{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T06:24:07Z","timestamp":1775715847961,"version":"3.50.1"},"reference-count":42,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T00:00:00Z","timestamp":1670889600000},"content-version":"vor","delay-in-days":12,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T00:00:00Z","timestamp":1670889600000},"content-version":"tdm","delay-in-days":12,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100009708","name":"Novo Nordisk Fonden","doi-asserted-by":"crossref","award":["NNF19OC0057822"],"award-info":[{"award-number":["NNF19OC0057822"]}],"id":[{"id":"10.13039\/501100009708","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Quantum mechanical methods like density functional theory (DFT) are used with great success alongside efficient search algorithms for studying kinetics of reactive systems. However, DFT is prohibitively expensive for large scale exploration. Machine learning (ML) models have turned out to be excellent emulators of small molecule DFT calculations and could possibly replace DFT in such tasks. For kinetics, success relies primarily on the models\u2019 capability to accurately predict the potential energy surface around transition-states and minimal energy paths. Previously this has not been possible due to scarcity of relevant data in the literature. In this paper we train equivariant graph neural network-based models on data from 10 000 elementary reactions from the recently published Transition1x dataset. We apply the models as potentials for the nudged elastic band algorithm and achieve a mean average error of 0.23\u2009eV and root mean squared error of 0.52\u2009eV on barrier energies on unseen reactions. We compare the results against equivalent models trained on QM9x and ANI1x. We also compare with and outperform Density Functional based Tight Binding on both accuracy and required computational resources. The implication is that ML models are now at a level where they can be applied to studying chemical reaction kinetics given a sufficient amount of data relevant to this task.<\/jats:p>","DOI":"10.1088\/2632-2153\/aca23e","type":"journal-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T22:42:55Z","timestamp":1668206575000},"page":"045022","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["NeuralNEB\u2014neural networks can find reaction paths fast"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7649-843X","authenticated-orcid":true,"given":"Mathias","family":"Schreiner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3198-5116","authenticated-orcid":false,"given":"Arghya","family":"Bhowmik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1484-0284","authenticated-orcid":true,"given":"Tejs","family":"Vegge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4404-7276","authenticated-orcid":false,"given":"Peter Bj\u00f8rn","family":"J\u00f8rgensen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1966-3205","authenticated-orcid":false,"given":"Ole","family":"Winther","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2022,12,13]]},"reference":[{"key":"mlstaca23ebib1","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.neunet.2020.06.006","article-title":"A gentle introduction to deep learning for graphs","volume":"129","author":"Bacciu","year":"2019","journal-title":"Neural Netw."},{"key":"mlstaca23ebib2","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: a review of methods and applications","volume":"1","author":"Zhou","year":"2021","journal-title":"AI Open"},{"key":"mlstaca23ebib3","doi-asserted-by":"publisher","first-page":"5255","DOI":"10.1021\/acs.jctc.7b00577","article-title":"Prediction errors of molecular machine learning models lower than hybrid dft error","volume":"13","author":"Faber","year":"2017","journal-title":"J. Chem. Theory Comput."},{"key":"mlstaca23ebib4","doi-asserted-by":"publisher","DOI":"10.1063\/5.0047760","article-title":"Perspective on integrating machine learning into computational chemistry and materials science","volume":"154","author":"Westermayr","year":"2021","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib5","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab7d30","article-title":"Machine learning for the solution of the schr\u00f6dinger equation","volume":"1","author":"Campbell","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstaca23ebib6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.146401","article-title":"Generalized neural-network representation of high-dimensional potential-energy surfaces","volume":"98","author":"Behler","year":"2007","journal-title":"Phys. Rev. Lett."},{"key":"mlstaca23ebib7","doi-asserted-by":"publisher","first-page":"9873","DOI":"10.1021\/acs.chemrev.0c00749","article-title":"Machine learning for electronically excited states of molecules","volume":"121","author":"Westermayr","year":"2021","journal-title":"Chem. Rev."},{"key":"mlstaca23ebib8","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1021\/ar500432k","article-title":"The chemical space project","volume":"48","author":"Louis Reymond","year":"2015","journal-title":"Acc. Chem. Res."},{"key":"mlstaca23ebib9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.146401","article-title":"Generalized neural-network representation of high-dimensional potential-energy surfaces","volume":"98","author":"Behler","year":"2007b","journal-title":"Phys. Rev. Lett."},{"key":"mlstaca23ebib10","doi-asserted-by":"publisher","first-page":"1032","DOI":"10.1002\/qua.24890","article-title":"Constructing high-dimensional neural network potentials: A tutorial review","volume":"115","author":"Behler","year":"2015","journal-title":"Int. J. Quantum Chem."},{"key":"mlstaca23ebib11","doi-asserted-by":"publisher","first-page":"5255","DOI":"10.1021\/acs.jctc.7b00577","article-title":"Prediction errors of molecular machine learning models lower than hybrid dft error","volume":"13","author":"Faber","year":"2017","journal-title":"J. Chem. Theory Comput."},{"key":"mlstaca23ebib12","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume":"PMLR 70","author":"Gilmer","year":"2017"},{"key":"mlstaca23ebib13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.127.166001","article-title":"Atomic structure optimization with machine-learning enabled interpolation between chemical elements","volume":"127","author":"Kaappa","year":"2021","journal-title":"Phys. Rev. Lett."},{"key":"mlstaca23ebib14","doi-asserted-by":"publisher","DOI":"10.1002\/adts.201900210","article-title":"Interatomic potential model development: finite-temperature dynamics machine learning","volume":"3","author":"Wang","year":"2020","journal-title":"Adv. Theory Simul."},{"key":"mlstaca23ebib15","doi-asserted-by":"publisher","DOI":"10.1063\/1.2768948","article-title":"Theoretical investigation of the dissociation dynamics of vibrationally excited vinyl bromide on an ab initio potential-energy surface obtained using modified novelty sampling and feedforward neural networks. II. Numerical application of the method","volume":"127","author":"Malshe","year":"2007","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib16","doi-asserted-by":"publisher","DOI":"10.1063\/1.5063613","article-title":"Rate coefficients of the h+h2o2\u2192h2+ho2 reaction on an accurate fundamental invariant-neural network potential energy surface","volume":"149","author":"Lu","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib17","doi-asserted-by":"publisher","first-page":"10944","DOI":"10.1039\/D1SC01825F","article-title":"A transferable active-learning strategy for reactive molecular force fields","volume":"12","author":"Young","year":"2021","journal-title":"Chem. Sci."},{"key":"mlstaca23ebib18","doi-asserted-by":"publisher","first-page":"10187","DOI":"10.1021\/acs.chemrev.0c00665","article-title":"Neural network potential energy surfaces for small molecules and reactions","volume":"121","author":"Manzhos","year":"2020","journal-title":"Chem. Rev."},{"key":"mlstaca23ebib19","doi-asserted-by":"publisher","DOI":"10.1063\/1.4986787","article-title":"Nudged elastic band calculations accelerated with gaussian process regression","volume":"147","author":"Pekka Koistinen","year":"2017","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib20","doi-asserted-by":"publisher","DOI":"10.1063\/1.2841941","article-title":"Optimization methods for finding minimum energy paths","volume":"128","author":"Sheppard","year":"2008","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib21","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab6ac4","article-title":"Machine learning the computational cost of quantum chemistry","volume":"1","author":"Heinen","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstaca23ebib22","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1038\/s41570-020-0189-9","article-title":"Exploring chemical compound space with quantum-based machine learning","volume":"4","author":"von Lilienfeld","year":"2020","journal-title":"Nat. Rev. Chem."},{"key":"mlstaca23ebib23","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.193","article-title":"Ani-1, a data set of 20 million calculated off-equilibrium conformations for organic molecules","volume":"4","author":"Smith","year":"2017","journal-title":"Sci. Data"},{"key":"mlstaca23ebib24","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1038\/s41597-020-0473-z","article-title":"The ani-1ccx and ani-1x data sets, coupled-cluster and density functional theory properties for molecules","volume":"7","author":"Smith","year":"2020","journal-title":"Sci. Data"},{"key":"mlstaca23ebib25","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1021\/ci600423u","article-title":"Virtual exploration of the chemical universe up to 11 atoms of c, n, o, f: Assembly of 26.4 million structures (110.9 million stereoisomers) and analysis for new ring systems, stereochemistry, physicochemical properties, compound classes and drug discovery","volume":"47","author":"Fink","year":"2007","journal-title":"J. Chem. Inf. Model."},{"key":"mlstaca23ebib26","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1002\/anie.200462457","article-title":"Virtual exploration of the small-molecule chemical universe below 160 daltons","volume":"44","author":"Fink","year":"2005","journal-title":"Angew. Chem., Int. Ed."},{"key":"mlstaca23ebib27","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1002\/wcms.1094","article-title":"Density-functional tight binding\u2014an approximate density-functional theory method","volume":"2","author":"Seifert","year":"2012","journal-title":"Wiley Interdiscip. Rev.-Comput. Mol. Sci."},{"key":"mlstaca23ebib28","doi-asserted-by":"crossref","DOI":"10.1038\/s41597-022-01870-w","article-title":"Transition1x \u2013 a Dataset for Building Generalizable Reactive Machine Learning Potentials","author":"Schreiner","year":"2022"},{"key":"mlstaca23ebib29","doi-asserted-by":"publisher","first-page":"9901","DOI":"10.1063\/1.1329672","article-title":"A climbing image nudged elastic band method for finding saddle points and minimum energy paths","volume":"113","author":"Henkelman","year":"2000","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib30","doi-asserted-by":"publisher","DOI":"10.1063\/1.4878664","article-title":"Improved initial guess for minimum energy path calculations","volume":"140","author":"Smidstrup","year":"2014","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib31","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1093\/imamat\/6.1.76","article-title":"The convergence of a class of double-rank minimization algorithms 1. General considerations","volume":"6","author":"Broyden","year":"1970","journal-title":"IMA J. Appl. Math."},{"key":"mlstaca23ebib32","doi-asserted-by":"publisher","DOI":"10.1063\/1.5064465","article-title":"A preconditioning scheme for minimum energy path finding methods","volume":"150","author":"Makri","year":"2019","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib33","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.22","article-title":"Quantum chemistry structures and properties of 134 kilo molecules","volume":"1","author":"Ramakrishnan","year":"2014","journal-title":"Sci. Data"},{"key":"mlstaca23ebib34","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1063\/1.1674902","article-title":"Self-consistent molecular-orbital methods. ix. an extended gaussian-type basis for molecular-orbital studies of organic molecules","volume":"54","author":"Ditchfield","year":"2003","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib35","doi-asserted-by":"publisher","DOI":"10.1063\/1.2834918","article-title":"Systematic optimization of long-range corrected hybrid density functionals","volume":"128","author":"Da Chai","year":"2008","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib36","doi-asserted-by":"publisher","first-page":"5023","DOI":"10.1021\/cr1000173","article-title":"Stabilization and structure calculations for noncovalent interactions in extended molecular systems based on wave function and density functional theories","volume":"110","author":"Riley","year":"2010","journal-title":"Chem. Rev."},{"key":"mlstaca23ebib37","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1021\/ct100469b","article-title":"Assessment of the performance of dft and dft-d methods for describing distance dependence of hydrogen-bonded interactions","volume":"7","author":"Thanthiriwatte","year":"2011","journal-title":"J. Chem. Theory Comput."},{"key":"mlstaca23ebib38","doi-asserted-by":"publisher","DOI":"10.1063\/1.5023802","article-title":"Less is more: sampling chemical space with active learning","volume":"148","author":"Smith","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstaca23ebib39","first-page":"9377","article-title":"Equivariant message passing for the prediction of tensorial properties and molecular spectra","volume":"PMLR 139","author":"Sch\u00fctt","year":"2021"},{"key":"mlstaca23ebib40","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstaca23ebib41","article-title":"Performance analysis of out-of-distribution detection on various trained neural networks","author":"Henriksson","year":"2021"},{"key":"mlstaca23ebib42","first-page":"12427","article-title":"Understanding failures in out-of-distribution detection with deep generative models","volume":"PMLR 139","author":"Zhang","year":"2021"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca23e","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca23e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca23e","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca23e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca23e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca23e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca23e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca23e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T21:59:06Z","timestamp":1678571946000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca23e"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":42,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,12,13]]},"published-print":{"date-parts":[[2022,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/aca23e","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]},"assertion":[{"value":"NeuralNEB\u2014neural networks can find reaction paths fast","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-06-29","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-11-11","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-12-13","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}