Ecotoxicity prediction by adaptive fuzzy partitioning: comparing descriptors computed on 2D and 3D structures
- 1 April 2006
- journal article
- research article
- Published by Taylor & Francis in SAR and QSAR in Environmental Research
- Vol. 17 (2) , 225-251
Abstract
Classification models were established on four endpoints, i.e. trout, daphnia, quail and bee, including from 100 to 300 pesticides subdivided into 3 toxicity classes. For each species, five separate sets of molecular descriptors, computed by several software, were compared, including parameters related to 2D or 3D structures. The most relevant descriptors were selected with help of a procedure based on genetic algorithms. Then, structure-activity relationships were built by Adaptive Fuzzy Partition (AFP), a recursive partitioning method derived from Fuzzy Logic concepts. Globally, satisfactory results were obtained for each animal species. The best cross-validation and test set scores reached values of about 70–75%. More important, the relationships derived from the descriptors calculated from 2D structures were superior or similar to those computed from 3D structures. These results underline that the long computational time employed to compute 3D descriptors is often useless to improve the prediction ability of the ecotoxicity models. Finally, the differences in the prediction ability between the different software used were quite reduced and show the possibility to use different descriptor packages for obtaining similar satisfactory models.Keywords
This publication has 30 references indexed in Scilit:
- Database mining with adaptive fuzzy partition: Application to the prediction of pesticide toxicity on ratsEnvironmental Toxicology and Chemistry, 2003
- Predicting Toxicity against the fathead Minnow by Adaptive Fuzzy PartitionQSAR & Combinatorial Science, 2003
- The Importance of Being Earnest: Validation is the Absolute Essential for Successful Application and Interpretation of QSPR ModelsQSAR & Combinatorial Science, 2003
- Essential and desirable characteristics of ecotoxicity quantitative structure–activity relationshipsEnvironmental Toxicology and Chemistry, 2003
- Adaptive fuzzy partition in database mining: application to olfactionData Science Journal, 2002
- Factors Influencing Predictive Models for ToxicologySAR and QSAR in Environmental Research, 2001
- QSAR Modeling of Large Heterogeneous Sets of MoleculesSAR and QSAR in Environmental Research, 2001
- Database mining applied to central nervous system (CNS) activityEuropean Journal of Medicinal Chemistry, 2001
- Computational Neural Networks in Conjunction with Principal Component Analysis for Resolving Highly Nonlinear KineticsJournal of Chemical Information and Computer Sciences, 1997
- Recognition of overlapping particles in granular product images using statistics and neural networksFood Control, 1995