Prediction of enzyme activity with neural network models based on electronic and geometrical features of substrates.
Journal Title: Pharmacological Reports - Year 2012, Vol 64, Issue 4
Abstract
Background: Artificial Neural Networks (ANNs) are introduced as robust and versatile tools in quantitative structure-activity relationship (QSAR) modeling. Their application to the modeling of enzyme reactivity is discussed, along with methodological issues. Methods of input variable selection, optimization of network internal structure, data set division and model validation are discussed. The application of ANNs in the modeling of enzyme activity over the last 20 years is briefly recounted. Methods: The discussed methodology is exemplified by the case of ethylbenzene dehydrogenase (EBDH). Intelligent Problem Solver and genetic algorithms are applied for input vector selection, whereas k-means clustering is used to partition the data into training and test cases. Results: The obtained models exhibit high correlation between the predicted and experimental values (R(2) > 0.9). Sensitivity analyses and study of the response curves are used as tools for the physicochemical interpretation of the models in terms of the EBDH reaction mechanism. Conclusions: Neural networks are shown to be a versatile tool for the construction of robust QSAR models that can be applied to a range of aspects important in drug design and the prediction of biological activity.
Authors and Affiliations
Maciej Szaleniec
Keywords
Related Articles
- EP ID EP92847
- DOI -
- Views 77
- Downloads 0
Optimization of lidocaine application in tumescent local anesthesia.
Tumescent local anesthesia is based upon the infusion of large volumes of neutralized anesthetic solutions, mainly lidocaine, at very low concentrations. This results in the paralysis of sensory nerve endings and minute...
Renal vascular cytochrome P450-derived eicosanoids in androgen-induced hypertension.
Androgen has been linked to higher incidence of cardiovascular disease based on the simple observation that men have more cardiovascular and renal events than women at similar ages. The Cytochrome P450 (CYP)-derived eico...
11β-Hydroxysteroid dehydrogenase type 1: potential therapeutic target for metabolic syndrome.
Obesity and associated metabolic syndrome is one of the greatest health threat to the modern society. Cortisol excess and the glucocorticoid receptor signaling pathway in the metabolically active tissues have been implic...
Effect of NMDA receptor antagonists on behavioral impairment induced by chronic treatment with dexamethasone.
Severe and prolonged stress but also long-term treatment with glucocorticoids (GCs) have been described to cause brain damage (especially hippocampal and striatal neurons) in humans as well as in animals. GCs potentiate...
Possible new organoselenium supplement - evaluation of its influence on the kidneys in comparison with inorganic sodium selenite.
The aim of this work was to evaluate the possibility of using of the new selenoorganic ring compound, 3-(o-chlorobenzoylamino)-2-(o-tolylimino)-4-methyl-4-selenazoline, as a selenium supplement by investigating the influ...