Related Experiment Videos
New tyrosinase inhibitors selected by atomic linear indices-based classification models
Gerardo M Casañola-Martín1, Mahmud Tareq Hassan Khan, Yovani Marrero-Ponce
1Department of Pharmacy, Faculty of Chemistry-Pharmacy, Central University of Las Villas, Santa Clara, 54830 Villa Clara, Cuba.
Bioorganic & Medicinal Chemistry Letters
|November 9, 2005
Summary
Atom-based linear indices effectively discriminate tyrosinase inhibitors. This computational tool aids in identifying new tyrosinase inhibitor compounds from herbal sources with high accuracy.
Area of Science:
- Medicinal Chemistry
- Computational Chemistry
- Pharmacology
Background:
- Tyrosinase inhibitors are crucial for treating hyperpigmentation disorders.
- Developing accurate predictive models for tyrosinase inhibition is essential for drug discovery.
- Cycloartane compounds from herbal plants are potential therapeutic agents.
Purpose of the Study:
- To present atom-based linear indices for discriminating tyrosinase inhibitor compounds.
- To develop and validate discriminant models for predicting tyrosinase inhibitory activity.
- To screen novel cycloartane compounds using the developed models.
Main Methods:
- Application of atom-based linear indices (non-stochastic and stochastic).
- Development of discriminant models for classification tasks.
- Validation using training and external prediction sets.
- Screening of new cycloartane compounds.
Main Results:
- High classification accuracy achieved: 93.51% (non-stochastic) and 92.46% (stochastic) on the training set.
- External prediction accuracies of 91.67% and 89.44% were obtained.
- Theoretical predictions showed good agreement with experimental results for new compounds.
Conclusions:
- Atom-based linear indices provide a reliable tool for identifying tyrosinase inhibitors.
- The developed discriminant models are effective for virtual screening.
- This approach facilitates the discovery of novel tyrosinase inhibitor compounds from natural sources.