CypScore: Quantitative Prediction of Reactivity toward Cytochromes P450 Based on Semiempirical Molecular Orbital Theory

Abstract

CypScore is an in silico approach for predicting the likely sites of cytochrome P450-mediated metabolism of druglike organic molecules. It consists of multiple models for the most important P450 oxidation reactions such as aliphatic hydroxylation, N-dealkylation, O-dealkylation, aromatic hydroxylation, double-bond oxidation, N-oxidation, and S-oxidation. Each of these models is based on atomic reactivity descriptors derived from surface-based properties calculated with ParaSurf and based on AM1 semiempirical molecular orbital theory. The models were trained with data derived from Bayer Schering Pharma's in-house MajorMetabolite Database with more than 2300 transformations and more than 800 molecules collected from the primary literature. The models have been balanced to allow the treatment of relative intramolecular, intra-chemotype, and inter-chemotype reactivities of the labile sites toward oxidation. The models were evaluated with promising hit rates on three public datasets of varying quality in the annotation of the experimental positions. For 39 well-characterized compounds from 14 in-house lead optimization programs, we could detect at least one major metabolite for the three highest-ranked positions in 87 % of the compounds and overall more than 62 % of all major metabolites, with promising true- to false-positive ratios of 0.9.

Selecting Relevant Descriptors for Classification by Bayesian Estimates: A Comparison with Decision Trees and Support Vector Machines Approaches for Disparate Data Sets

“…Also CypScore is a quantitative method to predict regioselective metabolization. [30] Here, all three isoforms are considered together as a "super-enzyme". The corresponding descriptors used in the QSAR equations are all derived from quantum chemical calculation and predominately reflect contributions of hydrogen, carbon, nitrogen, and sulfur atoms to the electrostatic potential at the molecular surface.…”

Assessment of the genotoxic and carcinogenic potentials of 3‐aminothiophene derivatives using in vitro and in silico methodologies

“…From these descriptors, CypScore currently provides six different models for seven generic P450-mediated oxidation reactions, namely aliphatic hydroxylation (model 1), N-dealkylation (model 1), O-dealkylation (model 1), aromatic hydroxylation (model 2), double-bond epoxidation/oxidation (model 3), N-oxidation of amines (model 4a) or imines (model 4b) and S-oxidation (model 5). A description of the models and an exhaustive list of the descriptors involved in each model can be found in the original publication of Hennemann et al (2009). Finally, an easily understood score, called percent lability, was calculated for each C, N, and S atom visible on the molecular surface.…”

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

“…According to reaction types, values of activation energies were empirically assessed in the literatures. The values of activation energy for aliphatic oxidation (1)(2)(3)(4)(5) are cited from Reference, [13] and those of aromatic oxidation (6 and 7) are cited from Reference. [14] Fukui functions are derivatives of the electron density in terms of the number of electrons.…”

“…[1][2][3][4][5][6][7][8][9] In relation to the isoform specificity prediction, Gasteiger [4] and Yap [6] independently built support vector machine (SVM) models with high accuracy rates for CYP 3A4, 2D6, and 2C9. Recently, we built an isoform specificity model for CYP 3A4.…”