Related Experiment Videos
A new statistical approach to predicting aromatic hydroxylation sites. Comparison with model-based approaches
Yu Borodina1, A Rudik, D Filimonov
1Laboratory of Structure-Function Based Drug Design, Institute of Biomedical Chemistry of the Russian Academy of Medical Sciences, 10 Pogodinskaya Str., Moscow 119121, Russia.
Journal of Chemical Information and Computer Sciences
|November 24, 2004
Summary
A new statistical method accurately predicts metabolic sites for drug metabolism. This approach shows high accuracy for aromatic hydroxylation, aiding early drug discovery.
Area of Science:
- Medicinal Chemistry
- Computational Chemistry
- Pharmacology
Background:
- Predicting metabolic transformations is crucial for drug discovery.
- Existing computational models for P450-mediated aromatic hydroxylation have limitations.
Purpose of the Study:
- To develop and validate a novel statistical approach for predicting metabolic sites.
- To assess the predictive accuracy of this method for aromatic hydroxylation.
Main Methods:
- Statistical analysis of literature-reported metabolic transformations.
- Training on aromatic hydroxylation reactions from the Metabolism database.
- Validation using diverse aromatic compounds from the Metabolite database.
Main Results:
- Achieved an average prediction accuracy of 84.5% for experimentally observed hydroxylation sites across 1552 substrates.
- The statistical method demonstrated superior accuracy for hetero- and polycyclic compounds compared to electronic models.
- Outperformed or matched electronic models for benzene derivatives.
Conclusions:
- The proposed statistical approach offers broad applicability and high computational speed for metabolism prediction.
- This method is suitable for high-throughput screening in early drug discovery.
- It provides a valuable tool for identifying probable metabolic sites, particularly for complex aromatic structures.