MetaQSAR: An Integrated Database Engine to Manage and Analyze Metabolic Data

"DompeKeys": a set of novel substructure-based descriptors for efficient chemical space mapping, development and structural interpretation of machine learning models, and indexing of large databases

The conversion of chemical structures into computer-readable descriptors, able to capture key structural aspects, is of pivotal importance in the field of cheminformatics and computer-aided drug design. Molecular fingerprints represent a widely employed class of descriptors; however, their generation process is time-consuming for large databases and is susceptible to bias. Therefore, descriptors able to accurately detect predefined structural fragments and devoid of lengthy generation procedures would be highly desirable. To meet additional needs, such descriptors should also be interpretable by medicinal chemists, and suitable for indexing databases with trillions of compounds. To this end, we developed-as integral part of EXSCALATE, Dompé's end-to-end drug discovery platform-the DompeKeys (DK), a new substructure-based descriptor set, which encodes the chemical features that characterize compounds of pharmaceutical interest. DK represent an exhaustive collection of curated SMARTS strings, defining chemical features at different levels of complexity, from specific functional groups and structural patterns to simpler pharmacophoric points, corresponding to a network of hierarchically interconnected substructures. Because of their extended and hierarchical structure, DK can be used, with good performance, in different kinds of applications. In particular, we demonstrate how they are very well suited for effective mapping of chemical space, as well as substructure search and virtual screening. Notably, the incorporation of DK yields highly performing machine learning models for the prediction of both compounds' activity and metabolic reaction occurrence. The protocol to generate the DK is freely available at https://dompekeys.exscalate.eu and is fully integrated with the Molecular Anatomy protocol for the generation and analysis of hierarchically interconnected molecular scaffolds and frameworks, thus providing a comprehensive and flexible tool for drug design applications.

Active Learning Approach for Guiding Site-of-Metabolism Measurement and Annotation

The ability to determine and predict metabolically labile atom positions in a molecule (also called "sites of metabolism" or "SoMs") is of high interest to the design and optimization of bioactive compounds, such as drugs, agrochemicals, and cosmetics. In recent years, several in silico models for SoM prediction have become available, many of which include a machine-learning component. The bottleneck in advancing these approaches is the coverage of distinct atom environments and rare and complex biotransformation events with high-quality experimental data. Pharmaceutical companies typically have measured metabolism data available for several hundred to several thousand compounds. However, even for metabolism experts, interpreting these data and assigning SoMs are challenging and time-consuming. Therefore, a significant proportion of the potential of the existing metabolism data, particularly in machine learning, remains dormant. Here, we report on the development and validation of an active learning approach that identifies the most informative atoms across molecular data sets for SoM annotation. The active learning approach, built on a highly efficient reimplementation of SoM predictor FAME 3, enables experts to prioritize their SoM experimental measurements and annotation efforts on the most rewarding atom environments. We show that this active learning approach yields competitive SoM predictors while requiring the annotation of only 20% of the atom positions required by FAME 3. The source code of the approach presented in this work is publicly available.

MetaSpot: A General Approach for Recognizing the Reactive Atoms Undergoing Metabolic Reactions Based on the MetaQSAR Database

The prediction of drug metabolism is attracting great interest for the possibility of discarding molecules with unfavorable ADME/Tox profile at the early stage of the drug discovery process. In this context, artificial intelligence methods can generate highly performing predictive models if they are trained by accurate metabolic data. MetaQSAR-based datasets were collected to predict the sites of metabolism for most metabolic reactions. The models were based on a set of structural, physicochemical, and stereo-electronic descriptors and were generated by the random forest algorithm. For each considered biotransformation, two types of models were developed: the first type involved all non-reactive atoms and included atom types among the descriptors, while the second type involved only non-reactive centers having the same atom type(s) of the reactive atoms. All the models of the first type revealed very high performances; the models of the second type show on average worst performances while being almost always able to recognize the reactive centers; only conjugations with glucuronic acid are unsatisfactorily predicted by the models of the second type. Feature evaluation confirms the major role of lipophilicity, self-polarizability, and H-bonding for almost all considered reactions. The obtained results emphasize the possibility of recognizing the sites of metabolism by classification models trained on MetaQSAR database. The two types of models can be synergistically combined since the first models identify which atoms can undergo a given metabolic reactions, while the second models detect the truly reactive centers. The generated models are available as scripts for the VEGA program.

Artificial Intelligence in Drug Metabolism and Excretion Prediction: Recent Advances, Challenges, and Future Perspectives

Drug metabolism and excretion play crucial roles in determining the efficacy and safety of drug candidates, and predicting these processes is an essential part of drug discovery and development. In recent years, artificial intelligence (AI) has emerged as a powerful tool for predicting drug metabolism and excretion, offering the potential to speed up drug development and improve clinical success rates. This review highlights recent advances in AI-based drug metabolism and excretion prediction, including deep learning and machine learning algorithms. We provide a list of public data sources and free prediction tools for the research community. We also discuss the challenges associated with the development of AI models for drug metabolism and excretion prediction and explore future perspectives in the field. We hope this will be a helpful resource for anyone who is researching in silico drug metabolism, excretion, and pharmacokinetic properties.

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.

Novel advances in biotransformation and bioactivation research - 2020 year in review

This annual review is the sixth of its kind since 2016 (see references). Our objective is to explore and share articles which we deem influential and significant in the field of biotransformation and bioactivation. These fields are constantly evolving with new molecular structures and discoveries of corresponding pathways for metabolism that impact relevant drug development with respect to efficacy and safety. Based on the selected articles, we created three sections: (1) drug design, (2) metabolites and drug metabolizing enzymes, and (3) bioactivation and safety (Table 1). Unlike in years past, more biotransformation experts have joined and contributed to this effort while striving to maintain a balance of authors from academic and industry settings.

The VEGA suite of programs: an versatile platform for cheminformatics and drug design projects

The purpose of the article is to offer an overview of the latest release of the VEGA suite of programs. This software has been constantly developed and freely released during the last 20 years and has now reached a significant diffusion and technology level as confirmed by the about 22 500 registered users. While being primarily developed for drug design studies, the VEGA package includes cheminformatics and modeling features, which can be fruitfully utilized in various contexts of the computational chemistry. To offer a glimpse of the remarkable potentials of the software, some examples of the implemented features in the cheminformatics field and for structure-based studies are discussed. Finally, the flexible architecture of the VEGA program which can be expanded and customized by plug-in technology or scripting languages will be described focusing attention on the HyperDrive library including highly optimized functions.

AVAILABILITY AND IMPLEMENTATION

The VEGA suite of programs and the source code of the VEGA command-line version are available free of charge for non-profit organizations at http://www.vegazz.net.

MetaTREE, a Novel Database Focused on Metabolic Trees, Predicts an Important Detoxification Mechanism: The Glutathione Conjugation

(1) Background: Data accuracy plays a key role in determining the model performances and the field of metabolism prediction suffers from the lack of truly reliable data. To enhance the accuracy of metabolic data, we recently proposed a manually curated database collected by a meta-analysis of the specialized literature (MetaQSAR). Here we aim to further increase data accuracy by focusing on publications reporting exhaustive metabolic trees. This selection should indeed reduce the number of false negative data. (2) Methods: A new metabolic database (MetaTREE) was thus collected and utilized to extract a dataset for metabolic data concerning glutathione conjugation (MT-dataset). After proper pre-processing, this dataset, along with the corresponding dataset extracted from MetaQSAR (MQ-dataset), was utilized to develop binary classification models using a random forest algorithm. (3) Results: The comparison of the models generated by the two collected datasets reveals the better performances reached by the MT-dataset (MCC raised from 0.63 to 0.67, sensitivity from 0.56 to 0.58). The analysis of the applicability domain also confirms that the model based on the MT-dataset shows a more robust predictive power with a larger applicability domain. (4) Conclusions: These results confirm that focusing on metabolic trees represents a convenient approach to increase data accuracy by reducing the false negative cases. The encouraging performances shown by the models developed by the MT-dataset invites to use of MetaTREE for predictive studies in the field of xenobiotic metabolism.

NERDD: a web portal providing access to in silico tools for drug discovery

SUMMARY

The New E-Resource for Drug Discovery (NERDD) is a quickly expanding web portal focused on the provision of peer-reviewed in silico tools for drug discovery. NERDD currently hosts tools for predicting the sites of metabolism (FAME) and metabolites (GLORY) of small organic molecules, for flagging compounds that are likely to interfere with biological assays (Hit Dexter), and for identifying natural products and natural product derivatives in large compound collections (NP-Scout). Several additional models and components are currently in development.

AVAILABILITY AND IMPLEMENTATION

The NERDD web server is available at https://nerdd.zbh.uni-hamburg.de. Most tools are also available as software packages for local installation.

Dissipative particle dynamics model of homogalacturonan based on molecular dynamics simulations

In this study we present an alternative dissipative particle dynamics (DPD) parametrization strategy based on data extracted from the united-atom molecular simulations. The model of the homogalacturonan was designed to test the ability of the formation of large-scale structures via hydrogen bonding in water. The extraction of coarse-grained parameters from atomistic molecular dynamics was achieved by means of the proposed molecule aggregation algorithm based on an iterative nearest neighbour search. A novel approach to a time-scale calibration scheme based on matching the average velocities of coarse-grained particles enabled the DPD forcefield to reproduce essential structural features of homogalacturonan molecular chains. The successful application of the proposed parametrization method allowed for the reproduction of the shapes of radial distribution functions, particle velocities and diffusivity of the atomistic molecular dynamics model using DPD force field. The structure of polygalacturonic acid molecules was mapped into the DPD force field by means of the distance and angular bond characteristics, which closely matched the MD results. The resulting DPD trajectories showed that randomly dispersed homogalacturonan chains had a tendency to aggregate into highly organized 3D structures. The final structure resembled a three-dimensional network created by tightly associated homogalacturonan chains organized into thick fibres.

GLORYx: Prediction of the Metabolites Resulting from Phase 1 and Phase 2 Biotransformations of Xenobiotics

Predicting the structures of metabolites formed in humans can provide advantageous insights for the development of drugs and other compounds. Here we present GLORYx, which integrates machine learning-based site of metabolism (SoM) prediction with reaction rule sets to predict and rank the structures of metabolites that could potentially be formed by phase 1 and/or phase 2 metabolism. GLORYx extends the approach from our previously developed tool GLORY, which predicted metabolite structures for cytochrome P450-mediated metabolism only. A robust approach to ranking the predicted metabolites is attained by using the SoM probabilities predicted by the FAME 3 machine learning models to score the predicted metabolites. On a manually curated test data set containing both phase 1 and phase 2 metabolites, GLORYx achieves a recall of 77% and an area under the receiver operating characteristic curve (AUC) of 0.79. Separate analysis of performance on a large amount of freely available phase 1 and phase 2 metabolite data indicates that achieving a meaningful ranking of predicted metabolites is more difficult for phase 2 than for phase 1 metabolites. GLORYx is freely available as a web server at https://nerdd.zbh.uni-hamburg.de/ and is also provided as a software package upon request. The data sets as well as all the reaction rules from this work are also made freely available.

Novel Potent Muscarinic Receptor Antagonists: Investigation on the Nature of Lipophilic Substituents in the 5- and/or 6-Positions of the 1,4-Dioxane Nucleus

A series of novel 1,4-dioxane analogues of the muscarinic acetylcholine receptor (mAChR) antagonist 2 was synthesized and studied for their affinity at M₁–M₅ mAChRs. The 6-cyclohexyl-6-phenyl derivative 3b, with a cis configuration between the CH₂N⁺(CH₃)₃ chain in the 2-position and the cyclohexyl moiety in the 6-position, showed pK_i values for mAChRs higher than those of 2 and a selectivity profile analogous to that of the clinically approved drug oxybutynin. The study of the enantiomers of 3b and the corresponding tertiary amine 33b revealed that the eutomers are (2S,6S)-(−)-3b and (2S,6S)-(−)-33b, respectively. Docking simulations on the M₃ mAChR-resolved structure rationalized the experimental observations. The quaternary ammonium function, which should prevent the crossing of the blood–brain barrier, and the high M₃/M₂ selectivity, which might limit cardiovascular side effects, make 3b a valuable starting point for the design of novel antagonists potentially useful in peripheral diseases in which M₃ receptors are involved.

Investigation of the Role of Chirality in the Interaction with σ Receptors and Effect on Binge Eating Episode of a Potent σ1 Antagonist Analogue of Spipethiane

The enantiomers of the potent σ1 receptor antagonist (±)-1 were synthesized and evaluated for their affinity at σ1, σ2 receptors and dopamine transporter (DAT). Analogously to (±)-1, both of the enantiomers showed very high affinity for the σ1 receptor and unprecedented selectivity over both the σ2 receptor and DAT. The lack of enantioselectivity between (+)-1 and (-)-1 indicated that the center of chirality in the 2-position of the benzothiochromane nucleus does not play a crucial role in the interaction with any of the studied targets. Docking studies confirmed that the configuration of the enantiomers has only marginal effects on the molecular interactions with the σ1 receptor. In in vivo studies in a female rat model of binge eating, (±)-1 dose-dependently decreased the binge eating episode elicited by a history of intermittent food restriction and stress, confirming and strengthening the important role played by the σ1 receptor in bingeing-related eating disorders.

FAME 3: Predicting the Sites of Metabolism in Synthetic Compounds and Natural Products for Phase 1 and Phase 2 Metabolic Enzymes

In this work we present the third generation of FAst MEtabolizer (FAME 3), a collection of extra trees classifiers for the prediction of sites of metabolism (SoMs) in small molecules such as drugs, druglike compounds, natural products, agrochemicals, and cosmetics. FAME 3 was derived from the MetaQSAR database ( Pedretti et al. J. Med. Chem. 2018 , 61 , 1019 ), a recently published data resource on xenobiotic metabolism that contains more than 2100 substrates annotated with more than 6300 experimentally confirmed SoMs related to redox reactions, hydrolysis and other nonredox reactions, and conjugation reactions. In tests with holdout data, FAME 3 models reached competitive performance, with Matthews correlation coefficients (MCCs) ranging from 0.50 for a global model covering phase 1 and phase 2 metabolism, to 0.75 for a focused model for phase 2 metabolism. A model focused on cytochrome P450 metabolism yielded an MCC of 0.57. Results from case studies with several synthetic compounds, natural products, and natural product derivatives demonstrate the agreement between model predictions and literature data even for molecules with structural patterns clearly distinct from those present in the training data. The applicability domains of the individual models were estimated by a new, atom-based distance measure (FAMEscore) that is based on a nearest-neighbor search in the space of atom environments. FAME 3 is available via a public web service at https://nerdd.zbh.uni-hamburg.de/ and as a self-contained Java software package, free for academic and noncommercial research.

Prediction of UGT-mediated Metabolism Using the Manually Curated MetaQSAR Database

Even though glucuronidations are the most frequent metabolic reactions of conjugation, both in quantitative and qualitative terms, they have rather seldom been investigated using computational approaches. To fill this gap, we have used the manually collected MetaQSAR metabolic reaction database to generate two models for the prediction of UGT-mediated metabolism, both based on molecular descriptors and implementing the Random Forest algorithm. The first model predicts the occurrence of the reaction and was internally validated with a Matthew correlation coefficient (MCC) of 0.76 and an area under the ROC curve (AUC) of 0.94, and further externally validated using a test set composed of 120 additional xenobiotics (MCC of 0.70 and AUC of 0.90). The second model distinguishes between O- and N-glucuronidations and was optimized by the random undersampling procedure to improve the predictive accuracy during the internal validation, with the recall measure of the minority class increasing from 0.55 to 0.78.

Prediction of the Formation of Reactive Metabolites by A Novel Classifier Approach Based on Enrichment Factor Optimization (EFO) as Implemented in the VEGA Program

The study is aimed at developing linear classifiers to predict the capacity of a given substrate to yield reactive metabolites. While most of the hitherto reported predictive models are based on the occurrence of known structural alerts (e.g., the presence of toxophoric groups), the present study is focused on the generation of predictive models involving linear combinations of physicochemical and stereo-electronic descriptors. The development of these models is carried out by using a novel classification approach based on enrichment factor optimization (EFO) as implemented in the VEGA suite of programs. The study took advantage of metabolic data as collected by manually curated analysis of the primary literature and published in the years 2004⁻2009. The learning set included 977 substrates among which 138 compounds yielded reactive first-generation metabolites, plus 212 substrates generating reactive metabolites in all generations (i.e., metabolic steps). The results emphasized the possibility of developing satisfactory predictive models especially when focusing on the first-generation reactive metabolites. The extensive comparison of the classifier approach presented here using a set of well-known algorithms implemented in Weka 3.8 revealed that the proposed EFO method compares with the best available approaches and offers two relevant benefits since it involves a limited number of descriptors and provides a score-based probability thus allowing a critical evaluation of the obtained results. The last analyses on non-cheminformatics UCI datasets emphasize the general applicability of the EFO approach, which conveniently performs using both balanced and unbalanced datasets.