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
    View PDF on arXiv
    116 Citations
    Background Citations
    13
    Methods Citations
    5

    Figures and Tables from this paper

    Figures and Tables

    116 Citations
    Citation Type

    Citation Type

    Constant size descriptors for accurate machine learning models of molecular properties.
    • 40
    Alchemical and structural distribution based representation for universal quantum machine learning.
    • 104
    • PDF
    Bond type restricted radial distribution functions for accurate machine learning prediction of atomization energies
    • PDF
    Chemical diversity in molecular orbital energy predictions with kernel ridge regression.
    • 16
    • PDF
    Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity.
    • 136
    • 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
    Applying machine learning techniques to predict the properties of energetic materials
    • 37
    • PDF

    References

    SHOWING 1-10 OF 125 REFERENCES
    Machine Learning of Molecular Electronic Properties in Chemical Compound Space
    • 315
    • PDF
    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
    First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties
    • 85
    • PDF
    Fast and accurate modeling of molecular atomization energies with machine learning.
    • 799
    • PDF
    On representing chemical environments
    • 571
    • PDF
    The Signature Molecular Descriptor. 1. Using Extended Valence Sequences in QSAR and QSPR Studies
    • 173
    Quantum chemistry structures and properties of 134 kilo molecules
    • 405
    • PDF
    Virtual Exploration of the Chemical Universe up to 11 Atoms of C, N, O, F: Assembly of 26.4 Million Structures (110.9 Million Stereoisomers) and Analysis for New Ring Systems, Stereochemistry, Physicochemical Properties, Compound Classes, and Drug Discovery
    • 291
    • PDF
    Density functionals with broad applicability in chemistry.
    • 3,985