Decision trees for classification of endocrine disruptors

Abstract : With the current concern of limiting experimental assays, increased interest now focuses on in silico models able to predict toxicity of chemicals. Endocrine disruptors cover a large number of environmental and industrial chemicals which may affect the functions of natural hormones in humans and wildlife. In this study a large set of about 200 chemicals covering a broad range of structural classes was considered in order to categorize their relative binding affinity (RBA) to the androgen receptor. Classification of chemicals into three activity groups, with respect to their RBA value, was carried out in a cascade of recursive partitioning trees, from descriptors calculated from CODESSA software and encoding topological, geometrical and quantum chemical properties. The hydrophobicity parameter (log P), Balaban index, and indices relying on charge distribution (max. partial charge, nucleophilic index on oxygen atoms, charged surface area, etc.) appeared to play a major role in the chemical partitioning. Separation of strongly active compounds was rather straightforward. Similarly, about 90% of the inactive compounds were identified. More intricate was the separation of active compounds into subsets of moderate and weak binders, the task requiring a more complex tree.
Document type :
Conference papers
Complete list of metadatas

https://hal-ineris.archives-ouvertes.fr/ineris-00970314
Contributor : Gestionnaire Civs <>
Submitted on : Wednesday, April 2, 2014 - 3:46:51 PM
Last modification on : Friday, January 4, 2019 - 5:32:55 PM

Identifiers

  • HAL Id : ineris-00970314, version 1
  • INERIS : EN-2007-333

Citation

Annick Panaye, James Devillers, Jean-Pierre Doucet, Nathalie Marchand-Geneste, Jean-Marc Porcher. Decision trees for classification of endocrine disruptors. 4. International Symposium "Computational Methods in Toxicology and Pharmacology Integrating Internet Resources" (CMTPI 2007), Sep 2007, Moscou, Russia. ⟨ineris-00970314⟩

Share

Metrics

Record views

112