Modeling Reactivity to Biological Macromolecules with a Deep Multitask Network

Tackling assay interference associated with small molecules

Biochemical and cell-based assays are essential to discovering and optimizing efficacious and safe drugs, agrochemicals and cosmetics. However, false assay readouts stemming from colloidal aggregation, chemical reactivity, chelation, light signal attenuation and emission, membrane disruption, and other interference mechanisms remain a considerable challenge in screening synthetic compounds and natural products. To address assay interference, a range of powerful experimental approaches are available and in silico methods are now gaining traction. This Review begins with an overview of the scope and limitations of experimental approaches for tackling assay interference. It then focuses on theoretical methods, discusses strategies for their integration with experimental approaches, and provides recommendations for best practices. The Review closes with a summary of the critical facts and an outlook on potential future developments.

Thiophene Stability in Photodynamic Therapy: A Mathematical Model Approach

Thiophene-containing photosensitizers are gaining recognition for their role in photodynamic therapy (PDT). However, the inherent reactivity of the thiophene moiety toward singlet oxygen threatens the stability and efficiency of these photosensitizers. This study presents a novel mathematical model capable of predicting the reactivity of thiophene toward singlet oxygen in PDT, using Conceptual Density Functional Theory (CDFT) and genetic programming. The research combines advanced computational methods, including various DFT techniques and symbolic regression, and is validated with experimental data. The findings underscore the capacity of the model to classify photosensitizers based on their photodynamic efficiency and safety, particularly noting that photosensitizers with a constant rate 1000 times lower than that of unmodified thiophene retain their photodynamic performance without substantial singlet oxygen quenching. Additionally, the research offers insights into the impact of electronic effects on thiophene reactivity. Finally, this study significantly advances thiophene-based photosensitizer design, paving the way for therapeutic agents that achieve a desirable balance between efficiency and safety in PDT.

Unlocking The Mysteries of DNA Adducts with Artificial Intelligence

Cellular genome is considered a dynamic blueprint of a cell since it encodes genetic information that gets temporally altered due to various endogenous and exogenous insults. Largely, the extent of genomic dynamicity is controlled by the trade-off between DNA repair processes and the genotoxic potential of the causative agent (genotoxins or potential carcinogens). A subset of genotoxins form DNA adducts by covalently binding to the cellular DNA, triggering structural or functional changes that lead to significant alterations in cellular processes via genetic (e. g., mutations) or non-genetic (e. g., epigenome) routes. Identification, quantification, and characterization of DNA adducts are indispensable for their comprehensive understanding and could expedite the ongoing efforts in predicting carcinogenicity and their mode of action. In this review, we elaborate on using Artificial Intelligence (AI)-based modeling in adducts biology and present multiple computational strategies to gain advancements in decoding DNA adducts. The proposed AI-based strategies encompass predictive modeling for adduct formation via metabolic activation, novel adducts' identification, prediction of biochemical routes for adduct formation, adducts' half-life predictions within biological ecosystems, and, establishing methods to predict the link between adducts chemistry and its location within the genomic DNA. In summary, we discuss some futuristic AI-based approaches in DNA adduct biology.

Mechanistic Task Groupings Enhance Multitask Deep Learning of Strain-Specific Ames Mutagenicity

The Ames test is a gold standard mutagenicity assay that utilizes various Salmonella typhimurium strains with and without S9 fraction to provide insights into the mechanisms by which a chemical can mutate DNA. Multitask deep learning is an ideal framework for developing QSAR models with multiple end points, such as the Ames test, as the joint training of multiple predictive tasks may synergistically improve the prediction accuracy of each task. This work investigated how toxicology domain knowledge can be used to handcraft task groupings that better guide the training of multitask neural networks compared to a naïve ungrouped multitask neural network developed on a complete set of tasks. Sixteen S. typhimurium ± S9 strain tasks were used to generate groupings based on mutagenic and metabolic mechanisms that were reflected in correlation data analyses. Both grouped and ungrouped multitask neural networks predicted the 16 strain tasks with a higher balanced accuracy compared with single task controls, with grouped multitask neural networks consistently featuring incremental increases in predictivity over the ungrouped approach. We conclude that the main variable driving these performance improvements is the general multitask effect with mechanistic task groupings acting as an enhancement step to further concentrate synergistic training signals united by a common biological mechanism. This approach enables incorporation of toxicology domain knowledge into multitask QSAR model development allowing for more transparent and accurate Ames mutagenicity prediction.

Reactive intermediates formation and bioactivation pathways of spebrutinib revealed by LC-MS/MS: In vitro and in silico metabolic study

Spebrutinib is a new Bruton tyrosine kinase inhibitor developed by Avila Therapeutics and Celgene. Spebrutinib (SPB) is currently in phase Ib clinical trials for the treatment of lymphoma in the United States. Preliminary in-silico studies were first performed to predict susceptible sites of metabolism, reactivity pathways and structural alerts for toxicities by StarDrop WhichP450™ module, Xenosite web predictor tool and DEREK software; respectively. SPB metabolites and adducts were characterized in vitro from rat liver microsomes (RLM) using LC-MS/MS. Formation of reactive intermediates was investigated using potassium cyanide (KCN), glutathione (GSH) and methoxylamine as trapping nucleophiles for the unstable and reactive iminium, iminoquinone and aldehyde intermediates, respectively, with the aim to produce stable adducts that can be detected and characterized using mass spectrometry. Fourteen phase I metabolites, four cyanide adducts, six GSH adducts and three methoxylamine adducts of SPB were identified and characterized. The proposed metabolic pathways involved in generation of phase I metabolites of SPB are oxidation, hydroxylation, o-dealkylation, epoxidation, defluorination and reduction. Several in vitro reactive intermediates were identified and characterized, the formation of which can aid in explaining the adverse drug reactions of SPB. Several iminium, 2-iminopyrimidin-5(2H)-one and aldehyde intermediates of SPB were revealed. Acrylamide is identified as a structural alert for toxicity by DEREK report and was found to be involved in the formation of several glycidamide and aldehyde reactive intermediates.

Message Passing Neural Networks Improve Prediction of Metabolite Authenticity

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

Multitask Deep Neural Networks for Ames Mutagenicity Prediction

The Ames mutagenicity test constitutes the most frequently used assay to estimate the mutagenic potential of drug candidates. While this test employs experimental results using various strains of Salmonella typhimurium, the vast majority of the published in silico models for predicting mutagenicity do not take into account the test results of the individual experiments conducted for each strain. Instead, such QSAR models are generally trained employing overall labels (i.e., mutagenic and nonmutagenic). Recently, neural-based models combined with multitask learning strategies have yielded interesting results in different domains, given their capabilities to model multitarget functions. In this scenario, we propose a novel neural-based QSAR model to predict mutagenicity that leverages experimental results from different strains involved in the Ames test by means of a multitask learning approach. To the best of our knowledge, the modeling strategy hereby proposed has not been applied to model Ames mutagenicity previously. The results yielded by our model surpass those obtained by single-task modeling strategies, such as models that predict the overall Ames label or ensemble models built from individual strains. For reproducibility and accessibility purposes, all source code and datasets used in our experiments are publicly available.

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.

Crosstalk Between Aryl Hydrocarbon Receptor (AhR) and BCL-2 Pathways Suggests the Use of AhR Antagonist to Maintain Normal Differentiation State of Mammary Epithelial Cells During BCL-2 Inhibition Therapy

INTRODUCTION

Activating the aryl hydrocarbon receptor upon exposure to environmental pollutants promotes development of breast cancer stem cell (CSCs). BCL-2 family proteins protect cancer cells from the apoptotic effects of chemotherapeutic drugs. However, the crosstalk between AhR and the BCL-2 family in CSC development remains uninvestigated.

OBJECTIVES

This study explored the interaction mechanisms between AhR and BCL-2 in CSC development and chemoresistance.

METHODS

A quantitative proteomic analysis study was performed as a tool for comparative expression analysis of breast cancer cells treated by AhR agonist. The basal and inducible levels of BCL-2, AhR, and CYP1A1 in vitro breast cancer and epithelial cell lines and in vivo mice animal models were determined by RT-PCR, Western blot analysis, immunofluorescence, flow cytometry, silencing of the target, and immunohistochemistry. In addition, an in silico toxicity study was conducted using DEREK software.

RESULTS

Activation of the AhR/CYP1A1 pathway in mice increased EpCAM^High/CD49f^Low CD61⁺ luminal progenitor-like cells in early tumor formation but not in advanced tumors. In parallel, a chemoproteomic study on breast cancer MCF-7 cells revealed that the BCL-2 protein expression was the most upregulated upon AhR activation. The crosstalk between the AhR and BCL-2 pathways in vitro and in vivo modulated the CSCs features and chemoresistance. Interestingly, inhibition of BCL-2 in mice by venetoclax (VCX) increased EpCAM^High/CD49f^Low CD61⁺ luminal progenitor-like cells, causing inhibition of epithelial lineage markers, disruption of mammary gland branching and induced the epithelial-mesenchymal transition in mammary epithelial cells (MECs). The combined treatment of VCX and AhR antagonists in mice corrected the abnormal differentiation in MECs and protected mammary gland branching and cell identity.

CONCLUSIONS

This is the first study to report crosstalk between AhR and BCL-2 in breast CSCs and provides the rationale for using a combined treatment of BCL-2 inhibitor and AhR antagonist for more effective cancer prevention and treatment.

MetNC: Predicting Metabolites in vivo for Natural Compounds

Natural compounds (NCs) undergo complicated biotransformation in vivo to produce diverse forms of metabolites dynamically, many of which are of high medicinal value. Predicting the profiles of chemical products may help to narrow down possible candidates, yet current computational methods for predicting biotransformation largely focus on synthetic compounds. Here, we proposed a method of MetNC, a tailor-made method for NC biotransformation prediction, after exploring the overall patterns of NC in vivo metabolism. Based on 850 pairs of the biotransformation dataset validated by comprehensive in vivo experiments with sourcing compounds from medicinal plants, MetNC was designed to produce a list of potential metabolites through simulating in vivo biotransformation and then prioritize true metabolites into the top list according to the functional groups in compound structures and steric hindrance around the reaction sites. Among the well-known peers of GLORYx and BioTransformer, MetNC gave the highest performance in both the metabolite coverage and the ability to short-list true products. More importantly, MetNC seemed to display an extra advantage in recommending the microbiota-transformed metabolites, suggesting its potential usefulness in the overall metabolism estimation. In summary, complemented to those techniques focusing on synthetic compounds, MetNC may help to fill the gap of natural compound metabolism and narrow down those products likely to be identified in vivo.

A Comprehensive In Silico Exploration of Pharmacological Properties, Bioactivities, Molecular Docking, and Anticancer Potential of Vieloplain F from Xylopia vielana Targeting B-Raf Kinase

Compounds derived from plants have several anticancer properties. In the current study, one guaiane-type sesquiterpene dimer, vieloplain F, isolated from Xylopia vielana species, was tested against B-Raf kinase protein (PDB: 3OG7), a potent target for melanoma. A comprehensive in silico analysis was conducted in this research to understand the pharmacological properties of a compound encompassing absorption, distribution, metabolism, excretion, and toxicity (ADMET), bioactivity score predictions, and molecular docking. During ADMET estimations, the FDA-approved medicine vemurafenib was hepatotoxic, cytochrome-inhibiting, and non-cardiotoxic compared to the vieloplain F. The bioactivity scores of vieloplain F were active for nuclear receptor ligand and enzyme inhibitor. During molecular docking experiments, the compound vieloplain F has displayed a higher binding potential with −11.8 kcal/mol energy than control vemurafenib −10.2 kcal/mol. It was shown that intermolecular interaction with the B-Raf complex and the enzyme’s active gorge through hydrogen bonding and hydrophobic contacts was very accurate for the compound vieloplain F, which was then examined for MD simulations. In addition, simulations using MM-GBSA showed that vieloplain F had the greatest propensity to bind to active site residues. The vieloplain F has predominantly represented a more robust profile compared to control vemurafenib, and these results opened the road for vieloplain F for its utilization as a plausible anti-melanoma agent and anticancer drug in the next era.

Profiling of in vivo, in vitro and reactive zorifertinib metabolites using liquid chromatography ion trap mass spectrometry

Zorifertinib (AZD-3759; ZFB) is a potent, novel, oral, small molecule used for the treatment of non-small cell lung cancer (NSCLC). ZFB is Epidermal Growth Factor Receptor (EGFR) inhibitor that is characterized by good permeability of the blood–brain barrier for (NSCLC) patients with EGFR mutations. The present research reports the profiling of in vitro, in vivo and reactive metabolites of ZFB. Prediction of vulnerable metabolic sites and reactivity pathways (cyanide and GSH) of ZFB were performed by WhichP450™ module (StarDrop software package) and XenoSite reactivity model (XenoSite Web Predictor-Home), respectively. ZFB in vitro metabolites were done by incubation with isolated perfused rat liver hepatocytes and rat liver microsomes (RLMs). Extraction of ZFB and its related metabolites from the incubation matrix was done by protein precipitation. In vivo metabolism was performed by giving ZFB (10 mg kg⁻¹) through oral gavage to Sprague Dawley rats that were housed in metabolic cages. Urine was collected at specific time intervals (0, 6, 12, 18, 24, 48, 72, 96 and 120 h) from ZFB dosing. The collected urine samples were filtered then stored at −70 °C. N-Methyl piperazine ring of ZFB undergoes phase I metabolism forming iminium intermediates that were stabilized using potassium cyanide as a trapping agent. Incubation of ZFB with RLMs were performed in the presence of 1.0 mM KCN and 1.0 mM glutathione to check reactive intermediates as it is may be responsible for toxicities associated with ZFB usage. For in vitro metabolites there were six in vitro phase I metabolites, three in vitro phase II metabolites, seven reactive intermediates (four GSH conjugates and three cyano adducts) of ZFB were detected by LC-IT-MS. For in vivo metabolites there were six in vivo phase I and three in vivo phase II metabolites of ZFB were detected by LC-IT-MS. In vitro and in vivo phase I metabolic pathways were N-demethylation, O-demethylation, hydroxylation, reduction, defluorination and dechlorination. In vivo phase II metabolic reaction was direct sulphate and glucuronic acid conjugation with ZFB.

Six in vitro phase I metabolites, three in vitro phase II metabolites, seven reactive intermediates (four GSH conjugates and three cyano adducts), six in vivo phase I and three in vivo phase II metabolites of ZFB were detected by LC-IT-MS.

Deep Learning Coordinate-Free Quantum Chemistry

Computing quantum chemical properties of small molecules and polymers can provide insights valuable into physicists, chemists, and biologists when designing new materials, catalysts, biological probes, and drugs. Deep learning can compute quantum chemical properties accurately in a fraction of time required by commonly used methods such as density functional theory. Most current approaches to deep learning in quantum chemistry begin with geometric information from experimentally derived molecular structures or pre-calculated atom coordinates. These approaches have many useful applications, but they can be costly in time and computational resources. In this study, we demonstrate that accurate quantum chemical computations can be performed without geometric information by operating in the coordinate-free domain using deep learning on graph encodings. Coordinate-free methods rely only on molecular graphs, the connectivity of atoms and bonds, without atom coordinates or bond distances. We also find that the choice of graph-encoding architecture substantially affects the performance of these methods. The structures of these graph-encoding architectures provide an opportunity to probe an important, outstanding question in quantum mechanics: what types of quantum chemical properties can be represented by local variable models? We find that Wave, a local variable model, accurately calculates the quantum chemical properties, while graph convolutional architectures require global variables. Furthermore, local variable Wave models outperform global variable graph convolution models on complex molecules with large, correlated systems.

Computational Exploration of Anti-Cancer Potential of Guaiane Dimers from Xylopia vielana by Targeting B-Raf Kinase Using Chemo-Informatics, Molecular Docking and MD Simulation Studies

BACKGROUND

Natural products from herbs are prolific to display robust anticancer activities.

OBJECTIVES

In the current study, B-Raf kinase protein (PDB: 3OG7), a potent target for melanoma, was tested against two guaiane-type sesquiterpene dimers, xylopin E-F, obtained from Xylopia vielana.

METHODS

In this work, a systematic in silico study using ADMET analysis, bioactivity score forecasts, molecular docking, and its simulations were conducted to understand compounds' pharmacological properties.

RESULTS

During ADMET predictions of both the compounds, Xylopin E-F has displayed a safer profile in hepatotoxicity, cytochrome inhibition, and only xylopin F displayed as non-cardiotoxic compared to FDA approved drug vemurafenib. Both the compounds were proceeded to molecular docking experiments using Autodock docking software and both the compounds Xylopin E-F have displayed higher binding potential with -11.5Kcal/mol energy compared to control vemurafenib -10.2 Kcal/mol. All the compounds were further evaluated for their MD simulations and their molecular interactions with the B-Raf kinase complex displayed precise interactions with the active gorge of the enzyme by hydrogen bonding.

CONCLUSIONS

Overall, xylopin F had a better profile relative to xylopin E and vemurafenib, and these findings indicated that this bio-molecule could be used as an anti-melanoma agent and as a possible anticancer drug in the future. Therefore, this is a systematic optimized in silico approach to creating an anticancer pathway for guaiane dimers against the backdrop of its potential for future drug development.

Constructing xenobiotic maps of metabolism to predict enzymes catalyzing metabolites capable of binding to DNA

Background

The liver plays a major role in the metabolic activation of xenobiotics (drugs, chemicals such as pollutants, pesticides, food additives...). Among environmental contaminants of concern, heterocyclic aromatic amines (HAA) are xenobiotics classified by IARC as possible or probable carcinogens (2A or 2B). There exist little information about the effect of these HAA in humans. While HAA is a family of more than thirty identified chemicals, the metabolic activation and possible DNA adduct formation have been fully characterized in human liver for only a few of them (MeIQx, PhIP, A\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\alpha$$\end{document}αC).

Results

We have developed a modeling approach in order to predict all the possible metabolites of a xenobiotic and enzymatic profiles that are linked to the production of metabolites able to bind DNA. Our prediction of metabolites approach relies on the construction of an enriched and annotated map of metabolites from an input metabolite.The pipeline assembles reaction prediction tools (SyGMa), sites of metabolism prediction tools (Way2Drug, SOMP and Fame 3), a tool to estimate the ability of a xenobotics to form DNA adducts (XenoSite Reactivity V1), and a filtering procedure based on Bayesian framework. This prediction pipeline was evaluated using caffeine and then applied to HAA. The method was applied to determine enzymes profiles associated with the maximization of metabolites derived from each HAA which are able to bind to DNA. The classification of HAA according to enzymatic profiles was consistent with their chemical structures.

Conclusions

Overall, a predictive toxicological model based on an in silico systems biology approach opens perspectives to estimate the genotoxicity of various chemical classes of environmental contaminants. Moreover, our approach based on enzymes profile determination opens the possibility of predicting various xenobiotics metabolites susceptible to bind to DNA in both normal and physiopathological situations.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04363-6.

A natural language processing approach based on embedding deep learning from heterogeneous compounds for quantitative structure-activity relationship modeling

Over the past decade, rapid development in biological and chemical technologies such as high-throughput screening, parallel synthesis, has been significantly increased the amount of data, which requires the creation and the integration of new analytical methods, especially deep learning models. Recently, there is an increasing interest in deep learning utilization in computer-aided drug discovery due to its exceptional successful application in many fields. The present work proposed a natural language processing approach, based on embedding deep neural networks. Our method aims to transform the Simplified Molecular Input Line Entry System format into word embedding vectors to represent the semantics of compounds. These vectors are fed into supervised machine learning algorithms such as convolutional long short-term memory neural network, support vector machine, and random forest to build up quantitative structure-activity relationship models on toxicity data sets. The obtained results on toxicity data to the ciliate Tetrahymena pyriformis (IGC₅₀ ), and acute toxicity rat data expressed as median lethal dose of treated rats (LD₅₀ ) show that our approach can eventually be used to predict the activities of chemical compounds efficiently. All material used in this study is available online through the GitHub portal (https://github.com/BoukeliaAbdelbasset/NLPDeepQSAR.git).

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.

Natural dye from Caesalpinia sappan L. heartwood for eco-friendly coloring of recycled paper based packing material and its in silico toxicity analysis

The uses of natural dyes are getting popularized due to the increased awareness regarding the toxicity of many chemical colorants. The chemical colorants are being replaced by the natural colorants for the various industrial applications. The plant-based natural colorants are considered eco-friendly and toxic free. In the present study, we report a natural dye from the heartwood of Caesalpinia sappan suitable for paper based packing materials. This forms the first report on the study of natural dye obtained from the heartwood of C. sappan on paper material. The extracted dye had a good photostability and able to make imprints on recycled paper bags. Moreover, a significant inhibition of bacterial growth was observed at a higher dye concentration of 100 μg mL^-1 against P. aeruginosa which was higher than the standard antibiotics. Growth inhibition was also observed in case of B. subtilis (22 ± 0.17 mm) and K. pneumonia (21 ± 0.53 mm) at 100 μg mL^-1. The dye could be used in making medicated packing materials and have many other bio-potential which was validated through in silico toxicity analysis. The application of such natural dyes in paper material value addition will help in a cleaner and sustainable process during paper recycling.

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.

Characterization of Stable and Reactive Metabolites of the Anticancer Drug, Ensartinib, in Human Liver Microsomes Using LC-MS/MS: An in silico and Practical Bioactivation Approach

BACKGROUND

Ensartinib (ESB) is a novel anaplastic lymphoma kinase inhibitor (ALK) with additional activity against Abelson murine leukemia (ABL), met proto-oncogene (MET), receptor tyrosine kinase (AXL), and v-ros UR2 sarcoma virus oncogene homolog 1 (ROS1) and is considered a safer alternative for other ALK inhibitors. ESB chemical structure contains a dichloro-fluorophenyl ring and cyclic tertiary amine rings (piperazine) that can be bioactivated generating reactive intermediates.

METHODS

In vitro metabolic study of ESB with human liver microsomes (HLMs) was performed and the hypothesis of generating reactive intermediates during metabolism was tested utilizing trapping agents to capture and stabilize reactive intermediates to facilitate their LC-MS/MS detection. Reduced glutathione (GSH) and potassium cyanide (KCN) were utilized as trapping agents for quinone methide and iminium intermediates, respectively.

RESULTS

Four in vitro ESB phase I metabolites were characterized. Three reactive intermediates including one epoxide and one iminium intermediates were characterized. ESB bioactivation is proposed to occur through unexpected metabolic pathways. The piperazine ring was bioactivated through iminium ions intermediates generation, while the dichloro-phenyl group was bioactivated through a special mechanism that was revealed by LC-MS/MS.

CONCLUSION

These findings lay the foundations for additional work on ESB toxicity. Substituents to the bioactive centers (piperazine ring), either for blocking or isosteric replacement, would likely block or interrupt hydroxylation reaction that will end the bioactivation sequence.

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.

XenoNet: Inference and Likelihood of Intermediate Metabolite Formation

Drug metabolism is a common cause of adverse drug reactions. Drug molecules can be metabolized into reactive metabolites, which can conjugate to biomolecules, like protein and DNA, in a process termed bioactivation. To mitigate adverse reactions caused by bioactivation, both experimental and computational screening assays are utilized. Experimental assays for assessing the formation of reactive metabolites are low throughput and expensive to perform, so they are often reserved until later stages of the drug development pipeline when the drug candidate pools are already significantly narrowed. In contrast, computational methods are high throughput and cheap to perform to screen thousands to millions of compounds for potentially toxic molecules during the early stages of the drug development pipeline. Commonly used computational methods focus on detecting and structurally characterizing reactive metabolite-biomolecule adducts or predicting sites on a drug molecule that are liable to form reactive metabolites. However, such methods are often only concerned with the structure of the initial drug molecule or of the adduct formed when a biomolecule conjugates to a reactive metabolite. Thus, these methods are likely to miss intermediate metabolites that may lead to subsequent reactive metabolite formation. To address these shortcomings, we create XenoNet, a metabolic network predictor, that can take a pair of a substrate and a target product as input and (1) enumerate pathways, or sequences of intermediate metabolite structures, between the pair, and (2) compute the likelihood of those pathways and intermediate metabolites. We validate XenoNet on a large, chemically diverse data set of 17 054 metabolic networks built from a literature-derived reaction database. Each metabolic network has a defined substrate molecule that has been experimentally observed to undergo metabolism into a defined product metabolite. XenoNet can predict experimentally observed pathways and intermediate metabolites linking the input substrate and product pair with a recall of 88 and 46%, respectively. Using likelihood scoring, XenoNet also achieves a top-one pathway and intermediate metabolite accuracy of 93.6 and 51.9%, respectively. We further validate XenoNet against prior methods for metabolite prediction. XenoNet significantly outperforms all prior methods across multiple metrics. XenoNet is available at https://swami.wustl.edu/xenonet.

In silico toxicology: From structure–activity relationships towards deep learning and adverse outcome pathways

In silico toxicology is an emerging field. It gains increasing importance as research is aiming to decrease the use of animal experiments as suggested in the 3R principles by Russell and Burch. In silico toxicology is a means to identify hazards of compounds before synthesis, and thus in very early stages of drug development. For chemical industries, as well as regulatory agencies it can aid in gap‐filling and guide risk minimization strategies. Techniques such as structural alerts, read‐across, quantitative structure–activity relationship, machine learning, and deep learning allow to use in silico toxicology in many cases, some even when data is scarce. Especially the concept of adverse outcome pathways puts all techniques into a broader context and can elucidate predictions by mechanistic insights.

This article is categorized under:

Structure and Mechanism > Computational Biochemistry and Biophysics

Data Science > Chemoinformatics

Spectral deep learning for prediction and prospective validation of functional groups

State-of-the-art identification of the functional groups present in an unknown chemical entity requires the expertise of a skilled spectroscopist to analyse and interpret Fourier transform infra-red (FTIR), mass spectroscopy (MS) and/or nuclear magnetic resonance (NMR) data. This process can be time-consuming and error-prone, especially for complex chemical entities that are poorly characterised in the literature, or inefficient to use with synthetic robots producing molecules at an accelerated rate. Herein, we introduce a fast, multi-label deep neural network for accurately identifying all the functional groups of unknown compounds using a combination of FTIR and MS spectra. We do not use any database, pre-established rules, procedures, or peak-matching methods. Our trained neural network reveals patterns typically used by human chemists to identify standard groups. Finally, we experimentally validated our neural network, trained on single compounds, to predict functional groups in compound mixtures. Our methodology showcases practical utility for future use in autonomous analytical detection.

DEEPScreen: high performance drug-target interaction prediction with convolutional neural networks using 2-D structural compound representations

The identification of physical interactions between drug candidate compounds and target biomolecules is an important process in drug discovery. Since conventional screening procedures are expensive and time consuming, computational approaches are employed to provide aid by automatically predicting novel drug-target interactions (DTIs). In this study, we propose a large-scale DTI prediction system, DEEPScreen, for early stage drug discovery, using deep convolutional neural networks. One of the main advantages of DEEPScreen is employing readily available 2-D structural representations of compounds at the input level instead of conventional descriptors that display limited performance. DEEPScreen learns complex features inherently from the 2-D representations, thus producing highly accurate predictions. The DEEPScreen system was trained for 704 target proteins (using curated bioactivity data) and finalized with rigorous hyper-parameter optimization tests. We compared the performance of DEEPScreen against the state-of-the-art on multiple benchmark datasets to indicate the effectiveness of the proposed approach and verified selected novel predictions through molecular docking analysis and literature-based validation. Finally, JAK proteins that were predicted by DEEPScreen as new targets of a well-known drug cladribine were experimentally demonstrated in vitro on cancer cells through STAT3 phosphorylation, which is the downstream effector protein. The DEEPScreen system can be exploited in the fields of drug discovery and repurposing for in silico screening of the chemogenomic space, to provide novel DTIs which can be experimentally pursued. The source code, trained "ready-to-use" prediction models, all datasets and the results of this study are available at ; https://github.com/cansyl/DEEPscreen.

Pesticide application inhibit the microbial carbonic anhydrase-mediated carbon sequestration in a soil microcosm

Heterotrophic system for carbon sequestration is gaining importance in the recent decades. Carbonic anhydrase (CA) is a major enzyme involved in carbon sequestration and biomineralization process. In this paper, we evaluate the effect of pesticide on CA activity using inhibitory assay. 2,4-D, being one of the most extensively used pesticide, being deleterious to soil health, its usage should be minimized to regain the soil health. Maximum inhibitory constant (K_i) was observed for 5% 2,4-D (49.53 mM) followed by 5% glyphosate (43.92 mM). The maximum Km increase with increase in pesticide concentration by 3.05-fold was in case of glyphosate which was higher than that of 2,4-D (2.08-fold) and dichlorvos (2.38-fold). Moreover, we evaluated the carbon sequestration using CA enzyme in the soil microcosm. In the present study, we identified the negative impact of 2,4-D on carbonic anhydrase produced by Bacillus halodurans PO15. The inhibition was a mixed type and had significantly lowered the carbon reduction to about 2.38 ± 0.17% in a soil microcosm study. Based on the molecular docking, the inhibition was contributed due to weak H-bonding interaction with amino acid residues (Gly65, Gly95, Val147, Ser150 and Gly65, Ser146, and Ser150).

In silico and in vitro metabolism of ribociclib: a mass spectrometric approach to bioactivation pathway elucidation and metabolite profiling

Ribociclib (RBC, Kisqali®) is a highly selective CDK4/6 inhibitor that has been approved for breast cancer therapy. Initially, prediction of susceptible sites of metabolism and reactivity pathways were performed by the StarDrop WhichP450™ module and the Xenosite web predictor tool, respectively. Later, in vitro metabolites and adducts of RBC were characterized from rat liver microsomes using LC-MS/MS. Subsequently, in silico data was used as a guide for the in vitro work. Finally, in silico toxicity assessment of RBC metabolites was carried out using DEREK software and structural modification was proposed to reduce their side effects and to validate the bioactivation pathway theory using the StarDrop DEREK module. In vitro phase I metabolic profiling of RBC was performed utilizing rat liver microsomes (RLMs). Generation of reactive metabolites was investigated using potassium cyanide (KCN) as a trapping nucleophile for the transient and reactive iminium intermediates to form a stable cyano adduct that can be identified and characterized using mass spectrometry. Nine phase I metabolites and one cyano adduct of RBC were characterized. The proposed metabolic pathways involved in generation of these metabolites are hydroxylation, oxidation and reduction. The reactive intermediate generation mechanism of RBC may provide an explanation of its adverse reactions. Aryl piperazine is considered a structural alert for toxicity as proposed by the DEREK report. We propose that the generation of only one reactive metabolite of RBC in a very small concentration is due to the decreased reactivity of the piperazine ring compared to previous reports of similar drugs. Docking analysis was performed for RBC and its proposed derivatives at the active site of the human CDK6 enzyme. Methyl-RBC exhibited the best ADMET and docking analysis and fewer side effects compared to RBC and fluoro-RBC. Further drug discovery studies can be conducted taking into account this concept allowing the development of new drugs with enhanced safety profiles that were confirmed by using StarDrop software. To the best of our knowledge, this is the first literature report of RBCin vitro metabolic profiling and structural characterization and toxicological properties of the generated metabolites.

Nine phase I metabolites and one product of KCN trapping of RBC were characterized. Aryl piperazine is considered a structural alert for toxicity as proposed by the DEREK report. Methyl-RBC exhibited less toxicity and more binding affinity to CDK6.

Applications of Deep-Learning in Exploiting Large-Scale and Heterogeneous Compound Data in Industrial Pharmaceutical Research

In recent years, the development of high-throughput screening (HTS) technologies and their establishment in an industrialized environment have given scientists the possibility to test millions of molecules and profile them against a multitude of biological targets in a short period of time, generating data in a much faster pace and with a higher quality than before. Besides the structure activity data from traditional bioassays, more complex assays such as transcriptomics profiling or imaging have also been established as routine profiling experiments thanks to the advancement of Next Generation Sequencing or automated microscopy technologies. In industrial pharmaceutical research, these technologies are typically established in conjunction with automated platforms in order to enable efficient handling of screening collections of thousands to millions of compounds. To exploit the ever-growing amount of data that are generated by these approaches, computational techniques are constantly evolving. In this regard, artificial intelligence technologies such as deep learning and machine learning methods play a key role in cheminformatics and bio-image analytics fields to address activity prediction, scaffold hopping, de novo molecule design, reaction/retrosynthesis predictions, or high content screening analysis. Herein we summarize the current state of analyzing large-scale compound data in industrial pharmaceutical research and describe the impact it has had on the drug discovery process over the last two decades, with a specific focus on deep-learning technologies.

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.

Deep Learning Intervention for Health Care Challenges: Some Biomedical Domain Considerations

The use of deep learning (DL) for the analysis and diagnosis of biomedical and health care problems has received unprecedented attention in the last decade. The technique has recorded a number of achievements for unearthing meaningful features and accomplishing tasks that were hitherto difficult to solve by other methods and human experts. Currently, biological and medical devices, treatment, and applications are capable of generating large volumes of data in the form of images, sounds, text, graphs, and signals creating the concept of big data. The innovation of DL is a developing trend in the wake of big data for data representation and analysis. DL is a type of machine learning algorithm that has deeper (or more) hidden layers of similar function cascaded into the network and has the capability to make meaning from medical big data. Current transformation drivers to achieve personalized health care delivery will be possible with the use of mobile health (mHealth). DL can provide the analysis for the deluge of data generated from mHealth apps. This paper reviews the fundamentals of DL methods and presents a general view of the trends in DL by capturing literature from PubMed and the Institute of Electrical and Electronics Engineers database publications that implement different variants of DL. We highlight the implementation of DL in health care, which we categorize into biological system, electronic health record, medical image, and physiological signals. In addition, we discuss some inherent challenges of DL affecting biomedical and health domain, as well as prospective research directions that focus on improving health management by promoting the application of physiological signals and modern internet technology.

A Time-Embedding Network Models the Ontogeny of 23 Hepatic Drug Metabolizing Enzymes

Pediatric patients are at elevated risk of adverse drug reactions, and there is insufficient information on drug safety in children. Complicating risk assessment in children, there are numerous age-dependent changes in the absorption, distribution, metabolism, and elimination of drugs. A key contributor to age-dependent drug toxicity risk is the ontogeny of drug metabolism enzymes, the changes in both abundance and type throughout development from the fetal period through adulthood. Critically, these changes affect not only the overall clearance of drugs but also exposure to individual metabolites. In this study, we introduce time-embedding neural networks in order to model population-level variation in metabolism enzyme expression as a function of age. We use a time-embedding network to model the ontogeny of 23 drug metabolism enzymes. The time-embedding network recapitulates known demographic factors impacting 3A5 expression. The time-embedding network also effectively models the nonlinear dynamics of 2D6 expression, enabling a better fit to clinical data than prior work. In contrast, a standard neural network fails to model these features of 3A5 and 2D6 expression. Finally, we combine the time-embedding model of ontogeny with additional information to estimate age-dependent changes in reactive metabolite exposure. This simple approach identifies age-dependent changes in exposure to valproic acid and dextromethorphan metabolites and suggests potential mechanisms of valproic acid toxicity. This approach may help researchers evaluate the risk of drug toxicity in pediatric populations.

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.

Virtual Screening Meets Deep Learning

BACKGROUND

Automated compound testing is currently the de facto standard method for drug screening, but it has not brought the great increase in the number of new drugs that was expected. Computer- aided compounds search, known as Virtual Screening, has shown the benefits to this field as a complement or even alternative to the robotic drug discovery. There are different methods and approaches to address this problem and most of them are often included in one of the main screening strategies. Machine learning, however, has established itself as a virtual screening methodology in its own right and it may grow in popularity with the new trends on artificial intelligence.

OBJECTIVE

This paper will attempt to provide a comprehensive and structured review that collects the most important proposals made so far in this area of research. Particular attention is given to some recent developments carried out in the machine learning field: the deep learning approach, which is pointed out as a future key player in the virtual screening landscape.

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.

Atomic structure of boron resolved using machine learning and global sampling

Boron crystals, despite their simple composition, must rank top for complexity: even the atomic structure of the ground state of β-B remains uncertain after 60 years' study. This makes it difficult to understand the many exotic photoelectric properties of boron. The presence of self-doping atoms in the crystal interstitial sites forms an astronomical configurational space, making the determination of the real configuration virtually impossible using current techniques. Here, by combining machine learning with the latest stochastic surface walking (SSW) global optimization, we explore for the first time the potential energy surface of β-B, revealing 15 293 distinct configurations out of the 2 × 105 minima visited, and reveal the key rules governing the filling of the interstitial sites. This advance is only allowed by the construction of an accurate and efficient neural network (NN) potential using a new series of structural descriptors that can sensitively discriminate the complex boron bonding environment. We show that, in contrast to the conventional views on the numerous energy-degenerate configurations, only 40 minima of β-B are identified to be within 7 meV per atom in energy above the global minimum of β-B, most of them having been discovered for the first time. These low energy structures are classified into three types of skeletons and six patterns of doping configurations, with a clear preference for a few characteristic interstitial sites. The observed β-B and its properties are influenced strongly by a particular doping site, the B19 site that neighbors the B18 site, which has an exceptionally large vibrational entropy. The configuration with this B19 occupancy, which ranks only 15th at 0 K, turns out to be dominant at high temperatures. Our results highlight the novel SSW-NN architecture as the leading problem solver for complex material phenomena, which would then expedite substantially the building of a material genome database.

Modeling Small-Molecule Reactivity Identifies Promiscuous Bioactive Compounds

Scientists rely on high-throughput screening tools to identify promising small-molecule compounds for the development of biochemical probes and drugs. This study focuses on the identification of promiscuous bioactive compounds, which are compounds that appear active in many high-throughput screening experiments against diverse targets but are often false-positives which may not be easily developed into successful probes. These compounds can exhibit bioactivity due to nonspecific, intractable mechanisms of action and/or by interference with specific assay technology readouts. Such "frequent hitters" are now commonly identified using substructure filters, including pan assay interference compounds (PAINS). Herein, we show that mechanistic modeling of small-molecule reactivity using deep learning can improve upon PAINS filters when modeling promiscuous bioactivity in PubChem assays. Without training on high-throughput screening data, a deep learning model of small-molecule reactivity achieves a sensitivity and specificity of 18.5% and 95.5%, respectively, in identifying promiscuous bioactive compounds. This performance is similar to PAINS filters, which achieve a sensitivity of 20.3% at the same specificity. Importantly, such reactivity modeling is complementary to PAINS filters. When PAINS filters and reactivity models are combined, the resulting model outperforms either method alone, achieving a sensitivity of 24% at the same specificity. However, as a probabilistic model, the sensitivity and specificity of the deep learning model can be tuned by adjusting the threshold. Moreover, for a subset of PAINS filters, this reactivity model can help discriminate between promiscuous and nonpromiscuous bioactive compounds even among compounds matching those filters. Critically, the reactivity model provides mechanistic hypotheses for assay interference by predicting the precise atoms involved in compound reactivity. Overall, our analysis suggests that deep learning approaches to modeling promiscuous compound bioactivity may provide a complementary approach to current methods for identifying promiscuous compounds.

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.

Opportunities and obstacles for deep learning in biology and medicine

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.