Abstract
We introduce a novel class of localized atomic environment representations based upon the Coulomb matrix. By combining these functions with the Gaussian approximation potential approach, we present LC-GAP, a new system for generating atomic potentials through machine learning (ML). Tests on the QM7, QM7b and GDB9 biomolecular datasets demonstrate that potentials created with LC-GAP can successfully predict atomization energies for molecules larger than those used for training to chemical accuracy, and can (in the case of QM7b) also be used to predict a range of other atomic properties with accuracy in line with the recent literature. As the best-performing representation has only linear dimensionality in the number of atoms in a local atomic environment, this represents an improvement in both prediction accuracy and computational cost when compared to similar Coulomb matrix-based methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
All non-hydrogen atoms are considered heavy.
- 2.
The atomization energy is the potential energy of a molecule that has been adjusted by the combined potential energy of its isolated atoms [5].
- 3.
Here, we tested values (α, r cut) ∈ {3, 4, …, 7} ×{ 3. 0, 3. 5, 4. 0, 4. 5, …, 7. 0}.
References
A.P. Bartók, R. Kondor, G. Csányi, On representing chemical environments. Phys. Rev. B 87, 184115 (2013)
A.P. Bartók, M.C. Payne, R. Kondor, G. Csányi, Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. Phys. Rev. Lett. 04, 136403 (2010)
L.C. Blum, J.-L. Reymond, 970 million druglike small molecules for virtual screening in the chemical universe database GDB-13. J. Am. Chem. Soc. 131, 8732–8733 (2009)
S. De, A.P. Bartók, G. Csányi, M. Ceriotti, Comparing molecules and solids across structural and alchemical space. Phys. Chem. Chem. Phys. 18, 13754–13769 (2016)
S. Fliszár, Atoms, Chemical Bonds, and Bond Dissociation Energies. Lecture Notes in Chemistry (Springer, Berlin, 1994)
M. Griebel, S. Knapek, G. Zumbusch, Numerical Simulation in Molecular Dynamics: Numerics, Algorithms, Parallelization, Applications. Texts in Computational Science and Engineering, vol. 5 (Springer Science & Business Media, Heidelberg, 2007)
K. Hansen, G. Montavon, F. Biegler et al., Assessment and validation of machine learning methods for predicting molecular atomization energies. J. Chem. Theory Comput. 9, 3404–3419 (2013)
K. Hansen, F. Biegler, R. Ramakrishnan et al., Machine learning predictions of molecular properties: accurate many-body potentials and nonlocality in chemical space. J. Phys. Chem. Lett. 6, 2326–2331 (2015)
W. Kohn, Density functional and density matrix method scaling linearly with the number of atoms. Phys. Rev. Lett. 76, 3168–3171 (1996)
G. Montavon, K. Hansen, S. Fazli et al., Learning invariant representations of molecules for atomization energy prediction, in Advances in Neural Information Processing Systems (Springer, Berlin, 2012), pp. 440–448
G. Montavon, M. Rupp, V. Gobre et al., Machine learning of molecular electronic properties in chemical compound space. New J. Phys. 15, 095003 (2013)
S.J. Plimpton, A.P. Thompson, Computational aspects of many-body potentials. MRS Bull. 37, 513–521 (2012)
E. Prodan, W. Kohn, Nearsightedness of electronic matter. Proc. Natl. Acad. Sci. U. S. A. 102, 11635–11638 (2005)
R. Ramakrishnan, P.O. Dral, M. Rupp, O.A. von Lilienfeld, Quantum chemistry structures and properties of 134 kilo molecules. Sci. Data 1 (2014). doi:10.1038/sdata.2014.22
C.E. Rasmussen, C.K.I. Williams, Gaussian Processes for Machine Learning (The MIT Press, Cambridge, 2006)
M. Rupp, Machine learning for quantum mechanics in a nutshell. Int. J. Quantum Chem. 115, 1058–1073 (2015)
M. Rupp, A. Tkatchenko, K.-R. Müller, O.A. von Lilienfeld, Fast and accurate modeling of molecular atomization energies with machine learning. Phys. Rev. Lett. 108, 058301 (2012)
M. Rupp, R. Ramakrishnan, O.A. von Lilienfeld, Machine learning for quantum mechanical properties of atoms in molecules. J. Phys. Chem. Lett. 6, 3309–3313 (2015)
E. Tadmor, R. Miller, Modeling Materials: Continuum, Atomistic and Multiscale Techniques (Cambridge University Press, Cambridge, 2011)
C.J. Willmott, K. Matsuura, Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 30, 79–82 (2005)
Acknowledgements
This work was funded in part by the German Federal Ministry for Education and Research under the Eurostars project E!6935 ATOMMODEL. We would also like to thank Maharavo Randrianarivony for fruitful discussions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Barker, J., Bulin, J., Hamaekers, J., Mathias, S. (2017). LC-GAP: Localized Coulomb Descriptors for the Gaussian Approximation Potential. In: Griebel, M., Schüller, A., Schweitzer, M. (eds) Scientific Computing and Algorithms in Industrial Simulations. Springer, Cham. https://doi.org/10.1007/978-3-319-62458-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-62458-7_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-62457-0
Online ISBN: 978-3-319-62458-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)