Quantitative Prediction of Regioselectivity Toward Cytochrome P450/3A4 Using Machine Learning Approaches

Hasegawa, Kiyoshi; Koyama, Mamoru; Funatsu, Kimito

doi:10.1002/minf.200900086

Cited by 20 publications

(19 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of these in silico models involving predicting the type of substrate [24][25][26][27], regioselectivity [28][29][30][31][32][33][34], stereoselectivity [35][36][37], rate of metabolism [38][39][40][41] have been described in other articles. The latest buzzword site of metabolism refers to the specific atoms in a substrate where metabolic reaction occurs, initiating pharmaceutical researchers to develop tools capable of predicting probable metabolism of endogenous compounds, drugs or drug candidates [42,43].…”

Section: Drug Metabolismmentioning

confidence: 99%

In Silico Prediction of Cytochrome P450-Mediated Site of Metabolism (SOM)

Liu¹,

Shen²,

Li³

et al. 2013

Protein and Peptide Letters

View full text Add to dashboard Cite

Drug metabolism is a major consideration for modifying drug clearance and also a primary source for drug metabolite-induced toxicity. Cytochromes P450 (CYPs) are the major enzymes involved in drug metabolism and bioactivation, accounting for almost 75% of the total drug metabolism. Predicting the sites of cytochrome P450-mediated metabolism of drug-like molecules using in silico methods would be highly beneficial and time efficient. An ideal system would enable researchers to make a confident elimination decision based purely on the structure of a new compound. In this review, several tools and models for predicting probable site of metabolism (SOM) have been compared and discussed. The methods are generally based on enzyme structure, ligand structure, and combined methods. Although all the methods have certain accuracy and considerable progress has been made, the results of the calculations still need careful inspection.

show abstract

Section: Drug Metabolismmentioning

confidence: 99%

In Silico Prediction of Cytochrome P450-Mediated Site of Metabolism (SOM)

Liu¹,

Shen²,

Li³

et al. 2013

Protein and Peptide Letters

View full text Add to dashboard Cite

show abstract

“…Positions where H·-abstraction resulted in an energy difference dE < 30 kcal mol −1 were considered as potential SOMs. As CYP-catalyzed oxidation reactions require accessibility of the SOM [47][48][49], we implemented a second selection criterion in our SOM prediction. Based on the energy-minimized structure from H·-abstraction calculations, we calculated solvent accessible surface areas (SASAs) for all hydrogens using MOE [31].…”

Section: Prediction Of Site Of Metabolismmentioning

confidence: 99%

Precursors for cytochrome P450 profiling breath tests from an in silico screening approach

et al. 2014

View full text Add to dashboard Cite

The family of cytochrome P450 enzymes (CYPs) is a major player in the metabolism of drugs and xenobiotics. Genetic polymorphisms and transcriptional regulation give a complex patientindividual CYP activity profile for each human being. Therefore, personalized medicine demands easy and non-invasive measurement of the CYP phenotype. Breath tests detect volatile organic compounds (VOCs) in the patients' exhaled air after administration of a precursor molecule. CYP breath tests established for individual CYP isoforms are based on the detection of 13 CO 2 or 14 CO 2 originating from CYP-catalyzed oxidative degradation reactions of isotopically labeled precursors.We present an in silico work-flow aiming at the identification of novel precursor molecules, likely to result in VOCs other than CO 2 upon oxidative degradation as we aim at label-free precursor molecules. The ligand-based work-flow comprises five parts: (1) CYP profiling was encoded as a decision tree based on 2D molecular descriptors derived from established models in the literature and validated against publicly available data extracted from the DrugBank. (2) Likely sites of metabolism were identified by reactivity and accessibility estimation for abstractable hydrogen radical. (3) Oxidative degradation reactions (O-and N-dealkylations) were found to be most promising in the release of VOCs. Thus, the CYP-catalyzed oxidative degradation reaction was encoded as SMIRKS (a programming language style to implement reactions based on the SMARTS description) to enumerate possible reaction products. (4) A quantitative structure property relation (QSPR) model aiming to predict the Henry constant H was derived from data for 488 organic compounds and identifies potentially VOCs amongst CYP reaction products.(5) A blacklist of naturally occurring breath components was implemented to identify marker molecules allowing straightforward detection within the exhaled air.

show abstract

“…166 A few groups have used a more simple description of the protein than the previous all-atom approaches. Oh et al used a catalyticphore-based docking method in combination with activation energies determined by the AM1-based method of Korzekwa,150,154 whereas Hasegawa et al used a somewhat related method, 167 except that the precomputed activation energies from our work were applied. 32,85 Both models managed to correctly predict the site of metabolism within top two in rank for about 80% of the substrates.…”

Section: Reactivities Combined With Effect Of the Proteinmentioning

confidence: 99%

Quantum-Mechanical Studies of Reactions Performed by Cytochrome P450 Enzymes

Rydberg

Olsen²,

Ryde³

2012

CIC

View full text Add to dashboard Cite

We review density functional theory studies of various types of reactions performed by the cytochrome P450 family of enzymes. We describe the various reactions on equal footing with an emphasisis on models to predict sites of metabolism for an arbitrary molecule. The activation barriers range between 0 and 109 kJ/mol, depending more on the atoms surrounding the reactive site than on the type of reaction. Therefore, the intrinsic reactivity can rather well be predicted by simple chemical rules. However, for a full predictive model, the steric effects of the enzyme surrounding the heme group need also to be modeled, which often is harder.

show abstract

Quantitative Prediction of Regioselectivity Toward Cytochrome P450/3A4 Using Machine Learning Approaches

Cited by 20 publications

References 17 publications

In Silico Prediction of Cytochrome P450-Mediated Site of Metabolism (SOM)

In Silico Prediction of Cytochrome P450-Mediated Site of Metabolism (SOM)

Precursors for cytochrome P450 profiling breath tests from an in silico screening approach

Quantum-Mechanical Studies of Reactions Performed by Cytochrome P450 Enzymes

Contact Info

Product

Resources

About