Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties

@article{Lilienfeld2013FourierSO,
  title={Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties},
  author={O. A. V. Lilienfeld and R. Ramakrishnan and M. Rupp and A. Knoll},
  journal={International Journal of Quantum Chemistry},
  year={2013},
  volume={115},
  pages={1084-1093}
}
  • O. A. V. Lilienfeld, R. Ramakrishnan, +1 author A. Knoll
  • Published 2013
  • Chemistry, Mathematics, Physics
  • International Journal of Quantum Chemistry
  • We introduce a fingerprint representation of molecules based on a Fourier series of atomic radial distribution functions. This fingerprint is unique (except for chirality), continuous, and differentiable with respect to atomic coordinates and nuclear charges. It is invariant with respect to translation, rotation, and nuclear permutation, and requires no preconceived knowledge about chemical bonding, topology, or electronic orbitals. As such, it meets many important criteria for a good molecular… CONTINUE READING
    116 Citations

    Figures and Tables from this paper

    Chemical diversity in molecular orbital energy predictions with kernel ridge regression.
    • 16
    • PDF
    Machine learning model for non-equilibrium structures and energies of simple molecules.
    • 4
    Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error.
    • 227
    • PDF
    Atom-density representations for machine learning.
    • 53
    • PDF
    Predicting molecular properties with covariant compositional networks.
    • 29
    • PDF

    References

    SHOWING 1-10 OF 125 REFERENCES
    Comment on "Fast and accurate modeling of molecular atomization energies with machine learning".
    • J. Moussa
    • Physics, Medicine
    • Physical review letters
    • 2012
    • 24
    • PDF
    Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies.
    • 319
    • PDF
    Density functionals with broad applicability in chemistry.
    • 3,985