Get access

Physicochemical vs. Vibrational Descriptors for Prediction of Odor Receptor Responses

Authors

  • Stephan Gabler,

    1. Theoretical Neuroscience, Institute of Biology, Dept. of Biology, Chemistry, Pharmacy, Freie Universität Berlin, Königin-Luise-Str. 1–3, D-14195 Berlin, Germany
    2. Bernstein Center for Computational Neuroscience Berlin, Philippstr. 13, Haus 6, D-10115 Berlin, Germany
    Search for more papers by this author
    • These authors contributed equally to this work

  • Jan Soelter,

    1. Theoretical Neuroscience, Institute of Biology, Dept. of Biology, Chemistry, Pharmacy, Freie Universität Berlin, Königin-Luise-Str. 1–3, D-14195 Berlin, Germany
    Search for more papers by this author
    • These authors contributed equally to this work

  • Taufia Hussain,

    1. Max Planck Institute for Chemical Ecology, Hans-Knöll-Straße 8, D-07745 Jena, Germany
    Search for more papers by this author
  • Silke Sachse,

    1. Max Planck Institute for Chemical Ecology, Hans-Knöll-Straße 8, D-07745 Jena, Germany
    Search for more papers by this author
  • Michael Schmuker

    Corresponding author
    1. Theoretical Neuroscience, Institute of Biology, Dept. of Biology, Chemistry, Pharmacy, Freie Universität Berlin, Königin-Luise-Str. 1–3, D-14195 Berlin, Germany
    2. Bernstein Center for Computational Neuroscience Berlin, Philippstr. 13, Haus 6, D-10115 Berlin, Germany
    • Theoretical Neuroscience, Institute of Biology, Dept. of Biology, Chemistry, Pharmacy, Freie Universität Berlin, Königin-Luise-Str. 1–3, D-14195 Berlin, Germany

    Search for more papers by this author

Abstract

Responses of olfactory receptors (ORs) can be predicted by applying machine learning methods on a multivariate encoding of an odorant’s chemical structure. Physicochemical descriptors that encode features of the molecular graph are a popular choice for such an encoding. Here, we explore the EVA descriptor set, which encodes features derived from the vibrational spectrum of a molecule. We assessed the performance of Support Vector Regression (SVR) and Random Forest Regression (RFR) to predict the gradual response of Drosophila ORs. We compared a 27-dimensional variant of the EVA descriptor against a set of 1467 descriptors provided by the eDragon software package, and against a 32-dimensional subset thereof that has been proposed as the basis for an odor metric consisting of 32 descriptors (HADDAD). The best prediction performance was reproducibly achieved using SVR on the highest-dimensional feature set. The low-dimensional EVA and HADDAD feature sets predicted odor-OR interactions with similar accuracy. Adding charge and polarizability information to the EVA descriptor did not improve the results but rather decreased predictive power. Post-hoc in vivo measurements confirmed these results. Our findings indicate that EVA provides a meaningful low-dimensional representation of odor space, although EVA hardly outperformed “classical” descriptor sets.

Ancillary