Metabolic Forest: Predicting the Diverse Structures of Drug Metabolites

Message Passing Neural Networks Improve Prediction of Metabolite Authenticity

Cytochrome P450 enzymes aid in the elimination of a preponderance of small molecule drugs, but can generate reactive metabolites that may adversely react with protein and DNA and prompt drug candidate attrition or market withdrawal. Previously developed models help understand how these enzymes modify molecule structure by predicting sites of metabolism or characterizing formation of metabolite-biomolecule adducts. However, the majority of reactive metabolites are formed by multiple metabolic steps, and understanding the progenitor molecule's network-level behavior necessitates an integrative approach that blends multiple site of metabolism and structure inference models. Our previously developed tool, XenoNet 1.0, generates metabolic networks, where nodes are molecules and weighted edges are metabolic transformations. We extend XenoNet with a bidirectional message passing neural network that integrates edge feature information and local network structure using edge-conditioned graph convolutions and jumping knowledge to predict the authenticity of inferred Phase I metabolite structures. Our model significantly outperformed prior work and algorithmic baselines on a data set of 311 networks and 6606 intermediates annotated using a chemically diverse set of 20 736 individual in vitro and in vivo reaction records accounting for 92.3% of all human Phase I metabolism in the Accelrys Metabolite Database. Cross-validated predictions resulted in area under the receiver operating characteristic curves of 88.5% and 87.6% for separating experimentally observed and unobserved metabolites at global and network levels, respectively. Further analysis verified robustness to networks of varying depth and breadth, accurate detection of metabolites, such as d,l-methamphetamine, that are experimentally observed or unobserved in different network contexts, extraction of important metabolic subnetworks, and identification of known bioactivation pathways, such as for nimesulide and terbinafine. By exploiting network structures, our approach accurately suggests unreported metabolites for experimental study and may rationalize modifications for avoiding deleterious pathways antecedent to reactive metabolite formation.

Consensus Prediction of Human Gut Microbiota-Mediated Metabolism Susceptibility for Small Molecules by Machine Learning, Structural Alerts, and Dietary Compounds-Based Average Similarity Methods

The human gut microbiota (HGM) colonizing human gastrointestinal tract (HGT) confers a repertoire of dynamic and unique metabolic capacities that are not possessed by the host and therefore is tentatively perceived as an alternative metabolic ″organ″ besides the liver in the host. Nevertheless, the significant contribution of HGM to the overall human metabolism is often overlooked in the modern drug discovery pipeline. Hence, a systematic evaluation of HGM-mediated drug metabolism is gradually important, and its computational prediction becomes increasingly necessary. In this work, a new data set containing both the HGM-mediated metabolism susceptible (HGMMS) and insusceptible (HGMMI) compounds (329 vs 320) was manually curated. Based on this data set, the first machine learning (ML) model, a new structural alerts (SA) model, and the K-nearest neighboring dietary compounds-based average similarity (AS) model were proposed to directly predict the HGM-mediated metabolism susceptibility for small molecules, and exhibit promising performance on three independent test sets. Finally, consensus prediction (ML/SA/AS) for DrugBank molecules revealed an intriguing phenomenon that a typical Michael acceptor ″α,β-unsaturated carbonyl group″ is a very common warhead for the design of covalent inhibitors and inclined to be metabolized by HGM in anaerobic HGT to generate the reduced metabolite without the reactive warhead, which could be a new concern to medicinal chemists. To the best of our knowledge, we gleaned the first HGMMS/HGMMI data set, developed the first HGMMS/HGMMI classification model, implemented a relatively comprehensive program based on ML/SA/AS approaches, and found a new phenomenon on the HGM-mediated deactivation of an extensively used warhead for covalent inhibitors.

MetaClass, a Comprehensive Classification System for Predicting the Occurrence of Metabolic Reactions Based on the MetaQSAR Database

(1) Background: Machine learning algorithms are finding fruitful applications in predicting the ADME profile of new molecules, with a particular focus on metabolism predictions. However, the development of comprehensive metabolism predictors is hampered by the lack of highly accurate metabolic resources. Hence, we recently proposed a manually curated metabolic database (MetaQSAR), the level of accuracy of which is well suited to the development of predictive models. (2) Methods: MetaQSAR was used to extract datasets to predict the metabolic reactions subdivided into major classes, classes and subclasses. The collected datasets comprised a total of 3788 first-generation metabolic reactions. Predictive models were developed by using standard random forest algorithms and sets of physicochemical, stereo-electronic and constitutional descriptors. (3) Results: The developed models showed satisfactory performance, especially for hydrolyses and conjugations, while redox reactions were predicted with greater difficulty, which was reasonable as they depend on many complex features that are not properly encoded by the included descriptors. (4) Conclusions: The generated models allowed a precise comparison of the propensity of each metabolic reaction to be predicted and the factors affecting their predictability were discussed in detail. Overall, the study led to the development of a freely downloadable global predictor, MetaClass, which correctly predicts 80% of the reported reactions, as assessed by an explorative validation analysis on an external dataset, with an overall MCC = 0.44.

Bioactivation of Isoxazole-Containing Bromodomain and Extra-Terminal Domain (BET) Inhibitors

The 3,5-dimethylisoxazole motif has become a useful and popular acetyl-lysine mimic employed in isoxazole-containing bromodomain and extra-terminal (BET) inhibitors but may introduce the potential for bioactivations into toxic reactive metabolites. As a test, we coupled deep neural models for quinone formation, metabolite structures, and biomolecule reactivity to predict bioactivation pathways for 32 BET inhibitors and validate the bioactivation of select inhibitors experimentally. Based on model predictions, inhibitors were more likely to undergo bioactivation than reported non-bioactivated molecules containing isoxazoles. The model outputs varied with substituents indicating the ability to scale their impact on bioactivation. We selected OXFBD02, OXFBD04, and I-BET151 for more in-depth analysis. OXFBD’s bioactivations were evenly split between traditional quinones and novel extended quinone-methides involving the isoxazole yet strongly favored the latter quinones. Subsequent experimental studies confirmed the formation of both types of quinones for OXFBD molecules, yet traditional quinones were the dominant reactive metabolites. Modeled I-BET151 bioactivations led to extended quinone-methides, which were not verified experimentally. The differences in observed and predicted bioactivations reflected the need to improve overall bioactivation scaling. Nevertheless, our coupled modeling approach predicted BET inhibitor bioactivations including novel extended quinone methides, and we experimentally verified those pathways highlighting potential concerns for toxicity in the development of these new drug leads.

Recent advances in computational metabolite structure predictions and altered metabolic pathways assessment to inform drug development processes

Many drug candidates fail during preclinical and clinical trials due to variable or unexpected metabolism which may lead to variability in drug efficacy or adverse drug reactions. The drug metabolism field aims to address this important issue from many angles which range from the study of drug-drug interactions, pharmacogenomics, computational metabolic modeling, and others. This manuscript aims to provide brief but comprehensive manuscript summaries highlighting the conclusions and scientific importance of seven exceptional manuscripts published in recent years within the field of drug metabolism. Two main topics within the field are reviewed: novel computational metabolic modeling approaches which provide complex outputs beyond site of metabolism predictions, and experimental approaches designed to discern the impacts of interindividual variability and species differences on drug metabolism. The computational approaches discussed provide novel outputs in metabolite structure and formation likelihood and/or extend beyond the saturated field of drug phase I metabolism, while the experimental metabolic pathways assessments aim to highlight the impacts of genetic polymorphisms and clinical animal model metabolic differences on human metabolism and subsequent health outcomes.

Extraction of Data on Parent Compounds and Their Metabolites from Texts of Scientific Abstracts

The growing amount of experimental data on chemical objects includes properties of small molecules, results of studies of their interaction with human and animal proteins, and methods of synthesis of organic compounds (OCs). The data obtained can be used to identify the names of OCs automatically, including all possible synonyms and relevant data on the molecular properties and biological activity. Utilization of different synonymic names of chemical compounds allows researchers to increase the completeness of data on their properties available from publications. Enrichment of the data on the names of chemical compounds by information about their possible metabolites can help estimate the biological effects of parent compounds and their metabolites more thoroughly. Therefore, an attempt at automated extraction of the names of parent compounds and their metabolites from the texts is a rather important task. In our study, we aimed at developing a method that provides the extraction of the named entities (NEs) of parent compounds and their metabolites from abstracts of scientific publications. Based on the application of the conditional random fields' algorithm, we extracted the NEs of chemical compounds. We developed a set of rules allowing identification of parent compound NEs and their metabolites in the texts. We evaluated the possibility of extracting the names of potential metabolites based on cosine similarity between strings representing names of parent compounds and all other chemical NEs found in the text. Additionally, we used conditional random fields to fetch the names of parent compounds and their metabolites from the texts based on the corpus of texts labeled manually. Our computational experiments showed that usage of rules in combination with cosine similarity could increase the accuracy of recognition of the names of metabolites compared to the rule-based algorithm and application of a machine-learning algorithm (conditional random fields).

Modeling the Bioactivation and Subsequent Reactivity of Drugs

Electrophilically reactive drug metabolites are implicated in many adverse drug reactions. In this mechanism-termed bioactivation-metabolic enzymes convert drugs into reactive metabolites that often conjugate to nucleophilic sites within biological macromolecules like proteins. Toxic metabolite-product adducts induce severe immune responses that can cause sometimes fatal disorders, most commonly in the form of liver injury, blood dyscrasia, or the dermatologic conditions toxic epidermal necrolysis and Stevens-Johnson syndrome. This study models four of the most common metabolic transformations that result in bioactivation: quinone formation, epoxidation, thiophene sulfur-oxidation, and nitroaromatic reduction, by synthesizing models of metabolism and reactivity. First, the metabolism models predict the formation probabilities of all possible metabolites among the pathways studied. Second, the exact structures of these metabolites are enumerated. Third, using these structures, the reactivity model predicts the reactivity of each metabolite. Finally, a feedfoward neural network converts the metabolism and reactivity predictions to a bioactivation prediction for each possible metabolite. These bioactivation predictions represent the joint probability that a metabolite forms and that this metabolite subsequently conjugates to protein or glutathione. Among molecules bioactivated by these pathways, we predicted the correct pathway with an AUC accuracy of 89.98%. Furthermore, the model predicts whether molecules will be bioactivated, distinguishing bioactivated and nonbioactivated molecules with 81.06% AUC. We applied this algorithm to withdrawn drugs. The known bioactivation pathways of alclofenac and benzbromarone were identified by the algorithm, and high probability bioactivation pathways not yet confirmed were identified for safrazine, zimelidine, and astemizole. This bioactivation model-the first of its kind that jointly considers both metabolism and reactivity-enables drug candidates to be quickly evaluated for a toxicity risk that often evades detection during preclinical trials. The XenoSite bioactivation model is available at http://swami.wustl.edu/xenosite/p/bioactivation.