Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1171073 | Analytica Chimica Acta | 2006 | 10 Pages |
Abstract
Feed-forward neural networks (FFNNs) were used to predict the skeletal type of molecules belonging to six classes of terpenoids. A database that contains the 13C NMR spectra of about 5000 compounds was used to train the FFNNs. An efficient representation of the spectra was designed and the constitution of the best FFNN input vector format resorted from an heuristic approach. The latter was derived from general considerations on terpenoid structures.
Related Topics
Physical Sciences and Engineering
Chemistry
Analytical Chemistry
Authors
Vicente P. Emerenciano, Sandra A.V. Alvarenga, Marcus Tullius Scotti, Marcelo J.P. Ferreira, Ricardo Stefani, Jean-Marc Nuzillard,