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.

Obesity and Type 2 Diabetes: Adiposopathy as a Triggering Factor and Therapeutic Options.

Obesity and type 2 diabetes (T2DM) are major public health concerns associated with serious morbidity and increased mortality. Both obesity and T2DM are strongly associated with adiposopathy, a term that describes the pathophysiological changes of the adipose tissue. In this review, we have highlighted adipose tissue dysfunction as a major factor in the etiology of these conditions since it promotes chronic inflammation, dysregulated glucose homeostasis, and impaired adipogenesis, leading to the accumulation of ectopic fat and insulin resistance. This dysfunctional state can be effectively ameliorated by the loss of at least 15% of body weight, that is correlated with better glycemic control, decreased likelihood of cardiometabolic disease, and an improvement in overall quality of life. Weight loss can be achieved through lifestyle modifications (healthy diet, regular physical activity) and pharmacotherapy. In this review, we summarized different effective management strategies to address weight loss, such as bariatric surgery and several classes of drugs, namely metformin, GLP-1 receptor agonists, amylin analogs, and SGLT2 inhibitors. These drugs act by targeting various mechanisms involved in the pathophysiology of obesity and T2DM, and they have been shown to induce significant weight loss and improve glycemic control in obese individuals with T2DM.

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.

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.

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.

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.

Impact of the Journal of Chemical Information and Modeling Special Issue on Women in Computational Chemistry.

In this Viewpoint, we provide a commentary on the impact of the Journal of Chemical Information and Modeling Special Issue on Women in Computational Chemistry published in May 2019 and the feedback we received.

Unveiling the molecular mechanisms underpinning biorecognition of early-glycated human serum albumin and receptor for advanced glycation end products.

Serum levels of early-glycated albumin are significantly increased in patients with diabetes mellitus and may play a role in worsening inflammatory status and sustaining diabetes-related complications. To investigate possible pathological recognition involving early-glycated albumin and the receptor for advanced glycation end products (RAGE), an early-glycated human serum albumin (HSAgly), with a glycation pattern representative of the glycated HSA form abundant in diabetic patients, and the recombinant human RAGE ectodomain (VC1) were used. Biorecognition between the two interactants was investigated by combining surface plasmon resonance (SPR) analysis and affinity chromatography coupled with mass spectrometry (affinity-MS) for peptide extraction and identification. SPR analysis proved early-glycated albumin could interact with the RAGE ectodomain with a steady-state affinity constant of 6.05 ± 0.96 × 10-7 M. Such interaction was shown to be specific, as confirmed by a displacement assay with chondroitin sulfate, a known RAGE binder. Affinity-MS studies were performed to map the surface area involved in the recognition. These studies highlighted that a region surrounding Lys525 and part of subdomain IA were involved in VC1 recognition. Finally, an in silico analysis highlighted (i) a key role for glycation at Lys525 (the most commonly glycated residue in HSA in diabetic patients) through a triggering mechanism similar to that previously observed for AGEs or advanced lipoxidation end products and (ii) a stabilizing role for subdomain IA. Albeit a moderate affinity for complex formation, the high plasma levels of early-glycated albumin and high percentage of glycation at Lys525 in diabetic patients make this interaction of possible pathological relevance. Graphical abstract.

Repositioning Dequalinium as Potent Muscarinic Allosteric Ligand by Combining Virtual Screening Campaigns and Experimental Binding Assays.

Structure-based virtual screening is a truly productive repurposing approach provided that reliable target structures are available. Recent progresses in the structural resolution of the G-Protein Coupled Receptors (GPCRs) render these targets amenable for structure-based repurposing studies. Hence, the present study describes structure-based virtual screening campaigns with a view to repurposing known drugs as potential allosteric (and/or orthosteric) ligands for the hM2 muscarinic subtype which was indeed resolved in complex with an allosteric modulator thus allowing a precise identification of this binding cavity. First, a docking protocol was developed and optimized based on binding space concept and enrichment factor optimization algorithm (EFO) consensus approach by using a purposely collected database including known allosteric modulators. The so-developed consensus models were then utilized to virtually screen the DrugBank database. Based on the computational results, six promising molecules were selected and experimentally tested and four of them revealed interesting affinity data; in particular, dequalinium showed a very impressive allosteric modulation for hM2. Based on these results, a second campaign was focused on bis-cationic derivatives and allowed the identification of other two relevant hM2 ligands. Overall, the study enhances the understanding of the factors governing the hM2 allosteric modulation emphasizing the key role of ligand flexibility as well as of arrangement and delocalization of the positively charged moieties.

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.

Rescoring and Linearly Combining: A Highly Effective Consensus Strategy for Virtual Screening Campaigns.

The study proposes a novel consensus strategy based on linear combinations of different docking scores to be used in the evaluation of virtual screening campaigns. The consensus models are generated by applying the recently proposed Enrichment Factor Optimization (EFO) method, which develops the linear equations by exhaustively combining the available docking scores and by optimizing the resulting enrichment factors. The performances of such a consensus strategy were evaluated by simulating the entire Directory of Useful Decoys (DUD datasets). In detail, the poses were initially generated by the PLANTS docking program and then rescored by ReScore+ with and without the minimization of the complexes. The so calculated scores were then used to generate the mentioned consensus models including two or three different scoring functions. The reliability of the generated models was assessed by a per target validation as performed by default by the EFO approach. The encouraging performances of the here proposed consensus strategy are emphasized by the average increase of the 17% in the Top 1% enrichment factor (EF) values when comparing the single best score with the linear combination of three scores. Specifically, kinases offer a truly convincing demonstration of the efficacy of the here proposed consensus strategy since their Top 1% EF average ranges from 6.4 when using the single best performing primary score to 23.5 when linearly combining scoring functions. The beneficial effects of this consensus approach are clearly noticeable even when considering the entire DUD datasets as evidenced by the area under the curve (AUC) averages revealing a 14% increase when combining three scores. The reached AUC values compare very well with those reported in literature by an extended set of recent benchmarking studies and the three-variable models afford the highest AUC average.

WarpEngine, a Flexible Platform for Distributed Computing Implemented in the VEGA Program and Specially Targeted for Virtual Screening Studies.

The manuscript describes WarpEngine, a novel platform implemented within the VEGA ZZ suite of software for performing distributed simulations both in local and wide area networks. Despite being tailored for structure-based virtual screening campaigns, WarpEngine possesses the required flexibility to carry out distributed calculations utilizing various pieces of software, which can be easily encapsulated within this platform without changing their source codes. WarpEngine takes advantages of all cheminformatics features implemented in the VEGA ZZ program as well as of its largely customizable scripting architecture thus allowing an efficient distribution of various time-demanding simulations. To offer an example of the WarpEngine potentials, the manuscript includes a set of virtual screening campaigns based on the ACE data set of the DUD-E collections using PLANTS as the docking application. Benchmarking analyses revealed a satisfactory linearity of the WarpEngine performances, the speed-up values being roughly equal to the number of utilized cores. Again, the computed scalability values emphasized that a vast majority (i.e., >90%) of the performed simulations benefit from the distributed platform presented here. WarpEngine can be freely downloaded along with the VEGA ZZ program at www.vegazz.net .

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.

Quenching activity of carnosine derivatives towards reactive carbonyl species: Focus on α-(methylglyoxal) and ß-(malondialdehyde) dicarbonyls.

The study combines HPLC-based with MS-based competitive analyses to evaluate the quenching activity of a set of carnosine derivatives towards methylglyoxal (MGO) and malondialdehyde (MDA) chosen as representative of α- and ß-dicarbonyls, respectively. The obtained results underline that these derivatives are moderately reactive towards MDA with which they form the corresponding N-propenal adduct via Michael addition. In contrast they proved a rather poor quenching activity towards MGO with which they can condense to give MOLD-like adducts through a concerted mechanism involving more quenchers molecules. Even though both quenching mechanisms involve the amino group in its neutral form, in silico studies revealed that the reported reactivity values depend on different stereo-electronic parameters which are reflected in the different observed quenching mechanism. Finally, the MGO quenching reactivity and the unselective (and unwanted) pyridoxal quenching are found to be influenced by the same parameters thus rationalizing the known difficulty in the design of potent and selective quenchers towards ß-dicarbonyls.

Binding Space Concept: A New Approach To Enhance the Reliability of Docking Scores and Its Application to Predicting Butyrylcholinesterase Hydrolytic Activity.

Docking simulations are very popular approaches able to assess the capacity of a given ligand to interact with a target. Docking simulations are usually focused on a single best complex even though many studies showed that ligands retain a significant mobility within a binding pocket by assuming different binding modes all of which may contribute to the monitored ligand affinity. The present study describes an innovative concept, the binding space, which allows an exploration of the ligand mobility within the binding pocket by simultaneously considering several ligand poses as generated by docking simulations. The multiple poses and the relative docking scores can then be analyzed by taking advantage of the same concepts already used in the property space analysis; hence the binding space can be parametrized by (a) mean scores, (b) score ranges, and (c) score sensitivity values. The first parameter represents a very simple procedure to account for the contribution of the often neglected alternative binding modes, while the last two descriptors encode the degree of mobility which a given ligand retains within the binding cavity (score range) as well as the ease with which a ligand explores such a mobility (score sensitivity). Here, the binding space concept is applied to the prediction of the hydrolytic activity of BChE by synergistically considering multiple poses and multiple protein structures. The obtained results shed light on the remarkable potential of the binding space concept, whose parameters allow a significant increase of the predictive power of the docking results as revealed by extended correlative analyses. Mean scores are the parameters affording the largest statistical improvement, and all the here proposed docking-based descriptors show enhancing effects in developing predictive models. Finally, the study describes a new score function (Contacts score) simply based on the number of surrounding residues which appears to be particularly productive in the framework of the binding space.

Improvement of Topical Palmitoylethanolamide Anti-Inflammatory Activity by Pegylated Prodrugs.

A small library of polyethylene glycol esters of palmitoylethanolamide (PEA) was synthesized with the aim of improving the pharmacokinetic profile of the parent drug after topical administration. Synthesized prodrugs were studied for their skin accumulation, pharmacological activities, in vitro chemical stability, and in silico enzymatic hydrolysis. Prodrugs proved to be able to delay and prolong the pharmacological activity of PEA by modification of its skin accumulation profile. Pharmacokinetic improvements were particularly evident when specific structural requirements, such as flexibility and reduced molecular weight, were respected. Some of the synthesized prodrugs prolonged the pharmacological effects 5 days following topical administration, while a formulation composed by PEA and two pegylated prodrugs showed both rapid onset and long-lasting activity, suggesting the potential use of polyethylene glycol prodrugs of PEA as a suitable candidate for the treatment of skin inflammatory diseases.

Mode of interaction of 1,4-dioxane agonists at the M2 and M3 muscarinic receptor orthosteric sites.

The methyl group in cis stereochemical relationship with the basic chain of all pentatomic cyclic analogues of ACh is crucial for the agonist activity at mAChR. Among these only cevimeline (1) is employed in the treatment of xerostomia associated with Sjögren's syndrome. Here we demonstrated that, unlike 1,3-dioxolane derivatives, in the 1,4-dioxane series the methyl group is not essential for the activation of mAChR subtypes. Docking studies, using the crystal structures of human M2 and rat M3 receptors, demonstrated that the 5-methylene group of the 1,4-dioxane nucleus of compound 10 occupies the same lipophilic pocket as the methyl group of the 1,3-dioxolane 4.