Hostname: page-component-586b7cd67f-tf8b9 Total loading time: 0 Render date: 2024-11-30T07:26:31.112Z Has data issue: false hasContentIssue false
  • English
  • Français

Artificial neural network correction for density-functional tight-binding molecular dynamics simulations

Published online by Cambridge University Press:  28 June 2019

Junmian Zhu Open the ORCID record for Junmian Zhu [Opens in a new window] ,
Van Quan Vuong Open the ORCID record for Van Quan Vuong [Opens in a new window] ,
Bobby G. Sumpter Open the ORCID record for Bobby G. Sumpter [Opens in a new window]  and
Stephan Irle Open the ORCID record for Stephan Irle [Opens in a new window]
Junmian Zhu
Affiliation:
Department of Chemistry, Grinnell College, Grinnell, IA, USA
Van Quan Vuong
Affiliation:
Bredesen Center for Interdisciplinary Research and Graduate Education, University of Tennessee, Knoxville, TN, USA
Bobby G. Sumpter
Affiliation:
Center for Nanophase Materials Sciences and Computational Sciences & Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
Stephan Irle*
Affiliation:
Bredesen Center for Interdisciplinary Research and Graduate Education, University of Tennessee, Knoxville, TN, USA Center for Nanophase Materials Sciences and Computational Sciences & Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA Chemical Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
*
Address all correspondence to Stephan Irle at [email protected]
Get access

Abstract

The authors developed a Behler–Parrinello-type neural network (NN) to improve the density-functional tight-binding (DFTB) energy and force prediction. The Δ-machine learning approach was adopted and the NN was designed to predict the energy differences between the density functional theory (DFT) quantum chemical potential and DFTB for a given molecular structure. Most notably, the DFTB-NN method is capable of improving the energetics of intramolecular hydrogen bonds and torsional potentials without modifying the framework of DFTB itself. This improvement enables considerably larger simulations of complex chemical systems that currently could not easily been accomplished using DFT or higher level ab initio quantum chemistry methods alone.

Type
Artificial Intelligence Research Letters
Information
MRS Communications , Volume 9 , Issue 3 , September 2019 , pp. 867 - 873
Copyright
Copyright © Materials Research Society 2019 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

1.Foulkes, W.M.C. and Haydock, R.: Tight-binding models and density-functional theory. Phys. Rev. B 39, 12520–12536 (1989).Google Scholar
2.Porezag, D., Frauenheim, T., Köhler, T., Seifert, G., and Kaschner, R.: Construction of tight-binding-like potentials on the basis of density-functional theory: application to carbon. Phys. Rev. B 51, 12947–12957 (1995).Google Scholar
3.Seifert, G., Porezag, D., and Frauenheim, T.: Calculations of molecules, clusters, and solids with a simplified LCAO-DFT-LDA scheme. Int. J. Quantum Chem. 58, 185–192 (1996).Google Scholar
4.Elstner, M., Porezag, D., Jungnickel, G., Elsner, J., Haugk, M., Frauenheim, T., Suhai, S., and Seifert, G.: Self-consistent-charge density-functional tight-binding method for simulations of complex materials properties. Phys. Rev. B 58, 7260–7268 (1998).Google Scholar
5.Aradi, B., Hourahine, B., and Frauenheim, T.: DFTB+, a sparse matrix-based implementation of the DFTB method. J. Phys. Chem. A 111, 5678–5684 (2007).Google Scholar
6.Elstner, M. and Seifert, G.: Density functional tight binding. Philos. Trans. R. Soc. A 372, 20120483–20120494 (2014).Google Scholar
7.Christensen, A.S., Kubar, T., Cui, Q. and Elstner, M.: Semiempirical quantum mechanical methods for noncovalent interactions for chemical and biochemical applications. Chem. Rev. 116, 5301–5337 (2016).Google Scholar
8.Lee, K.H., Schnupf, U., Sumpter, B.G., and Irle, S.: Performance of density-functional tight-binding in comparison to ab initio and first-principles methods for isomer geometries and energies of glucose epimers in vacuo and solution. ACS Omega 3, 16899–16915 (2018).Google Scholar
9.Gaus, M., Goez, A., and Elstner, M.: Parametrization and benchmark of DFTB3 for organic molecules. J. Chem. Theory Comput. 9, 338–354 (2013).Google Scholar
10.Vuong, V.Q., Akkarapattiakal Kuriappan, J., Kubillus, M., Kranz, J.J., Mast, T., Niehaus, T.A., Irle, S., and Elstner, M.: Parametrization and benchmark of long-range corrected DFTB2 for organic molecules. J. Chem. Theory Comput. 14, 115–125 (2018).Google Scholar
11.Behler, J. and Parrinello, M.: Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 146401 (2007).Google Scholar
12.Behler, J.: Atom-centered symmetry functions for constructing high-dimensional neural network potentials. J. Chem. Phys. 134, 074106 (2011).Google Scholar
13.Behler, J.: Representing potential energy surfaces by high-dimensional neural network potentials. J. Phys.: Condens. Matter 26, 183001 (2014).Google Scholar
14.Behler, J.: Constructing high-dimensional neural network potentials: a tutorial review. Int. J. Quantum Chem. 115, 1032–1050 (2015).Google Scholar
15.Smith, J.S., Isayev, O., and Roitberg, A.E.: ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chem. Sci. 8, 3192–3203 (2017).Google Scholar
16.Schütt, K.T., Arbabzadah, F., Chmiela, S., Müller, K.R., and Tkatchenko, A.: Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8, 13890 (2017).Google Scholar
17.Ramakrishnan, R., Dral, P.O., Rupp, M., and von Lilienfeld, O.A.: Big data meets quantum chemistry approximations: the Δ-machine learning approach. J. Chem. Theory Comput. 11, 2087–2096 (2015).Google Scholar
18.Nguyen, T.T., Székely, E., Imbalzano, G., Behler, J., Csányi, G., Ceriotti, M., Götz, A.W., and Paesani, F.: Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions. J. Chem. Phys. 148, 241725 (2018).Google Scholar
19.Shen, L., Wu, J., and Yang, W.: Multiscale quantum mechanics/molecular mechanics simulations with neural networks. J. Chem. Theory Comput. 12, 4934–4946 (2016).Google Scholar
20.Shen, L. and Yang, W.: Molecular dynamics simulations with quantum mechanics/molecular mechanics and adaptive neural networks. J. Chem. Theory Comput. 14, 1442–1455 (2018).Google Scholar
21.Gaus, M., Cui, Q., and Elstner, M.: DFTB3: extension of the self-consistent-charge density-functional tight-binding method (SCC-DFTB). J. Chem. Theory Comput. 7, 931–948 (2011).Google Scholar
22.Keras: Deep Learning for humans. https://github.com/keras-team/keras.Google Scholar
23.Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D.G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: a system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16) (2016), pp. 265–283.Google Scholar
24.Nguyen, D. and Widrow, B.: Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. In 1990 IJCNN International Joint Conference on Neural Networks, (1990) (1990), pp. 21–26.Google Scholar
25.Becke, A.D.: Density-functional thermochemistry. III. The role of exact exchange. J. Chem. Phys. 98, 5648–5652 (1993).Google Scholar
26.Hjorth Larsen, A., Jørgen Mortensen, J., Blomqvist, J., Castelli, I.E., Christensen, R., Dułak, M., Friis, J., Groves, M.N., Hammer, B., Hargus, C., Hermes, E.D., Jennings, P.C., Bjerre Jensen, P., Kermode, J., Kitchin, J.R., Leonhard Kolsbjerg, E., Kubal, J., Kaasbjerg, K., Lysgaard, S., Bergmann Maronsson, J., Maxson, T., Olsen, T., Pastewka, L., Peterson, A., Rostgaard, C., Schiøtz, J., Schütt, O., Strange, M., Thygesen, K.S., Vegge, T., Vilhelmsen, L., Walter, M., Zeng, Z., and Jacobsen, K.W.: The atomic simulation environment-a Python library for working with atoms. J. Phys.: Condens. Matter 29, 273002 (2017).Google Scholar
27.Valiev, M., Bylaska, E., Govind, N., Kowalski, K., Straatsma, T., Van Dam, H., Wang, D., Nieplocha, J., Apra, E., Windus, T., and de Jong, W.: NWChem: a comprehensive and scalable open-source solution for large scale molecular simulations. Comput. Phys. Commun. 181, 1477–1489 (2010).Google Scholar
28.Addicoat, M.A., Fukuoka, S., Page, A.J., and Irle, S.: Stochastic structure determination for conformationally flexible heterogenous molecular clusters: application to ionic liquids. J. Comput. Chem. 34, 2591–2600 (2013).Google Scholar
29.Rezáč, J., Riley, K.E., and Hobza, P.: S66: a well-balanced database of benchmark interaction energies relevant to biomolecular structures. J. Chem. Theory Comput. 7, 2427–2438 (2011).Google Scholar
30.Rezáč, J.: Empirical self-consistent correction for the description of hydrogen bonds in DFTB3. J. Chem. Theory Comput. 13, 4804–4817 (2017).Google Scholar
Supplementary material: PDF

Zhu et al. supplementary material

Zhu et al. supplementary material 1

Download Zhu et al. supplementary material(PDF)
PDF 156.3 KB