| Attributs | Valeurs |
|---|
| type
| |
| Is Part Of
| |
| Subject
| |
| Title
| - Genetic Algorithm Applied to the Selection of Factors in Principal Component-ArtificialNeural Networks: Application to QSAR Study of Calcium Channel Antagonist Activityof 1,4-Dihydropyridines (Nifedipine Analogous)
|
| has manifestation of work
| |
| related by
| |
| Author
| |
| Abstract
| - A QSAR algorithm, principal component-genetic algorithm-artificial neural network (PC-GA-ANN), hasbeen applied to a set of newly synthesized calcium channel blockers, which are of special interest becauseof their role in cardiac diseases. A data set of 124 1,4-dihydropyridines bearing different ester substituentsat the C-3 and C-5 positions of the dihydropyridine ring and nitroimidazolyl, phenylimidazolyl, andmethylsulfonylimidazolyl groups at the C-4 position with known Ca2+ channel binding affinities was employedin this study. Ten different sets of descriptors (837 descriptors) were calculated for each molecule. Theprincipal component analysis was used to compress the descriptor groups into principal components. Themost significant descriptors of each set were selected and used as input for the ANN. The genetic algorithm(GA) was used for the selection of the best set of extracted principal components. A feed forward artificialneural network with a back-propagation of error algorithm was used to process the nonlinear relationshipbetween the selected principal components and biological activity of the dihydropyridines. A comparisonbetween PC-GA-ANN and routine PC-ANN shows that the first model yields better prediction ability.
|
| article type
| |
| is part of this journal
| |
