articleNew Journal of PhysicsSep 4, 2013GOLD OA

Machine learning of molecular electronic properties in chemical compound space

GMGrégoire MontavonMRMatthias RuppVGVivekanand GobreAVAlvaro Vazquez-MayagoitiaKHKatja Hansen

Technische Universität Berlin · ETH Zurich · +4 more institutions

Indexed inarxivcrossrefdoaj

Abstract

The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amount of data amenable to intelligent data analysis for the identification of meaningful, novel and predictive structure-property relationships. Such relationships enable high-throughput screening for relevant properties in an exponentially growing pool of virtual compounds that are synthetically accessible. Here, we present a machine learning model, trained on a database of ab initio calculation results for thousands of organic molecules, that simultaneously predicts multiple electronic ground- and excited-state properties. The properties include atomization energy, polarizability, frontier orbital…

Citation impact

628
total citations
FWCI
6.44
Percentile
100%
References
56
Citations per year

Authors

8
  • GM
    Grégoire Montavon

    Technische Universität Berlin

  • MR
    Matthias Rupp

    ETH Zurich

  • VG
    Vivekanand Gobre

    Fritz Haber Institute of the Max Planck Society

  • AV
    Alvaro Vazquez-Mayagoitia

    Argonne National Laboratory

  • KH
    Katja Hansen

    Fritz Haber Institute of the Max Planck Society

Topics & keywords

Topics
Keywords
  • Chemical space
  • Artificial neural network
  • Identification (biology)
  • Space (punctuation)
  • Excitation
  • Convolutional neural network
  • Organic molecules
  • Electronic structure
No related works found for this paper.

Funding