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 112
- Downloads 0
Increased synphilin-1 expression in human elderly brains with substantia nigra Marinesco bodies.
The aim of the present study was to examine the expression of synphilin-1, alpha-synuclein, and tyrosine hydroxylase in human elderly brains and the incidence of Marinesco bodies (MBs, intranuclear inclusions) in the neu...
Role of nitric oxide in the development of tolerance to diazepam-induced motor impairment in mice.
Chronic treatment with the benzodiazepines is well known to produce tolerance, which has been extensively documented to be attributed to modifications in the gamma-aminobutyric acid (GABA)ergic neurotransmission. However...
Prediction of enzyme activity with neural network models based on electronic and geometrical features of substrates.
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 discus...
Omeprazole affects neither electroconvulsive threshold nor anticonvulsant activity of diphenylhydantoin and carbamazepine in mice.
Omeprazole is a commonly prescribed drug for patients with peptic ulcerations. Its main mechanism of action is related to inhibition of H(+)-K(+)-ATP-ase, albeit it may also block carbonic anhydrase. This study evaluates...
Effect of antidepressant drugs on cytochrome P450 2C11 (CYP2C11) in rat liver.
Background: Rat CYP2C11 (besides CYP2C6) can be regarded as a functional counterpart of human CYP2C9. The aim of the present study was to investigate the influence of classic and novel antidepressant drugs on the activit...