{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T11:52:39Z","timestamp":1774525959317,"version":"3.50.1"},"reference-count":135,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"crossref","award":["BIFOLD24B"],"award-info":[{"award-number":["BIFOLD24B"]}],"id":[{"id":"10.13039\/501100002347","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":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Molecular relaxation, finding the equilibrium state of a non-equilibrium structure, is an essential component of computational chemistry to understand reactivity. Classical force field (FF) methods often rely on insufficient local energy minimization, while neural network FF models require large labeled datasets encompassing both equilibrium and non-equilibrium structures. As a remedy, we propose MoreRed, molecular relaxation by reverse diffusion, a conceptually novel and purely statistical approach where non-equilibrium structures are treated as noisy instances of their corresponding equilibrium states. To enable the denoising of arbitrarily noisy inputs via a generative diffusion model, we further introduce a novel diffusion time step predictor. Notably, MoreRed learns a simpler pseudo potential energy surface (PES) instead of the complex physical PES. It is trained on a significantly smaller, and thus computationally cheaper, dataset consisting of solely unlabeled equilibrium structures, avoiding the computation of non-equilibrium structures altogether. We compare MoreRed to classical FFs, equivariant neural network FFs trained on a large dataset of equilibrium and non-equilibrium data, as well as a semi-empirical tight-binding model. To assess this quantitatively, we evaluate the root-mean-square deviation between the found equilibrium structures and the reference equilibrium structures as well as their energies.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad652c","type":"journal-article","created":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T22:58:50Z","timestamp":1721343530000},"page":"035038","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Molecular relaxation by reverse diffusion with time step prediction"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5702-0021","authenticated-orcid":true,"given":"Khaled","family":"Kahouli","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8399-2193","authenticated-orcid":true,"given":"Stefaan Simon Pierre","family":"Hessmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3861-7685","authenticated-orcid":false,"given":"Klaus-Robert","family":"M\u00fcller","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3970-4569","authenticated-orcid":false,"given":"Shinichi","family":"Nakajima","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6257-1923","authenticated-orcid":false,"given":"Stefan","family":"Gugler","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9149-7424","authenticated-orcid":true,"given":"Niklas Wolf Andreas","family":"Gebauer","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,8,6]]},"reference":[{"key":"mlstad652cbib1","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1002\/wcms.34","article-title":"Geometry optimization","volume":"1","author":"Schlegel","year":"2011","journal-title":"Wiley Interdiscip. Rev.-Comput. Mol. Sci."},{"key":"mlstad652cbib2","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1021\/ie00028a003","article-title":"Computer generated pyrolysis modeling: on-the-fly generation of species, reactions and rates","volume":"33","author":"Broadbelt","year":"1994","journal-title":"Ind. Eng. Chem. Res."},{"key":"mlstad652cbib3","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/0098-1354(94)00009-D","article-title":"Computer generated reaction modelling: decomposition and encoding algorithms for determining species uniqueness","volume":"20","author":"Broadbelt","year":"1996","journal-title":"Comput. Chem. Eng."},{"key":"mlstad652cbib4","doi-asserted-by":"publisher","first-page":"2112","DOI":"10.1002\/aic.10599","article-title":"Lexicography of kinetic modeling of complex reaction networks","volume":"51","author":"Broadbelt","year":"2005","journal-title":"AIChE J."},{"key":"mlstad652cbib5","doi-asserted-by":"publisher","first-page":"7263","DOI":"10.1002\/anie.200502272","article-title":"Architecture and evolution of organic chemistry","volume":"44","author":"Fialkowski","year":"2005","journal-title":"Angew. Chem., Int. Ed."},{"key":"mlstad652cbib6","doi-asserted-by":"publisher","first-page":"7922","DOI":"10.1002\/anie.201202155","article-title":"Rewiring chemistry: algorithmic discovery and experimental validation of one-pot reactions in the network of organic chemistry","volume":"51","author":"Gothard","year":"2012","journal-title":"Angew. Chem., Int. Ed."},{"key":"mlstad652cbib7","doi-asserted-by":"publisher","first-page":"7928","DOI":"10.1002\/anie.201202209","article-title":"Parallel optimization of synthetic pathways within the network of organic chemistry","volume":"51","author":"Kowalik","year":"2012","journal-title":"Angew. Chem., Int. Ed."},{"key":"mlstad652cbib8","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1021\/acs.accounts.6b00023","article-title":"Computational catalysis using the artificial force induced reaction method","volume":"49","author":"Sameera","year":"2016","journal-title":"Acc. Chem. Res."},{"key":"mlstad652cbib9","doi-asserted-by":"publisher","first-page":"e1354","DOI":"10.1002\/wcms.1354","article-title":"Methods for exploring reaction space in molecular systems","volume":"8","author":"Dewyer","year":"2017","journal-title":"Wiley Interdiscip. Rev.-Comput. Mol. Sci."},{"key":"mlstad652cbib10","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1002\/anie.201005336","article-title":"Finding reaction pathways for multicomponent reactions: the Passerini reaction is a four-component reaction","volume":"50","author":"Maeda","year":"2010","journal-title":"Angew. Chem., Int. Ed."},{"key":"mlstad652cbib11","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.1021\/acscentsci.8b00507","article-title":"Potentialnet for molecular property prediction","volume":"4","author":"Feinberg","year":"2018","journal-title":"ACS Cent. Sci."},{"key":"mlstad652cbib12","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1021\/acs.jpca.8b10007","article-title":"Exploration of reaction pathways and chemical transformation networks","volume":"123","author":"Simm","year":"2018","journal-title":"J. Phys. Chem. A"},{"key":"mlstad652cbib13","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1146\/annurev-physchem-071119-040123","article-title":"The exploration of chemical reaction networks","volume":"71","author":"Unsleber","year":"2020","journal-title":"Annu. Rev. Phys. Chem."},{"key":"mlstad652cbib14","article-title":"qcscine\/utilities: release 5.0.0","author":"Baiardi","year":"2022"},{"key":"mlstad652cbib15","doi-asserted-by":"publisher","first-page":"2465","DOI":"10.1002\/aic.690441114","article-title":"Modeling the partial oxidation of methane in a short-contact-time reactor","volume":"44","author":"Deutschmann","year":"1998","journal-title":"AIChE J."},{"key":"mlstad652cbib16","doi-asserted-by":"publisher","first-page":"A2427","DOI":"10.1149\/1.2116607","article-title":"Modeling elementary heterogeneous chemistry and electrochemistry in solid-oxide fuel cells","volume":"152","author":"Zhu","year":"2005","journal-title":"J. Electrochem. Soc."},{"key":"mlstad652cbib17","doi-asserted-by":"publisher","first-page":"227","DOI":"10.3390\/catal9030227","article-title":"An improved computer-aided method for developing catalytic reaction mechanisms","volume":"9","author":"Gossler","year":"2019","journal-title":"Catalysts"},{"key":"mlstad652cbib18","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms14621","article-title":"To address surface reaction network complexity using scaling relations machine learning and dft calculations","volume":"8","author":"Ulissi","year":"2017","journal-title":"Nat. Commun."},{"key":"mlstad652cbib19","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1007\/s11244-021-01543-9","article-title":"Autonomous reaction network exploration in homogeneous and heterogeneous catalysis","volume":"65","author":"Steiner","year":"2022","journal-title":"Top. Catal."},{"key":"mlstad652cbib20","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1016\/j.proci.2006.08.025","article-title":"Structure of a spatially developing turbulent lean methane\u2013air Bunsen flame","volume":"31","author":"Sankaran","year":"2007","journal-title":"Proc. Combust. Inst."},{"key":"mlstad652cbib21","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.combustflame.2010.06.002","article-title":"Comprehensive reaction mechanism for n-butanol pyrolysis and combustion","volume":"158","author":"Harper","year":"2011","journal-title":"Combust. Flame"},{"key":"mlstad652cbib22","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1146\/annurev-chembioeng-062011-081108","article-title":"Unraveling reaction pathways and specifying reaction kinetics for complex systems","volume":"3","author":"Vinu","year":"2012","journal-title":"Annu. Rev. Chem. Biomol. Eng."},{"key":"mlstad652cbib23","doi-asserted-by":"publisher","first-page":"4063","DOI":"10.1021\/cr500488p","article-title":"Theoretical chemical kinetics in tropospheric chemistry: methodologies and applications","volume":"115","author":"Vereecken","year":"2015","journal-title":"Chem. Rev."},{"key":"mlstad652cbib24","doi-asserted-by":"publisher","first-page":"3297","DOI":"10.1021\/acs.jctc.7b00235","article-title":"Reliable estimation of prediction uncertainty for physicochemical property models","volume":"13","author":"Proppe","year":"2017","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad652cbib25","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1021\/acs.jctc.8b00310","article-title":"Mechanism deduction from noisy chemical reaction networks","volume":"15","author":"Proppe","year":"2018","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad652cbib26","doi-asserted-by":"publisher","first-page":"4248","DOI":"10.1021\/acs.jctc.5b00407","article-title":"Automated discovery of elementary chemical reaction steps using freezing string and Berny optimization methods","volume":"11","author":"Suleimanov","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad652cbib27","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1016\/j.cpc.2016.02.013","article-title":"Reaction mechanism generator: automatic construction of chemical kinetic mechanisms","volume":"203","author":"Gao","year":"2016","journal-title":"Comput. Phys. Commun."},{"key":"mlstad652cbib28","doi-asserted-by":"publisher","first-page":"3731","DOI":"10.1021\/jp9637690","article-title":"Rate-based construction of kinetic models for complex systems","volume":"101","author":"Susnow","year":"1997","journal-title":"J. Phys. Chem. A"},{"key":"mlstad652cbib29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.compchemeng.2017.01.003","article-title":"On-the-fly pruning for rate-based reaction mechanism generation","volume":"100","author":"Han","year":"2017","journal-title":"Comput. Chem. Eng."},{"key":"mlstad652cbib30","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-019-0341-z","article-title":"Exploring the GDB-13 chemical space using deep generative models","volume":"11","author":"Ar\u00fas-Pous","year":"2019","journal-title":"J. Cheminform."},{"key":"mlstad652cbib31","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1039\/C9ME00069K","article-title":"Enumeration of de novo inorganic complexes for chemical discovery and machine learning","volume":"5","author":"Gugler","year":"2020","journal-title":"Mol. Syst. Des. Eng."},{"key":"mlstad652cbib32","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1021\/ar500432k","article-title":"The chemical space project","volume":"48","author":"Reymond","year":"2015","journal-title":"Acc. Chem. Res."},{"key":"mlstad652cbib33","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/nrd2220","article-title":"A decade of fragment-based drug design: strategic advances and lessons learned","volume":"6","author":"Hajduk","year":"2007","journal-title":"Nat. Rev. Drug Discovery"},{"key":"mlstad652cbib34","doi-asserted-by":"publisher","first-page":"17147","DOI":"10.1039\/c1jm12216a","article-title":"Novel mixed polyanions lithium-ion battery cathode materials predicted by high-throughput ab initio computations","volume":"21","author":"Hautier","year":"2011","journal-title":"J. Mater. Chem."},{"key":"mlstad652cbib35","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1016\/j.ensm.2019.06.011","article-title":"A perspective on inverse design of battery interphases using multi-scale modelling, experiments and generative deep learning","volume":"21","author":"Bhowmik","year":"2019","journal-title":"Energy Storage Mater."},{"key":"mlstad652cbib36","doi-asserted-by":"publisher","first-page":"6595","DOI":"10.1021\/acs.chemrev.8b00759","article-title":"Search for catalysts by inverse design: artificial intelligence, mountain climbers and alchemists","volume":"119","author":"Freeze","year":"2019","journal-title":"Chem. Rev."},{"key":"mlstad652cbib37","doi-asserted-by":"publisher","DOI":"10.1002\/minf.201900087","article-title":"Inverse-QSPR for de novo design: a review","volume":"39","author":"Gantzer","year":"2020","journal-title":"Mol. Inform."},{"key":"mlstad652cbib38","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":"mlstad652cbib39","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1002\/andp.19273892002","article-title":"Zur quantentheorie der molekeln","volume":"389","author":"Born","year":"1927","journal-title":"Ann. Phys., Lpz."},{"key":"mlstad652cbib40","first-page":"pp 19","author":"Sutcliffe","year":"1992"},{"key":"mlstad652cbib41","author":"Jensen","year":"2017","edition":"3rd edn"},{"key":"mlstad652cbib42","author":"Cramer","year":"2004","edition":"2nd edn"},{"key":"mlstad652cbib43","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1002\/(SICI)1096-987X(199604)17:5\/6<490::AID-JCC1>3.0.CO;2-P","article-title":"Merck molecular force field. I. Basis, form, scope, parameterization and performance of MMFF94","volume":"17","author":"Halgren","year":"1996","journal-title":"J. Comput. Chem."},{"key":"mlstad652cbib44","doi-asserted-by":"publisher","first-page":"10024","DOI":"10.1021\/ja00051a040","article-title":"UFF, a full periodic table force field for molecular mechanics and molecular dynamics simulations","volume":"114","author":"Rapp\u00e9","year":"1992","journal-title":"J. Am. Chem. Soc."},{"key":"mlstad652cbib45","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1002\/jcc.21367","article-title":"CHARMM general force field: a force field for drug-like molecules compatible with the CHARMM all-atom additive biological force fields","volume":"31","author":"Vanommeslaeghe","year":"2010","journal-title":"J. Comput. Chem."},{"key":"mlstad652cbib46","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1021\/acs.jctc.8b01176","article-title":"GFN2-xTB\u2014an accurate and broadly parametrized self-consistent tight-binding quantum chemical method with multipole electrostatics and density-dependent dispersion contributions","volume":"15","author":"Bannwarth","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad652cbib47","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1007\/s00894-007-0233-4","article-title":"Optimization of parameters for semiempirical methods V: modification of NDDO approximations and application to 70 elements","volume":"13","author":"Stewart","year":"2007","journal-title":"J. Mol. Model."},{"key":"mlstad652cbib48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00894-012-1667-x","article-title":"Optimization of parameters for semiempirical methods VI: more modifications to the NDDO approximations and re-optimization of parameters","volume":"19","author":"Stewart","year":"2013","journal-title":"J. Mol. Model."},{"key":"mlstad652cbib49","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s002149900083","article-title":"Orthogonalization corrections for semiempirical methods","volume":"103","author":"Weber","year":"2000","journal-title":"Theor. Chem. Acc."},{"key":"mlstad652cbib50","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.108.058301","article-title":"Fast and accurate modeling of molecular atomization energies with machine learning","volume":"108","author":"Rupp","year":"2012","journal-title":"Phys. Rev. Lett."},{"key":"mlstad652cbib51","doi-asserted-by":"publisher","first-page":"13754","DOI":"10.1039\/C6CP00415F","article-title":"Comparing molecules and solids across structural and alchemical space","volume":"18","author":"De","year":"2016","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstad652cbib52","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":"mlstad652cbib53","doi-asserted-by":"publisher","DOI":"10.1063\/1.5020710","article-title":"Alchemical and structural distribution based representation for universal quantum machine learning","volume":"148","author":"Faber","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstad652cbib54","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13890","article-title":"Quantum-chemical insights from deep tensor neural networks","volume":"8","author":"Sch\u00fctt","year":"2017","journal-title":"Nat. Commun."},{"key":"mlstad652cbib55","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.1039\/C6SC05720A","article-title":"ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost","volume":"8","author":"Smith","year":"2017","journal-title":"Chem. Sci."},{"key":"mlstad652cbib56","article-title":"Directional message passing for molecular graphs","author":"Gasteiger","year":"2020"},{"key":"mlstad652cbib57","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1038\/s41467-022-29939-5","article-title":"E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials","volume":"13","author":"Batzner","year":"2022","journal-title":"Nat. Commun."},{"key":"mlstad652cbib58","first-page":"pp 9323","article-title":"E(n) equivariant graph neural networks","author":"Satorras","year":"2021"},{"key":"mlstad652cbib59","first-page":"pp 29400","article-title":"So3krates: equivariant attention for interactions on arbitrary length-scales in molecular systems","volume":"vol 35","author":"Frank","year":"2022"},{"key":"mlstad652cbib60","article-title":"MACE: higher order equivariant message passing neural networks for fast and accurate force fields","author":"Batatia","year":"2022"},{"key":"mlstad652cbib61","doi-asserted-by":"publisher","first-page":"eadn4397","DOI":"10.1126\/sciadv.adn4397","article-title":"Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments","volume":"10","author":"Unke","year":"2024","journal-title":"Sci. Adv."},{"key":"mlstad652cbib62","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1038\/s41467-023-36329-y","article-title":"Learning local equivariant representations for large-scale atomistic dynamics","volume":"14","author":"Musaelian","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstad652cbib63","article-title":"Tensor field networks: rotation-and translation-equivariant neural networks for 3D point clouds","author":"Thomas","year":"2018"},{"key":"mlstad652cbib64","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1146\/annurev-physchem-042018-052331","article-title":"Machine learning for molecular simulation","volume":"71","author":"No\u00e9","year":"2020","journal-title":"Annu. Rev. Phys. Chem."},{"key":"mlstad652cbib65","doi-asserted-by":"publisher","first-page":"10142","DOI":"10.1021\/acs.chemrev.0c01111","article-title":"Machine learning force fields","volume":"121","author":"Unke","year":"2021","journal-title":"Chem. Rev."},{"key":"mlstad652cbib66","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.1603015","article-title":"Machine learning of accurate energy-conserving molecular force fields","volume":"3","author":"Chmiela","year":"2017","journal-title":"Sci. Adv."},{"key":"mlstad652cbib67","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.cpc.2019.02.007","article-title":"sGDML: constructing accurate and data efficient molecular force fields using machine learning","volume":"240","author":"Chmiela","year":"2019","journal-title":"Comput. Phys. Commun."},{"key":"mlstad652cbib68","doi-asserted-by":"publisher","first-page":"eadf0873","DOI":"10.1126\/sciadv.adf0873","article-title":"Accurate global machine learning force fields for molecules with hundreds of atoms","volume":"9","author":"Chmiela","year":"2023","journal-title":"Sci. Adv."},{"key":"mlstad652cbib69","first-page":"pp 991","article-title":"SchNet: a continuous-filter convolutional neural network for modeling quantum interactions","volume":"vol 30","author":"Sch\u00fctt","year":"2017"},{"key":"mlstad652cbib70","doi-asserted-by":"publisher","DOI":"10.1063\/1.5019779","article-title":"SchNet\u2014a deep learning architecture for molecules and materials","volume":"148","author":"Sch\u00fctt","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstad652cbib71","doi-asserted-by":"publisher","first-page":"3678","DOI":"10.1021\/acs.jctc.9b00181","article-title":"PhysNet: a neural network for predicting energies, forces, dipole moments and partial charges","volume":"15","author":"Unke","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad652cbib72","doi-asserted-by":"publisher","first-page":"7273","DOI":"10.1038\/s41467-021-27504-0","article-title":"SpookyNet: learning force fields with electronic degrees of freedom and nonlocal effects","volume":"12","author":"Unke","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstad652cbib73","first-page":"pp 8867","article-title":"Equivariant diffusion for molecule generation in 3D","author":"Hoogeboom","year":"2022"},{"key":"mlstad652cbib74","first-page":"pp 36533","article-title":"Diffusion-based molecule generation with informative prior bridges","volume":"vol 35","author":"Wu","year":"2022"},{"key":"mlstad652cbib75","first-page":"pp 5105","article-title":"MDM: molecular diffusion model for 3D molecule generation","volume":"vol 37","author":"Huang","year":"2023"},{"key":"mlstad652cbib76","first-page":"pp 38592","article-title":"Geometric latent diffusion models for 3D molecule generation","author":"Xu","year":"2023"},{"key":"mlstad652cbib77","first-page":"pp 27611","article-title":"MolDiff: addressing the atom-bond inconsistency problem in 3D molecule diffusion generation","author":"Peng","year":"2023"},{"key":"mlstad652cbib78","article-title":"GeoDiff: a geometric diffusion model for molecular conformation generation","author":"Xu","year":"2022"},{"key":"mlstad652cbib79","article-title":"Digress: discrete denoising diffusion for graph generation","author":"Vignac","year":"2023"},{"key":"mlstad652cbib80","first-page":"pp 17391","article-title":"Autoregressive diffusion model for graph generation","author":"Kong","year":"2023"},{"key":"mlstad652cbib81","first-page":"pp 7566","article-title":"Symmetry-adapted generation of 3D point sets for the targeted discovery of molecules","volume":"vol 32","author":"Gebauer","year":"2019"},{"key":"mlstad652cbib82","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1038\/s41467-022-28526-y","article-title":"Inverse design of 3D molecular structures with conditional generative neural networks","volume":"13","author":"Gebauer","year":"2022","journal-title":"Nat. Commun."},{"key":"mlstad652cbib83","first-page":"pp 8959","article-title":"Reinforcement learning for molecular design guided by quantum mechanics","author":"Simm","year":"2020"},{"key":"mlstad652cbib84","article-title":"Symmetry-aware actor-critic for 3D molecular design","author":"Simm","year":"2021"},{"key":"mlstad652cbib85","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3eb4","article-title":"Generating stable molecules using imitation and reinforcement learning","volume":"3","author":"Meldgaard","year":"2022","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad652cbib86","doi-asserted-by":"publisher","first-page":"eaaw1147","DOI":"10.1126\/science.aaw1147","article-title":"Boltzmann generators: sampling equilibrium states of many-body systems with deep learning","volume":"365","author":"No\u00e9","year":"2019","journal-title":"Science"},{"key":"mlstad652cbib87","first-page":"pp 5361","article-title":"Equivariant flows: exact likelihood generative learning for symmetric densities","author":"K\u00f6hler","year":"2020"},{"key":"mlstad652cbib88","first-page":"pp 4181","article-title":"E(n) equivariant normalizing flows","volume":"vol 34","author":"Garcia Satorras","year":"2021"},{"key":"mlstad652cbib89","article-title":"Timewarp: transferable acceleration of molecular dynamics by learning time-coarsened dynamics","author":"Klein","year":"2023"},{"key":"mlstad652cbib90","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-56773-5","article-title":"Molecular geometry prediction using a deep generative graph neural network","volume":"9","author":"Mansimov","year":"2019","journal-title":"Sci. Rep."},{"key":"mlstad652cbib91","first-page":"pp 8949","article-title":"A generative model for molecular distance geometry","author":"Simm","year":"2020"},{"key":"mlstad652cbib92","first-page":"pp 20142","article-title":"TorsionNet: a reinforcement learning approach to sequential conformer search","volume":"vol 33","author":"Gogineni","year":"2020"},{"key":"mlstad652cbib93","first-page":"pp 13757","article-title":"GeoMol: torsional geometric generation of molecular 3D conformer ensembles","volume":"vol 34","author":"Ganea","year":"2021"},{"key":"mlstad652cbib94","first-page":"pp 11537","article-title":"An end-to-end framework for molecular conformation generation via bilevel programming","author":"Xu","year":"2021"},{"key":"mlstad652cbib95","doi-asserted-by":"publisher","first-page":"4468","DOI":"10.1038\/s41467-021-24525-7","article-title":"Machine learning based energy-free structure predictions of molecules, transition states and solids","volume":"12","author":"Lemm","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstad652cbib96","article-title":"Torsional diffusion for molecular conformer generation","author":"Jing","year":"2022"},{"key":"mlstad652cbib97","doi-asserted-by":"publisher","first-page":"5077","DOI":"10.1021\/acs.jctc.3c00289","article-title":"Denoise pretraining on nonequilibrium molecules for accurate and transferable neural potentials","volume":"19","author":"Wang","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad652cbib98","first-page":"pp 9938","article-title":"Fractional denoising for 3D molecular pre-training","author":"Feng","year":"2023"},{"key":"mlstad652cbib99","article-title":"Pre-training via denoising for molecular property prediction","author":"Zaidi","year":"2023"},{"key":"mlstad652cbib100","article-title":"Molecular geometry pretraining with SE(3)-invariant denoising distance matching","author":"Liu","year":"2023"},{"key":"mlstad652cbib101","article-title":"Simple GNN regularisation for 3D molecular property prediction and beyond","author":"Godwin","year":"2022"},{"key":"mlstad652cbib102","first-page":"pp 1096","article-title":"Extracting and composing robust features with denoising autoencoders","author":"Vincent","year":"2008"},{"key":"mlstad652cbib103","article-title":"Score-based denoising for atomic structure identification","author":"Hsu","year":"2022"},{"key":"mlstad652cbib104","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1038\/s41597-021-00812-2","article-title":"QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules","volume":"8","author":"Hoja","year":"2021","journal-title":"Sci. Data"},{"key":"mlstad652cbib105","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1021\/acs.jpclett.7b03234","article-title":"Structure and stability of molecular crystals with many-body dispersion-inclusive density functional tight binding","volume":"9","author":"Mortazavi","year":"2018","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstad652cbib106","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1002\/(SICI)1097-461X(1996)58:2>185::AID-QUA7<3.0.CO;2-U","article-title":"Calculations of molecules, clusters and solids with a simplified LCAO-DFT-LDA scheme","volume":"58","author":"Seifert","year":"1996","journal-title":"Int. J. Quantum Chem."},{"key":"mlstad652cbib107","doi-asserted-by":"publisher","first-page":"7260","DOI":"10.1103\/PhysRevB.58.7260","article-title":"Self-consistent-charge density-functional tight-binding method for simulations of complex materials properties","volume":"58","author":"Elstner","year":"1998","journal-title":"Phys. Rev. B"},{"key":"mlstad652cbib108","doi-asserted-by":"publisher","first-page":"931","DOI":"10.1021\/ct100684s","article-title":"DFTB3: extension of the self-consistent-charge density-functional tight-binding method (SCC-DFTB)","volume":"7","author":"Gaus","year":"2011","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad652cbib109","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.108.236402","article-title":"Accurate and efficient method for many-body van der Waals interactions","volume":"108","author":"Tkatchenko","year":"2012","journal-title":"Phys. Rev. Lett."},{"key":"mlstad652cbib110","doi-asserted-by":"publisher","first-page":"18A508","DOI":"10.1063\/1.4865104","article-title":"Long-range correlation energy calculated from coupled atomic response functions","volume":"140","author":"Ambrosetti","year":"2014","journal-title":"J. Chem. Phys."},{"key":"mlstad652cbib111","doi-asserted-by":"publisher","first-page":"8732","DOI":"10.1021\/ja902302h","article-title":"970 million druglike small molecules for virtual screening in the chemical Universe database GDB-13","volume":"131","author":"Blum","year":"2009","journal-title":"J. Am. Chem. Soc."},{"key":"mlstad652cbib112","doi-asserted-by":"publisher","first-page":"6158","DOI":"10.1063\/1.478522","article-title":"Toward reliable density functional methods without adjustable parameters: the PBE0 model","volume":"110","author":"Adamo","year":"1999","journal-title":"J. Chem. Phys."},{"key":"mlstad652cbib113","doi-asserted-by":"publisher","first-page":"9982","DOI":"10.1063\/1.472933","article-title":"Rationale for mixing exact exchange with density functional approximations","volume":"105","author":"Perdew","year":"1996","journal-title":"J. Chem. Phys."},{"key":"mlstad652cbib114","doi-asserted-by":"publisher","first-page":"2175","DOI":"10.1016\/j.cpc.2009.06.022","article-title":"Ab initio molecular simulations with numeric atom-centered orbitals","volume":"180","author":"Blum","year":"2009","journal-title":"Comput. Phys. Commun."},{"key":"mlstad652cbib115","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/14\/5\/053020","article-title":"Resolution-of-identity approach to Hartree\u2013Fock, hybrid density functionals, RPA, MP2 and GW with numeric atom-centered orbital basis functions","volume":"14","author":"Ren","year":"2012","journal-title":"New J. Phys."},{"key":"mlstad652cbib116","first-page":"pp 2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015"},{"key":"mlstad652cbib117","first-page":"pp 6840","article-title":"Denoising diffusion probabilistic models","volume":"vol 33","author":"Ho","year":"2020"},{"key":"mlstad652cbib118","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021"},{"key":"mlstad652cbib119","first-page":"pp 9377","article-title":"Equivariant message passing for the prediction of tensorial properties and molecular spectra","author":"Sch\u00fctt","year":"2021"},{"key":"mlstad652cbib120","author":"Bishop","year":"2006"},{"key":"mlstad652cbib121","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1021\/acs.jctc.8b00908","article-title":"SchNetPack: a deep learning toolbox for atomistic systems","volume":"15","author":"Sch\u00fctt","year":"2018","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad652cbib122","doi-asserted-by":"publisher","DOI":"10.1063\/5.0138367","article-title":"SchNetPack 2.0: a neural network toolbox for atomistic machine learning","volume":"158","author":"Sch\u00fctt","year":"2023","journal-title":"J. Chem. Phys."},{"key":"mlstad652cbib123","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/1758-2946-3-33","article-title":"Open babel: an open chemical toolbox","volume":"3","author":"O\u2019Boyle","year":"2011","journal-title":"J. Cheminform."},{"key":"mlstad652cbib124","doi-asserted-by":"publisher","DOI":"10.1088\/1361-648X\/aa680e","article-title":"The atomic simulation environment\u2014a Python library for working with atoms","volume":"29","author":"Larsen","year":"2017","journal-title":"J. Phys.: Condens. Matter"},{"key":"mlstad652cbib125","doi-asserted-by":"publisher","first-page":"3297","DOI":"10.1039\/b508541a","article-title":"Balanced basis sets of split valence, triple zeta valence and quadruple zeta valence quality for H to Rn: design and assessment of accuracy","volume":"7","author":"Weigend","year":"2005","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstad652cbib126","doi-asserted-by":"publisher","first-page":"1664","DOI":"10.1002\/jcc.23981","article-title":"Libcint: an efficient general integral library for Gaussian basis functions","volume":"36","author":"Sun","year":"2015","journal-title":"J. Comput. Chem."},{"key":"mlstad652cbib127","doi-asserted-by":"publisher","first-page":"e1340","DOI":"10.1002\/wcms.1352","article-title":"PYSCF: the Python-based simulations of chemistry framework","volume":"8","author":"Sun","year":"2017","journal-title":"Wiley Interdiscip. Rev.-Comput. Mol. Sci."},{"key":"mlstad652cbib128","doi-asserted-by":"publisher","DOI":"10.1063\/5.0006074","article-title":"Recent developments in the PYSCF program package","volume":"153","author":"Sun","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstad652cbib129","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10927872","article-title":"MoreRed: molecular relaxation by reverse diffusion with time step prediction","author":"Kahouli","year":"2024"},{"key":"mlstad652cbib130","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","article-title":"Enumeration of 166 billion organic small molecules in the chemical Universe database GDB-17","volume":"52","author":"Ruddigkeit","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"mlstad652cbib131","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":"mlstad652cbib132","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"mlstad652cbib133","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"mlstad652cbib134","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022"},{"key":"mlstad652cbib135","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad652c","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad652c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad652c","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad652c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad652c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad652c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad652c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad652c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T09:25:09Z","timestamp":1722936309000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad652c"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,6]]},"references-count":135,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,8,6]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad652c","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,6]]},"assertion":[{"value":"Molecular relaxation by reverse diffusion with time step prediction","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 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-04-09","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-07-18","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-06","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}