Classification Models for Predicting Cytochrome P450 Enzyme-Substrate Selectivity

Machine Learning Models to Predict Cytochrome P450 2B6 Inhibitors and Substrates

Cytochrome P450 2B6 (CYP2B6) is responsible for the metabolism of ∼7% of marketed drugs. The in vitro drug interaction studies guidance for industry issued by the FDA stipulates that drug sponsors need to evaluate whether the investigated drugs interact with the major drug-metabolizing P450s including CYP2B6. Therefore, there has been greater attention to the development of predictive models for CYP2B6 inhibitors and substrates. In this study, conventional machine learning and deep learning models were developed to predict CYP2B6 inhibitors and substrates. Our results showed that the best CYP2B6 inhibitor model yielded the AUC values of 0.95 and 0.75 with the 10-fold cross-validation and the test set, respectively, and the best CYP2B6 substrate model produced the AUC values of 0.93 and 0.90 with the 10-fold cross-validation and the test set, respectively. The generalization ability of the CYP2B6 inhibitor and substrate models was assessed by using the external validation sets. Several significant substructural fragments relevant to CYP2B6 inhibitors and substrates were detected via frequency substructure analysis and information gain. In addition, the applicability domain of the models was defined by employing a nonparametric method based on the probability density distribution. We anticipate that our results would be useful for the prediction of potential CYP2B6 inhibitors and substrates in the early stage of drug discovery.

Predictive Models for Human Cytochrome P450 3A7 Selective Inhibitors and Substrates

Inappropriate use of prescription drugs is potentially more harmful in fetuses/neonates than in adults. Cytochrome P450 (CYP) 3A subfamily undergoes developmental changes in expression, such as a transition from CYP3A7 to CYP3A4 shortly after birth, which provides a potential way to distinguish medication effects on fetuses/neonates and adults. The purpose of this study was to build first-in-class predictive models for both inhibitors and substrates of CYP3A7/CYP3A4 using chemical structure analysis. Three metrics were used to evaluate model performance: area under the receiver operating characteristic curve (AUC-ROC), balanced accuracy (BA), and Matthews correlation coefficient (MCC). The performance varied for each CYP3A7/CYP3A4 inhibitor/substrate model depending on the data set type, model type, rebalancing method, and specific feature set. For the active inhibitor/substrate data set, the optimal models achieved AUC-ROC values ranging from 0.77 ± 0.01 to 0.84 ± 0.01. For the selective inhibitor/substrate data set, the optimal models achieved AUC-ROC values ranging from 0.72 ± 0.02 to 0.79 ± 0.04. The predictive power of the optimal models was validated by compounds with known potencies as CYP3A7/CYP3A4 inhibitors or substrates. In addition, we identified structural features significant for CYP3A7/CYP3A4 selective or common inhibitors and substrates. In summary, the top performing models can be further applied as a tool to rapidly evaluate the safety and efficacy of new drugs separately for fetuses/neonates and adults. The significant structural features could guide the design of new therapeutic drugs as well as aid in the optimization of existing medicine for fetuses/neonates.

The FDA-Approved Drug Cobicistat Synergizes with Remdesivir To Inhibit SARS-CoV-2 Replication In Vitro and Decreases Viral Titers and Disease Progression in Syrian Hamsters

Combinations of direct-acting antivirals are needed to minimize drug resistance mutations and stably suppress replication of RNA viruses. Currently, there are limited therapeutic options against the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), and testing of a number of drug regimens has led to conflicting results. Here, we show that cobicistat, which is an FDA-approved drug booster that blocks the activity of the drug-metabolizing proteins cytochrome P450-3As (CYP3As) and P-glycoprotein (P-gp), inhibits SARS-CoV-2 replication. Two independent cell-to-cell membrane fusion assays showed that the antiviral effect of cobicistat is exerted through inhibition of spike protein-mediated membrane fusion. In line with this, incubation with low-micromolar concentrations of cobicistat decreased viral replication in three different cell lines including cells of lung and gut origin. When cobicistat was used in combination with remdesivir, a synergistic effect on the inhibition of viral replication was observed in cell lines and in a primary human colon organoid. This was consistent with the effects of cobicistat on two of its known targets, CYP3A4 and P-gp, the silencing of which boosted the in vitro antiviral activity of remdesivir in a cobicistat-like manner. When administered in vivo to Syrian hamsters at a high dose, cobicistat decreased viral load and mitigated clinical progression. These data highlight cobicistat as a therapeutic candidate for treating SARS-CoV-2 infection and as a potential building block of combination therapies for COVID-19.

DTI-MLCD: predicting drug-target interactions using multi-label learning with community detection method

Identifying drug-target interactions (DTIs) is an important step for drug discovery and drug repositioning. To reduce the experimental cost, a large number of computational approaches have been proposed for this task. The machine learning-based models, especially binary classification models, have been developed to predict whether a drug-target pair interacts or not. However, there is still much room for improvement in the performance of current methods. Multi-label learning can overcome some difficulties caused by single-label learning in order to improve the predictive performance. The key challenge faced by multi-label learning is the exponential-sized output space, and considering label correlations can help to overcome this challenge. In this paper, we facilitate multi-label classification by introducing community detection methods for DTI prediction, named DTI-MLCD. Moreover, we updated the gold standard data set by adding 15,000 more positive DTI samples in comparison to the data set, which has widely been used by most of previously published DTI prediction methods since 2008. The proposed DTI-MLCD is applied to both data sets, demonstrating its superiority over other machine learning methods and several existing methods. The data sets and source code of this study are freely available at https://github.com/a96123155/DTI-MLCD.

Enhancing reaction-based de novo design using a multi-label reaction class recommender

Reaction-based de novo design refers to the in-silico generation of novel chemical structures by combining reagents using structural transformations derived from known reactions. The driver for using reaction-based transformations is to increase the likelihood of the designed molecules being synthetically accessible. We have previously described a reaction-based de novo design method based on reaction vectors which are transformation rules that are encoded automatically from reaction databases. A limitation of reaction vectors is that they account for structural changes that occur at the core of a reaction only, and they do not consider the presence of competing functionalities that can compromise the reaction outcome. Here, we present the development of a Reaction Class Recommender to enhance the reaction vector framework. The recommender is intended to be used as a filter on the reaction vectors that are applied during de novo design to reduce the combinatorial explosion of in-silico molecules produced while limiting the generated structures to those which are most likely to be synthesisable. The recommender has been validated using an external data set extracted from the recent medicinal chemistry literature and in two simulated de novo design experiments. Results suggest that the use of the recommender drastically reduces the number of solutions explored by the algorithm while preserving the chance of finding relevant solutions and increasing the global synthetic accessibility of the designed molecules.

Survey of Machine Learning Techniques for Prediction of the Isoform Specificity of Cytochrome P450 Substrates

Background:

Determination or prediction of the Absorption, Distribution, Metabolism, and Excretion (ADME) properties of drug candidates and drug-induced toxicity plays crucial roles in drug discovery and development. Metabolism is one of the most complicated pharmacokinetic properties to be understood and predicted. However, experimental determination of the substrate binding, selectivity, sites and rates of metabolism is time- and recourse- consuming. In the phase I metabolism of foreign compounds (i.e., most of drugs), cytochrome P450 enzymes play a key role. To help develop drugs with proper ADME properties, computational models are highly desired to predict the ADME properties of drug candidates, particularly for drugs binding to cytochrome P450.

Objective:

This narrative review aims to briefly summarize machine learning techniques used in the prediction of the cytochrome P450 isoform specificity of drug candidates.

Results:

Both single-label and multi-label classification methods have demonstrated good performance on modelling and prediction of the isoform specificity of substrates based on their quantitative descriptors.

Conclusion:

This review provides a guide for researchers to develop machine learning-based methods to predict the cytochrome P450 isoform specificity of drug candidates.

Predicting mammalian metabolism and toxicity of pesticides in silico

Pesticides must be effective to be commercially viable but they must also be reasonably safe for those who manufacture them, apply them, or consume the food they are used to produce. Animal testing is key to ensuring safety, but it comes late in the agrochemical development process, is expensive, and requires relatively large amounts of material. Surrogate assays used as in vitro models require less material and shift identification of potential mammalian toxicity back to earlier stages in development. Modern in silico methods are cost-effective complements to such in vitro models that make it possible to predict mammalian metabolism, toxicity and exposure for a pesticide, crop residue or other metabolite before it has been synthesized. Their broader use could substantially reduce the amount of time and effort wasted in pesticide development. This contribution reviews the kind of in silico models that are currently available for vetting ideas about what to synthesize and how to focus development efforts; the limitations of those models; and the practical considerations that have slowed development in the area. Detailed discussions are provided of how bacterial mutagenicity, human cytochrome P450 (CYP) metabolism, and bioavailability in humans and rats can be predicted. © 2018 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Molecular mechanisms of drug resistance in ovarian cancer

Ovarian cancer is the most lethal malignancy among the gynecological cancers, with a 5-year survival rate, mainly due to being diagnosed at advanced stages, recurrence and resistance to the current chemotherapeutic agents. Drug resistance is a complex phenomenon and the number of known involved genes and cross-talks between signaling pathways in this process is growing rapidly. Thus, discovering and understanding the underlying molecular mechanisms involved in chemo-resistance are crucial for management of treatment and identifying novel and effective drug targets as well as drug discovery to improve therapeutic outcomes. In this review, the major and recently identified molecular mechanisms of drug resistance in ovarian cancer from relevant literature have been investigated. In the final section of the paper, new approaches for studying detailed mechanisms of chemo-resistance have been briefly discussed.

Computational explanation for bioactivation mechanism of targeted anticancer agents mediated by cytochrome P450s: A case of Erlotinib

EGFR inhibitors, even with therapeutics superiorities in anticancer, can cause idiosyncratic pulmonary and hepatic toxicities that are associated with the reactive electrophile bioactivated by Cytochrome P450s (P450s). Until now, neither has the electrophilic intermediate been caught experimentally, nor has the subtle mechanism been declared. Herein, the underlying mechanism of bioactivation mediated by P450s was explored by DFT calculations for a case of EGFR inhibitor, Erlotinib. Based on the calculation and analysis, we suggest that with other metabolites, reactive electrophiles of Erlotinib: epoxide and quinine-imine, can be generated by several steps along the oxidative reaction pathway. The generation of epoxide needs two steps: (1) the addition of Erlotinib to Compound I (Cpd I) and (2) the rearrangement of protons. Whereas, quinine-imine needs a further oxidation step (3) via which quinone is generated and ultimately turns into quinine-imine. Although both reactive electrophiles can be produced for either face-on or side-on pose of Erlotinib, the analysis of energy barriers indicates that the side-on path is preferred in solvent environment. In the rate-determining step, e.g. the addition of Erlotinib to the porphyrin, the reaction barrier for side-on conformation is decreased in aqueous and protein environment compared with gas phase, whereas, the barrier for face-on pose is increased in solvent environment. The simulated mechanism is in good agreement with the speculation in previous experiment. The understanding of the subtle mechanism of bioactivation of Erlotinib will provide theoretical support for toxicological mechanism of EGFR inhibitors.

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

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 patient-individual 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)CO2 or (14)CO2 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 CO2 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.Evident oxidative degradation reactions served as test case for the screening approach. Comparisons to metabolism data from literature support the results' plausibility. Thus, a large scale screening for potential novel breath test precursor using the presented five stage work-flow is promising.

Modelling species selectivity in rat and human cytochrome P450 2D enzymes

Updated models of the Rat Cytochrome P450 2D enzymes are produced based on the recent x-ray structures of the Human P450 2D6 enzyme both with and without a ligand bound. The differences in species selectivity between the epimers quinine and quinidine are rationalised using these models and the results are discussed with regard to previous studies. A close approach to the heme is not observed in this study. The x-ray structure of the enzyme with a ligand bound is shown to be a better model for explaining the observed experimental binding of quinine and quinidine. Hence models with larger closed binding sites are recommended for comparative docking studies. This is consistent with molecular recognition in Cytochrome P450 enzymes being the result of a number of non-specific interactions in a large binding site.

Predicting CYP2C19 catalytic parameters for enantioselective oxidations using artificial neural networks and a chirality code

Cytochromes P450 (CYP for isoforms) play a central role in biological processes especially metabolism of chiral molecules; thus, development of computational methods to predict parameters for chiral reactions is important for advancing this field. In this study, we identified the most optimal artificial neural networks using conformation-independent chirality codes to predict CYP2C19 catalytic parameters for enantioselective reactions. Optimization of the neural networks required identifying the most suitable representation of structure among a diverse array of training substrates, normalizing distribution of the corresponding catalytic parameters (k(cat), K(m), and k(cat)/K(m)), and determining the best topology for networks to make predictions. Among different structural descriptors, the use of partial atomic charges according to the CHelpG scheme and inclusion of hydrogens yielded the most optimal artificial neural networks. Their training also required resolution of poorly distributed output catalytic parameters using a Box-Cox transformation. End point leave-one-out cross correlations of the best neural networks revealed that predictions for individual catalytic parameters (k(cat) and K(m)) were more consistent with experimental values than those for catalytic efficiency (k(cat)/K(m)). Lastly, neural networks predicted correctly enantioselectivity and comparable catalytic parameters measured in this study for previously uncharacterized CYP2C19 substrates, R- and S-propranolol. Taken together, these seminal computational studies for CYP2C19 are the first to predict all catalytic parameters for enantioselective reactions using artificial neural networks and thus provide a foundation for expanding the prediction of cytochrome P450 reactions to chiral drugs, pollutants, and other biologically active compounds.