Atomic decomposition; Body representations; Condensed phase; Energy; Forcefields; Invariant polynomials; Learning potential; Machine-learning; Many body; Permutationally invariant; Computer Science (miscellaneous); Computer Science Applications; Computer Networks and Communications
Résumé :
[en] Most widely used machine learning potentials for condensed-phase applications rely on many-body permutationally invariant polynomial or atom-centered neural networks. However, these approaches face challenges in achieving chemical interpretability in atomistic energy decomposition and fully matching the computational efficiency of traditional force fields. Here we present a method that combines aspects of both approaches and balances accuracy and force-field-level speed. This method utilizes a monomer-centered representation, where the potential energy is decomposed into the sum of chemically meaningful monomeric energies. The structural descriptors of monomers are described by one-body and two-body effective interactions, enforced by appropriate sets of permutationally invariant polynomials as inputs to the feed-forward neural networks. Systematic assessments of models for gas-phase water trimer, liquid water, methane-water cluster and liquid carbon dioxide are performed. The improved accuracy, efficiency and flexibility of this method have promise for constructing accurate machine learning potentials and enabling large-scale quantum and classical simulations for complex molecular systems.
Disciplines :
Chimie
Auteur, co-auteur :
Yu, Qi ; Department of Chemistry, Fudan University, Shanghai, China. qi_yu@fudan.edu.cn ; Shanghai Innovation Institute, Shanghai, China. qi_yu@fudan.edu.cn
Ma, Ruitao; Department of Chemistry, Fudan University, Shanghai, China
Q.Y. and D.H.Z. acknowledge the support from National Natural Science Foundation of China (grant numbers 22473030 and 22288201). J.M.B. acknowledges support from NASA grant (80NSSC22K1167). R.C. thanks Universit\u00E0 degli Studi di Milano for financial support under grant PSR2022_DIP_005_PI_RCONT.
R.J. Bartlett M. Musiał Coupled-cluster theory in quantum chemistry Rev. Mod. Phys. 79 291 352 10.1103/RevModPhys.79.291
P. Gkeka et al. Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems J. Chem. Theory Comput. 16 4757 4775 10.1021/acs.jctc.0c00355
V.L. Deringer M.A. Caro G. Csányi Machine learning interatomic potentials as emerging tools for materials science Adv. Mat. 31 1902765 10.1002/adma.201902765
S. Manzhos R. Dawes T. Carrington Neural network-based approaches for building high dimensional and quantum dynamics-friendly potential energy surfaces Int. J. Quantum Chem. 115 1012 1020 10.1002/qua.24795
S. Manzhos T. Carrington Jr Neural network potential energy surfaces for small molecules and reactions Chem. Rev. 121 10187 10217 10.1021/acs.chemrev.0c00665
M. Meuwly Machine learning for chemical reactions Chem. Rev. 121 10218 10239 10.1021/acs.chemrev.1c00033
B.J. Braams J.M. Bowman Permutationally invariant potential energy surfaces in high dimensionality Int. Rev. Phys. Chem. 28 577 606 10.1080/01442350903234923
C. Qu Q. Yu J.M. Bowman Permutationally invariant potential energy surfaces Annu. Rev. Phys. Chem. 69 151 175 10.1146/annurev-physchem-050317-021139
B. Jiang H. Guo Permutation invariant polynomial neural network approach to fitting potential energy surfaces J. Chem. Phys. 139 054112 10.1063/1.4817187
B. Jiang J. Li H. Guo Potential energy surfaces from high fidelity fitting of ab initio points: the permutation invariant polynomial–neural network approach Int. Rev. Phys. Chem. 35 479 506 10.1080/0144235X.2016.1200347
K. Shao J. Chen Z. Zhao D.H. Zhang Fitting potential energy surfaces with fundamental invariant neural network J. Chem. Phys. 145 071101 10.1063/1.4961454
B. Fu D.H. Zhang Accurate fundamental invariant-neural network representation of ab initio potential energy surfaces Natl Sci. Rev. 10 nwad321 10.1093/nsr/nwad321
J. Behler M. Parrinello Generalized neural-network representation of high-dimensional potential-energy surfaces Phys. Rev. Lett. 98 146401 10.1103/PhysRevLett.98.146401
J. Behler Four generations of high-dimensional neural network potentials Chem. Rev. 121 10037 10072 10.1021/acs.chemrev.0c00868
S. Chmiela H.E. Sauceda K.-R. Müller A. Tkatchenko Towards exact molecular dynamics simulations with machine-learned force fields Nat. Commun. 9 10.1038/s41467-018-06169-2 3887
A.P. Bartók M.C. Payne R. Kondor G. Csányi Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons Phys. Rev. Lett. 104 136403 10.1103/PhysRevLett.104.136403
E. Uteva R.S. Graham R.D. Wilkinson R.J. Wheatley Interpolation of intermolecular potentials using Gaussian processes J. Chem. Phys. 147 161706 10.1063/1.4986489
K.T. Schütt H.E. Sauceda P.-J. Kindermans A. Tkatchenko K.-R. Müller SchNet—a deep learning architecture for molecules and materials J. Chem. Phys. 148 241722 10.1063/1.5019779
O.T. Unke M. Meuwly PhysNet: a neural network for predicting energies, forces, dipole moments, and partial charges J. Chem. Theory Comput. 15 3678 3693 10.1021/acs.jctc.9b00181
L. Zhang J. Han H. Wang R. Car E. Weinan Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics Phys. Rev. Lett. 120 143001 10.1103/PhysRevLett.120.143001
Y. Zhang C. Hu B. Jiang Embedded atom neural network potentials: efficient and accurate machine learning with a physically inspired representation J. Phys. Chem. Lett. 10 4962 4967 10.1021/acs.jpclett.9b02037
S. Batzner et al. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials Nat. Commun. 13 10.1038/s41467-022-29939-5 2453
I. Batatia D.P. Kovacs G. Simm C. Ortner G. Csanyi MACE: higher order equivariant message passing neural networks for fast and accurate force fields Adv. Neural Inf. Process. Syst. 35 11423 11436
A. Musaelian et al. Learning local equivariant representations for large-scale atomistic dynamics Nat. Commun. 14 10.1038/s41467-023-36329-y 579
F. Heidar-Zadeh et al. Information-theoretic approaches to atoms-in-molecules: Hirshfeld family of partitioning schemes J. Phys. Chem. A. 122 4219 4245 10.1021/acs.jpca.7b08966
Uhlig, F, Tovey, S. & Holm, C. Emergence of accurate atomic energies from machine learned noble gas potentials. Preprint at https://arxiv.org/abs/2403.00377 (2024).
A. Konovalov B.C. Symons P.L. Popelier On the many-body nature of intramolecular forces in FFLUX and its implications J. Comput. Chem. 42 107 116 10.1002/jcc.26438
B.C. Symons P.L. Popelier Application of quantum chemical topology force field FFLUX to condensed matter simulations: liquid water J. Chem. Theory Comput. 18 5577 5588 10.1021/acs.jctc.2c00311
Y.T. Manchev P.L. Popelier Modeling many-body interactions in water with Gaussian process regression J. Phys. Chem. A. 128 9345 9351 10.1021/acs.jpca.4c05873
Popelier, P. L. A. The Chemical Bond 271–308 (John Wiley & Sons, 2014).
M.S. Gordon D.G. Fedorov S.R. Pruitt L.V. Slipchenko Fragmentation methods: a route to accurate calculations on large systems Chem. Rev. 112 632 672 10.1021/cr200093j
M.P. Hodges A.J. Stone S.S. Xantheas Contribution of many-body terms to the energy for small water clusters: a comparison of ab initio calculations and accurate model potentials J. Phys. Chem. A 101 9163 9168 10.1021/jp9716851
E.E. Dahlke D.G. Truhlar Electrostatically embedded many-body correlation energy, with applications to the calculation of accurate second-order Møller–Plesset perturbation theory energies for large water clusters J. Chem. Theory Comput. 3 1342 1348 10.1021/ct700057x
Y.M. Wang B.C. Shepler B.J. Braams J.M. Bowman Full-dimensional, ab initio potential energy and dipole moment surfaces for water J. Chem. Phys. 131 054511 10.1063/1.3196178
U. Góra R. Podeszwa W. Cencek K. Szalewicz Interaction energies of large clusters from many-body expansion J. Chem. Phys. 135 224102 10.1063/1.3664730
G.R. Medders A.W. Götz M.A. Morales P. Bajaj F. Paesani On the representation of many-body interactions in water J. Chem. Phys. 143 104102 10.1063/1.4930194
Q. Yu J.M. Bowman VSCF/VCI vibrational spectroscopy of H7O3+ and H9O4+ using high-level, many-body potential energy surface and dipole moment surfaces J. Chem. Phys. 146 121102 10.1063/1.4979601
J.P. Heindel S.S. Xantheas The many-body expansion for aqueous systems revisited: I. Water–water interactions J. Chem. Theory Comput. 16 6843 6855 10.1021/acs.jctc.9b00749
X. Zhu M. Riera E.F. Bull-Vulpe F. Paesani MB-pol(2023): sub-chemical accuracy for water simulations from the gas to the liquid phase J. Chem. Theory Comput. 19 3551 3556 10.1021/acs.jctc.3c00326
Q. Yu et al. q-AQUA: a many-body CCSD(T) water potential, including 4-body interactions, demonstrates the quantum nature of water from clusters to the liquid phase J. Phys. Chem. Lett. 13 5068 5074 10.1021/acs.jpclett.2c00966
C. Qu et al. Interfacing q-AQUA with a polarizable force field: the best of both worlds J. Chem. Theory Comput. 19 3446 3459 10.1021/acs.jctc.3c00334
H. Partridge D.W. Schwenke The determination of an accurate isotope dependent potential energy surface for water from extensive ab initio calculations and experimental data J. Chem. Phys. 106 4618 10.1063/1.473987
Y.-C. Zhu et al. Torsional tunneling splitting in a water trimer J. Am. Chem. Soc. 144 21356 21362 10.1021/jacs.2c09909
B. Fu D.H. Zhang Ab initio potential energy surfaces and quantum dynamics for polyatomic bimolecular reactions J. Chem. Theory Comput. 14 2289 2303 10.1021/acs.jctc.8b00006
B. Cheng E.A. Engel J. Behler C. Dellago M. Ceriotti Ab initio thermodynamics of liquid and solid water Proc. Natl Acad. Sci. USA 116 1110 1115 10.1073/pnas.1815117116
Y. Zhang J. Xia B. Jiang REANN: a PyTorch-based end-to-end multi-functional deep neural network package for molecular, reactive, and periodic systems J. Chem. Phys. 156 114801 10.1063/5.0080766
Y. Zhai A. Caruso S.L. Bore Z. Luo F. Paesani A ‘short blanket’ dilemma for a state-of-the-art neural network potential for water: reproducing experimental properties or the physics of the underlying many-body interactions? J. Chem. Phys. 158 084111 10.1063/5.0142843
G.R. Medders V. Babin F. Paesani Development of a ‘first-principles’ water potential with flexible monomers. III. Liquid phase properties J. Chem. Theory Comput. 10 2906 2910 10.1021/ct5004115
V. Kapil et al. i-PI 2.0: a universal force engine for advanced molecular simulations Comput. Phys. Commun. 236 214 223 10.1016/j.cpc.2018.09.020
S.K. Reddy et al. On the accuracy of the MB-pol many-body potential for water: interaction energies, vibrational frequencies, and classical thermodynamic and dynamical properties from clusters to liquid water and ice J. Chem. Phys. 145 194504 10.1063/1.4967719
P.L. Houston et al. No headache for PIPs: a PIP potential for aspirin runs much faster and with similar precision than other machine-learned potentials J. Chem. Theory Comput. 20 3008 3018 10.1021/acs.jctc.4c00054
S. Habershon T.E. Markland D.E. Manolopoulos Competing quantum effects in the dynamics of a flexible water model J. Chem. Phys. 131 024501 10.1063/1.3167790
G.S. Fanourgakis S.S. Xantheas Development of transferable interaction potentials for water. V. Extension of the flexible, polarizable, Thole-type model potential (TTM3-F, v. 3.0) to describe the vibrational spectra of water clusters and liquid water J. Chem. Phys. 128 074506 10.1063/1.2837299
B. Cheng Cartesian atomic cluster expansion for machine learning interatomic potentials npj Comput. Mater. 10 157 10.1038/s41524-024-01332-4
R. Conte C. Qu J.M. Bowman Permutationally invariant fitting of many-body, non-covalent interactions with application to three-body methane–water–water J. Chem. Theory Comput. 11 1631 1638 10.1021/acs.jctc.5b00091
R. Mathur M.C. Muniz S. Yue R. Car A.Z. Panagiotopoulos First-principles-based machine learning models for phase behavior and transport properties of CO2 J. Phys. Chem. B 127 4562 4569 10.1021/acs.jpcb.3c00610
P.L. Houston et al. PESPIP: software to fit complex molecular and many-body potential energy surfaces with permutationally invariant polynomials J. Chem. Phys. 158 044109 10.1063/5.0134442
R. Chen K. Shao B. Fu D.H. Zhang Fitting potential energy surfaces with fundamental invariant neural network. II. Generating fundamental invariants for molecular systems with up to ten atoms J. Chem. Phys. 152 204307 10.1063/5.0010104
Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry. In International Conference on Machine Learning (eds. Precup, D. & Teh, Y. W.) 1263–1272 (PMLR, 2017).
K.T. Schütt F. Arbabzadah S. Chmiela K.R. Müller A. Tkatchenko Quantum-chemical insights from deep tensor neural networks Nat. Commun. 8 10.1038/ncomms13890 13890
C. Qu J.M. Bowman Communication: a fragmented, permutationally invariant polynomial approach for potential energy surfaces of large molecules: application to N-methyl acetamide J. Chem. Phys. 150 141101 10.1063/1.5092794
Moré, J. J. The Levenberg–Marquardt algorithm: implementation and theory. In Numerical Analysis: Proc. Biennial Conference held at Dundee, June 28–July 1, 1977 (ed. Watson, G. A.) 105–116 (Springer Berlin Heidelberg, 2006).
J.B. Anderson A random-walk simulation of the Schrödinger equation: H3+ J. Chem. Phys. 63 1499 1503 10.1063/1.431514
Yu, Q. et al. Data files for developing and testing MB-PIPNet models on water trimer, methane-water cluster, and liquid water. figshare https://doi.org/10.6084/m9.figshare.28510238.v1 (2025).
Yu, Q. Source code and example of MB-PIPNet approach. Zenodo https://doi.org/10.5281/zenodo.14954863 (2025).
Y. Wang J.M. Bowman Rigorous calculation of dissociation energies (D) of the water trimer, (H2O)3 and (D2O)3 J. Chem. Phys. 135 131101 10.1063/1.3647584
Y. Zhang C. Hu B. Jiang Accelerating atomistic simulations with piecewise machine-learned ab initio potentials at a classical force field-like cost Phys. Chem. Chem. Phys. 23 1815 1821 10.1039/D0CP05089J
D.P. Kovács I. Batatia E.S. Arany G. Csányi Evaluation of the MACE force field architecture: from medicinal chemistry to materials science J. Chem. Phys. 159 044118 10.1063/5.0155322
R. Mills Self-diffusion in normal and heavy water in the range 1–45° J. Phys. Chem. 77 685 688 10.1021/j100624a025
M. Holz S.R. Heil A. Sacco Temperature-dependent self-diffusion coefficients of water and six selected molecular liquids for calibration in accurate 1H NMR PFG measurements Phys. Chem. Chem. Phys. 2 4740 4742 10.1039/b005319h
L.B. Skinner et al. Benchmark oxygen–oxygen pair-distribution function of ambient water from X-ray diffraction measurements with a wide Q-range J. Chem. Phys. 138 074506 10.1063/1.4790861
L.B. Skinner C.J. Benmore J.C. Neuefeind J.B. Parise The structure of water around the compressibility minimum J. Chem. Phys. 141 214507 10.1063/1.4902412
A. Soper C. Benmore Quantum differences between heavy and light water Phys. Rev. Lett. 101 065502 10.1103/PhysRevLett.101.065502
