Deep Learning to Predict the Formation of Quinone Species in Drug Metabolism

In Silico Investigation against Inhibitors of Alpha-Amylase Using Structure-based Screening, Molecular Docking, and Molecular Simulations Studies

Type-II diabetes mellitus is a chronic disorder that results from fluctuations in the glucose level leading to hyperglycemia with severe adverse effects increasing worldwide. Alpha-Amylase is the key enzyme involved in the mechanism of glucose formation therefore Alpha-Amylase inhibitors have become a therapeutic target in the development of new leads as they have the potential to suppress glucose levels. Existing drugs targeting Alpha-Amylase highlight major drawbacks in terms of poor absorption rate that causes several gastrointestinal issues. So, this research is aimed to develop novel inhibitors interacting with Alpha-Amylase's active site using structural-based screening, binding pattern analysis, and molecular dynamic simulation. Hence, to search for a potential lead, we analyzed a total of 133 valiolamine derivatives and 535 desoxynojirimycin derivatives that exhibited drug-like properties screened through Lipinski filters. Virtual screening followed by binding interaction analysis we identified ten compounds that exhibited better binding energy scores compared to the standard drugs voglibose and miglitol, used in our study. The docking analysis, ADMET and metabolic site prediction estimated the best top two compounds with good drug profiles. Further, top compounds VG9 and VG15 were promoted to simulation study using the Biovia Discovery study to access the stability at a time interval of 100 ns. MD simulation results revealed that our compound VG9 possesses better conformational stability in the complex to the active site residues of Alpha-Amylase target protein than standard drug voglibose. Thus, our investigation revealed that compound VG9 also exhibits the best pharmacokinetic as well as binding affinity results and could act as a potential lead compound targeting Alpha-Amylase for Type II diabetes.

Machine Learning Enables Accurate Prediction of Quinone Formation during Drug Metabolism

Metabolism helps in the elimination of drugs from the human body by making them more hydrophilic. Sometimes, drugs can be bioactivated to highly reactive metabolites or intermediates during metabolism. These reactive metabolites are often responsible for the toxicities associated with the drugs. Identification of reactive metabolites of drug candidates can be very helpful in the initial stages of drug discovery. Quinones are soft electrophiles that are generated as reactive intermediates during metabolism. Quinones make up more than 40% of the reactive metabolites. In this work, a reliable data set of 510 molecules was used to develop machine learning and deep learning-based predictive models to predict the formation of quinone-type metabolites. For representing molecules, two-dimensional (2D) descriptors, PubChem fingerprints, electro-topological state (E-state) fingerprints, and metabolic reactivity-based descriptors were used. Developed models were compared to the existing Xenosite web server using the untouched test set of 102 molecules. The best model achieved an accuracy of 86.27%, while the Xenosite server could achieve an accuracy of only 52.94% on the test set. Descriptor analysis revealed that the presence of greater numbers of polar moieties in a molecule can prevent the formation of quinone-type metabolites. In addition, the presence of a nitrogen atom in an aromatic ring and the presence of metabolophores V51, V52, and V53 (SMARTCyp descriptors) decrease the probability of quinone formation. Finally, a tool based on the best machine learning models was developed, which is accessible at http://14.139.57.41/quinonepred/.

Electrochemistry/mass spectrometry (EC/MS) for fast generation and identification of novel reactive metabolites of two unsymmetrical bisacridines with anticancer activity

The development of a new drug requires knowledge about its metabolic fate in a living organism, regarding the comprehensive assessment of both drug therapeutic activity and toxicity profiles. Electrochemistry (EC) coupled with mass spectrometry (MS) is an efficient tool for predicting the phase I metabolism of redox-sensitive drugs. In particular, EC/MS represents a clear advantage for the generation of reactive drug transformation products and their direct identification compared to biological matrices. In this work, we focused on the characterization of novel electrochemical products of two representative unsymmetrical bisacridines (C-2028 and C-2045) with demonstrated high anticancer activity. The electrochemical thin-layer flow-through cell μ-PrepCell 2.0 (Antec Scientific) was used here for the effective metabolite electrosynthesis. The electrochemical simulation of C-2028 reductive and C-2045 oxidative metabolism resulted in the generation of new products that were not observed before. The formation of nitroso [M-O+H]+ and azoxy [2M-3O+H]+ species from C-2028, as well as a series of hydroxylated and/or dehydrogenated products, including possible quinones [M-2H+H]+ and [M+O-2H+H]+ from C-2045, was demonstrated. For the latter, a glutathione S-conjugate (m/z 935.3130) was also obtained in measurements supplemented with the excess of reduced glutathione. For the identification of the products of interest, structural confirmation based on MS/MS fragmentation experiments was performed. Novel products of electrochemical conversions of unsymmetrical bisacridines were discussed in the context of their possible biological effect on the human organism.

Deep learning in drug discovery: a futuristic modality to materialize the large datasets for cheminformatics

Artificial intelligence (AI) development imitates the workings of the human brain to comprehend modern problems. The traditional approaches such as high throughput screening (HTS) and combinatorial chemistry are lengthy and expensive to the pharmaceutical industry as they can only handle a smaller dataset. Deep learning (DL) is a sophisticated AI method that uses a thorough comprehension of particular systems. The pharmaceutical industry is now adopting DL techniques to enhance the research and development process. Multi-oriented algorithms play a crucial role in the processing of QSAR analysis, de novo drug design, ADME evaluation, physicochemical analysis, preclinical development, followed by clinical trial data precision. In this study, we investigated the performance of several algorithms, including deep neural networks (DNN), convolutional neural networks (CNN) and multi-task learning (MTL), with the aim of generating high-quality, interpretable big and diverse databases for drug design and development. Studies have demonstrated that CNN, recurrent neural network and deep belief network are compatible, accurate and effective for the molecular description of pharmacodynamic properties. In Covid-19, existing pharmacological compounds has also been repurposed using DL models. In the absence of the Covid-19 vaccine, remdesivir and oseltamivir have been widely employed to treat severe SARS-CoV-2 infections. In conclusion, the results indicate the potential benefits of employing the DL strategies in the drug discovery process.Communicated by Ramaswamy H. Sarma.

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

Drug toxicity prediction is an important step in ensuring patient safety during drug design studies. While traditional preclinical studies have historically relied on animal models to evaluate toxicity, recent advances in deep-learning approaches have shown great promise in advancing drug safety science and reducing animal use in preclinical studies. However, deep-learning-based approaches also face challenges in handling large biological data sets, model interpretability, and regulatory acceptance. In this review, we provide an overview of recent developments in deep-learning-based approaches for predicting drug toxicity, highlighting their potential advantages over traditional methods and the need to address their limitations. Deep-learning models have demonstrated excellent performance in predicting toxicity outcomes from various data sources such as chemical structures, genomic data, and high-throughput screening assays. The potential of deep learning for automated feature engineering is also discussed. This review emphasizes the need to address ethical concerns related to the use of deep learning in drug toxicity studies, including the reduction of animal use and ensuring regulatory acceptance. Furthermore, emerging applications of deep learning in drug toxicity prediction, such as predicting drug-drug interactions and toxicity in rare subpopulations, are highlighted. The integration of deep-learning-based approaches with traditional methods is discussed as a way to develop more reliable and efficient predictive models for drug safety assessment, paving the way for safer and more effective drug discovery and development. Overall, this review highlights the critical role of deep learning in predictive toxicology and drug safety evaluation, emphasizing the need for continued research and development in this rapidly evolving field. By addressing the limitations of traditional methods, leveraging the potential of deep learning for automated feature engineering, and addressing ethical concerns, deep-learning-based approaches have the potential to revolutionize drug toxicity prediction and improve patient safety in drug discovery and development.

Structure-based pharmacophore modeling, virtual screening and simulation studies for the identification of potent anticancerous phytochemical lead targeting cyclin-dependent kinase 2

Cyclin-dependent kinases are of critical importance in directing various cell cycle phases making them as potential tumor targets. Cyclin-dependent kinase 2 (CDK2) in particular plays a significant part during cell cycle events and its imbalance roots out tumorogenic environment. Herein, we built a structure-based pharmacophore model complementing the ATP pocket site of CDK2 with four pharmacophoric features, using a series of structures obtained from cluster analysis during MD simulation assessment. This was followed by its validation and further database screening against Taiwan indigenous plants database (5284 compounds). The screened compounds were subjected toward Lipinski's rule (RO5) and ADMET filter followed by docking analysis and simulation study. In filtering hits (10 compounds) via molecular docking against CDK2, Schinilenol with -8.1 kcal/mol fetched out as a best lead phytoinhibitor in the presence of standard drug (Dinaciclib). Additionally, pharmacophore mapping analysis also indicated relative fit values of dinaciclib and schinilenol as 2.37 and 2.31, respectively. Optimization, flexibility prediction and the stability of CDK2 in complex with the ligands were also ascertained by means of molecular dynamics for 50 ns, which further proposed schinilenol having better binding stability than dinaciclib with RMSD values ranging from 0.31 to 0.34 nm. Reactivity site, biological activity detection and cardiotoxicity assessment also proposed schinilenol as a better phytolead inhibitor than the existing dinaciclib. Abbreviations: CDK2: Cyclin dependent kinase2; ATP: Adenosine triphosphate; MD: Molecular dynamics, RO5: Rule of five; ADMET: Absorption, distribution, metabolism, and excretion; RMSD: Root mean square deviation; DS: Discovery Studio; SOM: Site of metabolism; RBPM: receptor based pharmacophore model; TIP: Schinilenol; hERG: human Ether-à-go-go - Related GeneCommunicated by Ramaswamy H. Sarma.

Carba Analogues of Flupirtine and Retigabine with Improved Oxidation Resistance and Reduced Risk of Quinoid Metabolite Formation

The K_V7 potassium channel openers flupirtine and retigabine have been valuable options in the therapy of pain and epilepsy. However, as a result of adverse reactions, both drugs are currently no longer in therapeutic use. The flupirtine‐induced liver injury and the retigabine linked tissue discolouration do not appear related at first glance; nevertheless, both events can be attributed to the triaminoaryl scaffold, which is affected by oxidation leading to elusive reactive quinone diimine or azaquinone diimine metabolites. Since the mechanism of action, i. e. K_V7 channel opening, seems not to be involved in toxicity, this study aimed to further develop safer replacements for flupirtine and retigabine. In a ligand‐based design strategy, replacing amino substituents of the triaminoaryl core with alkyl substituents led to carba analogues with improved oxidation resistance and negligible risk of quinoid metabolite formation. In addition to these improved safety features, some of the novel analogues exhibited significantly improved K_V7.2/3 channel opening activity, indicated by an up to 13‐fold increase in potency and an efficacy of up to 176 % compared to flupirtine, thus being attractive candidates for further development.

Modifications of the Triaminoaryl Metabophore of Flupirtine and Retigabine Aimed at Avoiding Quinone Diimine Formation

The potassium channel opening drugs flupirtine and retigabine have been withdrawn from the market due to occasional drug-induced liver injury (DILI) and tissue discoloration, respectively. While the mechanism underlying DILI after prolonged flupirtine use is not entirely understood, evidence indicates that both drugs are metabolized in an initial step to reactive ortho- and/or para-azaquinone diimines or ortho- and/or para-quinone diimines, respectively. Aiming to develop safer alternatives for the treatment of pain and epilepsy, we have attempted to separate activity from toxicity by employing a drug design strategy of avoiding the detrimental oxidation of the central aromatic ring by shifting oxidation toward the formation of benign metabolites. In the present investigation, an alternative retrometabolic design strategy was followed. The nitrogen atom, which could be involved in the formation of both ortho- or para-quinone diimines of the lead structures, was shifted away from the central ring, yielding a substitution pattern with nitrogen substituents in the meta position only. Evaluation of K_V7.2/3 opening activity of the 11 new specially designed derivatives revealed surprisingly steep structure-activity relationship data with inactive compounds and an activity cliff that led to the identification of an apparent "magic methyl" effect in the case of N-(4-fluorobenzyl)-6-[(4-fluorobenzyl)amino]-2-methoxy-4-methylnicotinamide. This flupirtine analogue showed potent K_V7.2/3 opening activity, being six times as active as flupirtine itself, and by design is devoid of the potential for azaquinone diimine formation.

In Silico Tools and Software to Predict ADMET of New Drug Candidates

Implication of computational techniques and in silico tools promote not only reduction of animal experimentations but also save time and money followed by rational designing of drugs as well as controlled synthesis of those "Hits" which show drug-likeness and possess suitable absorption, distribution, metabolism, excretion, and toxicity (ADMET) profile. With globalization of diseases, resistance of drugs over the time and modification of viruses and microorganisms, computational tools, and artificial intelligence are the future of drug design and one of the important areas where the principles of sustainability and green chemistry (GC) perfectly fit. Most of the new drug entities fail in the clinical trials over the issue of drug-associated human toxicity. Although ecotoxicity related to new drugs is rarely considered, but this is the high time when ecotoxicity prediction should get equal importance along with human-associated drug toxicity. Thus, the present book chapter discusses the available in silico tools and software for the fast and preliminary prediction of a series of human-associated toxicity and ecotoxicity of new drug entities to screen possibly safer drugs before going into preclinical and clinical trials.

2,6-Di-tert-butylphenol and its quinone metabolite trigger aberrant transcriptional responses in C57BL/6 mice liver

2,6-Di-tert-butylphenol (2,6-DTBP) is used as an antioxidant with wide commercial applications and its residues have been detected in various environmental matrices. 2,6-DTBP may enter human body via ingestion, inhalation or other exposure pathways. However, its susceptibility to biotransformation and potential of the metabolic products to trigger aberrant transcriptional responses remain unclear. Here, we investigated in vitro and in vivo biotransformation of 2,6-DTBP and characterized the RNA-Seq based transcriptional profiling of C57BL/6 mice liver after the exposure to 2,6-DTBP and its metabolites. 2,6-DTBP was metabolized into hydroxylated (2,6-DTBH) and para-quinone (2,6-DTBQ) products with residues detected in serum and liver of C57BL/6 mice. 2,6-DTBP and 2,6-DTBQ induced the aberrant transcription in C57BL/6 mice liver featured with 373-2861 differentially expressed genes (DEGs). They also up-regulated 1.09-2.92 fold mRNA expression of carcinogenesis-related genes such as Ccnd1, TGFβ1 and FOS in C57BL/6 mice liver. Our study indicated potential carcinogenic risk of 2,6-DTBP and its metabolites, beneficial to further evaluation of health risk of TBPs-related contaminants.

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.

Impacts of diphenylamine NSAID halogenation on bioactivation risks

Diphenylamine NSAIDs are highly prescribed therapeutics for chronic pain despite causing symptomatic hepatotoxicity through mitochondrial damage in five percent of patients taking them. Differences in toxicity are attributed to structural modifications to the diphenylamine scaffold rather than its inherent toxicity. We hypothesize that marketed diphenylamine NSAID substituents affect preference and efficiency of bioactivation pathways and clearance. We parsed the FDA DILIrank hepatotoxicity database and modeled marketed drug bioactivation into quinone-species metabolites to identify a family of seven clinically relevant diphenylamine NSAIDs. These drugs fell into two subgroups, i.e., acetic acid and propionic acid diphenylamines, varying in hepatotoxicity risks and modeled bioactivation propensities. We carried out steady-state kinetic studies to assess bioactivation pathways by trapping quinone-species metabolites with dansyl glutathione. Analysis of the glutathione adducts by mass spectrometry characterized structures while dansyl fluorescence provided quantitative yields for their formation. Resulting kinetics identified four possible bioactivation pathways among the drugs, but reaction preference and efficiency depended upon structural modifications to the diphenylamine scaffold. Strikingly, diphenylamine dihalogenation promotes formation of quinone metabolites through four distinct metabolic pathways with high efficiency, whereas those without aromatic halogen atoms were metabolized less efficiently through two or fewer metabolic pathways. Overall metabolism of the drugs was comparable with bioactivation accounting for 4-13% of clearance. Lastly, we calculated daily bioload exposure of quinone-species metabolites based on bioactivation efficiency, bioavailability, and maximal daily dose. The results revealed stratification into the two subgroups; propionic acid diphenylamines had an average four-fold greater daily bioload compared to acetic acid diphenylamines. However, the lack of sufficient study on the hepatotoxicity for all drugs prevents further correlative analyses. These findings provide critical insights on the impact of diphenylamine bioactivation as a precursor to hepatotoxicity and thus, provide a foundation for better risk assessment in drug discovery and development.

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.

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.

Amine functionalization of N,N,N′,N′-tetramethyl-p-phenylenediamine for the electrosynthesis of a wide range of p-phenylenediamines in green conditions

An efficient derivative of TMPD is introduced by amine functionalization. Despite TMPD, two-electron oxidation of this compound is stable. This property opens a window for the electrosynthesis of new phenylenediamines in green conditions.

Significance of Multiple Bioactivation Pathways for Meclofenamate as Revealed through Modeling and Reaction Kinetics

Meclofenamate is a nonsteroidal anti-inflammatory drug used in the treatment of mild-to-moderate pain yet poses a rare risk of hepatotoxicity through an unknown mechanism. Nonsteroidal anti-inflammatory drug (NSAID) bioactivation is a common molecular initiating event for hepatotoxicity. Thus, we hypothesized a similar mechanism for meclofenamate and leveraged computational and experimental approaches to identify and characterize its bioactivation. Analyses employing our XenoNet model indicated possible pathways to meclofenamate bioactivation into 19 reactive metabolites subsequently trapped into glutathione adducts. We describe the first reported bioactivation kinetics for meclofenamate and relative importance of those pathways using human liver microsomes. The findings validated only four of the many bioactivation pathways predicted by modeling. For experimental studies, dansyl glutathione was a critical trap for reactive quinone metabolites and provided a way to characterize adduct structures by mass spectrometry and quantitate yields during reactions. Of the four quinone adducts, we were able to characterize structures for three of them. Based on kinetics, the most efficient bioactivation pathway led to the monohydroxy para-quinone-imine followed by the dechloro-ortho-quinone-imine. Two very inefficient pathways led to the dihydroxy ortho-quinone and a likely multiply adducted quinone. When taken together, bioactivation pathways for meclofenamate accounted for approximately 13% of total metabolism. In sum, XenoNet facilitated prediction of reactive metabolite structures, whereas quantitative experimental studies provided a tractable approach to validate actual bioactivation pathways for meclofenamate. Our results provide a foundation for assessing reactive metabolite load more accurately for future comparative studies with other NSAIDs and drugs in general.

Metabolic Forest: Predicting the Diverse Structures of Drug Metabolites

Adverse drug metabolism often severely impacts patient morbidity and mortality. Unfortunately, drug metabolism experimental assays are costly, inefficient, and slow. Instead, computational modeling could rapidly flag potentially toxic molecules across thousands of candidates in the early stages of drug development. Most metabolism models focus on predicting sites of metabolism (SOMs): the specific substrate atoms targeted by metabolic enzymes. However, SOMs are merely a proxy for metabolic structures: knowledge of an SOM does not explicitly provide the actual metabolite structure. Without an explicit metabolite structure, computational systems cannot evaluate the new molecule's properties. For example, the metabolite's reactivity cannot be automatically predicted, a crucial limitation because reactive drug metabolites are a key driver of adverse drug reactions (ADRs). Additionally, further metabolic events cannot be forecast, even though the metabolic path of the majority of substrates includes two or more sequential steps. To overcome the myopia of the SOM paradigm, this study constructs a well-defined system-termed the metabolic forest-for generating exact metabolite structures. We validate the metabolic forest with the substrate and product structures from a large, chemically diverse, literature-derived dataset of 20 736 records. The metabolic forest finds a pathway linking each substrate and product for 79.42% of these records. By performing a breadth-first search of depth two or three, we improve performance to 88.43 and 88.77%, respectively. The metabolic forest includes a specialized algorithm for producing accurate quinone structures, the most common type of reactive metabolite. To our knowledge, this quinone structure algorithm is the first of its kind, as the diverse mechanisms of quinone formation are difficult to systematically reproduce. We validate the metabolic forest on a previously published dataset of 576 quinone reactions, predicting their structures with a depth three performance of 91.84%. The metabolic forest accurately enumerates metabolite structures, enabling promising new directions such as joint metabolism and reactivity modeling.

Site-Level Bioactivity of Small-Molecules from Deep-Learned Representations of Quantum Chemistry

Atom- or bond-level chemical properties of interest in medicinal chemistry, such as drug metabolism and electrophilic reactivity, are important to understand and predict across arbitrary new molecules. Deep learning can be used to map molecular structures to their chemical properties, but the data sets for these tasks are relatively small, which can limit accuracy and generalizability. To overcome this limitation, it would be preferable to model these properties on the basis of the underlying quantum chemical characteristics of small molecules. However, it is difficult to learn higher level chemical properties from lower level quantum calculations. To overcome this challenge, we pretrained deep learning models to compute quantum chemical properties and then reused the intermediate representations constructed by the pretrained network. Transfer learning, in this way, substantially outperformed models based on chemical graphs alone or quantum chemical properties alone. This result was robust, observable in five prediction tasks: identifying sites of epoxidation by metabolic enzymes and identifying sites of covalent reactivity with cyanide, glutathione, DNA and protein. We see that this approach may substantially improve the accuracy of deep learning models for specific chemical structures, such as aromatic systems.

The integrated use of in silico methods for the hepatotoxicity potential of Piper methysticum

Herbal products as supplements and therapeutic intervention have been used for centuries. However, their toxicities are not completely evaluated and the mechanisms are not clearly understood. Dried rhizome of the plant kava (Piper methysticum) is used for its anxiolytic, and sedative effects. The drug is also known for its hepatotoxicity potential. Major constituents of the plant were identified as kavalactones, alkaloids and chalcones in previous studies. Kava hepatotoxicity mechanism and the constituent that causes the toxicity have been debated for decades. In this paper, we illustrated the use of computational tools for the hepatotoxicity of kava constituents. The proposed mechanisms and major constituents that are most probably responsible for the toxicity have been scrutinized. According to the experimental and prediction results, the kava constituents play a substantial role in hepatotoxicity by some means or other via glutathione depletion, CYP inhibition, reactive metabolite formation, mitochondrial toxicity and cyclooxygenase activity. Some of the constituents, which have not been tested yet, were predicted to involve mitochondrial membrane potential, caspase-3 stimulation, and AhR activity. Since Nrf2 activation could be favorable for prevention of hepatotoxicity, we also suggest that these compounds should undergo testing given that they were predicted not to be activating Nrf2. Among the major constituents, alkaloids appear to be the least studied and the least toxic group in general. The outcomes of the study could help to appreciate the mechanisms and to prioritize the kava constituents for further testing.

Open access in silico tools to predict the ADMET profiling of drug candidates

INTRODUCTION

We are in an era of bioinformatics and cheminformatics where we can predict data in the fields of medicine, the environment, engineering and public health. Approaches with open access in silico tools have revolutionized disease management due to early prediction of the absorption, distribution, metabolism, excretion, and toxicity (ADMET) profiles of the chemically designed and eco-friendly next-generation drugs.

AREAS COVERED

This review meticulously encompasses the fundamental functions of open access in silico prediction tools (webservers and standalone software) and advocates their use in drug discovery research for the safety and reliability of any candidate-drug. This review also aims to help support new researchers in the field of drug design.

EXPERT OPINION

The choice of in silico tools is critically important for drug discovery and the accuracy of ADMET prediction. The accuracy largely depends on the types of dataset, the algorithm used, the quality of the model, the available endpoints for prediction, and user requirement. The key is to use multiple in silico tools for predictions and comparing the results, followed by the identification of the most probable prediction.

An adverse outcome pathway for immune-mediated and allergic hepatitis: a case study with the NSAID diclofenac

Many drugs have the potential to cause drug-induced liver injury (DILI); however, underlying mechanisms are diverse. The concept of adverse outcome pathways (AOPs) has become instrumental for risk assessment of drug class effects. We report AOPs specific for immune-mediated and drug hypersensitivity/allergic hepatitis by considering genomic, histo- and clinical pathology data of mice and dogs treated with diclofenac. The findings are relevant for other NSAIDs and drugs undergoing iminoquinone and quinone reactive metabolite formation. We define reactive metabolites catalyzed by CYP monooxygenase and myeloperoxidases of neutrophils and Kupffer cells as well as acyl glucuronides produced by uridine diphosphoglucuronosyl transferase as molecular initiating events (MIE). The reactive metabolites bind to proteins and act as neo-antigen and involve antigen-presenting cells to elicit B- and T-cell responses. Given the diverse immune systems between mice and dogs, six different key events (KEs) at the cellular and up to four KEs at the organ level are defined with mechanistic plausibility for the onset and progression of liver inflammation. With mice, cellular stress response, interferon gamma-, adipocytokine- and chemokine signaling provided a rationale for the AOP of immune-mediated hepatitis. With dogs, an erroneous programming of the innate and adaptive immune response resulted in mast cell activation; their infiltration into liver parenchyma and the shift to M2-polarized Kupffer cells signify allergic hepatitis and the occurrence of granulomas of the liver. Taken together, diclofenac induces divergent immune responses among two important preclinical animal species, and the injury pattern seen among clinical cases confirms the relevance of the developed AOP for immune-mediated hepatitis.

A novel artificial intelligence protocol for finding potential inhibitors of acute myeloid leukemia

There is currently no effective treatment for acute myeloid leukemia, and surgery is also ineffective as an important treatment for most tumors. Rapidly developing artificial intelligence technology can be applied to different aspects of drug development, and it plays a key role in drug discovery. Based on network pharmacology and virtual screening, candidates were selected from the molecular database. Nine artificial intelligence algorithm models were used to further verify the candidates' potential. The 350 training results of the deep learning model showed higher credibility, and the R-square of the training set and test set of the optimal model reached 0.89 and 0.84, respectively. The random forest model has an R-square of 0.91 and a mean square error of only 0.003. The R-square of the Adaptive Boosting model and the Bagging model reached 0.92 and 0.88, respectively. Molecular dynamics simulation evaluated the stability of the ligand-protein complex and achieved good results. Artificial intelligence models had unearthed the promising candidates for STAT3 inhibitors, and the good performance of most models showed that they still had practical value on small data sets.

A deep neural network combined with molecular fingerprints (DNN-MF) to develop predictive models for hydroxyl radical rate constants of water contaminants

This work combined a Deep Neural Network (DNN) with molecular fingerprints (MF) to develop models to predict the OH radical rate constants of 593 organic contaminants. Molecular descriptors, most often used in establishing quantitative structural-activity relationships (QSARs), were not used here because of their complicated generation processes that rely on advanced physicochemical and computational knowledge. Instead, we only fed the most basic information of the contaminant structures, i.e., MF encoding the types of atoms and how they are connected, to DNN and DNN then developed predictive models automatically. Here, a dataset containing 457 contaminants and their OH rate constants was first used to develop predictive models by DNN-MF. The hence developed models showed comparable accuracy to the traditional QSARs. The root mean square error (RMSE) values of the test sets were 0.358-0.384. The length of 2048 bits for the MF and 3 hidden layers (each with 1024 neurons) were found to be the optimal parameters for DNN. The model containing additional 89 micorpollutants in the training set was then successfully applied to predict the OH rate constants of 17 organophosphorus flame retardants and 29 additional micropollutants, with comparable accuracy to the reported molecular descriptors-based QSARs.

Aza-ortho-Quinone Methide and Its Conjugated Acid: Reactivity, Stability and Acidity

Aza-o-quinone methides and their conjugated acids are reactive drug metabolites that might react with nucleophilic sites of DNAs and proteins to cause cancer or immune responses, and their reactivity with water is the key information to judge if these metabolites are harmful in living systems. For the first time, aza-o-quinone methide (1) and its conjugated acid (2) are observed by laser flash photolysis, and their reactivity, stability and acidity in water are determined.

The application of artificial neural networks in metabolomics: a historical perspective

BACKGROUND

Metabolomics data, with its complex covariance structure, is typically modelled by projection-based machine learning (ML) methods such as partial least squares (PLS) regression, which project data into a latent structure. Biological data are often non-linear, so it is reasonable to hypothesize that metabolomics data may also have a non-linear latent structure, which in turn would be best modelled using non-linear equations. A non-linear ML method with a similar projection equation structure to PLS is artificial neural networks (ANNs). While ANNs were first applied to metabolic profiling data in the 1990s, the lack of community acceptance combined with limitations in computational capacity and the lack of volume of data for robust non-linear model optimisation inhibited their widespread use. Due to recent advances in computational power, modelling improvements, community acceptance, and the more demanding needs for data science, ANNs have made a recent resurgence in interest across research communities, including a small yet growing usage in metabolomics. As metabolomics experiments become more complex and start to be integrated with other omics data, there is potential for ANNs to become a viable alternative to linear projection methods.

AIM OF REVIEW

We aim to first describe ANNs and their structural equivalence to linear projection-based methods, including PLS regression. We then review the historical, current, and future uses of ANNs in the field of metabolomics.

KEY SCIENTIFIC CONCEPT OF REVIEW

Is metabolomics ready for the return of artificial neural networks?

Open-source QSAR models for pKa prediction using multiple machine learning approaches

BACKGROUND

The logarithmic acid dissociation constant pKa reflects the ionization of a chemical, which affects lipophilicity, solubility, protein binding, and ability to pass through the plasma membrane. Thus, pKa affects chemical absorption, distribution, metabolism, excretion, and toxicity properties. Multiple proprietary software packages exist for the prediction of pKa, but to the best of our knowledge no free and open-source programs exist for this purpose. Using a freely available data set and three machine learning approaches, we developed open-source models for pKa prediction.

METHODS

The experimental strongest acidic and strongest basic pKa values in water for 7912 chemicals were obtained from DataWarrior, a freely available software package. Chemical structures were curated and standardized for quantitative structure-activity relationship (QSAR) modeling using KNIME, and a subset comprising 79% of the initial set was used for modeling. To evaluate different approaches to modeling, several datasets were constructed based on different processing of chemical structures with acidic and/or basic pKas. Continuous molecular descriptors, binary fingerprints, and fragment counts were generated using PaDEL, and pKa prediction models were created using three machine learning methods, (1) support vector machines (SVM) combined with k-nearest neighbors (kNN), (2) extreme gradient boosting (XGB) and (3) deep neural networks (DNN).

RESULTS

The three methods delivered comparable performances on the training and test sets with a root-mean-squared error (RMSE) around 1.5 and a coefficient of determination (R2) around 0.80. Two commercial pKa predictors from ACD/Labs and ChemAxon were used to benchmark the three best models developed in this work, and performance of our models compared favorably to the commercial products.

CONCLUSIONS

This work provides multiple QSAR models to predict the strongest acidic and strongest basic pKas of chemicals, built using publicly available data, and provided as free and open-source software on GitHub.

Deep Learning-Based Structure-Activity Relationship Modeling for Multi-Category Toxicity Classification: A Case Study of 10K Tox21 Chemicals With High-Throughput Cell-Based Androgen Receptor Bioassay Data

Deep learning (DL) has attracted the attention of computational toxicologists as it offers a potentially greater power for in silico predictive toxicology than existing shallow learning algorithms. However, contradicting reports have been documented. To further explore the advantages of DL over shallow learning, we conducted this case study using two cell-based androgen receptor (AR) activity datasets with 10K chemicals generated from the Tox21 program. A nested double-loop cross-validation approach was adopted along with a stratified sampling strategy for partitioning chemicals of multiple AR activity classes (i.e., agonist, antagonist, inactive, and inconclusive) at the same distribution rates amongst the training, validation and test subsets. Deep neural networks (DNN) and random forest (RF), representing deep and shallow learning algorithms, respectively, were chosen to carry out structure-activity relationship-based chemical toxicity prediction. Results suggest that DNN significantly outperformed RF (p < 0.001, ANOVA) by 22–27% for four metrics (precision, recall, F-measure, and AUPRC) and by 11% for another (AUROC). Further in-depth analyses of chemical scaffolding shed insights on structural alerts for AR agonists/antagonists and inactive/inconclusive compounds, which may aid in future drug discovery and improvement of toxicity prediction modeling.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

Novel Electrotopological Atomic Descriptors for the Prediction of Xenobiotic Cytochrome P450 Reactions

Cytochrome P450 (CYP) is an enzyme family that plays a crucial role in metabolism, mainly metabolizing xenobiotics to produce non-toxic structures, however, some metabolized products can cause hepatotoxicity. Hence, predicting the structures of CYP products is an important task in designing non-hepatotoxic drugs. Here, we have developed novel atomic descriptors to predict the sites of metabolism (SoM) in CYP substrates. We proposed descriptors that describe topological and electrostatic characteristics of CYP substrates using Gasteiger charge. The proposed descriptors were applied to CYP3A4 data analysis as a case study. As a result of the descriptor selection, we obtained a gradient boosting decision tree-based SoM classification model that used 139 existing descriptors and the proposed 45 descriptors, and the model performed well in terms of the Matthews correlation coefficient. We also developed a structure converter to predict CYP products. This converter correctly generated 51 structural formulas of experimentally observed CYP3A4 products according to a manual evaluation.

Prediction of the Antioxidant Response Elements' Response of Compound by Deep Learning

The antioxidant response elements (AREs) play a significant role in occurrence of oxidative stress and may cause multitudinous toxicity effects in the pathogenesis of a variety of diseases. Determining if one compound can activate AREs is crucial for the assessment of potential risk of compound. Here, a series of predictive models by applying multiple deep learning algorithms including deep neural networks (DNN), convolution neural networks (CNN), recurrent neural networks (RNN), and highway networks (HN) were constructed and validated based on Tox21 challenge dataset and applied to predict whether the compounds are the activators or inactivators of AREs. The built models were evaluated by various of statistical parameters, such as sensitivity, specificity, accuracy, Matthews correlation coefficient (MCC) and receiver operating characteristic (ROC) curve. The DNN prediction model based on fingerprint features has best prediction ability, with accuracy of 0.992, 0.914, and 0.917 for the training set, test set, and validation set, respectively. Consequently, these robust models can be adopted to predict the ARE response of molecules fast and accurately, which is of great significance for the evaluation of safety of compounds in the process of drug discovery and development.

Deep learning for predicting toxicity of chemicals: a mini review

Humans and wildlife inhabit a world with panoply of natural and synthetic chemicals. Alarmingly, only a limited number of chemicals have undergone comprehensive toxicological evaluation due to limitations of traditional toxicity testing. High-throughput screening assays provide a higher-speed alternative for conventional toxicity testing. Advancement of high-throughput bioassay technology has greatly increased chemical toxicity data volumes in the past decade, pushing toxicology research into a "big data" era. However, traditional data analysis methods fail to effectively process large data volumes, presenting both a challenge and an opportunity for toxicologists. Deep learning, a machine learning method leveraging deep neural networks (DNNs), is a proven useful tool for building quantitative structure-activity relationship (QSAR) models for toxicity prediction utilizing these new large datasets. In this mini review, a brief technical background on DNNs is provided, and the current state of chemical toxicity prediction models built with DNNs is reviewed. In addition, relevant toxicity data sources are summarized, possible limitations are discussed, and perspectives on DNN utilization in chemical toxicity prediction are given.

Iodine-Mediated Direct Generation of o-Quinone Methides at Room Temperature: A Facile Protocol for the Synthesis of ortho-Hydroxybenzyl Thioethers

An iodine-mediated preparation of ortho-quinone methides (o-QMs) from ortho-hydroxybenzyl alcohols by a C-O bond scission strategy is described. The in situ generated o-QMs were then employed for C-S bond formation by thio-Michael addition of thiols to provide the ortho-hydroxybenzyl thioethers (o-HBT) in moderate to excellent yields.

Biotransformation and bioactivation reactions - 2017 literature highlights *

This annual review is the third one to highlight recent advances in the study and assessment of biotransformations and bioactivations ( Table 1 ). We followed the same format as the previous years with selection and authoring each section (see Baillie et al. 2016 ; Khojasteh et al. 2017 ). We acknowledge that many universities no longer train students in mechanistic biotransformation studies reflecting a decline in the investment for those efforts by public funded granting institutions. We hope this work serves as a resource to appreciate the knowledge gained each year to understand and hopefully anticipate toxicological outcomes dependent on biotransformations and bioactivations. This effort itself also continues to evolve. I am pleased that Drs. Rietjens and Miller have again contributed to this annual review. We would like to welcome Kaushik Mitra as an author for this year's issue, and we thank Deepak Dalvie for his contributions to last year's edition. We have intentionally maintained a balance of authors such that two come from an academic setting and two come from industry. As always, please drop us a note if you find this review helpful. We would be pleased to hear your opinions of our commentary, and we extend an invitation to anyone who would like to contribute to a future edition of this review.

Advancing Predictive Hepatotoxicity at the Intersection of Experimental, in Silico, and Artificial Intelligence Technologies

Adverse drug reactions, particularly those that result in drug-induced liver injury (DILI), are a major cause of drug failure in clinical trials and drug withdrawals. Hepatotoxicity-mediated drug attrition occurs despite substantial investments of time and money in developing cellular assays, animal models, and computational models to predict its occurrence in humans. Underperformance in predicting hepatotoxicity associated with drugs and drug candidates has been attributed to existing gaps in our understanding of the mechanisms involved in driving hepatic injury after these compounds perfuse and are metabolized by the liver. Herein we assess in vitro, in vivo (animal), and in silico strategies used to develop predictive DILI models. We address the effectiveness of several two- and three-dimensional in vitro cellular methods that are frequently employed in hepatotoxicity screens and how they can be used to predict DILI in humans. We also explore how humanized animal models can recapitulate human drug metabolic profiles and associated liver injury. Finally, we highlight the maturation of computational methods for predicting hepatotoxicity, the untapped potential of artificial intelligence for improving in silico DILI screens, and how knowledge acquired from these predictions can shape the refinement of experimental methods.

Design, synthesis and structure-activity relationship studies of GPR40 agonists containing amide linker

Free fatty acid receptor 1 (FFAR1/GPR40) attracted significant attention as a potential target for developing novel antidiabetic drugs because of its unique mechanism in glucose homeostasis. Several reports have expressed concerns about central nervous system (CNS) penetration of GPR40 agonists, which is possibly attributed to their high lipophilicity and low total polar surface area. Herein, we report our efforts to improve the physicochemical properties and pharmacokinetic profiles of LY2881835, a GPR40 agonist that had undergone Phase I clinical trial, through a series of structural optimizations. We identified an orally efficacious compound, 15k, which possessed increased plasma exposure, prolonged half-life and reduced CNS exposure and liver to plasma distribution ratio compared with LY2881835. 15k is a potentially valuable lead compound in the development of safe and efficacious GPR40-targeted drugs to treat type 2 diabetes mellitus.

Big Data in Drug Discovery

Interpretation of Big Data in the drug discovery community should enhance project timelines and reduce clinical attrition through improved early decision making. The issues we encounter start with the sheer volume of data and how we first ingest it before building an infrastructure to house it to make use of the data in an efficient and productive way. There are many problems associated with the data itself including general reproducibility, but often, it is the context surrounding an experiment that is critical to success. Help, in the form of artificial intelligence (AI), is required to understand and translate the context. On the back of natural language processing pipelines, AI is also used to prospectively generate new hypotheses by linking data together. We explain Big Data from the context of biology, chemistry and clinical trials, showcasing some of the impressive public domain sources and initiatives now available for interrogation.

Computationally Assessing the Bioactivation of Drugs by N-Dealkylation

Cytochromes P450 (CYPs) oxidize alkylated amines commonly found in drugs and other biologically active molecules, cleaving them into an amine and an aldehyde. Metabolic studies usually neglect to report or investigate aldehydes, even though they can be toxic. It is assumed that they are efficiently detoxified into carboxylic acids and alcohols. Nevertheless, some aldehydes are reactive and escape detoxification pathways to cause adverse events by forming DNA and protein adducts. Herein, we modeled N-dealkylations that produce both amine and aldehyde metabolites and then predicted the reactivity of the aldehyde. This model used a deep learning approach previously developed by our group to predict other types of drug metabolism. In this study, we trained the model to predict N-dealkylation by human liver microsomes (HLM), finding that including isozyme-specific metabolism data alongside HLM data significantly improved results. The final HLM model accurately predicted the site of N-dealkylation within metabolized substrates (97% top-two and 94% area under the ROC curve). Next, we combined the metabolism, metabolite structure prediction, and previously published reactivity models into a bioactivation model. This combined model predicted the structure of the most likely reactive metabolite of a small validation set of drug-like molecules known to be bioactivated by N-dealkylation. Applying this model to approved and withdrawn medicines, we found that aldehyde metabolites produced from N-dealkylation may explain the hepatotoxicity of several drugs: indinavir, piperacillin, verapamil, and ziprasidone. Our results suggest that N-dealkylation may be an under-appreciated bioactivation pathway, especially in clinical contexts where aldehyde detoxification pathways are inhibited. Moreover, this is the first report of a bioactivation model constructed by combining a metabolism and reactivity model. These results raise hope that more comprehensive models of bioactivation are possible. The model developed in this study is available at http://swami.wustl.edu/xenosite/ .

Learning a Local-Variable Model of Aromatic and Conjugated Systems

A collection of new approaches to building and training neural networks, collectively referred to as deep learning, are attracting attention in theoretical chemistry. Several groups aim to replace computationally expensive ab initio quantum mechanics calculations with learned estimators. This raises questions about the representability of complex quantum chemical systems with neural networks. Can local-variable models efficiently approximate nonlocal quantum chemical features? Here, we find that convolutional architectures, those that only aggregate information locally, cannot efficiently represent aromaticity and conjugation in large systems. They cannot represent long-range nonlocality known to be important in quantum chemistry. This study uses aromatic and conjugated systems computed from molecule graphs, though reproducing quantum simulations is the ultimate goal. This task, by definition, is both computable and known to be important to chemistry. The failure of convolutional architectures on this focused task calls into question their use in modeling quantum mechanics. To remedy this heretofore unrecognized deficiency, we introduce a new architecture that propagates information back and forth in waves of nonlinear computation. This architecture is still a local-variable model, and it is both computationally and representationally efficient, processing molecules in sublinear time with far fewer parameters than convolutional networks. Wave-like propagation models aromatic and conjugated systems with high accuracy, and even models the impact of small structural changes on large molecules. This new architecture demonstrates that some nonlocal features of quantum chemistry can be efficiently represented in local variable models.

Computational Approach to Structural Alerts: Furans, Phenols, Nitroaromatics, and Thiophenes

Structural alerts are commonly used in drug discovery to identify molecules likely to form reactive metabolites and thereby become toxic. Unfortunately, as useful as structural alerts are, they do not effectively model if, when, and why metabolism renders safe molecules toxic. Toxicity due to a specific structural alert is highly conditional, depending on the metabolism of the alert, the reactivity of its metabolites, dosage, and competing detoxification pathways. A systems approach, which explicitly models these pathways, could more effectively assess the toxicity risk of drug candidates. In this study, we demonstrated that mathematical models of P450 metabolism can predict the context-specific probability that a structural alert will be bioactivated in a given molecule. This study focuses on the furan, phenol, nitroaromatic, and thiophene alerts. Each of these structural alerts can produce reactive metabolites through certain metabolic pathways but not always. We tested whether our metabolism modeling approach, XenoSite, can predict when a given molecule's alerts will be bioactivated. Specifically, we used models of epoxidation, quinone formation, reduction, and sulfur-oxidation to predict the bioactivation of furan-, phenol-, nitroaromatic-, and thiophene-containing drugs. Our models separated bioactivated and not-bioactivated furan-, phenol-, nitroaromatic-, and thiophene-containing drugs with AUC performances of 100%, 73%, 93%, and 88%, respectively. Metabolism models accurately predict whether alerts are bioactivated and thus serve as a practical approach to improve the interpretability and usefulness of structural alerts. We expect that this same computational approach can be extended to most other structural alerts and later integrated into toxicity risk models. This advance is one necessary step toward our long-term goal of building comprehensive metabolic models of bioactivation and detoxification to guide assessment and design of new therapeutic molecules.