Although machine learning potentials have recently had a substantial impact on molecular simulations, the construction of a robust training set can still become a limiting factor, especially due to the requirement of a reference ab initio simulation that covers all the relevant geometries of the system. Recognizing that this can be prohibitive for certain systems, we develop the method of transition tube sampling that mitigates the computational cost of training set and model generation. In this approach, we generate classical or quantum thermal geometries around a transition path describing a conformational change or a chemical reaction using only a sparse set of local normal mode expansions along this path and select from these geometries by an active learning protocol. This yields a training set with geometries that characterize the whole transition without the need for a costly reference trajectory. The performance of the method is evaluated on different molecular systems with the complexity of the potential energy landscape increasing from a single minimum to a double proton-transfer reaction with high barriers. Our results show that the method leads to training sets that give rise to models applicable in classical and path integral simulations alike that are on par with those based directly on ab initio calculations while providing the computational speedup we have come to expect from machine learning potentials.

Charles University Faculty of Mathematics and Physics Ke Karlovu 3 121 16 Prague 2 Czech Republic

Zobrazit více v PubMed

Tian P. Molecular dynamics simulations of nanoparticles. Annu. Rep. Prog. Chem., Sect. C: Phys. Chem. 2008, 104, 142–164. 10.1039/B703897F. DOI

De Vivo M.; Masetti M.; Bottegoni G.; Cavalli A. Role of Molecular Dynamics and Related Methods in Drug Discovery. J. Med. Chem. 2016, 59, 4035–4061. 10.1021/acs.jmedchem.5b01684. PubMed DOI

Hollingsworth S. A.; Dror R. O. Molecular Dynamics Simulation for All. Neuron 2018, 99, 1129–1143. 10.1016/j.neuron.2018.08.011. PubMed DOI PMC

Deringer V. L.; Caro M. A.; Csányi G. Machine Learning Interatomic Potentials as Emerging Tools for Materials Science. Adv. Mater. 2019, 31, 1902765.10.1002/adma.201902765. PubMed DOI

Yao N.; Chen X.; Fu Z. H.; Zhang Q. Applying Classical, Ab Initio, and Machine-Learning Molecular Dynamics Simulations to the Liquid Electrolyte for Rechargeable Batteries. Chem. Rev. 2022, 122, 10970–11021. 10.1021/acs.chemrev.1c00904. PubMed DOI

Marx D.; Hutter J.. Ab Initio Molecular Dynamics: Basic Theory and Advanced Methods; Cambridge University Press: New York, 2009.

Szabo A.; Ostlund N. S.. Modern Quantum Chemistry: Introduction to Advanced Electronic Structure Theory; Dover Publications, Inc.: Mineola, N.Y., 1996.

Parr R. G.; Yang W.. Density-Functional Theory of Atoms and Molecules; Oxford University Press: New York, 1989.

Hohenberg P.; Kohn W. Inhomogeneous Electron Gas. Phys. Rev. 1964, 136, B864–B871. 10.1103/physrev.136.b864. DOI

Kohn W.; Sham L. J. Self-Consistent Equations Including Exchange and Correlation Effects. Phys. Rev. 1965, 140, A1133–A1138. 10.1103/physrev.140.a1133. DOI

Marsalek O.; Chen P. Y.; Dupuis R.; Benoit M.; Méheut M.; Bačić Z.; Tuckerman M. E. Efficient calculation of free energy differences associated with isotopic substitution using path-integral molecular dynamics. J. Chem. Theory Comput. 2014, 10, 1440–1453. 10.1021/ct400911m. PubMed DOI

Spura T.; Elgabarty H.; Kühne T. D. On-the-fly” coupled cluster path-integral molecular dynamics: impact of nuclear quantum effects on the protonated water dimer. Phys. Chem. Chem. Phys. 2015, 17, 14355–14359. 10.1039/c4cp05192k. PubMed DOI

Kapil V.; VandeVondele J.; Ceriotti M. Accurate molecular dynamics and nuclear quantum effects at low cost by multiple steps in real and imaginary time: Using density functional theory to accelerate wavefunction methods. J. Chem. Phys. 2016, 144, 054111.10.1063/1.4941091. PubMed DOI

Behler J. Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations. Phys. Chem. Chem. Phys. 2011, 13, 17930–17955. 10.1039/c1cp21668f. PubMed DOI

Friederich P.; Häse F.; Proppe J.; Aspuru-Guzik A. Machine-learned potentials for next-generation matter simulations. Nat. Mater. 2021, 20, 750–761. 10.1038/s41563-020-0777-6. PubMed DOI

Behler J.; Parrinello M. Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces. Phys. Rev. Lett. 2007, 98, 146401.10.1103/physrevlett.98.146401. PubMed DOI

Bartók A. P.; Payne M. C.; Kondor R.; Csányi G. Gaussian approximation potentials: The accuracy of quantum mechanics, without the electrons. Phys. Rev. Lett. 2010, 104, 136403.10.1103/physrevlett.104.136403. PubMed DOI

Smith J. S.; Isayev O.; Roitberg A. E. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chem. Sci. 2017, 8, 3192–3203. 10.1039/c6sc05720a. PubMed DOI PMC

Schütt K. T.; Kindermans P. J.; Sauceda H. E.; Chmiela S.; Tkatchenko A.; Müller K. R. SchNet: A continuous-filter convolutional neural network for modeling quantum interactions. Adv. Neural Inf. Process. Syst. 2017, 30, 992–1002.

Batzner S.; Musaelian A.; Sun L.; Geiger M.; Mailoa J. P.; Kornbluth M.; Molinari N.; Smidt T. E.; Kozinsky B. E. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nat. Commun. 2022, 13, 2453.10.1038/s41467-022-29939-5. PubMed DOI PMC

Dral P. O. Quantum Chemistry in the Age of Machine Learning. J. Phys. Chem. Lett. 2020, 11, 2336–2347. 10.1021/acs.jpclett.9b03664. PubMed DOI

Behler J. Atom-centered symmetry functions for constructing high-dimensional neural network potentials. J. Chem. Phys. 2011, 134, 074106.10.1063/1.3553717. PubMed DOI

Natarajan S. K.; Behler J. Neural network molecular dynamics simulations of solid-liquid interfaces: Water at low-index copper surfaces. Phys. Chem. Chem. Phys. 2016, 18, 28704–28725. 10.1039/c6cp05711j. PubMed DOI

Schütt K. T.; Sauceda H. E.; Kindermans P. J.; Tkatchenko A.; Müller K. R. SchNet - A deep learning architecture for molecules and materials. J. Chem. Phys. 2018, 148, 241722.10.1063/1.5019779. PubMed DOI

Sivaraman G.; Krishnamoorthy A. N.; Baur M.; Holm C.; Stan M.; Csányi G.; Benmore C.; Vázquez-Mayagoitia Á. Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide. npj Comput. Mater. 2020, 6, 104.10.1038/s41524-020-00367-7. DOI

Schran C.; Thiemann F. L.; Rowe P.; Müller E. A.; Marsalek O.; Michaelides A. Machine learning potentials for complex aqueous systems made simple. Proc. Natl. Acad. Sci. U.S.A. 2021, 118, e211007711810.1073/pnas.2110077118. PubMed DOI PMC

Schran C.; Brezina K.; Marsalek O. Committee neural network potentials control generalization errors and enable active learning. J. Chem. Phys. 2020, 153, 104105.10.1063/5.0016004. PubMed DOI

Artrith N.; Behler J. High-dimensional neural network potentials for metal surfaces: A prototype study for copper. Phys. Rev. B: Condens. Matter Mater. Phys. 2012, 85, 045439.10.1103/physrevb.85.045439. DOI

Gastegger M.; Behler J.; Marquetand P. Machine learning molecular dynamics for the simulation of infrared spectra. Chem. Sci. 2017, 8, 6924–6935. 10.1039/c7sc02267k. PubMed DOI PMC

Smith J. S.; Nebgen B.; Lubbers N.; Isayev O.; Roitberg A. E. Less is more: Sampling chemical space with active learning. J. Chem. Phys. 2018, 148, 241733.10.1063/1.5023802. PubMed DOI

Hansen L. K.; Salamon P. Neural Network Ensembles. IEEE Trans. Pattern Anal. Mach. Intell. 1990, 12, 993–1001. 10.1109/34.58871. DOI

Cooper A. M.; Hallmen P. P.; Kästner J. Potential energy surface interpolation with neural networks for instanton rate calculations. J. Chem. Phys. 2018, 148, 094106.10.1063/1.5015950. DOI

Schran C.; Behler J.; Marx D. Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground. J. Chem. Theory Comput. 2020, 16, 88–99. 10.1021/acs.jctc.9b00805. PubMed DOI

Krogh A.; Vedelsby J. Neural Network Ensembles, Cross Validation, and Active Learning. Adv. Neural Inf. Process. Syst. 1995, 7, 231–238.

Seung H. S.; Opper M.; Sompolinsky H.. Query by committee. Proceedings of the Fifth Annual Workshop on Computational Learning Theory-COLT’92: New York, New York, USA, 1992; pp 287–294.

Chen L.; Sukuba I.; Probst M.; Kaiser A. Iterative training set refinement enables reactive molecular dynamics via machine learned forces. RSC Adv. 2020, 10, 4293–4299. 10.1039/c9ra09935b. PubMed DOI PMC

Morawietz T.; Singraber A.; Dellago C.; Behler J. How van der Waals interactions determine the unique properties of water. Proc. Natl. Acad. Sci. 2016, 113, 8368–8373. 10.1073/pnas.1602375113. PubMed DOI PMC

Musil F.; De S.; Yang J.; Campbell J. E.; Day G. M.; Ceriotti M. Machine learning for the structure-energy-property landscapes of molecular crystals. Chem. Sci. 2018, 9, 1289–1300. 10.1039/c7sc04665k. PubMed DOI PMC

Vandermause J.; Torrisi S. B.; Batzner S.; Xie Y.; Sun L.; Kolpak A. M.; Kozinsky B. On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events. npj Comput. Mater. 2020, 6, 20.10.1038/s41524-020-0283-z. DOI

Wang W.; Yang T.; Harris W. H.; Gómez-Bombarelli R. Active learning and neural network potentials accelerate molecular screening of ether-based solvate ionic liquids. Chem. Commun. 2020, 56, 8920–8923. 10.1039/d0cc03512b. PubMed DOI

Miksch A. M.; Morawietz T.; Kästner J.; Urban A.; Artrith N. Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations. Mach. Learn.: Sci. Technol. 2021, 2, 031001.10.1088/2632-2153/abfd96. DOI

Schwalbe-Koda D.; Tan A. R.; Gómez-Bombarelli R. Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks. Nat. Commun. 2021, 12, 5104–5112. 10.1038/s41467-021-25342-8. PubMed DOI PMC

Vandenhaute S.; Cools-Ceuppens M.; DeKeyser S.; Verstraelen T.; Van Speybroeck V. Machine learning potentials for metal-organic frameworks using an incremental learning approach. npj Comput. Mater. 2023, 9, 19.10.1038/s41524-023-00969-x. DOI

Rupp M.; Ramakrishnan R.; Von Lilienfeld O. A. Machine Learning for Quantum Mechanical Properties of Atoms in Molecules. J. Phys. Chem. Lett. 2015, 6, 3309–3313. 10.1021/acs.jpclett.5b01456. DOI

Schreiner M.; Bhowmik A.; Vegge T.; Busk J.; Winther O. Transition1x - a dataset for building generalizable reactive machine learning potentials. Sci. Data 2022, 9, 779.10.1038/s41597-022-01870-w. PubMed DOI PMC

Jónsson H.; Mills G.; Jacobsen K. W.. Nudged elastic band method for finding minimum energy paths of transitions. Classical and Quantum Dynamics in Condensed Phase Simulations; World Scientific, 1998; pp 385–404.

Ceriotti M.; Bussi G.; Parrinello M. Nuclear Quantum Effects in Solids Using a Colored-Noise Thermostat. Phys. Rev. Lett. 2009, 103, 030603.10.1103/physrevlett.103.030603. PubMed DOI

Hutter J.; Iannuzzi M.; Schiffmann F.; Vandevondele J. Cp2k: Atomistic simulations of condensed matter systems. Wiley Interdiscip. Rev.: Comput. Mol. Sci. 2014, 4, 15–25. 10.1002/wcms.1159. DOI

Vandevondele J.; Krack M.; Mohamed F.; Parrinello M.; Chassaing T.; Hutter J. Quickstep: Fast and accurate density functional calculations using a mixed Gaussian and plane waves approach. Comput. Phys. Commun. 2005, 167, 103–128. 10.1016/j.cpc.2004.12.014. DOI

Kühne T. D.; Iannuzzi M.; Del Ben M.; Rybkin V. V.; Seewald P.; Stein F.; Laino T.; Khaliullin R. Z.; Schütt O.; Schiffmann F.; et al. CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations. J. Chem. Phys. 2020, 152, 194103.10.1063/5.0007045. PubMed DOI

Porezag D.; Frauenheim T.; Köhler T.; Seifert G.; Kaschner R. Construction of tight-binding-like potentials on the basis of density-functional theory: Application to carbon. Phys. Rev. B: Condens. Matter Mater. Phys. 1995, 51, 12947–12957. 10.1103/physrevb.51.12947. PubMed DOI

Perdew J. P.; Burke K.; Ernzerhof M. Generalized gradient approximation made simple. Phys. Rev. Lett. 1996, 77, 3865–3868. 10.1103/physrevlett.77.3865. PubMed DOI

Zhang Y.; Yang W. Comment on “generalized gradient approximation made simple”. Phys. Rev. Lett. 1998, 80, 890.10.1103/physrevlett.80.890. DOI

Adamo C.; Barone V. Toward reliable density functional methods without adjustable parameters: The PBE0 model. J. Chem. Phys. 1999, 110, 6158–6170. 10.1063/1.478522. DOI

Goerigk L.; Grimme S. A thorough benchmark of density functional methods for general main group thermochemistry, kinetics, and noncovalent interactions. Phys. Chem. Chem. Phys. 2011, 13, 6670–6688. 10.1039/c0cp02984j. PubMed DOI

Guidon M.; Schiffmann F.; Hutter J.; Vandevondele J. Ab initio molecular dynamics using hybrid density functionals. J. Chem. Phys. 2008, 128, 214104–214115. 10.1063/1.2931945. PubMed DOI

Guidon M.; Hutter J.; VandeVondele J. Robust periodic Hartree-Fock exchange for large-scale simulations using Gaussian basis sets. J. Chem. Theory Comput. 2009, 5, 3010–3021. 10.1021/ct900494g. PubMed DOI

Goedecker S.; Teter M.; Hutter J. Separable dual-space Gaussian pseudopotentials. Phys. Rev. B: Condens. Matter Mater. Phys. 1996, 54, 1703–1710. 10.1103/physrevb.54.1703. PubMed DOI

Guidon M.; Hutter J.; Vandevondele J. Auxiliary density matrix methods for Hartree-Fock exchange calculations. J. Chem. Theory Comput. 2010, 6, 2348–2364. 10.1021/ct1002225. PubMed DOI

Singraber A.; Morawietz T.; Behler J.; Dellago C. Parallel Multistream Training of High-Dimensional Neural Network Potentials. J. Chem. Theory Comput. 2019, 15, 3075–3092. 10.1021/acs.jctc.8b01092. PubMed DOI

Shah S.; Palmieri F.; Datum M. Optimal filtering algorithms for fast learning in feedforward neural networks. Neural Network. 1992, 5, 779–787. 10.1016/s0893-6080(05)80139-x. DOI

Blank T. B.; Brown S. D. Adaptive, global, extended Kalman filters for training feedforward neural networks. J. Chemom. 1994, 8, 391–407. 10.1002/cem.1180080605. DOI

AML public GitHub repository. https://github.com/MarsalekGroup/aml (accessed March 20, 2023).

Broyden C. G. The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations. IMA J. Appl. Math. 1970, 6, 76–90. 10.1093/imamat/6.1.76. DOI

Hjorth Larsen A.; Jørgen Mortensen J.; Blomqvist J.; Castelli I. E.; Christensen R.; Dułak M.; Friis J.; Groves M. N.; Hammer B.; Hargus C.; et al. The atomic simulation environment - A Python library for working with atoms. J. Phys. Condens. Matter. 2017, 29, 273002.10.1088/1361-648x/aa680e. PubMed DOI

Bitzek E.; Koskinen P.; Gähler F.; Moseler M.; Gumbsch P. Structural relaxation made simple. Phys. Rev. Lett. 2006, 97, 170201.10.1103/physrevlett.97.170201. PubMed DOI

Henkelman G.; Uberuaga B. P.; Jónsson H. A climbing image nudged elastic band method for finding saddle points and minimum energy paths. J. Chem. Phys. 2000, 113, 9901–9904. 10.1063/1.1329672. DOI

Ceriotti M.; Parrinello M.; Markland T. E.; Manolopoulos D. E. Efficient stochastic thermostatting of path integral molecular dynamics. J. Chem. Phys. 2010, 133, 124104.10.1063/1.3489925. PubMed DOI

Bonomi M.; Branduardi D.; Bussi G.; Camilloni C.; Provasi D.; Raiteri P.; Donadio D.; Marinelli F.; Pietrucci F.; Broglia R. A.; Parrinello M. PLUMED: A portable plugin for free-energy calculations with molecular dynamics. Comput. Phys. Commun. 2009, 180, 1961–1972. 10.1016/j.cpc.2009.05.011. DOI

et al. Promoting transparency and reproducibility in enhanced molecular simulations. Nat. Methods 2019, 16, 670–673. 10.1038/s41592-019-0506-8. PubMed DOI

Tribello G. A.; Bonomi M.; Branduardi D.; Camilloni C.; Bussi G. PLUMED 2: New feathers for an old bird. Comput. Phys. Commun. 2014, 185, 604–613. 10.1016/j.cpc.2013.09.018. DOI

Bussi G.; Donadio D.; Parrinello M. Canonical sampling through velocity rescaling. J. Chem. Phys. 2007, 126, 014101.10.1063/1.2408420. PubMed DOI

Shirts M. R.; Chodera J. D. Statistically optimal analysis of samples from multiple equilibrium states. J. Chem. Phys. 2008, 129, 124105.10.1063/1.2978177. PubMed DOI PMC

WHAM . https://github.com/apallath/WHAM (accessed March 20, 2023).

Tuckerman M. E.; Marx D. Heavy-Atom Skeleton Quantization and Proton Tunneling in ”Intermediate-Barrier” Hydrogen Bonds. Phys. Rev. Lett. 2001, 86, 4946–4949. 10.1103/physrevlett.86.4946. PubMed DOI

Cahlík A.; Hellerstedt J.; Mendieta-Moreno J. I.; Švec M.; Santhini V. M.; Pascal S.; Soler-Polo D.; Erlingsson S. I.; Výborný K.; Mutombo P.; Marsalek O.; Siri O.; Jelínek P. Significance of Nuclear Quantum Effects in Hydrogen Bonded Molecular Chains. ACS Nano 2021, 15, 10357–10365. 10.1021/acsnano.1c02572. PubMed DOI

Smedarchina Z.; Siebrand W.; Fernández-Ramos A.; Meana-Pañeda R. Mechanisms of double proton transfer. Theory and applications. Z. Phys. Chem. 2008, 222, 1291–1309. 10.1524/zpch.2008.5389. DOI

Kästner J. Theory and simulation of atom tunneling in chemical reactions. Wiley Interdiscip. Rev. Comput. Mol. Sci. 2014, 4, 158–168. 10.1002/wcms.1165. DOI