Electronic spectra from TDDFT and machine learning in chemical space
Abstract
Due to its favorable computational efficiency, time-dependent (TD) density functional theory (DFT) enables the prediction of electronic spectra in a high-throughput manner across chemical space. Its predictions, however, can be quite inaccurate. In this work, we resolve this issue with machine learning models trained on deviations of reference second-order approximate coupled-cluster (CC2) singles and doubles spectra from TDDFT counterparts, or even from DFT gap. We applied this approach to low-lying singlet-singlet vertical electronic spectra of over 20 000 synthetically feasible small organic molecules with up to eight CONF atoms. The prediction errors decay monotonously as a function of training set size. For a training set of 10 000 molecules, CC2 excitation energies can be reproduced to within ±0.1 eV for the remaining molecules. Analysis of our spectral database via chromophore counting suggests that even higher accuracies can be achieved. Based on the evidence collected, we discuss open challenges associated with data-driven modeling of high-lying spectra and transition intensities.
- Authors:
-
- Univ. of Basel (Switzerland)
- California State Univ. (CalState), Long Beach, CA (United States)
- Univ. of Basel (Switzerland); Argonne National Lab. (ANL), Argonne, IL (United States). Argonne Leadership Computing Facility (ALCF)
- Publication Date:
- Research Org.:
- Argonne National Laboratory (ANL), Argonne, IL (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC); Swiss National Science Foundation (SNF)
- OSTI Identifier:
- 1392463
- Alternate Identifier(s):
- OSTI ID: 1229636
- Grant/Contract Number:
- AC02-06CH11357; PP00P2_138932
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Chemical Physics
- Additional Journal Information:
- Journal Volume: 143; Journal Issue: 8; Journal ID: ISSN 0021-9606
- Publisher:
- American Institute of Physics (AIP)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
Citation Formats
Ramakrishnan, Raghunathan, Hartmann, Mia, Tapavicza, Enrico, and von Lilienfeld, O. Anatole. Electronic spectra from TDDFT and machine learning in chemical space. United States: N. p., 2015.
Web. doi:10.1063/1.4928757.
Ramakrishnan, Raghunathan, Hartmann, Mia, Tapavicza, Enrico, & von Lilienfeld, O. Anatole. Electronic spectra from TDDFT and machine learning in chemical space. United States. https://doi.org/10.1063/1.4928757
Ramakrishnan, Raghunathan, Hartmann, Mia, Tapavicza, Enrico, and von Lilienfeld, O. Anatole. Tue .
"Electronic spectra from TDDFT and machine learning in chemical space". United States. https://doi.org/10.1063/1.4928757. https://www.osti.gov/servlets/purl/1392463.
@article{osti_1392463,
title = {Electronic spectra from TDDFT and machine learning in chemical space},
author = {Ramakrishnan, Raghunathan and Hartmann, Mia and Tapavicza, Enrico and von Lilienfeld, O. Anatole},
abstractNote = {Due to its favorable computational efficiency, time-dependent (TD) density functional theory (DFT) enables the prediction of electronic spectra in a high-throughput manner across chemical space. Its predictions, however, can be quite inaccurate. In this work, we resolve this issue with machine learning models trained on deviations of reference second-order approximate coupled-cluster (CC2) singles and doubles spectra from TDDFT counterparts, or even from DFT gap. We applied this approach to low-lying singlet-singlet vertical electronic spectra of over 20 000 synthetically feasible small organic molecules with up to eight CONF atoms. The prediction errors decay monotonously as a function of training set size. For a training set of 10 000 molecules, CC2 excitation energies can be reproduced to within ±0.1 eV for the remaining molecules. Analysis of our spectral database via chromophore counting suggests that even higher accuracies can be achieved. Based on the evidence collected, we discuss open challenges associated with data-driven modeling of high-lying spectra and transition intensities.},
doi = {10.1063/1.4928757},
journal = {Journal of Chemical Physics},
number = 8,
volume = 143,
place = {United States},
year = {Tue Aug 25 00:00:00 EDT 2015},
month = {Tue Aug 25 00:00:00 EDT 2015}
}
Web of Science
Works referenced in this record:
Recognizing molecular patterns by machine learning: An agnostic structural definition of the hydrogen bond
journal, November 2014
- Gasparotto, Piero; Ceriotti, Michele
- The Journal of Chemical Physics, Vol. 141, Issue 17
Generalized Gradient Approximation Made Simple
journal, October 1996
- Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias
- Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868
Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties
preprint, January 2013
- von Lilienfeld, O. Anatole; Ramakrishnan, Raghunathan; Rupp, Matthias
- arXiv
Machine learning for many-body physics: The case of the Anderson impurity model
journal, October 2014
- Arsenault, Louis-François; Lopez-Bezanilla, Alejandro; von Lilienfeld, O. Anatole
- Physical Review B, Vol. 90, Issue 15
Entangled trajectory molecular dynamics in multidimensional systems: Two-dimensional quantum tunneling through the Eckart barrier
journal, July 2012
- Martens, Craig C.
- The Journal of Chemical Physics, Vol. 137, Issue 3
Machine learning of molecular electronic properties in chemical compound space
text, January 2013
- Montavon, Gregoire; Rupp, Matthias; Gobre, Vivekanand
- IOP Publishing
Machine learning for many-body physics: The case of the Anderson impurity model
text, January 2014
- Arsenault, Louis-Francois; Lopez-Bezanilla, Alejandro; Von Lilienfeld, O. Anatole
- American Physical Society
Modeling electronic quantum transport with machine learning
text, January 2014
- Lopez-Bezanilla, Alejandro; Von Lilienfeld, O. Anatole
- American Physical Society
Many Molecular Properties from One Kernel in Chemical Space
text, January 2015
- Raghunathan, Ramakrishnan,; Anatole, von Lilienfeld, O.
- Schweizerische Chemische Gesellschaft
Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties
text, January 2015
- Von Lilienfeld, O. Anatole; Ramakrishnan, Raghunathan; Rupp, Matthias
- Wiley
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space
journal, June 2015
- Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan
- The Journal of Physical Chemistry Letters, Vol. 6, Issue 12
Adiabatic time-dependent density functional methods for excited state properties
journal, October 2002
- Furche, Filipp; Ahlrichs, Reinhart
- The Journal of Chemical Physics, Vol. 117, Issue 16
Highly Efficient and Photostable Photosensitizer Based on BODIPY Chromophore
journal, September 2005
- Yogo, Takatoshi; Urano, Yasuteru; Ishitsuka, Yukiko
- Journal of the American Chemical Society, Vol. 127, Issue 35
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach
text, January 2015
- Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias
- American Chemical Society
Many Molecular Properties from One Kernel in Chemical Space
journal, April 2015
- Ramakrishnan, Raghunathan; von Lilienfeld, O. Anatole
- CHIMIA International Journal for Chemistry, Vol. 69, Issue 4
Machine learning of molecular electronic properties in chemical compound space
journal, September 2013
- Montavon, Grégoire; Rupp, Matthias; Gobre, Vivekanand
- New Journal of Physics, Vol. 15, Issue 9
Benchmarking Coupled Cluster Methods on Valence Singlet Excited States
journal, July 2014
- Kánnár, Dániel; Szalay, Péter G.
- Journal of Chemical Theory and Computation, Vol. 10, Issue 9
Optimizing transition states via kernel-based machine learning
journal, May 2012
- Pozun, Zachary D.; Hansen, Katja; Sheppard, Daniel
- The Journal of Chemical Physics, Vol. 136, Issue 17
Excited-State Dynamics of Isolated and Microsolvated Cinnamate-Based UV-B Sunscreens
journal, July 2014
- Tan, Eric M. M.; Hilbers, Michiel; Buma, Wybren J.
- The Journal of Physical Chemistry Letters, Vol. 5, Issue 14
Improvements on the direct SCF method: Improved Direct SCF Method
journal, January 1989
- Häser, Marco; Ahlrichs, Reinhart
- Journal of Computational Chemistry, Vol. 10, Issue 1
Self-Consistent Equations Including Exchange and Correlation Effects
journal, November 1965
- Kohn, W.; Sham, L. J.
- Physical Review, Vol. 140, Issue 4A, p. A1133-A1138
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
journal, January 2012
- Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert
- Physical Review Letters, Vol. 108, Issue 5
Improving the performance of doped π-conjugated polymers for use in organic light-emitting diodes
journal, June 2000
- Gross, Markus; Müller, David C.; Nothofer, Heinz-Georg
- Nature, Vol. 405, Issue 6787
Excitation energies in density functional theory: An evaluation and a diagnostic test
journal, January 2008
- Peach, Michael J. G.; Benfield, Peter; Helgaker, Trygve
- The Journal of Chemical Physics, Vol. 128, Issue 4
Photoelectrochemical Cells
journal, February 1980
- Nozik, A. J.
- Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 295, Issue 1414
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach
journal, April 2015
- Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias
- Journal of Chemical Theory and Computation, Vol. 11, Issue 5
Energy Transfer Tunes Phosphorescent Color of Single-Dopant White OLEDs
journal, November 2011
- Han, Juan; Chen, XueBo; Shen, Lin
- Chemistry - A European Journal, Vol. 17, Issue 50
Correlated electron dynamics with time-dependent quantum Monte Carlo: Three-dimensional helium
journal, July 2011
- Christov, Ivan P.
- The Journal of Chemical Physics, Vol. 135, Issue 4
Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17
journal, November 2012
- Ruddigkeit, Lars; van Deursen, Ruud; Blum, Lorenz C.
- Journal of Chemical Information and Modeling, Vol. 52, Issue 11
Unravelling the details of vitamin D photosynthesis by non-adiabatic molecular dynamics simulations
journal, January 2011
- Tapavicza, Enrico; Meyer, Alexander M.; Furche, Filipp
- Physical Chemistry Chemical Physics, Vol. 13, Issue 47
Extensive TD-DFT Benchmark: Singlet-Excited States of Organic Molecules
journal, August 2009
- Jacquemin, Denis; Wathelet, Valérie; Perpète, Eric A.
- Journal of Chemical Theory and Computation, Vol. 5, Issue 9
Inverse Strategies for Molecular Design
journal, January 1996
- Kuhn, Christoph; Beratan, David N.
- The Journal of Physical Chemistry, Vol. 100, Issue 25
A Simplex Method for Function Minimization
journal, January 1965
- Nelder, J. A.; Mead, R.
- The Computer Journal, Vol. 7, Issue 4
Kernel density estimation via diffusion
journal, October 2010
- Botev, Z. I.; Grotowski, J. F.; Kroese, D. P.
- The Annals of Statistics, Vol. 38, Issue 5
Relaxed active space: Fixing tailored-CC with high order coupled cluster. I
journal, December 2012
- Melnichuk, Anna; Bartlett, Rodney J.
- The Journal of Chemical Physics, Vol. 137, Issue 21
Kernel density estimation via diffusion
text, January 2010
- Botev, Z. I.; Grotowski, J. F.; Kroese, D. P.
- arXiv
Finding Density Functionals with Machine Learning
journal, June 2012
- Snyder, John C.; Rupp, Matthias; Hansen, Katja
- Physical Review Letters, Vol. 108, Issue 25
A Computational Investigation of Organic Dyes for Dye-Sensitized Solar Cells: Benchmark, Strategies, and Open Issues
journal, March 2010
- Pastore, Mariachiara; Mosconi, Edoardo; De Angelis, Filippo
- The Journal of Physical Chemistry C, Vol. 114, Issue 15
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
text, January 2011
- Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert
- arXiv
Using Molecular Similarity to Develop Reliable Models of Chemical Reactions in Complex Environments
journal, November 2009
- Ediz, Volkan; Monda, Anthony C.; Brown, Robert P.
- Journal of Chemical Theory and Computation, Vol. 5, Issue 12
Double excitations within time-dependent density functional theory linear response
journal, April 2004
- Maitra, Neepa T.; Zhang, Fan; Cave, Robert J.
- The Journal of Chemical Physics, Vol. 120, Issue 13
Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties
journal, April 2015
- von Lilienfeld, O. Anatole; Ramakrishnan, Raghunathan; Rupp, Matthias
- International Journal of Quantum Chemistry, Vol. 115, Issue 16
Time-Dependent Density Functional Response Theory for Molecules
book, November 1995
- Casida, Mark E.
- Recent Advances in Density Functional Methods
CC2 excitation energy calculations on large molecules using the resolution of the identity approximation
journal, January 2000
- Hättig, Christof; Weigend, Florian
- The Journal of Chemical Physics, Vol. 113, Issue 13
A new hybrid exchange–correlation functional using the Coulomb-attenuating method (CAM-B3LYP)
journal, July 2004
- Yanai, Takeshi; Tew, David P.; Handy, Nicholas C.
- Chemical Physics Letters, Vol. 393, Issue 1-3, p. 51-57
Using molecular similarity to construct accurate semiempirical electronic structure theories
journal, September 2004
- Janesko, Benjamin G.; Yaron, David
- The Journal of Chemical Physics, Vol. 121, Issue 12
Oscillator Strength: How Does TDDFT Compare to EOM-CCSD?
journal, December 2010
- Caricato, Marco; Trucks, Gary W.; Frisch, Michael J.
- Journal of Chemical Theory and Computation, Vol. 7, Issue 2
Recognizing molecular patterns by machine learning: an agnostic structural definition of the hydrogen bond
text, January 2014
- Gasparotto, Piero; Ceriotti, Michele
- arXiv
Balanced basis sets of split valence, triple zeta valence and quadruple zeta valence quality for H to Rn: Design and assessment of accuracy
journal, January 2005
- Weigend, Florian; Ahlrichs, Reinhart
- Physical Chemistry Chemical Physics, Vol. 7, Issue 18, p. 3297-3305
Density Estimation for Statistics and Data Analysis
journal, November 1987
- Dehnad, Khosrow
- Technometrics, Vol. 29, Issue 4
Design strategies of metal free-organic sensitizers for dye sensitized solar cells: Role of donor and acceptor monomers
journal, June 2014
- Tseng, Chieh-Yu; Taufany, Fadlilatul; Nachimuthu, Santhanamoorthi
- Organic Electronics, Vol. 15, Issue 6
Modeling electronic quantum transport with machine learning
journal, June 2014
- Lopez-Bezanilla, Alejandro; von Lilienfeld, O. Anatole
- Physical Review B, Vol. 89, Issue 23
Fast and accurate modeling of molecular atomization energies with machine learning
text, January 2012
- Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert
- American Physical Society
Modeling Electronic Quantum Transport with Machine Learning
text, January 2014
- Lopez-Bezanilla, Alejandro; von Lilienfeld, O. Anatole
- arXiv
Assessing Excited State Methods by Adiabatic Excitation Energies
journal, July 2011
- Send, Robert; Kühn, Michael; Furche, Filipp
- Journal of Chemical Theory and Computation, Vol. 7, Issue 8
Assessment of the Perdew–Burke–Ernzerhof exchange-correlation functional
journal, March 1999
- Ernzerhof, Matthias; Scuseria, Gustavo E.
- The Journal of Chemical Physics, Vol. 110, Issue 11
Toward reliable density functional methods without adjustable parameters: The PBE0 model
journal, April 1999
- Adamo, Carlo; Barone, Vincenzo
- The Journal of Chemical Physics, Vol. 110, Issue 13
Inhomogeneous Electron Gas
journal, November 1964
- Hohenberg, P.; Kohn, W.
- Physical Review, Vol. 136, Issue 3B, p. B864-B871
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies
journal, July 2013
- Hansen, Katja; Montavon, Grégoire; Biegler, Franziska
- Journal of Chemical Theory and Computation, Vol. 9, Issue 8
First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties
preprint, January 2012
- von Lilienfeld, O. A.
- arXiv
First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties
journal, February 2013
- von Lilienfeld, O. Anatole
- International Journal of Quantum Chemistry, Vol. 113, Issue 12
Ultrafast Infrared Spectroscopy of Riboflavin: Dynamics, Electronic Structure, and Vibrational Mode Analysis
journal, October 2008
- Wolf, Matthias M. N.; Schumann, Christian; Gross, Ruth
- The Journal of Physical Chemistry B, Vol. 112, Issue 42
Machine learning of molecular electronic properties in chemical compound space
text, January 2013
- Montavon, Grégoire; Rupp, Matthias; Gobre, Vivekanand
- ETH Zurich
Long-range charge-transfer excited states in time-dependent density functional theory require non-local exchange
journal, August 2003
- Dreuw, Andreas; Weisman, Jennifer L.; Head-Gordon, Martin
- The Journal of Chemical Physics, Vol. 119, Issue 6
Rationale for mixing exact exchange with density functional approximations
journal, December 1996
- Perdew, John P.; Ernzerhof, Matthias; Burke, Kieron
- The Journal of Chemical Physics, Vol. 105, Issue 22, p. 9982-9985
Quantum chemistry structures and properties of 134 kilo molecules
journal, August 2014
- Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias
- Scientific Data, Vol. 1, Issue 1
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space
text, January 2015
- Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan
- American Chemical Society
Quantum chemistry structures and properties of 134 kilo molecules
text, January 2014
- Raghunathan, Ramakrishnan,; O., Dral, Pavlo; Matthias, Rupp,
- Springer Nature
Works referencing / citing this record:
Visualization of very large high-dimensional data sets as minimum spanning trees
journal, February 2020
- Probst, Daniel; Reymond, Jean-Louis
- Journal of Cheminformatics, Vol. 12, Issue 1
Size‐Extensive Molecular Machine Learning with Global Representations
journal, February 2020
- Jung, Hyunwook; Stocker, Sina; Kunkel, Christian
- ChemSystemsChem, Vol. 2, Issue 4
MoleculeNet: A Benchmark for Molecular Machine Learning
preprint, January 2017
- Wu, Zhenqin; Ramsundar, Bharath; Feinberg, Evan N.
- arXiv
Evolutionary Approach to Constructing a Deep Feedforward Neural Network for Prediction of Electronic Coupling Elements in Molecular Materials
journal, February 2019
- Çaylak, Onur; Yaman, Anil; Baumeier, Björn
- Journal of Chemical Theory and Computation, Vol. 15, Issue 3
Quantum chemical elucidation of the turn-on luminescence mechanism in two new Schiff bases as selective chemosensors of Zn 2+ : synthesis, theory and bioimaging applications
journal, January 2019
- Berrones-Reyes, Jessica C.; Muñoz-Flores, Blanca M.; Cantón-Diáz, Arelly M.
- RSC Advances, Vol. 9, Issue 53
Chemical diversity in molecular orbital energy predictions with kernel ridge regression
journal, May 2019
- Stuke, Annika; Todorović, Milica; Rupp, Matthias
- The Journal of Chemical Physics, Vol. 150, Issue 20
Quantum Machine Learning in Chemical Compound Space
journal, March 2018
- von Lilienfeld, O. Anatole
- Angewandte Chemie International Edition, Vol. 57, Issue 16
Recent advances and applications of machine learning in solid-state materials science
journal, August 2019
- Schmidt, Jonathan; Marques, Mário R. G.; Botti, Silvana
- npj Computational Materials, Vol. 5, Issue 1
Radiative decay channel assessment to understand the sensing mechanism of a fluorescent turn‐on Al 3+ chemosensor
journal, October 2019
- Treto‐Suárez, Manuel A.; Hidalgo‐Rosa, Yoan; Schott, Eduardo
- International Journal of Quantum Chemistry, Vol. 120, Issue 3
MoleculeNet: a benchmark for molecular machine learning
journal, January 2018
- Wu, Zhenqin; Ramsundar, Bharath; Feinberg, Evan N.
- Chemical Science, Vol. 9, Issue 2
Building attention and edge message passing neural networks for bioactivity and physical–chemical property prediction
journal, January 2020
- Withnall, M.; Lindelöf, E.; Engkvist, O.
- Journal of Cheminformatics, Vol. 12, Issue 1
Prediction model of band-gap for AX binary compounds by combination of density functional theory calculations and machine learning techniques
text, January 2015
- Lee, Joohwi; Seko, Atsuto; Shitara, Kazuki
- arXiv
Enriched optimization of molecular properties under constraints: an electrochromic example
journal, January 2018
- Rinderspacher, B. Christopher; Elward, Jennifer M.
- Molecular Systems Design & Engineering, Vol. 3, Issue 3
PotentialNet for Molecular Property Prediction
preprint, January 2018
- Feinberg, Evan N.; Sur, Debnil; Wu, Zhenqin
- arXiv
Visualization of Very Large High-Dimensional Data Sets as Minimum Spanning Trees
posted_content, November 2019
- Probst, Daniel; Reymond, Jean-Louis
- ChemRxiv. Theoretical and Computational Chemistry
Nonadiabatic Excited-State Dynamics with Machine Learning
journal, September 2018
- Dral, Pavlo O.; Barbatti, Mario; Thiel, Walter
- The Journal of Physical Chemistry Letters, Vol. 9, Issue 19
Building attention and edge message passing neural networks for bioactivity and physical–chemical property prediction
journal, January 2020
- Withnall, M.; Lindelöf, E.; Engkvist, O.
- Journal of Cheminformatics, Vol. 12, Issue 1
Structure-based sampling and self-correcting machine learning for accurate calculations of potential energy surfaces and vibrational levels
journal, June 2017
- Dral, Pavlo O.; Owens, Alec; Yurchenko, Sergei N.
- The Journal of Chemical Physics, Vol. 146, Issue 24
Atomic structures and orbital energies of 61,489 crystal-forming organic molecules
journal, February 2020
- Stuke, Annika; Kunkel, Christian; Golze, Dorothea
- Scientific Data, Vol. 7, Issue 1
Machine learning model for non-equilibrium structures and energies of simple molecules
journal, January 2019
- Iype, E.; Urolagin, S.
- The Journal of Chemical Physics, Vol. 150, Issue 2
Quantum Machine Learning in Chemistry and Materials
book, January 2020
- Huang, Bing; Symonds, Nadine O.; von Lilienfeld, O. Anatole
- Handbook of Materials Modeling
Machine learning modeling of Wigner intracule functionals for two electrons in one-dimension
journal, April 2019
- Bhavsar, Rutvij; Ramakrishnan, Raghunathan
- The Journal of Chemical Physics, Vol. 150, Issue 14
MoleculeNet: A Benchmark for Molecular Machine Learning
preprint, January 2017
- Wu, Zhenqin; Ramsundar, Bharath; Feinberg, Evan N.
- arXiv
Visualization of Very Large High-Dimensional Data Sets as Minimum Spanning Trees
journal, November 2019
- Probst, Daniel; Reymond, Jean-Louis
- ChemRxiv
Atomic structures and orbital energies of 61,489 crystal-forming organic molecules
preprint, January 2020
- Stuke, Annika; Kunkel, Christian; Golze, Dorothea
- arXiv
Solid harmonic wavelet scattering for predictions of molecule properties
journal, June 2018
- Eickenberg, Michael; Exarchakis, Georgios; Hirn, Matthew
- The Journal of Chemical Physics, Vol. 148, Issue 24
Constant size descriptors for accurate machine learning models of molecular properties
journal, June 2018
- Collins, Christopher R.; Gordon, Geoffrey J.; von Lilienfeld, O. Anatole
- The Journal of Chemical Physics, Vol. 148, Issue 24