Related Experiment Video
Updated: May 11, 2026

Development of Heterogeneous Enantioselective Catalysts using Chiral Metal-Organic Frameworks (MOFs)
Published on: January 17, 2020
Predicting CYP2C19 catalytic parameters for enantioselective oxidations using artificial neural networks and a
Jessica H Hartman1, Steven D Cothren, Sun-Ha Park
1Department of Biochemistry and Molecular Biology, University of Arkansas for Medical Sciences, 4301 W. Markham, Slot 516, Little Rock, AR 72205, USA.
This study developed optimal artificial neural networks to predict catalytic parameters for enantioselective reactions involving cytochrome P450 2C19 (CYP2C19). These models accurately predict enantioselectivity and catalytic parameters for new CYP2C19 substrates.
Area of Science:
- Computational chemistry
- Biocatalysis
- Pharmacology
Background:
- Cytochromes P450 (CYP) are crucial for metabolizing chiral molecules.
- Predicting parameters for chiral reactions is vital for advancing drug development and understanding biological processes.
- CYP2C19 is a key enzyme in drug metabolism.
Purpose of the Study:
- To develop and optimize artificial neural networks (ANNs) for predicting catalytic parameters of CYP2C19 in enantioselective reactions.
- To identify optimal structural descriptors and network topologies for accurate prediction.
- To validate the predictive capability of ANNs on previously uncharacterized substrates.
Main Methods:
- Utilized conformation-independent chirality codes for ANN training.
- Optimized ANNs by testing various structural representations, including partial atomic charges (CHelpG scheme) and hydrogen inclusion.
- Employed Box-Cox transformation to normalize catalytic parameter distributions (k(cat), K(m), k(cat)/K(m)).
- Performed leave-one-out cross-validation to assess prediction accuracy.
Main Results:
- Partial atomic charges and hydrogen inclusion yielded the most optimal ANNs.
- ANN predictions for individual catalytic parameters (k(cat), K(m)) showed higher consistency with experimental data than catalytic efficiency (k(cat)/K(m)).
- The developed ANNs accurately predicted enantioselectivity and catalytic parameters for R- and S-propranolol.
Conclusions:
- This study presents the first computational approach using ANNs to predict all catalytic parameters for enantioselective reactions catalyzed by CYP2C19.
- The findings provide a robust foundation for predicting reactions involving chiral drugs, pollutants, and other biologically active compounds.
- Optimized ANNs offer a powerful tool for advancing research in cytochrome P450-mediated metabolism.
Related Concept Videos
Reduction of Alkenes: Asymmetric Catalytic Hydrogenation
The metal catalyst used can be either heterogeneous or homogeneous. When hydrogenation of an alkene generates a chiral center, a pair of enantiomeric products is expected to form. However, an enantiomeric excess of one of the products can be facilitated using an enantioselective reaction or an...
Pharmacogenetics of Phase I Enzymes: Cytochrome P450 Isozymes
Sharpless Epoxidation
Predicting Reaction Outcomes
Stereochemical Effects of Enolization
Regioselective Formation of Enolates
