{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:26:29Z","timestamp":1792787189181,"version":"4.5.0"},"reference-count":75,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"41","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC-1818253"],"award-info":[{"award-number":["OAC-1818253"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-21-1-2476"],"award-info":[{"award-number":["N00014-21-1-2476"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Science Grid","award":["1148698"],"award-info":[{"award-number":["1148698"]}],"id":[{"id":"https:\/\/ror.org\/01ejwte55","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Adv."],"published-print":{"date-parts":[[2026,10,9]]},"abstract":"<jats:p>\n                    Mechanistic modeling of chemical transformations offers a compelling basis for understanding reactivity and allows for prediction of reaction outcomes before attempting experiments. Despite progress in machine-learned interatomic potentials (MLIPs), we demonstrate that available models lack the accuracy for diverse reaction modeling. With this motivation, we developed a general MLIP for mechanistic modeling of closed-shell carbon, hydrogen, nitrogen, and oxygen reactions, AIMNet2-rxn, using a dataset of \u223c4.7 \u00d7 10\n                    <jats:sup>6<\/jats:sup>\n                    range-separated density functional theory calculations. AIMNet2-rxn enables reaction modeling \u223c10\n                    <jats:sup>6<\/jats:sup>\n                    faster than the reference quantum mechanical (QM) methods while substantially outperforming graph-based ML, reaffirming the value using three-dimensional chemical information for training. On a test suite of well-known reaction mechanisms\u2014such as amide formation, proton transfers, and pericyclics\u2014AIMNet2-rxn yields 1 to 2 kilocalories per mole accuracy across reaction coordinates without retraining or system-specific fine-tuning. To exploit graphics processing unit parallelism and AIMNet2-rxn efficiency, we introduce a batched nudged elastic band procedure that readily achieves minimum energy pathway search on a millions-of-reactions scale. To demonstrate complex reaction characterization, the thermodynamics of an 11-step pathway producing hydroxymethylfurfural, the experimentally observed major product of glucose pyrolysis, is evaluated. Overall, the accuracy and efficiency afforded by AIMNet2-rxn create opportunities in high-throughput reaction discovery and deep reaction network analysis that would be infeasible with QM methods.\n                  <\/jats:p>","DOI":"10.1126\/sciadv.aea1557","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:58:33Z","timestamp":1791395913000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":0,"title":["AIMNet2-rxn: A machine-learned potential for generalized reaction modeling on a millions-of-pathways scale"],"prefix":"10.1126","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4458-7080","authenticated-orcid":true,"given":"Dylan M.","family":"Anstine","sequence":"first","affiliation":[{"name":"Department of Chemistry, Carnegie Mellon University, Pittsburgh, PA 15213, USA."},{"name":"Department of Chemical Engineering and Materials Science, Michigan State University, East Lansing, MI 48824, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3228-8160","authenticated-orcid":true,"given":"Qiyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, Purdue University, West Lafayette, IN 47907, USA."},{"name":"Deep Principle Inc., HangZhou, Zhejiang, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7285-9389","authenticated-orcid":true,"given":"Roman","family":"Zubatyuk","sequence":"additional","affiliation":[{"name":"Department of Chemistry, Carnegie Mellon University, Pittsburgh, PA 15213, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5174-1875","authenticated-orcid":true,"given":"Shuhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Chemistry, Carnegie Mellon University, Pittsburgh, PA 15213, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Veerupaksh","family":"Singla","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, University of Notre Dame, Notre Dame, IN 46556, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1157-9471","authenticated-orcid":true,"given":"Filipp","family":"Nikitin","sequence":"additional","affiliation":[{"name":"Department of Chemistry, Carnegie Mellon University, Pittsburgh, PA 15213, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7039-4039","authenticated-orcid":true,"given":"Brett M.","family":"Savoie","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, University of Notre Dame, Notre Dame, IN 46556, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7581-8497","authenticated-orcid":true,"given":"Olexandr","family":"Isayev","sequence":"additional","affiliation":[{"name":"Department of Chemistry, Carnegie Mellon University, Pittsburgh, PA 15213, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.5b01409"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-021-00022-5"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41570-024-00645-8"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.8b02266"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.progpolymsci.2021.101386"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.progpolymsci.2009.10.008"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41529-022-00277-7"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1002\/cssc.202100652"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrev.2c00798"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1039\/C5OB01892G"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1002\/anie.202312078"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1021\/acscatal.3c03921"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1021\/ar00072a001"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.accounts.6b00068"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aap9112"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.accounts.1c00119"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03213-y"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.accounts.0c00785"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.oprd.9b00140"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrev.1c00332"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adj0461"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax1566"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2442-2"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","unstructured":"J. L. Rapp D. M. Anstine F. Gusev F. Nikitin K. H. Yun M. A. Borden V. Bhat O. Isayev F. A. Leibfarth Design of tough 3D printable elastomers with human-in-the-loop reinforcement learning. chemrxiv-2025-w1563 [Preprint] (2025). https:\/\/doi.org\/10.26434\/chemrxiv-2025-w1563.","DOI":"10.26434\/chemrxiv-2025-w1563"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-024-01497-y"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41557-023-01427-3"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-023-00549-5"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2322040121"},{"key":"e_1_3_2_30_2","unstructured":"J. Gasteiger F. Becker S. G\u00fcnnemann GemNet: Universal directional graph neural networks for molecules. arXiv:2106.08903 [physics.comp-ph] (2024)."},{"key":"e_1_3_2_31_2","first-page":"021036","article-title":"Graph atomic cluster expansion for semilocal interactions beyond equivariant message passing","volume":"14","author":"Bochkarev A.","year":"2024","unstructured":"A. Bochkarev, Y. Lysogorskiy, R. Drautz, Graph atomic cluster expansion for semilocal interactions beyond equivariant message passing. Phys. Rev. \u00d7 14, 021036 (2024).","journal-title":"Phys. Rev. \u00d7"},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"G. Simeon G. Fabritiis TensorNet: Cartesian tensor representations for efficient learning of molecular potentials. arXiv:2306.06482 [cs.LG] (2023).","DOI":"10.52202\/075280-1623"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.5c09558"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29939-5"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36329-y"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0155600"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30687-9"},{"key":"e_1_3_2_38_2","unstructured":"D. P. Kov\u00e1cs J. H. Moore N. J. Browning I. Batatia J. T. Horton Y. Pu V. Kapil W. C. Witt I.-B. Magd\u0103u D. J. Cole G. Cs\u00e1nyi MACE-OFF23: Transferable machine learning force fields for organic molecules. arXiv:2312.15211 [physics.chem-ph] (2023)."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1039\/D4SC08572H"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aca23e"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-52481-5"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-0460-4"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01870-w"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.4952647"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02043-z"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.2c00395"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02690-2"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c01250"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1039\/D3SC02408C"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1354"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.1329672"},{"key":"e_1_3_2_52_2","doi-asserted-by":"crossref","unstructured":"H. J\u00f3nsson G. Mills K. W. Jacobsen \u201cNudged elastic band method for finding minimum energy paths of transitions \u201d in Classical and Quantum Dynamics in Condensed Phase Simulations (World Scientific 1998) p. 385\u2013404.","DOI":"10.1142\/9789812839664_0016"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.5012601"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.3c01111"},{"key":"e_1_3_2_55_2","doi-asserted-by":"crossref","unstructured":"M. Feinberg Foundations of Chemical Reaction Network Theory (Springer 2019).","DOI":"10.1007\/978-3-030-03858-8"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-022-00369-z"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10311-021-01273-0"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.4c01401"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpca.2c06778"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0031215"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.5128375"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-021-00101-3"},{"key":"e_1_3_2_63_2","unstructured":"A. R. Todd Perspectives in Organic Chemistry (Cambridge Univ. Press 1956)."},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.accounts.8b00087"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.4878664"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.8b01176"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1021\/ja00051a040"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.81"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1080\/00268976.2017.1333644"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.10318"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0058766"},{"key":"e_1_3_2_72_2","unstructured":"A. Paszke S. Gross F. Massa A. Lerer J. Bradbury G. Chanan T. Killeen Z. Lin N. Gimelshein L. Antiga A. Desmaison A. K\u00f6pf E. Yang Z. De Vito M. Raison A. Tejani S. Chilamkurthy B. Steiner L. Fang J. Bai S. Chintala Pytorch: An imperative style high-performance deep learning library. arXiv:1912.01703 [cs.LG] (2019)."},{"key":"e_1_3_2_73_2","unstructured":"L. Liu H. Jiang P. He W. Chen X. Liu J. Gao Han J On the variance of the adaptive learning rate and beyond. arXiv:1908.03265 [cs.LG] (2019)."},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1002\/qua.26390"},{"key":"e_1_3_2_75_2","unstructured":"M. J. Frisch G. W. Trucks H. B. Schlegel G. E. Scuseria M. A. Robb J. R. Cheeseman G. Scalmani V. Barone G. A. Petersson H. Nakatsuji X. Li M. Caricato A. V. Marenich J. Bloino B. G. Janesko R. Gomperts B. Mennucci H. P. Hratchian J. V. Ortiz A. F. Izmaylov J. L. Sonnenberg D. Williams-Young F. Ding F. Lipparini F. Egidi J. Goings B. Peng A. Petrone T. Henderson D. Ranasinghe V. G. Zakrzewski J. Gao N. Rega G. Zheng W. Liang M. Hada M. Ehara K. Toyota R. Fukuda J. Hasegawa M. Ishida T. Nakajima Y. Honda O. Kitao H. Nakai T. Vreven K. Throssell J. A. Montgomery Jr. J. E. Peralta F. Ogliaro M. J. Bearpark J. J. Heyd E. N. Brothers K. N. Kudin V. N. Staroverov T. A. Keith R. Kobayashi J. Normand K. Raghavachari A. P. Rendell J. C. Burant S. S. Iyengar J. Tomasi M. Cossi J. M. Millam M. Klene C. Adamo R. Cammi J. W. Ochterski R. L. Martin K. Morokuma O. Farkas J. B. Foresman D. J. Fox Gaussian 16 (Gaussian Inc. Wallingford CT 2016)."},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.1323224"}],"container-title":["Science Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/sciadv.aea1557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T18:00:30Z","timestamp":1791396030000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/sciadv.aea1557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,9]]},"references-count":75,"journal-issue":{"issue":"41","published-print":{"date-parts":[[2026,10,9]]}},"alternative-id":["10.1126\/sciadv.aea1557"],"URL":"https:\/\/doi.org\/10.1126\/sciadv.aea1557","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2025-hpdmg","asserted-by":"object"}]},"ISSN":["2375-2548"],"issn-type":[{"value":"2375-2548","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,9]]},"assertion":[{"value":"2025-06-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eaea1557"}}