":"17598","DOI":"10.1021\/jacs.4c07099","article-title":"MACE-OFF:\nShort-Range Transferable Machine Learning Force Fields for Organic\nMolecules","volume":"147","author":"Kova\u0301cs","year":"2025","journal-title":"J. Am. Chem. Soc."},{"key":"2026092209062561400_cit14","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1146\/annurev-physchem-082720-034254","article-title":"Neural Network\nPotentials: A Concise\nOverview of Methods","volume":"73","author":"Kocer","year":"2022","journal-title":"Annu. Rev. Phys. Chem."},{"key":"2026092209062561400_cit15","unstructured":"Schu\u0308tt, K. T.; Kindermans, P.-J.; Sauceda, H. E.; Chmiela, S.; et al.\n          SchNet: a continuous-filter convolutional\nneural network for modeling\nquantum interactions. In  Proceedings of the\n31st International Conference on Neural Information Processing Systems.\nRed Hook, NY, USA2017; pp 992\u20131002."},{"key":"2026092209062561400_cit16","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.1039\/C6SC05720A","article-title":"ANI-1: an extensible neural network\npotential with DFT accuracy at force field computational cost","volume":"8","author":"Smith","year":"2017","journal-title":"Chem. Sci."},{"key":"2026092209062561400_cit17","unstructured":"Gasteiger, J.; Gro\u00df, J.; Gu\u0308nnemann, S.\n          Directional Message\nPassing for Molecular Graphs. 2020."},{"key":"2026092209062561400_cit18","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27504-0","article-title":"SpookyNet: Learning force fields with\nelectronic degrees of freedom\nand nonlocal effects","volume":"12","author":"Unke","year":"2021","journal-title":"Nat. Commun."},{"key":"2026092209062561400_cit19","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29939-5","article-title":"E(3)-equivariant\ngraph neural networks for data-efficient and accurate interatomic\npotentials","volume":"13","author":"Batzner","year":"2022","journal-title":"Nat. Commun."},{"key":"2026092209062561400_cit20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36329-y","article-title":"Learning\nlocal equivariant representations for large-scale atomistic dynamics","volume":"14","author":"Musaelian","year":"2023","journal-title":"Nat. Commun."},{"key":"2026092209062561400_cit21","doi-asserted-by":"publisher","first-page":"12554","DOI":"10.1039\/D3SC02581K","article-title":"FENNIX: force-field-enhanced neural\nnetwork interactions: from local equivariant embedding to atom-in-molecule\nproperties and long-range effects","volume":"14","author":"Ple\u0301","year":"2023","journal-title":"Chem. Sci."},{"key":"2026092209062561400_cit22","doi-asserted-by":"publisher","DOI":"10.1063\/5.0155322","article-title":"Evaluation\nof the MACE force field architecture: From medicinal chemistry to\nmaterials science","volume":"159","author":"Kova\u0301cs","year":"2023","journal-title":"J. Chem. Phys."},{"key":"2026092209062561400_cit23","doi-asserted-by":"publisher","first-page":"10228","DOI":"10.1039\/D4SC08572H","article-title":"AIMNet2: a neural network potential\nto meet your neutral, charged, organic, and elemental-organic needs","volume":"16","author":"Anstine","year":"2025","journal-title":"Chem. Sci."},{"key":"2026092209062561400_cit24","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.193","article-title":"ANI-1, A data set of 20 million calculated\noff-equilibrium conformations for organic molecules","volume":"4","author":"Smith","year":"2017","journal-title":"Sci. Data"},{"key":"2026092209062561400_cit25","doi-asserted-by":"publisher","DOI":"10.1063\/5.0061990","article-title":"OrbNet Denali: A machine\nlearning potential for biological and organic\nchemistry with semi-empirical cost and DFT accuracy","volume":"155","author":"Christensen","year":"2021","journal-title":"J. Chem. Phys."},{"key":"2026092209062561400_cit26","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01882-6","article-title":"SPICE,\nA Dataset of Drug-like Molecules and Peptides for Training Machine\nLearning Potentials","volume":"10","author":"Eastman","year":"2023","journal-title":"Sci. Data"},{"key":"2026092209062561400_cit27","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-04972-3","article-title":"The QD\u03c0 dataset, training data for drug-like molecules and biopolymer fragments\nand their interactions","volume":"12","author":"Zeng","year":"2025","journal-title":"Sci. Data"},{"key":"2026092209062561400_cit28","unstructured":"Levine, D. S.; Shuaibi, M.; Spotte-Smith, E. W. C.; Taylor, M. G.; et al.\n          The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models. 2025."},{"key":"2026092209062561400_cit29","unstructured":"Batatia, I.; Benner, P.; Chiang, Y.; Elena, A. M.; et al.\n          A\nfoundation model for atomistic materials chemistry. 2024."},{"key":"2026092209062561400_cit30","doi-asserted-by":"crossref","unstructured":"Ple\u0301, T.; Adjoua, O.; Benali, A.; Posenitskiy, E.; et al.\n          A Foundation Model for Accurate Atomistic\nSimulations in Drug Design\n          ChemRxiv\n          2025.","DOI":"10.26434\/chemrxiv-2025-f1hgn-v2"},{"key":"2026092209062561400_cit31","doi-asserted-by":"publisher","first-page":"33723","DOI":"10.1021\/jacs.5c09558","article-title":"Molecular Simulations with a Pretrained\nNeural Network and Universal\nPairwise Force Fields","volume":"147","author":"Kabylda","year":"2025","journal-title":"J. Am. Chem. Soc."},{"key":"2026092209062561400_cit32","doi-asserted-by":"publisher","first-page":"3485","DOI":"10.1021\/acs.jcim.9b00439","article-title":"A Scalable\nMolecular Force Field Parameterization Method Based on Density Functional\nTheory and Quantum-Level Machine Learning","volume":"59","author":"Galvelis","year":"2019","journal-title":"J.\nChem. Inf. Model."},{"key":"2026092209062561400_cit33","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1038\/s41557-023-01427-3","article-title":"Exploring\nthe Frontiers of Condensed-Phase Chemistry with a General Reactive\nMachine Learning Potential","volume":"16","author":"Zhang","year":"2024","journal-title":"Nat. Chem."},{"key":"2026092209062561400_cit34","doi-asserted-by":"crossref","unstructured":"Anstine, D. M.; Zhao, Q.; Zubatiuk, R.; Zhang, S.; et al.\n          AIMNet2-rxn:\nA Machine Learned Potential for Generalized Reaction Modeling on a\nMillions-of-Pathways Scale. 2025.","DOI":"10.26434\/chemrxiv-2025-hpdmg"},{"key":"2026092209062561400_cit35","unstructured":"Batatia, I.; Baldwin, W. J.; Kuryla, D.; Hart, J.; et al.\n          MACE-POLAR-1:\nA Polarisable Electrostatic Foundation Model for Molecular Chemistry. 2026; https:\/\/arxiv.org\/abs\/2602.19411."},{"key":"2026092209062561400_cit36","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1021\/acs.jctc.4c01427","article-title":"Evaluation of Machine Learning\/Molecular Mechanics End-State Corrections\nwith Mechanical Embedding to Calculate Relative Protein\u2013Ligand\nBinding Free Energies","volume":"21","author":"Karwounopoulos","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209062561400_cit37","doi-asserted-by":"publisher","first-page":"12861","DOI":"10.1039\/D4SC00690A","article-title":"Machine-learned\nmolecular mechanics force fields from large-scale quantum chemical\ndata","volume":"15","author":"Takaba","year":"2024","journal-title":"Chem. Sci."},{"key":"2026092209062561400_cit38","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-73566-3","article-title":"Bridging quantum mechanics\nto liquid properties via a universal organic force field","volume":"17","author":"Zheng","year":"2026","journal-title":"Nat. Comm"},{"key":"2026092209062561400_cit39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.99.014104","article-title":"Atomic cluster\nexpansion for accurate and transferable interatomic potentials","volume":"99","author":"Drautz","year":"2019","journal-title":"Phys. Rev. B"},{"key":"2026092209062561400_cit40","doi-asserted-by":"crossref","unstructured":"Batatia, I.; Kova\u0301cs, D. P.; Simm, G. N. C.; Ortner, C.; et al.\n          MACE: Higher Order Equivariant Message Passing Neural Networks for\nFast and Accurate Force Fields. 2023.","DOI":"10.52202\/068431-0830"},{"key":"2026092209062561400_cit41","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.14.021036","article-title":"Graph Atomic Cluster\nExpansion for\nSemilocal Interactions beyond Equivariant Message Passing","volume":"14","author":"Bochkarev","year":"2024","journal-title":"Phys. Rev. X"},{"key":"2026092209062561400_cit42","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-026-01979-1","article-title":"Graph atomic cluster\nexpansion for\nfoundational machine learning interatomic potentials","volume":"12","author":"Lysogorskiy","year":"2026","journal-title":"Npj Comput. Mater."},{"key":"2026092209062561400_cit43","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1021\/acsmaterialsau.5c00174","article-title":"How Realistic\nAre Idealized Copper Surfaces? A Machine Learning Study of Rough Copper\u2013Water\nInterfaces","volume":"6","author":"Erhard","year":"2026","journal-title":"ACS Mater. Au"},{"key":"2026092209062561400_cit44","doi-asserted-by":"publisher","DOI":"10.1016\/j.actamat.2025.121283","article-title":"Lattice\ndistortions and non-sluggish diffusion in BCC refractory high entropy\nalloys","volume":"297","author":"Zhang","year":"2025","journal-title":"Acta Mater."},{"key":"2026092209062561400_cit45","doi-asserted-by":"crossref","unstructured":"Wood, B. M.; Dzamba, M.; Fu, X.; Gao, M.; et al.\n          UMA: A Family of Universal\nModels for Atoms. 2025.","DOI":"10.52202\/085713-4310"},{"key":"2026092209062561400_cit46","unstructured":"Picha, A. K.; Karwounopoulos, J.; Erhard, L. C.; Boresch, S.; et al.\n          GRACE-OFF:\nA machine learning interatomic potential for organic liquids using\nthe GRACE architecture. 202610.5281\/zenodo.18662355."},{"key":"2026092209062561400_cit47","doi-asserted-by":"publisher","DOI":"10.1063\/5.0006002","article-title":"PSI4\n1.4: Open-source software for high-throughput quantum chemistry","volume":"152","author":"Smith","year":"2020","journal-title":"J. Chem. Phys."},{"key":"2026092209062561400_cit48","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1021\/acs.jcim.1c01346","article-title":"TorsionNet:\nA Deep Neural Network to Rapidly Predict Small-Molecule Torsional\nEnergy Profiles with the Accuracy of Quantum Mechanics","volume":"62","author":"Rai","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026092209062561400_cit49","doi-asserted-by":"publisher","first-page":"6638","DOI":"10.1021\/ja00334a030","article-title":"Optimized intermolecular\npotential\nfunctions for liquid hydrocarbons","volume":"106","author":"Jorgensen","year":"1984","journal-title":"J. Am. Chem.\nSoc."},{"key":"2026092209062561400_cit50","doi-asserted-by":"publisher","first-page":"3586","DOI":"10.1021\/jp973084f","article-title":"All-Atom\nEmpirical Potential for Molecular Modeling and Dynamics Studies of\nProteins","volume":"102","author":"MacKerell","year":"1998","journal-title":"J. Phys. Chem. B"},{"key":"2026092209062561400_cit51","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1021\/ct200731v","article-title":"Force\nField Benchmark of Organic Liquids: Density, Enthalpy of Vaporization,\nHeat Capacities, Surface Tension, Isothermal Compressibility, Volumetric\nExpansion Coefficient, and Dielectric Constant","volume":"8","author":"Caleman","year":"2012","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209062561400_cit52","doi-asserted-by":"publisher","first-page":"2312","DOI":"10.1021\/acs.jctc.6b00027","article-title":"Biomolecular\nForce Field Parameterization via Atoms-in-Molecule Electron Density\nPartitioning","volume":"12","author":"Cole","year":"2016","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209062561400_cit53","unstructured":"Wang, X.; Wu, X.; Brooks, B.; Wang, J.\n          Accurate Free\nEnergy Calculation via\nMultiscale Simulations Driven by Hybrid Machine Learning and Molecular\nMechanics Potentials. 2025; https:\/\/chemrxiv.org\/engage\/chemrxiv\/article-details\/67c9c98881d2151a02592803."},{"key":"2026092209062561400_cit54","doi-asserted-by":"publisher","first-page":"9483","DOI":"10.1021\/acs.jcim.5c01355","article-title":"Transferable\nneural network potentials\nand condensed phase properties","volume":"65","author":"Picha","year":"2025","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026092209062561400_cit55","doi-asserted-by":"publisher","first-page":"4192","DOI":"10.1021\/acs.jctc.0c00121","article-title":"Extending\nthe Applicability of the ANI Deep Learning Molecular Potential to\nSulfur and Halogens","volume":"16","author":"Devereux","year":"2020","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209062561400_cit56","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adn4397","article-title":"Biomolecular dynamics\nwith machine-learned quantum-mechanical force\nfields trained on diverse chemical fragments","volume":"10","author":"Unke","year":"2024","journal-title":"Sci. Adv."},{"key":"2026092209062561400_cit57","unstructured":"Fu, X.; Wu, Z.; Wang, W.; Xie, T.; et al.\n          Forces are not Enough: Benchmark and\nCritical Evaluation for Machine Learning Force Fields with Molecular\nSimulations\n          Trans. Mach. Learn. Res.\n          2023, Survey Certification."},{"key":"2026092209062561400_cit58","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1021\/ct8000969","article-title":"Re-Evaluation of the Reported Experimental\nValues of the Heat of Vaporization of N-Methylacetamide","volume":"4","author":"MacKerell","year":"2008","journal-title":"J. Phys. Chem. B"},{"key":"2026092209062561400_cit59","doi-asserted-by":"publisher","first-page":"3032","DOI":"10.1021\/acs.jctc.5c00038","article-title":"ABCG2: A Milestone\nCharge Model for Accurate Solvation Free Energy Calculation","volume":"21","author":"He","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209062561400_cit60","doi-asserted-by":"publisher","first-page":"1859","DOI":"10.1002\/jcc.20945","article-title":"CHARMM-GUI: A web-based\ngraphical\nuser interface for CHARMM","volume":"29","author":"Jo","year":"2008","journal-title":"J. Comput. Chem."},{"key":"2026092209062561400_cit61","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1021\/acs.jctc.5b00935","article-title":"CHARMM-GUI\nInput Generator for NAMD, GROMACS, AMBER, OpenMM, and CHARMM\/OpenMM\nSimulations Using the CHARMM36 Additive Force Field","volume":"12","author":"Lee","year":"2016","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209062561400_cit62","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-49700-4","article-title":"CHARMM-GUI\nMulticomponent Assembler\nfor modeling and simulation of complex multicomponent systems","volume":"15","author":"Kern","year":"2024","journal-title":"Nat. Commun."},{"key":"2026092209062561400_cit63","doi-asserted-by":"publisher","first-page":"3155","DOI":"10.1021\/ci3003649","article-title":"Automation\nof the CHARMM General\nForce Field (CGenFF) II: Assignment of Bonded Parameters and Partial\nAtomic Charges","volume":"52","author":"Vanommeslaeghe","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"2026092209062561400_cit64","doi-asserted-by":"publisher","first-page":"3144","DOI":"10.1021\/ci300363c","article-title":"Automation\nof the CHARMM General Force Field (CGenFF)\nI: Bond Perception and Atom Typing","volume":"52","author":"Vanommeslaeghe","year":"2012","journal-title":"J. Chem.\nInf. Model."},{"key":"2026092209062561400_cit65","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1002\/jcc.23067","article-title":"Extension of the CHARMM general force\nfield to sulfonyl-containing\ncompounds and its utility in biomolecular simulations","volume":"33","author":"Yu","year":"2012","journal-title":"J. Comput. Chem."},{"key":"2026092209062561400_cit66","doi-asserted-by":"publisher","DOI":"10.1088\/1361-648X\/aa680e","article-title":"The atomic simulation environment\u2013a\nPython library for working with atoms","volume":"29","author":"Hjorth Larsen","year":"2017","journal-title":"J. Phys.:\nCondens. Matter"},{"key":"2026092209062561400_cit67","doi-asserted-by":"publisher","first-page":"2635","DOI":"10.1063\/1.463940","article-title":"Nose\u0301\u2013Hoover\nchains:\nThe canonical ensemble via continuous dynamics","volume":"97","author":"Martyna","year":"1992","journal-title":"J. Chem. Phys."},{"key":"2026092209062561400_cit68","doi-asserted-by":"publisher","first-page":"4177","DOI":"10.1063\/1.467468","article-title":"Constant pressure molecular dynamics\nalgorithms","volume":"101","author":"Martyna","year":"1994","journal-title":"J. Chem. Phys."},{"key":"2026092209062561400_cit69","doi-asserted-by":"publisher","first-page":"5629","DOI":"10.1088\/0305-4470\/39\/19\/S18","article-title":"A Liouville-operator\nderived measure-preserving integrator\nfor molecular dynamics simulations in the isothermal-isobaric ensemble","volume":"39","author":"Tuckerman","year":"2006","journal-title":"J. Phys. A"},{"key":"2026092209062561400_cit70","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1021\/acs.jpcb.3c06662","article-title":"OpenMM 8: Molecular Dynamics Simulation with\nMachine Learning Potentials","volume":"128","author":"Eastman","year":"2024","journal-title":"J. Phys. Chem.\nB"},{"key":"2026092209062561400_cit71","doi-asserted-by":"publisher","first-page":"17697","DOI":"10.1021\/acs.iecr.2c03342","article-title":"Predicting the Self-Diffusion\nCoefficient of Liquids Based on Backpropagation Artificial Neural\nNetwork: A Quantitative Structure-Property Relationship Study","volume":"61","author":"Zeng","year":"2022","journal-title":"Ind. Eng. Chem. Res."},{"key":"2026092209062561400_cit72","first-page":"2712","volume-title":"CRC Handbook of Chemistry and Physics: A Ready-Reference of Chemical\nand Physical Data (National Institute of Standards and Technology)","author":"Lide","year":"2004"},{"key":"2026092209062561400_cit73","doi-asserted-by":"publisher","first-page":"2938","DOI":"10.1021\/acs.jpclett.5b01066","article-title":"Family of Oxygen\u2013Oxygen Radial Distribution\nFunctions for Water","volume":"6","author":"Brookes","year":"2015","journal-title":"J. Phys. Chem. Lett."},{"key":"2026092209062561400_cit74","doi-asserted-by":"publisher","first-page":"12709","DOI":"10.1021\/acs.jctc.5c01400","article-title":"A Universal\nAugmentation Framework for Long-Range Electrostatics in Machine Learning\nInteratomic Potentials","volume":"21","author":"Kim","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209062561400_cit75","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1021\/ar980065v","article-title":"\u03b1 and 310: The Split\nPersonality of Polypeptide Helices","volume":"32","author":"Bolin","year":"1999","journal-title":"Acc. Chem.\nRes."},{"key":"2026092209062561400_cit76","doi-asserted-by":"crossref","unstructured":"Lysogorskiy, Y.; Bochkarev, A.; Drautz, R.\n          Graph\natomic cluster expansion for foundational machine learning interatomic\npotentials. 2025.","DOI":"10.1038\/s41524-026-01979-1"}],"container-title":["Journal of Chemical Theory\nand Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jctc.6c01169","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jctcce\/article-pdf\/22\/18\/9274\/68281204\/acs.jctc.6c01169.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jctcce\/article-pdf\/22\/18\/9274\/68281204\/acs.jctc.6c01169.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T13:50:16Z","timestamp":1790085016000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jctcce\/article\/22\/18\/9274\/5412826\/GRACE-OFF-A-Machine-Learned-Interatomic-Potential"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":76,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9,3]]},"published-print":{"date-parts":[[2026,9,22]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jctc.6c01169","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.15001529\/v1","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv.15001529\/v2","asserted-by":"object"}]},"ISSN":["1549-9618","1549-9626"],"issn-type":[{"value":"1549-9618","type":"print"},{"value":"1549-9626","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]}}}