{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T14:01:47Z","timestamp":1790085707556,"version":"4.0.1"},"reference-count":84,"publisher":"American Chemical Society (ACS)","issue":"18","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101077842"],"award-info":[{"award-number":["101077842"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007488","name":"Indian Institute of Technology Delhi","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/501100007488","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>Coarse-grained (CG) molecular dynamics (MD) simulations can simulate large molecular complexes over extended time scales by reducing degrees of freedom. A central challenge in CG modeling is the selection of the CG mapping algorithm, which directly influences both accuracy and the interpretability of the model. Despite significant progress, effective strategies for optimal CG mappings remain a challenging task, highlighting the necessity for a comprehensive computational framework. In this work, we introduce a multilevel graph-coarsening framework for coarse graining, inspired by recent advances in graph reduction with spectral and cut guarantees. CG sites are generated through edge contractions based on a local variational cost metric, while preserving essential spectral properties of the original graph. This construction ensures structural fidelity across scales. To learn the corresponding CG energy functions, we utilize the Message Passing Atomic Cluster Expansion (MACE), yielding efficient yet accurate CG potentials. We demonstrate the generality of the framework across isolated molecules, bulk molecular liquid, and crystal. Our approach provides a data-driven bottom-up computational framework for the development of systematically improvable CG potentials with controlled accuracy and physical interpretability.<\/jats:p>","DOI":"10.1021\/acs.jctc.6c00825","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T17:02:07Z","timestamp":1788973327000},"page":"9655-9665","source":"Crossref","is-referenced-by-count":0,"title":["Local Variational\nGraph Coarsening for Machine Learning\nCoarse-Grained Molecular Dynamics Simulations"],"prefix":"10.1021","volume":"22","author":[{"given":"Soumya","family":"Mondal","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Delhi , , Hauz Khas , ,","place":["New Delhi, India, 110016"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8811-8138","authenticated-orcid":true,"given":"Subhanu","family":"Halder","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Delhi , , Hauz Khas , ,","place":["New Delhi, India, 110016"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Debarchan","family":"Basu","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Delhi , , Hauz Khas , ,","place":["New Delhi, India, 110016"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franz","family":"Go\u0308rlich","sequence":"additional","affiliation":[{"name":"Technical University of Munich , , ,","place":["Munich, Germany, 80333"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandeep","family":"Kumar","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Delhi , , Hauz Khas , ,","place":["New Delhi, India, 110016"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8721-6247","authenticated-orcid":true,"given":"Tarak","family":"Karmakar","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Delhi , , Hauz Khas , ,","place":["New Delhi, India, 110016"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"2026092209073859700_cit1","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198803195.001.0001","article-title":"Computer Simulation\nof Liquids","author":"Allen","year":"2017"},{"key":"2026092209073859700_cit2","volume-title":"Understanding Molecular Simulation:\nfrom Algorithms to Applications","author":"Frenkel","year":"2023"},{"key":"2026092209073859700_cit3","doi-asserted-by":"publisher","first-page":"7812","DOI":"10.1021\/jp071097f","article-title":"The MARTINI\nforce field: coarse grained model for biomolecular simulations","volume":"111","author":"Marrink","year":"2007","journal-title":"J. Phys. Chem. B"},{"key":"2026092209073859700_cit4","doi-asserted-by":"publisher","first-page":"7898","DOI":"10.1021\/acs.chemrev.6b00163","article-title":"Coarse-grained protein models and their applications","volume":"116","author":"Kmiecik","year":"2016","journal-title":"Chem. Rev."},{"key":"2026092209073859700_cit5","doi-asserted-by":"publisher","first-page":"8987","DOI":"10.1021\/acs.jctc.3c01053","article-title":"K-means clustering coarse-graining\n(KMC-CG): A next\ngeneration methodology for determining optimal coarse-grained mappings\nof large biomolecules","volume":"19","author":"Wu","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit6","doi-asserted-by":"publisher","first-page":"10179","DOI":"10.1021\/acs.jctc.4c00579","article-title":"SOP-MULTI:\nA Self-Organized Polymer-Based Coarse-Grained\nModel for Multidomain and Intrinsically Disordered Proteins with Conformation\nEnsemble Consistent with Experimental Scattering Data","volume":"20","author":"Baratam","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit7","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.1021\/acs.jpcb.3c06890","article-title":"Insight into the Density-Dependence\nof Pair Potentials for Predictive\nCoarse-Grained Models","volume":"128","author":"Lesniewski","year":"2024","journal-title":"J. Phys. Chem. B"},{"key":"2026092209073859700_cit8","doi-asserted-by":"publisher","first-page":"3351","DOI":"10.1021\/acs.jpclett.5c00548","article-title":"Unveiling Interactions\nof a Peptide-Bound Monolayer-Protected\nMetal Nanocluster with a Lipid Bilayer","volume":"16","author":"Mondal","year":"2025","journal-title":"J. Phys.\nChem. Lett."},{"key":"2026092209073859700_cit9","doi-asserted-by":"publisher","first-page":"4874","DOI":"10.1021\/ct4005036","article-title":"Evolutionary\nalgorithm in the optimization of a coarse-grained force field","volume":"9","author":"Leonarski","year":"2013","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit10","doi-asserted-by":"publisher","first-page":"9124","DOI":"10.1021\/acs.jpca.2c07716","article-title":"Temporally coherent\nbackmapping of molecular trajectories from coarse-grained to atomistic\nresolution","volume":"126","author":"Shmilovich","year":"2022","journal-title":"J. Phys. Chem. A"},{"key":"2026092209073859700_cit11","doi-asserted-by":"publisher","first-page":"2469","DOI":"10.1021\/jp044629q","article-title":"A multiscale coarse-graining\nmethod for biomolecular\nsystems","volume":"109","author":"Izvekov","year":"2005","journal-title":"J. Phys. Chem. B"},{"key":"2026092209073859700_cit12","doi-asserted-by":"publisher","first-page":"5350","DOI":"10.1039\/C4SM00751D","article-title":"Structure\nof a tractable stochastic\nmimic of soft particles","volume":"10","author":"Craven","year":"2014","journal-title":"Soft Matter"},{"key":"2026092209073859700_cit13","doi-asserted-by":"publisher","DOI":"10.1063\/1.4880555","article-title":"Derivation of coarse-grained potentials\nvia multistate iterative Boltzmann inversion","volume":"140","author":"Moore","year":"2014","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit14","doi-asserted-by":"publisher","DOI":"10.1063\/1.4937383","article-title":"Bottom-up coarse-grained\nmodels that accurately describe\nthe structure, pressure, and compressibility of molecular liquids","volume":"143","author":"Dunn","year":"2015","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit15","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1021\/acs.jpclett.8b03872","article-title":"Transfer-learning-based\ncoarse-graining method for\nsimple fluids: toward deep inverse liquid-state theory","volume":"10","author":"Moradzadeh","year":"2019","journal-title":"J. Phys. Chem. Lett."},{"key":"2026092209073859700_cit16","doi-asserted-by":"publisher","first-page":"2435","DOI":"10.1039\/c001523g","article-title":"Influence of topology\non effective\npotentials: coarse-graining ring polymers","volume":"6","author":"Narros","year":"2010","journal-title":"Soft\nMatter"},{"key":"2026092209073859700_cit17","doi-asserted-by":"publisher","first-page":"14092","DOI":"10.1021\/jp505207h","article-title":"Effective surface coverage of coarse-grained\nsoft matter","volume":"118","author":"Craven","year":"2014","journal-title":"J. Phys. Chem. B"},{"key":"2026092209073859700_cit18","doi-asserted-by":"publisher","first-page":"11183","DOI":"10.1039\/c3sm51868j","article-title":"Solvent entropy and\ncoarse-graining of polymer lattice models","volume":"9","author":"Zhang","year":"2013","journal-title":"Soft\nMatter"},{"key":"2026092209073859700_cit19","doi-asserted-by":"publisher","first-page":"2302","DOI":"10.1021\/acs.jpcb.2c06354","article-title":"Integrating machine\nlearning in the coarse-grained\nmolecular simulation of polymers","volume":"127","author":"Ricci","year":"2023","journal-title":"J. Phys. Chem.\nB"},{"key":"2026092209073859700_cit20","doi-asserted-by":"publisher","first-page":"3674","DOI":"10.1021\/jp0550816","article-title":"Coarse grained protein-\nlipid model with application to lipoprotein particles","volume":"110","author":"Shih","year":"2006","journal-title":"J. Phys. Chem. B"},{"key":"2026092209073859700_cit21","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1146\/annurev-biophys-083012-130348","article-title":"Coarse-graining methods for computational biology","volume":"42","author":"Saunders","year":"2013","journal-title":"Annu. Rev. Biophys."},{"key":"2026092209073859700_cit22","doi-asserted-by":"publisher","DOI":"10.1063\/1.4818908","article-title":"Perspective:\nCoarse-grained models for biomolecular systems","volume":"139","author":"Noid","year":"2013","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit23","doi-asserted-by":"publisher","first-page":"2166","DOI":"10.1021\/acs.jcim.5c03035","article-title":"Mapping Still Matters:\nCoarse-Graining with Machine\nLearning Potentials","volume":"66","author":"Go\u0308rlich","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026092209073859700_cit24","doi-asserted-by":"publisher","first-page":"24061","DOI":"10.1073\/pnas.2000098117","article-title":"Exploring the landscape\nof model representations","volume":"117","author":"Foley","year":"2020","journal-title":"Proc. Natl. Acad.\nSci. U.S.A."},{"key":"2026092209073859700_cit25","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1021\/acs.jctc.7b00990","article-title":"A data-driven perspective on the\nhierarchical assembly of molecular structures","volume":"14","author":"Boninsegna","year":"2018","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit26","doi-asserted-by":"publisher","DOI":"10.1063\/5.0220989","article-title":"Analysis of mapping atomic models\nto coarse-grained resolution","volume":"161","author":"Kidder","year":"2024","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit27","doi-asserted-by":"publisher","first-page":"8537","DOI":"10.1021\/acs.jpcb.3c04473","article-title":"OpenMSCG: A software\ntool for bottom-up coarse-graining","volume":"127","author":"Peng","year":"2023","journal-title":"J. Phys.\nChem. B"},{"key":"2026092209073859700_cit28","doi-asserted-by":"publisher","first-page":"9524","DOI":"10.1039\/D0SC02458A","article-title":"Graph neural\nnetwork based coarse-grained mapping prediction","volume":"11","author":"Li","year":"2020","journal-title":"Chem. Sci."},{"key":"2026092209073859700_cit29","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-019-0261-5","article-title":"Coarse-graining\nauto-encoders for\nmolecular dynamics","volume":"5","author":"Wang","year":"2019","journal-title":"npj Comput. Mater."},{"key":"2026092209073859700_cit30","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1038\/s41592-021-01098-3","article-title":"Martini 3: a general purpose force field for coarse-grained molecular\ndynamics","volume":"18","author":"Souza","year":"2021","journal-title":"Nat. Methods"},{"key":"2026092209073859700_cit31","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41343-1","article-title":"Machine learning coarse-grained potentials of protein\nthermodynamics","volume":"14","author":"Majewski","year":"2023","journal-title":"Nat. Commun."},{"key":"2026092209073859700_cit32","doi-asserted-by":"publisher","DOI":"10.1063\/1.4793313","article-title":"Minimizing memory as an objective\nfor coarse-graining","volume":"138","author":"Guttenberg","year":"2013","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit33","doi-asserted-by":"publisher","first-page":"23034","DOI":"10.1039\/C7CP03926C","article-title":"Evaluation of mapping schemes for systematic coarse\ngraining of higher alkanes","volume":"19","author":"Dallavalle","year":"2017","journal-title":"Phys. Chem. Chem.\nPhys."},{"key":"2026092209073859700_cit34","doi-asserted-by":"publisher","first-page":"8384","DOI":"10.1021\/acs.jctc.3c00637","article-title":"CGCompiler:\nautomated coarse-grained molecule parametrization via noise-resistant\nmixed-variable optimization","volume":"19","author":"Stroh","year":"2023","journal-title":"J. Chem. Theory\nComput."},{"key":"2026092209073859700_cit35","doi-asserted-by":"publisher","first-page":"5777","DOI":"10.1021\/acs.jctc.1c00322","article-title":"Automated coarse-grained mapping\nalgorithm for the Martini force field and benchmarks for membrane-water\npartitioning","volume":"17","author":"Potter","year":"2021","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit36","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1021\/acs.jcim.4c01001","article-title":"Coarsenconf:\nEquivariant coarsening with aggregated\nattention for molecular conformer generation","volume":"65","author":"Reidenbach","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026092209073859700_cit37","doi-asserted-by":"publisher","first-page":"6795","DOI":"10.1021\/acs.jctc.0c00676","article-title":"An information-theory-based\napproach for optimal model reduction of biomolecules","volume":"16","author":"Giulini","year":"2020","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit38","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1021\/acs.jpca.3c05630","article-title":"Reformulation of all\nONIOM-type molecular\nfragmentation approaches and many-body theories using graph-theory-based\nprojection operators: Applications to dynamics, molecular potential\nsurfaces, machine learning, and quantum computing","volume":"128","author":"Iyengar","year":"2024","journal-title":"J. Phys. Chem. A"},{"key":"2026092209073859700_cit39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.107.085504","article-title":"Graph Theory Meets Ab Initio Molecular\nDynamics: Atomic\nStructures and Transformations at the Nanoscale","volume":"107","author":"Pietrucci","year":"2011","journal-title":"Phys. Rev. Lett."},{"key":"2026092209073859700_cit40","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1021\/acs.jctc.8b00920","article-title":"Graph-based\napproach to systematic\nmolecular coarse-graining","volume":"15","author":"Webb","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit41","doi-asserted-by":"publisher","DOI":"10.1063\/1.5040114","article-title":"Encoding\nand selecting coarse-grain mapping operators\nwith hierarchical graphs","volume":"149","author":"Chakraborty","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit42","doi-asserted-by":"publisher","first-page":"7518","DOI":"10.1021\/acs.jctc.3c00638","article-title":"Top-down machine learning of coarse-grained\nprotein force fields","volume":"19","author":"Navarro","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit43","doi-asserted-by":"publisher","DOI":"10.1063\/5.0059915","article-title":"Machine learning\nimplicit solvation for molecular dynamics","volume":"155","author":"Chen","year":"2021","journal-title":"J.\nChem. Phys."},{"key":"2026092209073859700_cit44","unstructured":"Unke, O. T.; Sto\u0308hr, M.; Ganscha, S.; Unterthiner, T.; Maennel, H.; Kashubin, S.; Ahlin, D.; Gastegger, M.; Sandonas, L. M.; Tkatchenko, A.; et al.\n          Accurate machine\nlearned quantum-mechanical force fields for biomolecular simulations. 2022. arXiv:2205.08306. arXiv.org e-Printarchive. https:\/\/doi.org\/10.48550\/arXiv.2205.08306."},{"key":"2026092209073859700_cit45","doi-asserted-by":"publisher","first-page":"3678","DOI":"10.1021\/acs.jctc.9b00181","article-title":"PhysNet: A neural network\nfor predicting energies,\nforces, dipole moments, and partial charges","volume":"15","author":"Unke","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit46","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1146\/annurev-physchem-042018-052331","article-title":"Machine learning for\nmolecular simulation","volume":"71","author":"Noe\u0301","year":"2020","journal-title":"Annu. Rev. Phys. Chem."},{"key":"2026092209073859700_cit47","doi-asserted-by":"publisher","DOI":"10.1063\/5.0041022","article-title":"Multi-body effects\nin a coarse-grained protein force\nfield","volume":"154","author":"Wang","year":"2021","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit48","doi-asserted-by":"publisher","DOI":"10.1063\/1.2938860","article-title":"The multiscale coarse-graining\nmethod. I. A rigorous bridge between atomistic and coarse-grained\nmodels","volume":"128","author":"Noid","year":"2008","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit49","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1021\/acscentsci.8b00913","article-title":"Machine learning of coarse-grained molecular dynamics\nforce fields","volume":"5","author":"Wang","year":"2019","journal-title":"ACS Cent. Sci."},{"key":"2026092209073859700_cit50","doi-asserted-by":"publisher","DOI":"10.1063\/5.0026133","article-title":"Coarse graining molecular dynamics with graph\nneural networks","volume":"153","author":"Husic","year":"2020","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit51","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2023.102533","article-title":"Machine learned coarse-grained protein force-fields:\nAre we there yet?","volume":"79","author":"Durumeric","year":"2023","journal-title":"Curr. Opin. Struct. Biol."},{"key":"2026092209073859700_cit52","doi-asserted-by":"publisher","first-page":"1284","DOI":"10.1038\/s41557-025-01874-0","article-title":"Navigating protein landscapes with a machine-learned\ntransferable coarse-grained model","volume":"17","author":"Charron","year":"2023","journal-title":"Nat. Chem."},{"key":"2026092209073859700_cit53","doi-asserted-by":"publisher","DOI":"10.1063\/5.0124538","article-title":"Deep coarse-grained potentials via\nrelative entropy minimization","volume":"157","author":"Thaler","year":"2022","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit54","unstructured":"Wang, Y.; Csanyi, G.; Ortner, C.\n          Many-Body Coarse-Grained\nMolecular Dynamics with the Atomic Cluster Expansion. 2025. arXiv:2502.04661. arXiv.org e-Printarchive. https:\/\/doi.org\/10.48550\/arXiv.2502.04661."},{"key":"2026092209073859700_cit55","doi-asserted-by":"crossref","unstructured":"Batatia, I.; Kovacs, D. P.; Simm, G.; Ortner, C.; Csa\u0301nyi, G.\n          MACE: Higher\nOrder Equivariant\nMessage Passing Neural Networks for Fast and Accurate Force Fields; Advances in Neural Information Processing Systems 35 (NeurIPS 2022); NIPS, 2022; pp 11423\u201311436.","DOI":"10.52202\/068431-0830"},{"key":"2026092209073859700_cit56","doi-asserted-by":"crossref","unstructured":"Poltavsky, I.; Charkin-Gorbulin, A.; Puleva, M.; Cordeiro Fonseca, G.; Batatia, I.; Browning, N.; Chmiela, S.; Cui, M.; Frank, J.; Heinen, S.; et al.\n          Crash Testing Machine\nLearning Force Fields for Molecules, Materials, and Interfaces: Model\nAnalysis in the TEA Challenge 2023\n          ChemRxiv\n          2024.","DOI":"10.26434\/chemrxiv-2024-ctdm3"},{"key":"2026092209073859700_cit57","doi-asserted-by":"publisher","first-page":"6151","DOI":"10.1021\/acs.jctc.3c00702","article-title":"Two for one: Diffusion models and force fields for coarse-grained\nmolecular dynamics","volume":"19","author":"Arts","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit58","doi-asserted-by":"crossref","unstructured":"Plainer, M.; Wu, H.; Klein, L.; Gu\u0308nnemann, S.; Noe\u0301, F.\n          Consistent\nSampling and Simulation:\nMolecular Dynamics with Energy-Based Diffusion Models; Advances\nin Neural Information Processing Systems 38 (NeurIPS 2025); NIPS, 2025.","DOI":"10.52202\/085713-0826"},{"key":"2026092209073859700_cit59","doi-asserted-by":"publisher","DOI":"10.1063\/5.0287366","article-title":"Operator forces for coarse-grained molecular dynamics","volume":"163","author":"Klein","year":"2025","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit60","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-70818-0","article-title":"Learning data efficient\ncoarse-grained molecular dynamics from forces and noise","volume":"17","author":"Durumeric","year":"2024","journal-title":"Nat. Commun."},{"key":"2026092209073859700_cit61","doi-asserted-by":"publisher","DOI":"10.1063\/1.2038787","article-title":"Multiscale coarse\ngraining of liquid-state systems","volume":"123","author":"Izvekov","year":"2005","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit62","doi-asserted-by":"publisher","DOI":"10.1063\/1.4917454","article-title":"Dynamic force matching:\nA method for constructing dynamical coarse-grained models with realistic\ntime dependence","volume":"142","author":"Davtyan","year":"2015","journal-title":"J. Chem. Phys."},{"key":"2026092209073859700_cit63","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1002\/cpa.20210","article-title":"Projection\nof diffusions on submanifolds:\nApplication to mean force computation","volume":"61","author":"Ciccotti","year":"2008","journal-title":"Commun.\nPure Appl. Math."},{"key":"2026092209073859700_cit64","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":"2026092209073859700_cit65","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.5c00272","article-title":"Transferability\nof Data Sets between Machine-Learned Interatomic Potential Algorithms","volume":"21","author":"Niblett","year":"2025","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit66","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1021\/acs.jctc.3c00710","article-title":"Transferable\nmachine learning interatomic potential for bond dissociation energy\nprediction of drug-like molecules","volume":"20","author":"Gelz\u030cinyte","year":"2024","journal-title":"J. Chem.\nTheory Comput."},{"key":"2026092209073859700_cit67","unstructured":"Kumar, M.; Sharma, A.; Saxena, S.; Kumar, S.\n          Featured Graph Coarsening\nwith Similarity\nGuarantees; Proceedings of the 40th International Conference\non Machine Learning; PMLR, 2023."},{"key":"2026092209073859700_cit68","first-page":"1","article-title":"A Unified\nFramework for Optimization-Based\nGraph Coarsening","volume":"24","author":"Kumar","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"2026092209073859700_cit69","unstructured":"Kumar, M.; Halder, S.; Kane, A.; Gupta, R.; Kumar, S.\n          Optimization Framework for Semi-supervised\nAttributed Graph\nCoarsening; Proceedings of the Fortieth Conference on Uncertainty\nin Artificial Intelligence; Uncertainty in Artificial\nIntelligence, 2024; pp 2064\u20132075."},{"key":"2026092209073859700_cit70","doi-asserted-by":"crossref","unstructured":"Halder, S.; Kumar, M.; Kumar, S.; et al.\n          Multi-Component Coarsened Graph\nLearning for Scaling Graph Machine Learning; Companion Proceedings\nof the ACM on Web Conference 2025; ACM: New York, NY, USA, 2025; pp 1001\u20131004.","DOI":"10.1145\/3701716.3715522"},{"key":"2026092209073859700_cit71","unstructured":"Jin, Y.; Loukas, A.; JaJa, J.\n          Graph Coarsening with Preserved Spectral\nProperties; Proceedings of the Twenty Third International\nConference on Artificial Intelligence and Statistics; PMLR, 2020; pp 4452\u20134462."},{"key":"2026092209073859700_cit72","first-page":"1","article-title":"Graph reduction\nwith spectral and cut guarantees","volume":"20","author":"Loukas","year":"2019","journal-title":"J. Machi.\nLearn. Res."},{"key":"2026092209073859700_cit73","doi-asserted-by":"publisher","first-page":"11398","DOI":"10.1021\/bi8007559","article-title":"Variations\nin clique and community patterns in protein\nstructures during allosteric communication: investigation of dynamically\nequilibrated structures of methionyl tRNA synthetase complexes","volume":"47","author":"Ghosh","year":"2008","journal-title":"Biochemistry"},{"key":"2026092209073859700_cit74","doi-asserted-by":"publisher","first-page":"2783","DOI":"10.1021\/acs.jctc.5b00056","article-title":"Automated parametrization of the coarse-grained Martini\nforce field for small organic molecules","volume":"11","author":"Bereau","year":"2015","journal-title":"J.\nChem. Theory Comput."},{"key":"2026092209073859700_cit75","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1016\/j.cpc.2013.09.018","article-title":"PLUMED 2: New feathers for an old\nbird","volume":"185","author":"Tribello","year":"2014","journal-title":"Comput.\nPhys. Commun."},{"key":"2026092209073859700_cit76","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1038\/s41592-019-0506-8","article-title":"Promoting\ntransparency and reproducibility in enhanced molecular simulations","volume":"16","author":"The PLUMED consortium.","year":"2019","journal-title":"Nat. Methods"},{"key":"2026092209073859700_cit77","doi-asserted-by":"publisher","first-page":"3499","DOI":"10.1021\/acs.jctc.5b00356","article-title":"Improved\npeptide and protein torsional\nenergetics with the OPLS-AA force field","volume":"11","author":"Robertson","year":"2015","journal-title":"J.\nChem. Theory Comput."},{"key":"2026092209073859700_cit78","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-024-00956-x","article-title":"The Design Space of E(3)-Equivariant\nAtom-Centered\nInteratomic Potentials","volume":"7","author":"Batatia","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026092209073859700_cit79","unstructured":"Schoenholz, S. S.; Cubuk, E. D.; JAX, M. D.\n          A Framework\nfor Differentiable Physics; Advances in Neural Information\nProcessing Systems 33 (NeurIPS 2020); NIPS, 2020."},{"key":"2026092209073859700_cit80","doi-asserted-by":"publisher","first-page":"7550","DOI":"10.1021\/acs.jctc.5c00996","article-title":"chemtrain-deploy: A\nparallel and scalable framework for machine learning potentials in\nmillion-atom MD simulations","volume":"21","author":"Fuchs","year":"2025","journal-title":"J. Chem. Theory\nComput."},{"key":"2026092209073859700_cit81","doi-asserted-by":"publisher","first-page":"5179","DOI":"10.1021\/ja00124a002","article-title":"A second generation force field for the simulation\nof proteins, nucleic acids, and organic molecules","volume":"117","author":"Cornell","year":"1995","journal-title":"J. Am. Chem. Soc."},{"key":"2026092209073859700_cit82","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1002\/jcc.20035","article-title":"Development\nand testing of a general amber force field","volume":"25","author":"Wang","year":"2004","journal-title":"J. Comput. Chem."},{"key":"2026092209073859700_cit83","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1021\/acs.jctc.5c01712","article-title":"Enhanced Sampling for\nEfficient Learning of Coarse-Grained Machine Learning Potentials","volume":"22","author":"Chen","year":"2026","journal-title":"J. Chem. Theory Comput."},{"key":"2026092209073859700_cit84","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1021\/acs.jctc.5c01178","article-title":"Fast Parametrization\nof Martini3Models for Fragments and Small Molecules","volume":"22","author":"Szczuka","year":"2026","journal-title":"J. Chem. Theory Comput."}],"container-title":["Journal of Chemical Theory\nand Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jctc.6c00825","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jctcce\/article-pdf\/22\/18\/9655\/68463918\/acs.jctc.6c00825.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jctcce\/article-pdf\/22\/18\/9655\/68463918\/acs.jctc.6c00825.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T13:16:41Z","timestamp":1790083001000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jctcce\/article\/22\/18\/9655\/5427235\/Local-Variational-Graph-Coarsening-for-Machine"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":84,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9,9]]},"published-print":{"date-parts":[[2026,9,22]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jctc.6c00825","relation":{},"ISSN":["1549-9618","1549-9626"],"issn-type":[{"value":"1549-9618","type":"print"},{"value":"1549-9626","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]}}}