Evolved neural networks for quantitative structure-activity relationships of anti-HIV compounds

Evolved neural networks for quantitative structure-activity relationships of anti-HIV compounds

This paper compares the utility of an evolved neural network to a linear model to describe the activity of a set of anti-HIV compounds. The results indicate that significant nonlinearity exists within the descriptors for these molecules. This nonlinearity can be captured in a neural network architec...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Landavazo, D., Fogel, G.B.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Artificial neural networks
Biological system modeling
Chemical analysis
Drugs
Evolutionary computation
Genetic algorithms
Genetic programming
Network topology
Neural networks
Testing
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper compares the utility of an evolved neural network to a linear model to describe the activity of a set of anti-HIV compounds. The results indicate that significant nonlinearity exists within the descriptors for these molecules. This nonlinearity can be captured in a neural network architecture for significantly increased predictive performance.
DOI:10.1109/CEC.2002.1006233