| Attributs | Valeurs |
|---|
| type
| |
| Is Part Of
| |
| Subject
| |
| Title
| - An Integrated SOM-Fuzzy ARTMAP Neural System for the Evaluation of Toxicity
|
| has manifestation of work
| |
| related by
| |
| Author
| |
| Abstract
| - Self-organized maps (SOM) have been applied to analyze the similarities of chemical compounds and toselect from a given pool of descriptors the smallest and more relevant subset needed to build robust QSARmodels based on fuzzy ARTMAP. First, the category maps for each molecular descriptor and for the targetactivity variable were created with SOM and then classified on the basis of topology and nonlinear distribution.The best subset of descriptors was obtained by choosing from each cluster the index with the highestcorrelation with the target variable and then in order of decreasing correlation. This process was terminatedwhen a dissimilarity measure increased, indicating that the inclusion of more molecular indices would notadd supplementary information. The optimal subset of descriptors was used as input to a fuzzy ARTMAParchitecture modified to effect predictive capabilities. The performance of the integrated SOM-fuzzy ARTMAPapproach was evaluated with the prediction of the acute toxicity LC50 of a homogeneous set of 69 benzenederivatives in the fathead minnow and the oral rat toxicity LD50 of a heterogeneous set of 155 organiccompounds. The proposed methodology minimized the problem of misclassification of similar compoundsand significantly enhanced the predictive capabilities of a properly trained fuzzy ARTMAP network.
|
| article type
| |
| is part of this journal
| |
