Enhancing transferability of machine learning-based polarizability models in condensed-phase systems via atomic polarizability constraint

Machine Learning


  • Chen, F. et al. Polarizability matters in enantio-selection. Nat. Commun. 15, 3394 (2024).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Qin, J., Liu, Z., Ma, M. & Li, Y. Optimizing and extending ion dielectric polarizability database for microwave frequencies using machine learning methods. npj Comput. Mater. 9, 132 (2023).

    Article 

    Google Scholar 

  • Wang, J., Xie, X. Q., Hou, T. & Xu, X. Fast approaches for molecular polarizability calculations. J. Phys. Chem. A 111, 4443–4448 (2007).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Berger, E. & Komsa, H.-P. Polarizability models for simulations of finite temperature Raman spectra from machine learning molecular dynamics. Phys. Rev. Mater. 8, 043802 (2024).

    Article 
    CAS 

    Google Scholar 

  • Thomas, M., Brehm, M., Fligg, R., Vöhringer, P. & Kirchner, B. Computing vibrational spectra from ab initio molecular dynamics. Phys. Chem. Chem. Phys. 15, 6608 (2013).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Nakata, H., Fedorov, D. G., Yokojima, S., Kitaura, K. & Nakamura, S. Simulations of Raman spectra using the fragment molecular orbital method. J. Chem. Theory Comput. 10, 3689–3698 (2014).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Guha, S., Menéndez, J., Page, J. B. & Adams, G. B. Empirical bond polarizability model for fullerenes. Phys. Rev. B 53, 13106–13114 (1996).

    Article 
    CAS 

    Google Scholar 

  • Applequist, J. An atom dipole interaction model for molecular optical properties. Acc. Chem. Res. 10, 79–85 (1977).

    Article 
    CAS 

    Google Scholar 

  • Bougeard, D. & Smirnov, K. S. Calculation of off-resonance Raman scattering intensities with parametric models. J. Raman Spectrosc. 40, 1704–1719 (2009).

    Article 
    CAS 

    Google Scholar 

  • Li, W., Dong, H., Ma, J. & Li, S. Structures and spectroscopic properties of large molecules and condensed-phase systems predicted by generalized energy-based fragmentation approach. Acc. Chem. Res. 54, 169–181 (2021).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Zhang, L., Cheng, Z., Li, W. & Li, S. Generalized energy-based fragmentation approach for accurate binding energies and Raman spectra of methane hydrate clusters. Chin. J. Chem. Phys. 35, 167–176 (2022).

    Article 
    CAS 

    Google Scholar 

  • Zhao, D. et al. Accurate and efficient prediction of post–Hartree–Fock polarizabilities of condensed-phase systems. J. Chem. Theory Comput. 19, 6461–6470 (2023).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Zhao, D. et al. Fragment-based deep learning for simultaneous prediction of polarizabilities and NMR shieldings of macromolecules and their aggregates. J. Chem. Theory Comput. 20, 2655–2665 (2024).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Wang, T. et al. Ab initio characterization of protein molecular dynamics with AI2BMD. Nature 635, 1019–1027 (2024).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Raghavachari, K. & Saha, A. Accurate composite and fragment-based quantum chemical models for large molecules. Chem. Rev. 115, 5643–5677 (2015).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Liu, J. & He, X. Fragment-based quantum mechanical approach to biomolecules, molecular clusters, molecular crystals and liquids. Phys. Chem. Chem. Phys. 22, 12341–12367 (2020).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Wilkins, D. M. et al. Accurate molecular polarizabilities with coupled cluster theory and machine learning. Proc. Natl. Acad. Sci. USA 116, 3401–3406 (2019).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Grisafi, A., Wilkins, D. M., Csányi, G. & Ceriotti, M. Symmetry-adapted machine learning for tensorial properties of atomistic systems. Phys. Rev. Lett. 120, 036002 (2018).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Zhang, Y. et al. Efficient and accurate simulations of vibrational and electronic spectra with symmetry-preserving neural network models for tensorial properties. J. Phys. Chem. B 124, 7284–7290 (2020).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Zhang, L. et al. Deep neural network for the dielectric response of insulators. Phys. Rev. B 102, 041121 (2020).

    Article 
    CAS 

    Google Scholar 

  • Sommers, G. M., Andrade, M. F. C., Zhang, L., Wang, H. & Car, R. Raman spectrum and polarizability of liquid water from deep neural networks. Phys. Chem. Chem. Phys. 22, 10592–10602 (2020).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Gastegger, M., Schütt, K. T. & Müller, K.-R. Machine learning of solvent effects on molecular spectra and reactions. Chem. Sci. 12, 11473–11483 (2021).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Schütt, K., Unke, O. & Gastegger, M. In Equivariant Message Passing for the Prediction of Tensorial Properties and Molecular Spectra 9377–9388 (PMLR, 2021).

  • Zhang, Y., Jiang, J. & Jiang, B. Learning dipole moments and polarizabilities. In Quantum Chemistry in the Age of Machine Learning 453–465 (Elsevier, 2023).

  • Raimbault, N., Grisafi, A., Ceriotti, M. & Rossi, M. Using Gaussian process regression to simulate the vibrational Raman spectra of molecular crystals. N. J. Phys. 21, 105001 (2019).

    Article 
    CAS 

    Google Scholar 

  • Zhang, Y. & Jiang, B. Universal machine learning for the response of atomistic systems to external fields. Nat. Commun. 14, 6424 (2023).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Kapil, V., Kovács, D. P., Csányi, G. & Michaelides, A. First-principles spectroscopy of aqueous interfaces using machine-learned electronic and quantum nuclear effects. Faraday Discuss 249, 50–68 (2024).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Xu, N. et al. Tensorial properties via the neuroevolution potential framework: fast simulation of infrared and Raman spectra. J. Chem. Theory Comput. 20, 3273 (2024).

  • Eckhoff, M. & Behler, J. From molecular fragments to the bulk: development of a neural network potential for MOF-5. J. Chem. Theory Comput. 15, 3793–3809 (2019).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Zaverkin, V., Holzmüller, D., Schuldt, R. & Kästner, J. Predicting properties of periodic systems from cluster data: a case study of liquid water. J. Chem. Phys. 156, 114103 (2022).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Schran, C., Brieuc, F. & Marx, D. Transferability of machine learning potentials: protonated water neural network potential applied to the protonated water hexamer. J. Chem. Phys. 154, 051101 (2021).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Herbold, M. & Behler, J. Machine learning transferable atomic forces for large systems from underconverged molecular fragments. Phys. Chem. Chem. Phys. 25, 12979–12989 (2023).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Chong, S. et al. Robustness of local predictions in atomistic machine learning models. J. Chem. Theory Comput. 19, 8020–8031 (2023).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • El-Machachi, Z., Wilson, M. & Deringer, V. L. Exploring the configurational space of amorphous graphene with machine-learned atomic energies. Chem. Sci. 13, 13720–13731 (2022).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Elola, M. D. & Ladanyi, B. M. Molecular dynamics study of polarizability anisotropy relaxation in aromatic liquids and its connection with local structure. J. Phys. Chem. B 110, 15525–15541 (2006).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Tuschel, D. Raman crystallography and the effect of Raman polarizability tensor element values. Spectroscopy 35, 5–12 (2020).

  • Hiener, D. C., Folmsbee, D. L., Langkamp, L. A. & Hutchison, G. R. Evaluating fast methods for static polarizabilities on extended conjugated oligomers. Phys. Chem. Chem. Phys. 24, 23173–23181 (2022).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Schran, C., Brezina, K. & Marsalek, O. Committee neural network potentials control generalization errors and enable active learning. J. Chem. Phys. 153, 104105 (2020).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Erlebach, A., Nachtigall, P. & Grajciar, L. Accurate large-scale simulations of siliceous zeolites by neural network potentials. npj Comput. Mater. 8, 174 (2022).

    Article 
    CAS 

    Google Scholar 

  • Margraf, J. T. Science-driven atomistic machine learning. Angew. Chem. Int. Ed. 62, e202219170 (2023).

    Article 
    CAS 

    Google Scholar 

  • Carrete, J., Montes-Campos, H., Wanzenböck, R., Heid, E. & Madsen, G. K. H. Deep ensembles vs committees for uncertainty estimation in neural-network force fields: comparison and application to active learning. J. Chem. Phys. 158, 204801 (2023).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Zhang, H., Juraskova, V. & Duarte, F. Modelling chemical processes in explicit solvents with machine learning potentials. Nat. Commun. 15, 6114 (2024).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Berger, E., Niemelä, J., Lampela, O., Juffer, A. H. & Komsa, H.-P. Raman spectra of amino acids and peptides from machine learning polarizabilities. J. Chem. Inf. Model. 64, 4601–4612 (2024).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Feng, C., Xi, J., Zhang, Y., Jiang, B. & Zhou, Y. Accurate and interpretable dipole interaction model-based machine learning for molecular polarizability. J. Chem. Theory Comput. 19, 1207–1217 (2023).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Dawes, R., Dwyer, J. R., Qu, W. & Gough, K. M. QTAIM investigation of the electronic structure and large Raman scattering intensity of bicyclo-[1.1.1]-pentane. J. Phys. Chem. A 115, 13149–13157 (2011).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Ángyán, J.G., Jansen, G., Loos, M., Hättig, C. & Hess, B.A. Distributed polarizabilities using the topological theory of atoms in molecules. In AIP Conference Proceedings Vol. 330 67–67 (AIP, 1995).

  • Macchi, P. & Krawczuk, A. The polarizability of organometallic bonds. Comput. Theor. Chem. 1053, 165–172 (2015).

    Article 
    CAS 

    Google Scholar 

  • Doherty, D. C. & Hopfinger, A. J. Molecular modeling of polymers: molecular dynamics simulation of the rotator phase of C 21 H 44. Phys. Rev. Lett. 72, 661–664 (1994).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Phillips, T. L. & Hanna, S. A comparison of computer models for the simulation of crystalline polyethylene and the long n-alkanes. Polymer 46, 11003–11018 (2005).

    Article 
    CAS 

    Google Scholar 

  • Ryckaert, J.-P., McDonald, I. R. & Klein, M. L. Disorder in the pseudohexagonal rotator phase of n-alkanes: molecular-dynamics calculations for tricosane. Mol. Phys. 67, 957–979 (1989).

    Article 
    CAS 

    Google Scholar 

  • Nosé, S. [Ubar] I. A molecular dynamics method for simulations in the canonical ensemble. Mol. Phys. 100, 191–198 (2002).

    Article 

    Google Scholar 

  • Nosé, S. A molecular dynamics method for simulations in the canonical ensemble. Mol. Phys. 52, 255–268 (1984).

    Article 

    Google Scholar 

  • Parrinello, M. & Rahman, A. Polymorphic transitions in single crystals: a new molecular dynamics method. J. Appl. Phys. 52, 7182–7190 (1981).

    Article 
    CAS 

    Google Scholar 

  • Sun, H., Ren, P. & Fried, J. The COMPASS force field: parameterization and validation for phosphazenes. Comput. Theor. Polym. Sci. 8, 229–246 (1998).

    Article 
    CAS 

    Google Scholar 

  • Thompson, A. P. et al. LAMMPS—a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Comput. Phys. Commun. 271, 108171 (2022).

    Article 
    CAS 

    Google Scholar 

  • Gastegger, M., Behler, J. & Marquetand, P. Machine learning molecular dynamics for the simulation of infrared spectra. Chem. Sci. 8, 6924–6935 (2017).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Goedecker, S., Teter, M. & Hutter, J. Separable dual-space Gaussian pseudopotentials. Phys. Rev. B 54, 1703 (1996).

    Article 
    CAS 

    Google Scholar 

  • Hartwigsen, C., Gœdecker, S. & Hutter, J. Relativistic separable dual-space Gaussian pseudopotentials from H to Rn. Phys. Rev. B 58, 3641 (1998).

    Article 
    CAS 

    Google Scholar 

  • Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865–3868 (1996).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Lippert, G., Hutter, J. & Parrinello, M. A hybrid Gaussian and plane wave density functional scheme. Mol. Phys. 92, 477–488 (1997).

    Article 
    CAS 

    Google Scholar 

  • Kühne, T. D. et al. CP2K: an electronic structure and molecular dynamics software package – Quickstep: efficient and accurate electronic structure calculations. J. Chem. Phys. 152, 194103 (2020).

    Article 
    PubMed 

    Google Scholar 

  • Fan, Z., Chen, W., Vierimaa, V. & Harju, A. Efficient molecular dynamics simulations with many-body potentials on graphics processing units. Comput. Phys. Commun. 218, 10–16 (2017).

    Article 
    CAS 

    Google Scholar 

  • Behler, J. & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 146401 (2007).

    Article 
    PubMed 

    Google Scholar 

  • Musil, F. et al. Physics-inspired structural representations for molecules and materials. Chem. Rev. 121, 9759–9815 (2021).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Langer, M. F., Goeßmann, A. & Rupp, M. Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning. npj Comput. Mater. 8, 41 (2022).

    Article 

    Google Scholar 

  • Fan, Z. et al. Neuroevolution machine learning potentials: combining high accuracy and low cost in atomistic simulations and application to heat transport. Phys. Rev. B 104, 104309 (2021).

    Article 
    CAS 

    Google Scholar 

  • Fan, Z. Improving the accuracy of the neuroevolution machine learning potential for multi-component systems. J. Phys.: Condens. Matter 34, 125902 (2022).

    CAS 

    Google Scholar 

  • Fan, Z. et al. GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations. J. Chem. Phys. 157, 114801 (2022).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Song, K. et al. General-purpose machine-learned potential for 16 elemental metals and their alloys. Nat. Commun. 15, 10208 (2024).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Fang, M. et al. Transferability of machine learning models for predicting Raman spectra. J. Phys. Chem. A 128, 2286–2294 (2024).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Bannwarth, C., Ehlert, S. & Grimme, S. GFN2-xTB—an accurate and broadly parametrized self-consistent tight-binding quantum chemical method with multipole electrostatics and density-dependent dispersion contributions. J. Chem. Theory Comput. 15, 1652–1671 (2019).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Caldeweyher, E. et al. A generally applicable atomic-charge dependent London dispersion correction. J. Chem. Phys. 150, 154122 (2019).

    Article 
    PubMed 

    Google Scholar 

  • Caldeweyher, E., Bannwarth, C. & Grimme, S. Extension of the D3 dispersion coefficient model. J. Chem. Phys. 147, 034112 (2017).

    Article 
    PubMed 

    Google Scholar 

  • Tkatchenko, A. & Scheffler, M. Accurate molecular van der Waals interactions from ground-state electron density and free-atom reference data. Phys. Rev. Lett. 102, 073005 (2009).

    Article 
    PubMed 

    Google Scholar 

  • Blair, S. A. & Thakkar, A. J. Relating polarizability to volume, ionization energy, electronegativity, hardness, moments of momentum, and other molecular properties. J. Chem. Phys. 141, 074306 (2014).

    Article 
    PubMed 

    Google Scholar 

  • Hermann, J., DiStasio, R. A. & Tkatchenko, A. First-principles models for van der Waals interactions in molecules and materials: concepts, theory, and applications. Chem. Rev. 117, 4714–4758 (2017).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Heid, E., Szabadi, A. & Schröder, C. Quantum mechanical determination of atomic polarizabilities of ionic liquids. Phys. Chem. Chem. Phys. 20, 10992–10996 (2018).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Lu, T. & Chen, F.-W. Comparison of computational methods for atomic charges. Acta Phys. Chim. Sin. 28, 1–18 (2012).

    Article 

    Google Scholar 

  • Lu, T. & Chen, F. Multiwfn: a multifunctional wavefunction analyzer. J. Comput. Chem. 33, 580–592 (2012).

    Article 
    PubMed 

    Google Scholar 



  • Source link

    Leave a Reply

    Your email address will not be published. Required fields are marked *