Subchronic Oral and Inhalation Toxicities: a Challenging Attempt for Modeling and Prediction

Authors

  • Dimaitar A. Dobchev,

    Corresponding author
    1. MolCode, Ltd. Turu 2, Tartu 51013, Estonia
    2. Department of Chemistry, Tallinn University of Technology, Akadeemia tee 15, Tallinn 19086, Estonia phone/fax: +372 6 202 814/+372 6 202 819
    • MolCode, Ltd. Turu 2, Tartu 51013, Estonia

    Search for more papers by this author
  • Indrek Tulp,

    1. Department of Chemistry, University of Tartu, Ravila 14a, Tartu 50411, Estonia
    Search for more papers by this author
  • Gunnar Karelson,

    1. MolCode, Ltd. Turu 2, Tartu 51013, Estonia
    2. Department of Chemistry, Tallinn University of Technology, Akadeemia tee 15, Tallinn 19086, Estonia phone/fax: +372 6 202 814/+372 6 202 819
    Search for more papers by this author
  • Tarmo Tamm,

    1. MolCode, Ltd. Turu 2, Tartu 51013, Estonia
    2. Institute of Technology, University of Tartu, Nooruse 1, Tartu 50411, Estonia
    Search for more papers by this author
  • Kaido Tämm,

    1. MolCode, Ltd. Turu 2, Tartu 51013, Estonia
    2. Department of Chemistry, University of Tartu, Ravila 14a, Tartu 50411, Estonia
    Search for more papers by this author
  • Mati Karelson

    1. Department of Chemistry, Tallinn University of Technology, Akadeemia tee 15, Tallinn 19086, Estonia phone/fax: +372 6 202 814/+372 6 202 819
    2. Department of Chemistry, University of Tartu, Ravila 14a, Tartu 50411, Estonia
    Search for more papers by this author

Abstract

The article deals with a challenging attempt to model and predict “difficult” properties as long-term subchronic oral and inhalation toxicities (90 days) using nonlinear QSAR approach. This investigation is one of the first to tackle such multicomplex properties where we have employed nonlinear models based on artificial neural network for the prediction of NOAEL (no observable adverse effect level). Despite the complex nature of the NOAEL property based on in vivo rat experiments, the successful models can be used as alternative tools to non-animal tests for the initial assessment of these chronic toxicities. The model for oral subchronic toxicity is able to describe 88 %, and the inhalation model 87 % of the statistical variance. For the sake of future predictions, we have also defined in a quantitative way the applicability domain of all neural network models.

Ancillary