Using 2D Structural Alerts to Define Chemical Categories for Molecular Initiating Events

Machine Learning-Based Toxicological Modeling for Screening Environmental Obesogens

The emerging presence of environmental obesogens, chemicals that disrupt energy balance and contribute to adipogenesis and obesity, has become a major public health challenge. Molecular initiating events (MIEs) describe biological outcomes resulting from chemical interactions with biomolecules. Machine learning models based on MIEs can predict complex toxic end points due to chemical exposure and improve the interpretability of models. In this study, a system was constructed that integrated six MIEs associated with adipogenesis and obesity. This system showed high accuracy in external validation, with an area under the receiver operating characteristic curve of 0.78. Molecular hydrophobicity (SlogP_VSA) and direct electrostatic interactions (PEOE_VSA) were identified as the two most critical molecular descriptors representing the obesogenic potential of chemicals. This system was further used to predict the obesogenic effects of chemicals on the candidate list of substances of very high concern (SVHCs). Results from 3T3-L1 adipogenesis assays verified that the system correctly predicted obesogenic or nonobesogenic effects of 10 of the 12 SVHCs tested, and identified four novel potential obesogens, including 2-benzotriazol-2-yl-4,6-ditert-butylphenol (UV-320), 4-(1,1,5-trimethylhexyl)phenol (p262-NP), 2-[4-(1,1,3,3-tetramethylbutyl)phenoxy]ethanol (OP1EO) and endosulfan. These validation data suggest that the screening system has good performance in adipogenic prediction.

In silico off-target profiling for enhanced drug safety assessment

Ensuring drug safety in the early stages of drug development is crucial to avoid costly failures in subsequent phases. However, the economic burden associated with detecting drug off-targets and potential side effects through in vitro safety screening and animal testing is substantial. Drug off-target interactions, along with the adverse drug reactions they induce, are significant factors affecting drug safety. To assess the liability of candidate drugs, we developed an artificial intelligence model for the precise prediction of compound off-target interactions, leveraging multi-task graph neural networks. The outcomes of off-target predictions can serve as representations for compounds, enabling the differentiation of drugs under various ATC codes and the classification of compound toxicity. Furthermore, the predicted off-target profiles are employed in adverse drug reaction (ADR) enrichment analysis, facilitating the inference of potential ADRs for a drug. Using the withdrawn drug Pergolide as an example, we elucidate the mechanisms underlying ADRs at the target level, contributing to the exploration of the potential clinical relevance of newly predicted off-target interactions. Overall, our work facilitates the early assessment of compound safety/toxicity based on off-target identification, deduces potential ADRs of drugs, and ultimately promotes the secure development of drugs.

Next generation risk assessment of human exposure to estrogens using safe comparator compound values based on in vitro bioactivity assays

In next generation risk assessment (NGRA), the Dietary Comparator Ratio (DCR) can be used to assess the safety of chemical exposures to humans in a 3R compliant approach. The DCR compares the Exposure Activity Ratio (EAR) for exposure to a compound of interest (EARtest) to the EAR for an established safe exposure level to a comparator compound (EARcomparator), acting by the same mode of action. It can be concluded that the exposure to a test compound is safe at a corresponding DCR ≤ 1. In this study, genistein (GEN) was selected as a comparator compound by comparison of reported safe internal exposures to GEN to its BMCL05, as no effect level, the latter determined in the in vitro estrogenic MCF7/Bos proliferation, T47D ER-CALUX, and U2OS ERα-CALUX assay. The EARcomparator was defined using the BMCL05 and EC50 values from the 3 in vitro assays and subsequently used to calculate the DCRs for exposures to 14 test compounds, predicting the (absence of) estrogenicity. The predictions were evaluated by comparison to reported in vivo estrogenicity in humans for these exposures. The results obtained support in the DCR approach as an important animal-free new approach methodology (NAM) in NGRA and show how in vitro assays can be used to define DCR values.

Identification of molecular initiating events (MIE) using chemical database analysis and nuclear receptor activity assays for screening potential inhalation toxicants

An adverse outcome pathway (AOP) framework can facilitate the use of alternative assays in chemical regulations by providing scientific evidence. Previously, an AOP, peroxisome proliferative-activating receptor gamma (PPARγ) antagonism that leads to pulmonary fibrosis, was developed. Based on a literature search, PPARγ inactivation has been proposed as a molecular initiating event (MIE). In addition, a list of candidate chemicals that could be used in the experimental validation was proposed using toxicity database and deep learning models. In this study, the screening of environmental chemicals for MIE was conducted using in silico and in vitro tests to maximize the applicability of this AOP for screening inhalation toxicants. Initially, potential inhalation exposure chemicals that are active in three or more key events were selected, and in silico molecular docking was performed. Among the chemicals with low binding energy to PPARγ, nine chemicals were selected for validation of the AOP using in vitro PPARγ activity assay. As a result, rotenone, triorthocresyl phosphate, and castor oil were proposed as PPARγ antagonists and stressor chemicals of the AOP. Overall, the proposed tiered approach of the database-in silico-in vitro can help identify the regulatory applicability and assist in the development and experimental validation of AOP.

A scheme to evaluate structural alerts to predict toxicity - Assessing confidence by characterising uncertainties

Structure-activity relationships (SARs) in toxicology have enabled the formation of structural rules which, when coded as structural alerts, are essential tools in in silico toxicology. Whilst other in silico methods have approaches for their evaluation, there is no formal process to assess the confidence that may be associated with a structural alert. This investigation proposes twelve criteria to assess the uncertainty associated with structural alerts, allowing for an assessment of confidence. The criteria are based around the stated purpose, description of the chemistry, toxicology and mechanism, performance and coverage, as well as corroborating and supporting evidence of the alert. Alerts can be given a confidence assessment and score, enabling the identification of areas where more information may be beneficial. The scheme to evaluate structural alerts was placed in the context of various use cases for industrial and regulatory applications. The analysis of alerts, and consideration of the evaluation scheme, identifies the different characteristics an alert may have, such as being highly specific or generic. These characteristics may determine when an alert can be used for specific uses such as identification of analogues for read-across or hazard identification.

•

Structural alerts are useful tools for predictive toxicology.

•

12 criteria to evaluate structural alerts have been identified.

•

A strategy to determine confidence of structural alerts is presented.

•

Different use cases require different characteristics of structural alerts.

•

A Scheme to Evaluate Structural Alerts to Predict Toxicity – Assessing Confidence By Characterising Uncertainties.

Machine learning and artificial intelligence in toxicological sciences

Machine learning and artificial intelligence approaches have revolutionized multiple disciplines, including toxicology. This review summarizes representative recent applications of machine learning and artificial intelligence approaches in different areas of toxicology, including physiologically based pharmacokinetic (PBPK) modeling, quantitative structure-activity relationship modeling for toxicity prediction, adverse outcome pathway analysis, high-throughput screening, toxicogenomics, big data and toxicological databases. By leveraging machine learning and artificial intelligence approaches, now it is possible to develop PBPK models for hundreds of chemicals efficiently, to create in silico models to predict toxicity for a large number of chemicals with similar accuracies compared to in vivo animal experiments, and to analyze a large amount of different types of data (toxicogenomics, high-content image data, etc.) to generate new insights into toxicity mechanisms rapidly, which was impossible by manual approaches in the past. To continue advancing the field of toxicological sciences, several challenges should be considered: (1) not all machine learning models are equally useful for a particular type of toxicology data, and thus it is important to test different methods to determine the optimal approach; (2) current toxicity prediction is mainly on bioactivity classification (yes/no), so additional studies are needed to predict the intensity of effect or dose-response relationship; (3) as more data become available, it is crucial to perform rigorous data quality check and develop infrastructure to store, share, analyze, evaluate, and manage big data; and (4) it is important to convert machine learning models to user-friendly interfaces to facilitate their applications by both computational and bench scientists.

Converging global crises are forcing the rapid adoption of disruptive changes in drug discovery

Spiralling research costs combined with urgent pressures from the Coronavirus 2019 (COVID-19) pandemic and the consequences of climate disruption are forcing changes in drug discovery. Increasing the predictive power of in vitro human assays and using them earlier in discovery would refocus resources on more successful research strategies and reduce animal studies. Increasing laboratory automation enables effective social distancing for researchers, while allowing integrated data capture from remote laboratory networks. Such disruptive changes would not only enable more cost-effective drug discovery, but could also reduce the overall carbon footprint of discovering new drugs.

Reactivity-directed analysis - a novel approach for the identification of toxic organic electrophiles in drinking water

Drinking water consumption results in exposure to complex mixtures of organic chemicals, including natural and anthropogenic chemicals and compounds formed during drinking water treatment such as disinfection by-products. The complexity of drinking water contaminant mixtures has hindered efforts to assess associated health impacts. Existing approaches focus primarily on individual chemicals and/or the evaluation of mixtures, without providing information about the chemicals causing the toxic effect. Thus, there is a need for the development of novel strategies to evaluate chemical mixtures and provide insights into the species responsible for the observed toxic effects. This critical review introduces the application of a novel approach called Reactivity-Directed Analysis (RDA) to assess and identify organic electrophiles, the largest group of known environmental toxicants. In contrast to existing in vivo and in vitro approaches, RDA utilizes in chemico methodologies that investigate the reaction of organic electrophiles with nucleophilic biomolecules, including proteins and DNA. This review summarizes the existing knowledge about the presence of electrophiles in drinking water, with a particular focus on their formation in oxidative treatment systems with ozone, advanced oxidation processes, and UV light, as well as disinfectants such as chlorine, chloramines and chlorine dioxide. This summary is followed by an overview of existing RDA approaches and their application for the assessment of aqueous environmental matrices, with an emphasis on drinking water. RDA can be applied beyond drinking water, however, to evaluate source waters and wastewater for human and environmental health risks. Finally, future research demands for the detection and identification of electrophiles in drinking water via RDA are outlined.

HPLC coupled with quadrupole time of flight tandem mass spectrometry for analysis of glycosylated components from the fresh flowers of two congeneric species: Robinia hispida L. and Robinia pseudoacacia L

Developing methods for the systematic and rapid identification of the chemical compositions of fresh plant tissues has long attracted the attention of phytochemists and pharmacologists. In the present study, based on highly efficient sample pretreatment and high-throughput analysis of high-performance liquid chromatography coupled with quadrupole time of flight tandem mass spectrometry data using molecular networks, a method was developed for systematically analyzing the chemical constituents of the fresh flowers of Robinia hispida L. and Robina pseudoacacia L., two congeneric ornamental species that lack prior consideration. A total of 44 glycosylated structures were characterized. And on the basis of establishing of the fragmentation pathways of 11 known flavonoid glycosides, together with the molecular networking analysis, 18 other ions of flavonoid glycosides in five classes were clustered. Moreover, 15 soyasaponins/triterpenoid glycosides were tentatively identified by comparison of their tandem mass spectrometry characteristic ions with those reported in the literature or the online Global Natural Product Social Molecular Networking database. The water extracts were separated by flash chromatography, which resulted in the discovery of one new compound, named rohispidascopolin, along with five known entities. The pharmacological targets were predicted by SwissTargetPrediction.

Confidence in Inactive and Active Predictions from Structural Alerts

Having a measure of confidence in computational predictions of biological activity from in silico tools is vital when making predictions for new chemicals, for example, in chemical risk assessment. Where predictions of biological activity are used as an indicator of a potential hazard, false-negative predictions are the most concerning prediction; however, assigning confidence in inactive predictions is particularly challenging. How can one confidently identify the absence of activating features? In this study, we present methods for assigning confidence to both active and inactive predictions from structural alerts for protein-binding molecular initiating events (MIEs). Structural alerts were derived through an iterative statistical method. Confidence in the activity predictions is assigned by measuring the Tanimoto similarity between Morgan fingerprints of chemicals in the test set to relevant chemicals in the training set, and suitable cutoff values have been defined to give different confidence categories. To avoid a potential compound series bias in the test set and hence overestimate the performance of the method, we measured the biological activity of 27 compounds with 24 proteins, which gave us an additional 648 experimental measurements; many of the measurements are currently nonexistent in the literature and databases. This data set was complemented with newly measured biological activities published in ChEMBL25 and formed a combined independent validation data set. Applying the confidence categories to the computational predictions for the new data leads to the identification of chemicals for which one should be confident of either an inactive or active prediction, allowing model predictions to be used responsibly.

A Next-Generation Risk Assessment Case Study for Coumarin in Cosmetic Products

Next-Generation Risk Assessment is defined as an exposure-led, hypothesis-driven risk assessment approach that integrates new approach methodologies (NAMs) to assure safety without the use of animal testing. These principles were applied to a hypothetical safety assessment of 0.1% coumarin in face cream and body lotion. For the purpose of evaluating the use of NAMs, existing animal and human data on coumarin were excluded. Internal concentrations (plasma Cmax) were estimated using a physiologically based kinetic model for dermally applied coumarin. Systemic toxicity was assessed using a battery of in vitro NAMs to identify points of departure (PoDs) for a variety of biological effects such as receptor-mediated and immunomodulatory effects (Eurofins SafetyScreen44 and BioMap Diversity 8 Panel, respectively), and general bioactivity (ToxCast data, an in vitro cell stress panel and high-throughput transcriptomics). In addition, in silico alerts for genotoxicity were followed up with the ToxTracker tool. The PoDs from the in vitro assays were plotted against the calculated in vivo exposure to calculate a margin of safety with associated uncertainty. The predicted Cmax values for face cream and body lotion were lower than all PoDs with margin of safety higher than 100. Furthermore, coumarin was not genotoxic, did not bind to any of the 44 receptors tested and did not show any immunomodulatory effects at consumer-relevant exposures. In conclusion, this case study demonstrated the value of integrating exposure science, computational modeling and in vitro bioactivity data, to reach a safety decision without animal data.

Neural network activation similarity: a new measure to assist decision making in chemical toxicology

Deep learning neural networks, constructed for the prediction of chemical binding at 79 pharmacologically important human biological targets, show extremely high performance on test data (accuracy 92.2 ± 4.2%, MCC 0.814 ± 0.093 and ROC-AUC 0.96 ± 0.04). A new molecular similarity measure, Neural Network Activation Similarity, has been developed, based on signal propagation through the network. This is complementary to standard Tanimoto similarity, and the combined use increases confidence in the computer's prediction of activity for new chemicals by providing a greater understanding of the underlying justification. The in silico prediction of these human molecular initiating events is central to the future of chemical safety risk assessment and improves the efficiency of safety decision making.

In Silico Guidance for In Vitro Androgen and Glucocorticoid Receptor ToxCast Assays

Molecular initiating events (MIEs) are key events in adverse outcome pathways that link molecular chemistry to target biology. As they are based on chemistry, these interactions are excellent targets for computational chemistry approaches to in silico modeling. In this work, we aim to link ligand chemical structures to MIEs for androgen receptor (AR) and glucocorticoid receptor (GR) binding using ToxCast data. This has been done using an automated computational algorithm to perform maximal common substructure searches on chemical binders for each target from the ToxCast dataset. The models developed show a high level of accuracy, correctly assigning 87.20% of AR binders and 96.81% of GR binders in a 25% test set using holdout cross-validation. The 2D structural alerts developed can be used as in silico models to predict these MIEs and as guidance for in vitro ToxCast assays to confirm hits. These models can target such experimental work, reducing the number of assays to be performed to gain required toxicological insight. Development of these models has also allowed some structural alerts to be identified as predictors for agonist or antagonist behavior at the receptor target. This work represents a first step in using computational methods to guide and target experimental approaches.

Identification of a novel toxicophore in anti-cancer chemotherapeutics that targets mitochondrial respiratory complex I

Disruption of mitochondrial function selectively targets tumour cells that are dependent on oxidative phosphorylation. However, due to their high energy demands, cardiac cells are disproportionately targeted by mitochondrial toxins resulting in a loss of cardiac function. An analysis of the effects of mubritinib on cardiac cells showed that this drug did not inhibit HER2 as reported, but directly inhibits mitochondrial respiratory complex I, reducing cardiac-cell beat rate, with prolonged exposure resulting in cell death. We used a library of chemical variants of mubritinib and showed that modifying the 1H-1,2,3-triazole altered complex I inhibition, identifying the heterocyclic 1,3-nitrogen motif as the toxicophore. The same toxicophore is present in a second anti-cancer therapeutic carboxyamidotriazole (CAI) and we demonstrate that CAI also functions through complex I inhibition, mediated by the toxicophore. Complex I inhibition is directly linked to anti-cancer cell activity, with toxicophore modification ablating the desired effects of these compounds on cancer cell proliferation and apoptosis.

The pharmaceutical industry needs to make safe and effective drugs. At the same time this industry is under pressure to keep the costs of developing these drugs at an acceptable level. Drugs work by interacting with and typically blocking a specific target, such as a protein in a particular type of cell. Sometimes, however, drugs also bind other unexpected targets. These “off-target” effects can be the reason for a drug’s toxicity, and it is important – both for the benefit of patients and the money that can be saved when developing drugs – to identify how drugs cause toxic side effects. The earlier researchers detect off-target effects, the better.

Recent data has suggested that an anti-cancer drug called mubritinib has off-target effects on the compartments within cells that provide the cell with most of their energy, the mitochondria. This drug’s intended target is a protein called HER2, which is found in large amounts on the surfaces of some breast cancer cells. Yet if mubritinib has this off-target effect on mitochondria, it may be harmful to other cells including heart cells because the heart is an organ that needs a large amount of energy from its mitochondria.

Stephenson et al. have now performed experiments to show that mubritinib does not actually interact with HER2 at all, but only targets mitochondria. The effect of mubritinib as an anti-cancer drug is therefore only due to its activity against mitochondria. Digging deeper into the chemistry revealed the small parts of its chemical structure that was responsible for mubritinib’s toxicity against heart cells, the so-called toxic substructure. Another anti-cancer drug called carboxyamidotriazole also has the same toxic substructure. Carboxyamidotriazole is supposed to stop cells from taking up calcium ions, but a final set of experiments demonstrated that this drug also only acts by inhibiting mitochondria.

Often there is not enough information about many drugs’ substructures, meaning off-target effects and toxicities cannot be predicted. The pharmaceutical industry will now be able to benefit from this new knowledge about the toxic substructures within some drugs. This research may also help patients who take mubritinib or carboxyamidotriazole, because their doctors will have to check for side effects on the heart more carefully.

Application of the hard and soft, acids and bases (HSAB) theory as a method to predict cumulative neurotoxicity

Xenobiotic electrophiles can form covalent adducts that may impair protein function, damage DNA, and may lead a range of adverse effects. Cumulative neurotoxicity is one adverse effect that has been linked to covalent protein binding as a Molecular Initiating Event (MIE). This paper describes a mechanistic in silico chemical screening approach for neurotoxicity based on Hard and Soft Acids and Bases (HSAB) theory. We evaluated the applicability of HSAB-based electrophilicity screening protocol for neurotoxicity on 19 positive and 19 negative reference chemicals. These reference chemicals were identified from the literature, using available information on mechanisms of neurotoxicity whenever possible. In silico screening was based on structural alerts for protein binding motifs and electrophilicity index in the range of known neurotoxicants. The approach demonstrated both a high positive prediction rate (82-90 %) and specificity (90 %). The overall sensitivity was relatively lower (47 %). However, when predicting the toxicity of chemicals known or suspected of acting via non-specific adduct formation mechanism, the HSAB approach identified 7/8 (sensitivity 88 %) of positive control chemicals correctly. Consequently, the HSAB-based screening is a promising approach of identifying possible neurotoxins with adduct formation molecular initiating events. While the approach must be expanded over time to capture a wider range of MIEs involved in neurotoxicity, the mechanistic nature of the screen allows users to flag chemicals for possible adduct formation MIEs. Thus, the HSAB based toxicity screening is a promising strategy for toxicity assessment and chemical prioritization in neurotoxicology and other health endpoints that involve adduct formation.

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

Structural Alerts and Random Forest Models in a Consensus Approach for Receptor Binding Molecular Initiating Events

A molecular initiating event (MIE) is the gateway to an adverse outcome pathway (AOP), a sequence of events ending in an adverse effect. In silico predictions of MIEs are a vital tool in a modern, mechanism-focused approach to chemical risk assessment. For 90 biological targets representing important human MIEs, structural alert-based models have been constructed with an automated procedure that uses Bayesian statistics to iteratively select substructures. These models give impressive average performance statistics (an average of 92% correct predictions across targets), significantly improving on previous models. Random Forest models have been constructed from physicochemical features for the same targets, giving similarly impressive performance statistics (93% correct predictions). A key difference between the models is interpretation of predictions-the structural alert models are transparent and easy to interpret, while Random Forest models can only identify the most important physicochemical features for making predictions. The two complementary models have been combined in a consensus model, improving performance compared to each individual model (94% correct predictions) and increasing confidence in predictions. Variation in model performance has been explained by calculating a modelability index (MODI), using Tanimoto coefficient between Morgan fingerprints to identify nearest neighbor chemicals. This work is an important step toward building confidence in the use of in silico tools for assessment of toxicity.

Discovery of isoxazolyl-based inhibitors of Plasmodium falciparum cGMP-dependent protein kinase

The cGMP-dependent protein kinase in Plasmodium falciparum (PfPKG) plays multiple roles in the life cycle of the parasite. As a result, this enzyme is a potential target for new antimalarial agents. Existing inhbitors, while potent and active in malaria models are not optimal. This communication describes initial optimization of a structurally distinct class of PfPKG inhibitors.

Quantitative Predictions for Molecular Initiating Events Using Three-Dimensional Quantitative Structure-Activity Relationships

The aim of human toxicity risk assessment is to determine a safe dose or exposure to a chemical for humans. This requires an understanding of the exposure of a person to a chemical and how much of the chemical is required to cause an adverse effect. To do this computationally, we need to understand how much of a chemical is required to perturb normal biological function in an adverse outcome pathway (AOP). The molecular initiating event (MIE) is the first step in an adverse outcome pathway and can be considered as a chemical interaction between a chemical toxicant and a biological molecule. Key chemical characteristics can be identified and used to model the chemistry of these MIEs. In this study, we do just this by using chemical substructures to categorize chemicals and 3D quantitative structure-activity relationships (QSARs) based on comparative molecular field analysis (CoMFA) to calculate molecular activity. Models have been constructed across a variety of human biological targets, the glucocorticoid receptor, mu opioid receptor, cyclooxygenase-2 enzyme, human ether-à-go-go related gene channel, and dopamine transporter. These models tend to provide molecular activity estimation well within one log unit and electronic and steric fields that can be visualized to better understand the MIE and biological target of interest. The outputs of these fields can be used to identify key aspects of a chemical's chemistry which can be changed to reduce its ability to activate a given MIE. With this methodology, the quantitative chemical activity can be predicted for a wide variety of MIEs, which can feed into AOP-based chemical risk assessments, and understanding of the chemistry behind the MIE can be gained.