Predicting hepatotoxicity using ToxCast in vitro bioactivity and chemical structure

A Data-Driven Computational Framework for Assessing the Risk of Placental Exposure to Environmental Chemicals

A computational framework based on placental gene networks was proposed in this work to improve the accuracy of the placental exposure risk assessment of environmental compounds. The framework quantitatively characterizes the ability of compounds to cross the placental barrier by systematically considering the interaction and pathway-level information on multiple placental transporters. As a result, probability scores were generated for 307 compounds crossing the placental barrier based on this framework. These scores were then used to categorize the compounds into different levels of transplacental transport range, creating a gradient partition. These probability scores not only facilitated a more intuitive understanding of a compound's ability to cross the placental barrier but also provided valuable information for predicting potential placental disruptors. Compounds with probability scores greater than 90% were considered to have significant transplacental transport potential, whereas those with probability scores less than 80% were classified as unlikely to cross the placental barrier. Furthermore, external validation set results showed that the probability score could accurately predict the compounds known to cross the placental barrier. In conclusion, the computational framework proposed in this study enhances the intuitive understanding of the ability of compounds to cross the placental barrier and opens up new avenues for assessing the placental exposure risk of compounds.

Artificial intelligence (AI)-it's the end of the tox as we know it (and I feel fine)

The rapid progress of AI impacts diverse scientific disciplines, including toxicology, and has the potential to transform chemical safety evaluation. Toxicology has evolved from an empirical science focused on observing apical outcomes of chemical exposure, to a data-rich field ripe for AI integration. The volume, variety and velocity of toxicological data from legacy studies, literature, high-throughput assays, sensor technologies and omics approaches create opportunities but also complexities that AI can help address. In particular, machine learning is well suited to handle and integrate large, heterogeneous datasets that are both structured and unstructured-a key challenge in modern toxicology. AI methods like deep neural networks, large language models, and natural language processing have successfully predicted toxicity endpoints, analyzed high-throughput data, extracted facts from literature, and generated synthetic data. Beyond automating data capture, analysis, and prediction, AI techniques show promise for accelerating quantitative risk assessment by providing probabilistic outputs to capture uncertainties. AI also enables explanation methods to unravel mechanisms and increase trust in modeled predictions. However, issues like model interpretability, data biases, and transparency currently limit regulatory endorsement of AI. Multidisciplinary collaboration is needed to ensure development of interpretable, robust, and human-centered AI systems. Rather than just automating human tasks at scale, transformative AI can catalyze innovation in how evidence is gathered, data are generated, hypotheses are formed and tested, and tasks are performed to usher new paradigms in chemical safety assessment. Used judiciously, AI has immense potential to advance toxicology into a more predictive, mechanism-based, and evidence-integrated scientific discipline to better safeguard human and environmental wellbeing across diverse populations.

Qi Fu Yin ameliorates neuroinflammation through inhibiting RAGE and TLR4/NF-κB pathway in AD model rats

The purpose of this study is to investigate the therapeutic effect of Qi Fu Yin (QFY) on Alzheimer's disease (AD) both computationally and experimentally. Network pharmacology analysis and molecular docking were conducted to identify potential targets and signaling pathways involved in QFY treating AD. Streptozotocin-induced AD rat model was used to verify important targets and predicted pathways. The components of QFY were identified using liquid chromatography-tandem mass spectrometry. The results indicate that the potential targets of QFY are highly enriched for anti-inflammatory pathways. Molecular docking analysis revealed stable structures formed between QFY's active compounds, including stigmasterol, β-sitosterol, and isorhamnetin, and the identified targets. In vivo, QFY improved cognitive memory in AD rats and reduced the mRNA expression levels of toll-like receptor 4 (TLR4), the receptor for advanced glycation end products (AGER), and the inflammatory factors interleukin-1β (IL-1β) and tumor necrosis factor-α (TNF-α) in the brains of AD rats. Furthermore, QFY effectively reduced nuclear translocation of nuclear factor-kappa B (NF-κB) and inhibited NF-κB and microglia activation. In conclusion, QFY can ameliorate neuroinflammation in AD model rats, partly via the inhibition of TLR4 and RAGE/NF-κB pathway and microglia activation, thereby enhancing learning and memory in AD model rats.

Review of machine learning and deep learning models for toxicity prediction

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

The regulation of endocrine-disrupting chemicals to minimize their impact on health

Endocrine-disrupting chemicals (EDCs) are substances generated by human industrial activities that are detrimental to human health through their effects on the endocrine system. The global societal and economic burden posed by EDCs is substantial. Poorly defined or unenforced policies can increase human exposure to EDCs, thereby contributing to human disease, disability and economic damage. Researchers have shown that policies and interventions implemented at both individual and government levels have the potential to reduce exposure to EDCs. This Review describes a set of evidence-based policy actions to manage, minimize or even eliminate the widespread use of these chemicals and better protect human health and society. A number of specific challenges exist: defining, identifying and prioritizing EDCs; considering the non-linear or non-monotonic properties of EDCs; accounting for EDC exposure effects that are latent and do not appear until later in life; and updating testing paradigms to reflect 'real-world' mixtures of chemicals and cumulative exposure. A sound strategy also requires partnering with health-care providers to integrate strategies to prevent EDC exposure in clinical care. Critical next steps include addressing EDCs within global policy frameworks by integrating EDC exposure prevention into emerging climate policy.

Collaborative SAR Modeling and Prospective In Vitro Validation of Oxidative Stress Activation in Human HepG2 Cells

Oxidative stress is the consequence of an abnormal increase of reactive oxygen species (ROS). ROS are generated mainly during the metabolism in both normal and pathological conditions as well as from exposure to xenobiotics. Xenobiotics can, on the one hand, disrupt molecular machinery involved in redox processes and, on the other hand, reduce the effectiveness of the antioxidant activity. Such dysregulation may lead to oxidative damage when combined with oxidative stress overpassing the cell capacity to detoxify ROS. In this work, a green fluorescent protein (GFP)-tagged nuclear factor erythroid 2-related factor 2 (NRF2)-regulated sulfiredoxin reporter (Srxn1-GFP) was used to measure the antioxidant response of HepG2 cells to a large series of drug and drug-like compounds (2230 compounds). These compounds were then classified as positive or negative depending on cellular response and distributed among different modeling groups to establish structure-activity relationship (SAR) models. A selection of models was used to prospectively predict oxidative stress induced by a new set of compounds subsequently experimentally tested to validate the model predictions. Altogether, this exercise exemplifies the different challenges of developing SAR models of a phenotypic cellular readout, model combination, chemical space selection, and results interpretation.

Knowledge graph aids comprehensive explanation of drug and chemical toxicity

In computational toxicology, prediction of complex endpoints has always been challenging, as they often involve multiple distinct mechanisms. State-of-the-art models are either limited by low accuracy, or lack of interpretability due to their black-box nature. Here, we introduce AIDTox, an interpretable deep learning model which incorporates curated knowledge of chemical-gene connections, gene-pathway annotations, and pathway hierarchy. AIDTox accurately predicts cytotoxicity outcomes in HepG2 and HEK293 cells. It also provides comprehensive explanations of cytotoxicity covering multiple aspects of drug activity, including target interaction, metabolism, and elimination. In summary, AIDTox provides a computational framework for unveiling cellular mechanisms for complex toxicity endpoints.

Identifying chemicals based on receptor binding/bioactivation/mechanistic explanation associated with potential to elicit hepatotoxicity and to support structure activity relationship-based read-across

The liver is the most common target organ in toxicology studies. The development of chemical structural alerts for identifying hepatotoxicity will play an important role in in silico model prediction and help strengthen the identification of analogs used in structure activity relationship (SAR)- based read-across. The aim of the current study is development of an SAR-based expert-system decision tree for screening of hepatotoxicants across a wide range of chemistry space and proposed modes of action for clustering of chemicals using defined core chemical categories based on receptor-binding or bioactivation. The decision tree is based on ∼ 1180 different chemicals that were reviewed for hepatotoxicity information. Knowledge of chemical receptor binding, metabolism and mechanistic information were used to group these chemicals into 16 different categories and 102 subcategories: four categories describe binders to 9 different receptors, 11 categories are associated with possible reactive metabolites (RMs) and there is one miscellaneous category. Each chemical subcategory has been associated with possible modes of action (MOAs) or similar key structural features. This decision tree can help to screen potential liver toxicants associated with core structural alerts of receptor binding and/or RMs and be used as a component of weight of evidence decisions based on SAR read-across, and to fill data gaps.

Risk assessment based on dose-responsive and time-responsive genes to build PLS-DA models for exogenously induced lung injury

Xenobiotics can easily harm human lungs owing to the openness of the respiratory system. Identifying pulmonary toxicity remains challenging owing to several reasons: 1) no biomarkers for pulmonary toxicity are available that might help to detect lung injury; 2) traditional animal experiments are time-consuming; 3) traditional detection methods solely focus on poisoning accidents; 4) analytical chemistry methods hardly achieve universal detection. An in vitro testing system able to identify the pulmonary toxicity of contaminants from food, the environment, and drugs is urgently needed. Compounds are virtually infinite, whereas toxicological mechanisms are countable. Therefore, universal methods to identify and predict the risks of contaminants can be designed based on these well-known toxicity mechanisms. In this study, we established a dataset based on transcriptome sequencing of A549 cells upon treatment with different compounds. The representativeness of our dataset was analyzed using bioinformatics methods. Artificial intelligence methods, namely partial least squares discriminant analysis (PLS-DA) models, were employed for toxicity prediction and toxicant identification. The developed model predicted the pulmonary toxicity of compounds with a 92 % accuracy. These models were submitted to an external validation using highly heterogeneous compounds, which supported the accuracy and robustness of our developed methodology. This assay exhibits universal potential applications for water quality monitoring, crop pollution detection, food and drug safety evaluation, as well as chemical warfare agent detection.

Effects of Class Imbalance and Data Scarcity on the Performance of Binary Classification Machine Learning Models Developed Based on ToxCast/Tox21 Assay Data

The development of toxicity classification models using the ToxCast database has been extensively studied. Machine learning approaches are effective in identifying the bioactivity of untested chemicals. However, ToxCast assays differ in the amount of data and degree of class imbalance (CI). Therefore, the resampling algorithm employed should vary depending on the data distribution to achieve optimal classification performance. In this study, the effects of CI and data scarcity (DS) on the performance of binary classification models were investigated using ToxCast bioassay data. An assay matrix based on CI and DS was prepared for 335 assays with biologically intended target information, and 28 CI assays and 3 DS assays were selected. Thirty models established by combining five molecular fingerprints (i.e., Morgan, MACCS, RDKit, Pattern, and Layered) and six algorithms [i.e., gradient boosting tree, random forest (RF), multi-layered perceptron, k-nearest neighbor, logistic regression, and naive Bayes] were trained using the selected assay data set. Of the 30 trained models, MACCS-RF showed the best performance and thus was selected for analyses of the effects of CI and DS. Results showed that recall and F1 were significantly lower when training with the CI assays than with the DS assays. In addition, hyperparameter tuning of the RF algorithm significantly improved F1 on CI assays. This study provided a basis for developing a toxicity classification model with improved performance by evaluating the effects of data set characteristics. This study also emphasized the importance of using appropriate evaluation metrics and tuning hyperparameters in model development.

Prioritization of chemicals in food for risk assessment by integrating exposure estimates and new approach methodologies: A next generation risk assessment case study

Next generation risk assessment is defined as a knowledge-driven system that allows for cost-efficient assessment of human health risk related to chemical exposure, without animal experimentation. One of the key features of next generation risk assessment is to facilitate prioritization of chemical substances that need a more extensive toxicological evaluation, in order to address the need to assess an increasing number of substances. In this case study focusing on chemicals in food, we explored how exposure data combined with the Threshold of Toxicological Concern (TTC) concept could be used to prioritize chemicals, both for existing substances and new substances entering the market. Using a database of existing chemicals relevant for dietary exposure we calculated exposure estimates, followed by application of the TTC concept to identify substances of higher concern. Subsequently, a selected set of these priority substances was screened for toxicological potential using high-throughput screening (HTS) approaches. Remarkably, this approach resulted in alerts for a selection of substances that are already on the market and represent relevant exposure in consumers. Taken together, the case study provides proof-of-principle for the approach taken to identify substances of concern, and this approach can therefore be considered a supportive element to a next generation risk assessment strategy.

Knowledge-guided deep learning models of drug toxicity improve interpretation

In drug development, a major reason for attrition is the lack of understanding of cellular mechanisms governing drug toxicity. The black-box nature of conventional classification models has limited their utility in identifying toxicity pathways. Here we developed DTox (deep learning for toxicology), an interpretation framework for knowledge-guided neural networks, which can predict compound response to toxicity assays and infer toxicity pathways of individual compounds. We demonstrate that DTox can achieve the same level of predictive performance as conventional models with a significant improvement in interpretability. Using DTox, we were able to rediscover mechanisms of transcription activation by three nuclear receptors, recapitulate cellular activities induced by aromatase inhibitors and pregnane X receptor (PXR) agonists, and differentiate distinctive mechanisms leading to HepG2 cytotoxicity. Virtual screening by DTox revealed that compounds with predicted cytotoxicity are at higher risk for clinical hepatic phenotypes. In summary, DTox provides a framework for deciphering cellular mechanisms of toxicity in silico.

On the Utility of ToxCast-Based Predictive Models to Evaluate Potential Metabolic Disruption by Environmental Chemicals

BACKGROUND

Research suggests environmental contaminants can impact metabolic health; however, high costs prohibit in vivo screening of putative metabolic disruptors. High-throughput screening programs, such as ToxCast, hold promise to reduce testing gaps and prioritize higher-order (in vivo) testing.

OBJECTIVES

We sought to a) examine the concordance of in vitro testing in 3T3-L1 cells to a targeted literature review for 38 semivolatile environmental chemicals, and b) assess the predictive utility of various expert models using ToxCast data against the set of 38 reference chemicals.

METHODS

Using a set of 38 chemicals with previously published results in 3T3-L1 cells, we performed a metabolism-targeted literature review to determine consensus activity determinations. To assess ToxCast predictive utility, we used two published ToxPi models: a) the 8-Slice model published by Janesick et al. (2016) and b) the 5-Slice model published by Auerbach et al. (2016). We examined the performance of the two models against the Janesick in vitro results and our own 38-chemical reference set. We further evaluated the predictive performance of various modifications to these models using cytotoxicity filtering approaches and validated our best-performing model with new chemical testing in 3T3-L1 cells.

RESULTS

The literature review revealed relevant publications for 30 out of the 38 chemicals (the remaining 8 chemicals were only examined in our previous 3T3-L1 testing). We observed a balanced accuracy (average of sensitivity and specificity) of 0.86 comparing our previous in vitro results to the literature-derived calls. ToxPi models provided balanced accuracies ranging from 0.55 to 0.88, depending on the model specifications and reference set. Validation chemical testing correctly predicted 29 of 30 chemicals as per 3T3-L1 testing, suggesting good adipogenic prediction performance for our best adapted model.

DISCUSSION

Using the most recent ToxCast data and an updated ToxPi model, we found ToxCast performed similarly to that of our own 3T3-L1 testing in predicting consensus calls. Furthermore, we provide the full ranked list of largely untested chemicals with ToxPi scores that predict adipogenic activity and that require further investigation. https://doi.org/10.1289/EHP6779.

Efficient Identification of Anti-SARS-CoV-2 Compounds Using Chemical Structure- and Biological Activity-Based Modeling

Identification of anti-SARS-CoV-2 compounds through traditional high-throughput screening (HTS) assays is limited by high costs and low hit rates. To address these challenges, we developed machine learning models to identify compounds acting via inhibition of the entry of SARS-CoV-2 into human host cells or the SARS-CoV-2 3-chymotrypsin-like (3CL) protease. The optimal classification models achieved good performance with area under the receiver operating characteristic curve (AUC-ROC) values of >0.78. Experimental validation showed that the best performing models increased the assay hit rate by 2.1-fold for viral entry inhibitors and 10.4-fold for 3CL protease inhibitors compared to those of the original drug repurposing screens. Twenty-two compounds showed potent (<5 μM) antiviral activities in a SARS-CoV-2 live virus assay. In conclusion, machine learning models can be developed and used as a complementary approach to HTS to expand compound screening capacities and improve the speed and efficiency of anti-SARS-CoV-2 drug discovery.

Machine Learning Models for Predicting Liver Toxicity

Liver toxicity is a major adverse drug reaction that accounts for drug failure in clinical trials and withdrawal from the market. Therefore, predicting potential liver toxicity at an early stage in drug discovery is crucial to reduce costs and the potential for drug failure. However, current in vivo animal toxicity testing is very expensive and time consuming. As an alternative approach, various machine learning models have been developed to predict potential liver toxicity in humans. This chapter reviews current advances in the development and application of machine learning models for prediction of potential liver toxicity in humans and discusses possible improvements to liver toxicity prediction.

In Silico Models for Hepatotoxicity

In this chapter, we review the state of the art of predicting human hepatotoxicity using in silico techniques. There has been significant progress in this area over the past 20 years but there are still some challenges ahead. Principally, these challenges are our partial understanding of a very complex biochemical system and our ability to emulate that in a predictive capacity. Here, we provide an overview of the published modeling approaches in this area to date and discuss their design, strengths and weaknesses. It is interesting to note the diversity in modeling approaches, whether they be statistical algorithms or evidenced-based approaches including structural alerts and pharmacophore models. Irrespective of modeling approach, it appears a common theme of access to appropriate, relevant, and high-quality data is a limitation to all and is likely to continue to be the focus of future research.

Joint Decision-Making Model Based on Consensus Modeling Technology for the Prediction of Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is the major cause of clinical trial failure and postmarketing withdrawals of approved drugs. It is very expensive and time-consuming to evaluate hepatotoxicity using animal or cell-based experiments in the early stage of drug development. In this study, an in silico model based on the joint decision-making strategy was developed for DILI assessment using a relatively large dataset of 2608 compounds. Five consensus models were developed with PaDEL descriptors and PubChem, Substructure, Estate, and Klekota–Roth fingerprints, respectively. Submodels for each consensus model were obtained through joint optimization. The parameters and features of each submodel were optimized jointly based on the hybrid quantum particle swarm optimization (HQPSO) algorithm. The application domain (AD) based on the frequency-weighted and distance (FWD)-based method and Tanimoto similarity index showed the wide AD of the qualified consensus models. A joint decision-making model was integrated by the qualified consensus models, and the overwhelming majority principle was used to improve the performance of consensus models. The application scope narrowing caused by the overwhelming majority principle was successfully solved by joint decision-making. The proposed model successfully predicted 99.2% of the compounds in the test set, with an accuracy of 80.0%, a sensitivity of 83.9, and a specificity of 73.3%. For an external validation set containing 390 compounds collected from DILIrank, 98.2% of the compounds were successfully predicted with an accuracy of 79.9%, a sensitivity of 97.1%, and a specificity of 66.0%. Furthermore, 25 privileged substructures responsible for DILI were identified from Substructure, PubChem, and Klekota–Roth fingerprints. These privileged substructures can be regarded as structural alerts in hepatotoxicity evaluation. Compared with the main published studies, our method exhibits certain advantage in data size, transparency, and standardization of the modeling process and accuracy and credibility of prediction results. It is a promising tool for virtual screening in the early stage of drug development.

TargetTox: A Feature Selection Pipeline for Identifying Predictive Targets Associated with Drug Toxicity

In silico assessment of drug toxicity is becoming a critical step in drug development. Conventional ligand-based models are limited by low accuracy and lack of interpretability. Further, they often fail to explain cellular mechanisms underlying structure-toxicity associations. We addressed these limitations by incorporating target profile as an intermediate connecting structure to toxicity. To accommodate for high-dimensional feature space, we developed a pipeline named TargetTox that can identity a subset of predictive features. We implemented TargetTox to study 569 targets and 815 adverse events. The features identified by TargetTox comprise less than 10% of the original feature space; nevertheless, they accurately predicted binding outcomes for 377 targets and toxicity outcomes for 36 adverse events. We demonstrated that predictive targets tend to be differentially expressed in the tissue of toxicity. We also rediscovered key cellular functions associated with cardiotoxicity from the predictive targets, as well as markers of skin and liver diseases. Furthermore, we found evidence supporting diagnostic and therapeutic applications of some predictive targets in hepatotoxicity and nephrotoxicity. Our findings highlighted the critical role of predictive targets in cellular mechanisms leading to toxicity. In general, our study improved the interpretability of toxicity prediction without sacrificing accuracy. Our novel pipeline may benefit future studies of high-dimensional data sets.

In silico approaches in organ toxicity hazard assessment: current status and future needs in predicting liver toxicity

Hepatotoxicity is one of the most frequently observed adverse effects resulting from exposure to a xenobiotic. For example, in pharmaceutical research and development it is one of the major reasons for drug withdrawals, clinical failures, and discontinuation of drug candidates. The development of faster and cheaper methods to assess hepatotoxicity that are both more sustainable and more informative is critically needed. The biological mechanisms and processes underpinning hepatotoxicity are summarized and experimental approaches to support the prediction of hepatotoxicity are described, including toxicokinetic considerations. The paper describes the increasingly important role of in silico approaches and highlights challenges to the adoption of these methods including the lack of a commonly agreed upon protocol for performing such an assessment and the need for in silico solutions that take dose into consideration. A proposed framework for the integration of in silico and experimental information is provided along with a case study describing how computational methods have been used to successfully respond to a regulatory question concerning non-genotoxic impurities in chemically synthesized pharmaceuticals.

A toxicogenomic data space for system-level understanding and prediction of EDC-induced toxicity

Endocrine disrupting compounds (EDCs) are a persistent threat to humans and wildlife due to their ability to interfere with endocrine signaling pathways. Inspired by previous work to improve chemical hazard identification through the use of toxicogenomics data, we developed a genomic-oriented data space for profiling the molecular activity of EDCs in an in silico manner, and for creating predictive models that identify and prioritize EDCs. Predictive models of EDCs, derived from gene expression data from rats (in vivo and in vitro primary hepatocytes) and humans (in vitro primary hepatocytes and HepG2), achieve testing accuracy greater than 90%. Negative test sets indicate that known safer chemicals are not predicted as EDCs. The rat in vivo-based classifiers achieve accuracy greater than 75% when tested for invitro to in vivoextrapolation. This study reveals key metabolic pathways and genes affected by EDCs together with a set of predictive models that utilize these pathways to prioritize EDCs in dose/time dependent manner and to predict EDCevokedmetabolic diseases.

AI in drug development: a multidisciplinary perspective

The introduction of a new drug to the commercial market follows a complex and long process that typically spans over several years and entails large monetary costs due to a high attrition rate. Because of this, there is an urgent need to improve this process using innovative technologies such as artificial intelligence (AI). Different AI tools are being applied to support all four steps of the drug development process (basic research for drug discovery; pre-clinical phase; clinical phase; and postmarketing). Some of the main tasks where AI has proven useful include identifying molecular targets, searching for hit and lead compounds, synthesising drug-like compounds and predicting ADME-Tox. This review, on the one hand, brings in a mathematical vision of some of the key AI methods used in drug development closer to medicinal chemists and, on the other hand, brings the drug development process and the use of different models closer to mathematicians. Emphasis is placed on two aspects not mentioned in similar surveys, namely, Bayesian approaches and their applications to molecular modelling and the eventual final use of the methods to actually support decisions. Promoting a perfect synergy.

Identification of average molecular weight (AMW) as a useful chemical descriptor to discriminate liver injury-inducing drugs

Drug-induced liver injury (DILI) is one of major causes of discontinuing drug development and withdrawing drugs from the market. In this study, we investigated chemical properties associated with DILI using in silico methods, to identify a physicochemical property useful for DILI screening at the early stages of drug development. Total of 652 drugs, including 432 DILI-positive drugs (DILI drugs) and 220 DILI-negative drugs (no-DILI drugs) were selected from Liver Toxicity Knowledge Base of US Food and Drug Administration. Decision tree models were constructed using 2,473 descriptors as explanatory variables. In the final model, the descriptor AMW, representing average molecular weight, was found to be at the first node and showed the highest importance value. With AMW alone, 276 DILI drugs (64%) and 156 no-DILI drugs (71%) were correctly classified. Discrimination with AMW was then performed using therapeutic category information. The performance of discrimination depended on the category and significantly high performance (>0.8 balanced accuracy) was obtained in some categories. Taken together, the present results suggest AMW as a novel descriptor useful for detecting drugs with DILI risk. The information presented may be valuable for the safety assessment of drug candidates at the early stage of drug development.

Mechanism-Driven Read-Across of Chemical Hepatotoxicants Based on Chemical Structures and Biological Data

Hepatotoxicity is a leading cause of attrition in the drug development process. Traditional preclinical and clinical studies to evaluate hepatotoxicity liabilities are expensive and time consuming. With the advent of critical advancements in high-throughput screening, there has been a rapid accumulation of in vitro toxicity data available to inform the risk assessment of new pharmaceuticals and chemicals. To this end, we curated and merged all available in vivo hepatotoxicity data obtained from the literature and public resources, which yielded a comprehensive database of 4089 compounds that includes hepatotoxicity classifications. After dividing the original database of chemicals into modeling and test sets, PubChem assay data were automatically extracted using an in-house data mining tool and clustered based on relationships between structural fragments and cellular responses in in vitro assays. The resultant PubChem assay clusters were further investigated. During the cross-validation procedure, the biological data obtained from several assay clusters exhibited high predictivity of hepatotoxicity and these assays were selected to evaluate the test set compounds. The read-across results indicated that if a new compound contained specific identified chemical fragments (ie, Molecular Initiating Event) and showed active responses in the relevant selected PubChem assays, there was potential for the chemical to be hepatotoxic in vivo. Furthermore, several mechanisms that might contribute to toxicity were derived from the modeling results including alterations in nuclear receptor signaling and inhibition of DNA repair. This modeling strategy can be further applied to the investigation of other complex chemical toxicity phenomena (eg, developmental and reproductive toxicities) as well as drug efficacy.

Predictive modeling of biological responses in the rat liver using in vitro Tox21 bioactivity: Benefits from high-throughput toxicokinetics

Computational methods are needed to more efficiently leverage data from in vitro cell-based models to predict what occurs within whole body systems after chemical insults. This study set out to test the hypothesis that in vitro high-throughput screening (HTS) data can more effectively predict in vivo biological responses when chemical disposition and toxicokinetic (TK) modeling are employed. In vitro HTS data from the Tox21 consortium were analyzed in concert with chemical disposition modeling to derive nominal, aqueous, and intracellular estimates of concentrations eliciting 50% maximal activity. In vivo biological responses were captured using rat liver transcriptomic data from the DrugMatrix and TG-Gates databases and evaluated for pathway enrichment. In vivo dosing data were translated to equivalent body concentrations using HTTK modeling. Random forest models were then trained and tested to predict in vivo pathway-level activity across 221 chemicals using in vitro bioactivity data and physicochemical properties as predictor variables, incorporating methods to address imbalanced training data resulting from high instances of inactivity. Model performance was quantified using the area under the receiver operator characteristic curve (AUC-ROC) and compared across pathways for different combinations of predictor variables. All models that included toxicokinetics were found to outperform those that excluded toxicokinetics. Biological interpretation of the model features revealed that rather than a direct mapping of in vitro assays to in vivo pathways, unexpected combinations of multiple in vitro assays predicted in vivo pathway-level activities. To demonstrate the utility of these findings, the highest-performing model was leveraged to make new predictions of in vivo biological responses across all biological pathways for remaining chemicals tested in Tox21 with adequate data coverage (n = 6617). These results demonstrate that, when chemical disposition and toxicokinetics are carefully considered, in vitro HT screening data can be used to effectively predict in vivo biological responses to chemicals.

Comparison of Cellular Morphological Descriptors and Molecular Fingerprints for the Prediction of Cytotoxicity- and Proliferation-Related Assays

Cell morphology features, such as those from the Cell Painting assay, can be generated at relatively low costs and represent versatile biological descriptors of a system and thereby compound response. In this study, we explored cell morphology descriptors and molecular fingerprints, separately and in combination, for the prediction of cytotoxicity- and proliferation-related in vitro assay endpoints. We selected 135 compounds from the MoleculeNet ToxCast benchmark data set which were annotated with Cell Painting readouts, where the relatively small size of the data set is due to the overlap of required annotations. We trained Random Forest classification models using nested cross-validation and Cell Painting descriptors, Morgan and ErG fingerprints, and their combinations. While using leave-one-cluster-out cross-validation (with clusters based on physicochemical descriptors), models using Cell Painting descriptors achieved higher average performance over all assays (Balanced Accuracy of 0.65, Matthews Correlation Coefficient of 0.28, and AUC-ROC of 0.71) compared to models using ErG fingerprints (BA 0.55, MCC 0.09, and AUC-ROC 0.60) and Morgan fingerprints alone (BA 0.54, MCC 0.06, and AUC-ROC 0.56). While using random shuffle splits, the combination of Cell Painting descriptors with ErG and Morgan fingerprints further improved balanced accuracy on average by 8.9% (in 9 out of 12 assays) and 23.4% (in 8 out of 12 assays) compared to using only ErG and Morgan fingerprints, respectively. Regarding feature importance, Cell Painting descriptors related to nuclei texture, granularity of cells, and cytoplasm as well as cell neighbors and radial distributions were identified to be most contributing, which is plausible given the endpoint considered. We conclude that cell morphological descriptors contain complementary information to molecular fingerprints which can be used to improve the performance of predictive cytotoxicity models, in particular in areas of novel structural space.

Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure

BACKGROUND

Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure. However, these models do not yet show sufficient predictive performance or interpretability to be useful for decision making by themselves, the former partially stemming from the underlying problem of labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models.

RESULTS

As part of the Critical Assessment of Massive Data Analysis (CAMDA) "CMap Drug Safety Challenge" 2019 ( http://camda2019.bioinf.jku.at ), chemical structure-based models were generated using the binarized DILIrank annotations. Support Vector Machine (SVM) and Random Forest (RF) classifiers showed comparable performance to previously published models with a mean balanced accuracy over models generated using 5-fold LOCO-CV inside a 10-fold training scheme of 0.759 ± 0.027 when predicting an external test set. In the models which used predicted protein targets as compound descriptors, we identified the most information-rich proteins which agreed with the mechanisms of action and toxicity of nonsteroidal anti-inflammatory drugs (NSAIDs), one of the most important drug classes causing DILI, stress response via TP53 and biotransformation. In addition, we identified multiple proteins involved in xenobiotic metabolism which could be novel DILI-related off-targets, such as CLK1 and DYRK2. Moreover, we derived potential structural alerts for DILI with high precision, including furan and hydrazine derivatives; however, all derived alerts were present in approved drugs and were over specific indicating the need to consider quantitative variables such as dose.

CONCLUSION

Using chemical structure-based descriptors such as structural fingerprints and predicted protein targets, DILI prediction models were built with a predictive performance comparable to previous literature. In addition, we derived insights on proteins and pathways statistically (and potentially causally) linked to DILI from these models and inferred new structural alerts related to this adverse endpoint.

Machine Learning in Predictive Toxicology: Recent Applications and Future Directions for Classification Models

In recent times, machine learning has become increasingly prominent in predictive toxicology as it has shifted from in vivo studies toward in silico studies. Currently, in vitro methods together with other computational methods such as quantitative structure-activity relationship modeling and absorption, distribution, metabolism, and excretion calculations are being used. An overview of machine learning and its applications in predictive toxicology is presented here, including support vector machines (SVMs), random forest (RF) and decision trees (DTs), neural networks, regression models, naïve Bayes, k-nearest neighbors, and ensemble learning. The recent successes of these machine learning methods in predictive toxicology are summarized, and a comparison of some models used in predictive toxicology is presented. In predictive toxicology, SVMs, RF, and DTs are the dominant machine learning methods due to the characteristics of the data available. Lastly, this review describes the current challenges facing the use of machine learning in predictive toxicology and offers insights into the possible areas of improvement in the field.

Probing the Mechanism of Hepatotoxicity of Hexabromocyclododecanes through Toxicological Network Analysis

The prediction and mechanism analysis of hepatotoxicity of contaminants, because of their various phenotypes and complex mechanisms, is still a key problem in environmental research. We applied a toxicological network analysis method to predict the hepatotoxicity of three hexabromocyclododecane (HBCD) diastereoisomers (α-HBCD, β-HBCD, and γ-HBCD) and explore their potential mechanisms. First, we collected the hepatotoxicity related genes and found that those genes were significantly localized in the human interactome. Therefore, these genes form a disease module of hepatotoxicity. We also collected targets of α-, β-, and γ-HBCD and found that their targets overlap with the hepatotoxicity disease module. Then, we trained a model to predict hepatotoxicity of three HBCD diastereoisomers based on the relationship between the hepatotoxicity disease module and targets of compounds. We found that 593 genes were significantly located in the hepatotoxicity disease module (Z = 11.9, p < 0.001) involved in oxidative stress, cellular immunity, and proliferation, and the accuracy of hepatotoxicity prediction of HBCD was 0.7095 ± 0.0193 and the recall score was 0.8355 ± 0.0352. HBCD mainly affects the core disease module genes to mediate the adenosine monophosphate-activated kinase, p38MAPK, PI3K/Akt, and TNFα pathways to regulate the immune reaction and inflammation. HBCD also induces the secretion of IL6 and STAT3 to lead hepatotoxicity by regulating NR3C1. This approach is transferable to other toxicity research studies of environmental pollutants.

Development of a Nicotinic Acetylcholine Receptor nAChR α7 Binding Activity Prediction Model

Despite the well-known adverse health effects associated with tobacco use, addiction to nicotine found in tobacco products causes difficulty in quitting among users. Nicotinic acetylcholine receptors (nAChRs) are the physiological targets of nicotine and facilitate addiction to tobacco products. The nAChR-α7 subtype plays an important role in addiction; therefore, predicting the binding activity of tobacco constituents to nAChR-α7 is an important component for assessing addictive potential of tobacco constituents. We developed an α7 binding activity prediction model based on a large training data set of 843 chemicals with human α7 binding activity data extracted from PubChem and ChEMBL. The model was tested using 1215 chemicals with rat α7 binding activity data from the same databases. Based on the competitive docking results, the docking scores were partitioned to the key residues that play important roles in the receptor-ligand binding. A decision forest was used to train the human α7 binding activity prediction model based on the partition of docking scores. Five-fold cross validations were conducted to estimate the performance of the decision forest models. The developed model was used to predict the potential human α7 binding activity for 5275 tobacco constituents. The human α7 binding activity data for 84 of the 5275 tobacco constituents were experimentally measured to confirm and empirically validate the prediction results. The prediction accuracy, sensitivity, and specificity were 64.3, 40.0, and 81.6%, respectively. The developed prediction model of human α7 may be a useful tool for high-throughput screening of potential addictive tobacco constituents.

KnowTox: pipeline and case study for confident prediction of potential toxic effects of compounds in early phases of development

Risk assessment of newly synthesised chemicals is a prerequisite for regulatory approval. In this context, in silico methods have great potential to reduce time, cost, and ultimately animal testing as they make use of the ever-growing amount of available toxicity data. Here, KnowTox is presented, a novel pipeline that combines three different in silico toxicology approaches to allow for confident prediction of potentially toxic effects of query compounds, i.e. machine learning models for 88 endpoints, alerts for 919 toxic substructures, and computational support for read-across. It is mainly based on the ToxCast dataset, containing after preprocessing a sparse matrix of 7912 compounds tested against 985 endpoints. When applying machine learning models, applicability and reliability of predictions for new chemicals are of utmost importance. Therefore, first, the conformal prediction technique was deployed, comprising an additional calibration step and per definition creating internally valid predictors at a given significance level. Second, to further improve validity and information efficiency, two adaptations are suggested, exemplified at the androgen receptor antagonism endpoint. An absolute increase in validity of 23% on the in-house dataset of 534 compounds could be achieved by introducing KNNRegressor normalisation. This increase in validity comes at the cost of efficiency, which could again be improved by 20% for the initial ToxCast model by balancing the dataset during model training. Finally, the value of the developed pipeline for risk assessment is discussed using two in-house triazole molecules. Compared to a single toxicity prediction method, complementing the outputs of different approaches can have a higher impact on guiding toxicity testing and de-selecting most likely harmful development-candidate compounds early in the development process.

Development of AOP relevant to microplastics based on toxicity mechanisms of chemical additives using ToxCast™ and deep learning models combined approach

Various additives are used in plastic products to improve the properties and the durability of the plastics. Their possible elution from the plastics when plastics are fragmented into micro- and nano-size in the environment is suspected to one of the major contributors to environmental and human toxicity of microplastics. In this context, to better understand the hazardous effect of microplastics, the toxicity of chemical additives was investigated. Fifty most common chemicals presented in plastics were selected as target additives. Their toxicity was systematically identified using apical and molecular toxicity databases, such as ChemIDplus and ToxCast™. Among the vast ToxCast assays, those having intended gene targets were selected for identification of the mechanism of toxicity of plastic additives. Deep learning artificial neural network models were further developed based on the ToxCast assays for the chemicals not tested in the ToxCast program. Using both the ToxCast database and deep learning models, active chemicals on each ToxCast assays were identified. Through correlation analysis between molecular targets from ToxCast and mammalian toxicity results from ChemIDplus, we identified the fifteen most relevant mechanisms of toxicity for the understanding mechanism of toxicity of plastic additives. They are neurotoxicity, inflammation, lipid metabolism, and cancer pathways. Based on these, along with, previously conducted systemic review on the mechanism of toxicity of microplastics, here we have proposed potential adverse outcome pathways (AOPs) relevant to microplastics pollution. This study also suggests in vivo and in vitro toxicity database and deep learning model combined approach is appropriate to provide insight into the toxicity mechanism of the broad range of environmental chemicals, such as plastic additives.

Predictive Models for Human Organ Toxicity Based on In Vitro Bioactivity Data and Chemical Structure

Traditional toxicity testing reliant on animal models is costly and low throughput, posing a significant challenge with the increasing numbers of chemicals that humans are exposed to in the environment. The purpose of this investigation was to build optimal prediction models for various human in vivo/organ-level toxicity end points (extracted from ChemIDPlus) using chemical structure and Tox21 in vitro quantitative high-throughput screening (qHTS) bioactivity assay data. Several supervised machine learning algorithms were applied to model 14 human toxicity end points pertaining to vascular, kidney, ureter and bladder, and liver organ systems. Three metrics were used to evaluate model performance: area under the receiver operating characteristic curve (AUC-ROC), balanced accuracy (BA), and Matthews correlation coefficient (MCC). The top four models, with AUC-ROC values >0.8, were derived for endocrine (0.90 ± 0.00), musculoskeletal (0.88 ± 0.02), peripheral nerve and sensation (0.85 ± 0.01), and brain and coverings (0.83 ± 0.02) toxicities, whereas the best model AUC-ROC values were >0.7 for the remaining 10 toxicities. Model performance was found to be dependent on the specific data set, model type, and feature selection method used. In addition, chemical structure and assay data showed different levels of contribution to the prediction of different toxicity end points. Although in vitro assay data, when combined with chemical structure, slightly improved the predictive accuracy for most end points (11 out of 14), a noteworthy finding was the near equal success of the structure-only models, which do not require Tox21 qHTS screening data, and the relatively poor performance of assay-only models. Thus, the top-performing structure-only models from this study could be applied for hazard screening of large sets of chemicals for potential human toxicity, whereas the largest assay contributions to models (i.e., cellular targets) could be used, along with the top-contributing structural features, to provide insight into toxicity mechanisms.

A Case Study with Triazole Fungicides to Explore Practical Application of Next-Generation Hazard Assessment Methods for Human Health

The ongoing developments in chemical risk assessment have led to new concepts building on integration of sophisticated nonanimal models for hazard characterization. Here we explore a pragmatic approach for implementing such concepts, using a case study of three triazole fungicides, namely, flusilazole, propiconazole, and cyproconazole. The strategy applied starts with evaluating the overall level of concern by comparing exposure estimates to toxicological potential, followed by a combination of in silico tools and literature-derived high-throughput screening assays and computational elaborations to obtain insight into potential toxicological mechanisms and targets in the organism. Additionally, some targeted in vitro tests were evaluated for their utility to confirm suspected mechanisms of toxicity and to generate points of departure. Toxicological mechanisms instead of the current "end point-by-end point" approach should guide the selection of methods and assays that constitute a toolbox for next-generation risk assessment. Comparison of the obtained in silico and in vitro results with data from traditional in vivo testing revealed that, overall, nonanimal methods for hazard identification can produce adequate qualitative hazard information for risk assessment. Follow-up studies are needed to further refine the proposed approach, including the composition of the toolbox, toxicokinetics models, and models for exposure assessment.

Artificial Intelligence for chemical risk assessment

As the basis for managing the risks of chemical exposure, the Chemical Risk Assessment (CRA) process can impact a substantial part of the economy, the health of hundreds of millions of people, and the condition of the environment. However, the number of properly assessed chemicals falls short of societal needs due to a lack of experts for evaluation, interference of third party interests, and the sheer volume of potentially relevant information on the chemicals from disparate sources. In order to explore ways in which computational methods may help overcome this discrepancy between the number of chemical risk assessments required on the one hand and the number and adequateness of assessments actually being conducted on the other, the European Commission's Joint Research Centre organised a workshop on Artificial Intelligence for Chemical Risk Assessment (AI4CRA). The workshop identified a number of areas where Artificial Intelligence could potentially increase the number and quality of regulatory risk management decisions based on CRA, involving process simulation, supporting evaluation, identifying problems, facilitating collaboration, finding experts, evidence gathering, systematic review, knowledge discovery, and building cognitive models. Although these are interconnected, they are organised and discussed under two main themes: scientific-technical process and social aspects and the decision making process.

Synthesis and preliminary hepatotoxicity evaluation of new caffeine-8-(2-thio)-propanoic hydrazid-hydrazone derivatives

New series of caffeine-8-(2-thio)-propanoic hydrazid-hydrazone derivatives were designed and synthesized. The targed compounds were obtained in yields of 51 to 96% and their structures were elucidated by FTIR,1H NMR,13C NMR, MS and microanalyses. All of the compounds were found to be “drug-like” as they fulfill the criteria of drug-likeness, which includes the MDDR-like rule. The tested compounds were subjected toin silicoprediction of substrate/metabolite specificity and Drug Induced Liver Injury (DILI). The prediction for indicated that the evaluated compounds would most probably act as CYP1A2 substrates. The performedin vitrostudies didn’t reveal statistically significant hepatotoxicity of the tested compounds, probably due to the pro-oxidant effects expressed on sub-cellular (isolated rat liver microsomes) level. The obtained experimental results confirmed the predicted low hepatotoxicity for the tested structures. Based on these results the compounds may be considered as promising structures for design of future molecules with low hepatotoxicity.

Progress in data interoperability to support computational toxicology and chemical safety evaluation

New approach methodologies (NAMs) in chemical safety evaluation are being explored to address the current public health implications of human environmental exposures to chemicals with limited or no data for assessment. For over a decade since a push toward "Toxicity Testing in the 21st Century," the field has focused on massive data generation efforts to inform computational approaches for preliminary hazard identification, adverse outcome pathways that link molecular initiating events and key events to apical outcomes, and high-throughput approaches to risk-based ratios of bioactivity and exposure to inform relative priority and safety assessment. Projects like the interagency Tox21 program and the US EPA ToxCast program have generated dose-response information on thousands of chemicals, identified and aggregated information from legacy systems, and created tools for access and analysis. The resulting information has been used to develop computational models as viable options for regulatory applications. This progress has introduced challenges in data management that are new, but not unique, to toxicology. Some of the key questions require critical thinking and solutions to promote semantic interoperability, including: (1) identification of bioactivity information from NAMs that might be related to a biological process; (2) identification of legacy hazard information that might be related to a key event or apical outcomes of interest; and, (3) integration of these NAM and traditional data for computational modeling and prediction of complex apical outcomes such as carcinogenesis. This work reviews a number of toxicology-related efforts specifically related to bioactivity and toxicological data interoperability based on the goals established by Findable, Accessible, Interoperable, and Reusable (FAIR) Data Principles. These efforts are essential to enable better integration of NAM and traditional toxicology information to support data-driven toxicology applications.

ToxRefDB version 2.0: Improved utility for predictive and retrospective toxicology analyses

The Toxicity Reference Database (ToxRefDB) structures information from over 5000 in vivo toxicity studies, conducted largely to guidelines or specifications from the US Environmental Protection Agency and the National Toxicology Program, into a public resource for training and validation of predictive models. Herein, ToxRefDB version 2.0 (ToxRefDBv2) development is described. Endpoints were annotated (e.g. required, not required) according to guidelines for subacute, subchronic, chronic, developmental, and multigenerational reproductive designs, distinguishing negative responses from untested. Quantitative data were extracted, and dose-response modeling for nearly 28,000 datasets from nearly 400 endpoints using Benchmark Dose (BMD) Modeling Software were generated and stored. Implementation of controlled vocabulary improved data quality; standardization to guideline requirements and cross-referencing with United Medical Language System (UMLS) connects ToxRefDBv2 observations to vocabularies linked to UMLS, including PubMed medical subject headings. ToxRefDBv2 allows for increased connections to other resources and has greatly enhanced quantitative and qualitative utility for predictive toxicology.

ProTox-II: a webserver for the prediction of toxicity of chemicals

Advancement in the field of computational research has made it possible for the in silico methods to offer significant benefits to both regulatory needs and requirements for risk assessments, and pharmaceutical industry to assess the safety profile of a chemical. Here, we present ProTox-II that incorporates molecular similarity, pharmacophores, fragment propensities and machine-learning models for the prediction of various toxicity endpoints; such as acute toxicity, hepatotoxicity, cytotoxicity, carcinogenicity, mutagenicity, immunotoxicity, adverse outcomes pathways (Tox21) and toxicity targets. The predictive models are built on data from both in vitro assays (e.g. Tox21 assays, Ames bacterial mutation assays, hepG2 cytotoxicity assays, Immunotoxicity assays) and in vivo cases (e.g. carcinogenicity, hepatotoxicity). The models have been validated on independent external sets and have shown strong performance. ProTox-II provides a freely available webserver for in silico toxicity prediction for toxicologists, regulatory agencies, computational and medicinal chemists, and all users without login at http://tox.charite.de/protox_II. The webserver takes a two-dimensional chemical structure as an input and reports the possible toxicity profile of the chemical for 33 models with confidence scores, and an overall toxicity radar chart along with three most similar compounds with known acute toxicity.

The Next Generation Blueprint of Computational Toxicology at the U.S. Environmental Protection Agency

The U.S. Environmental Protection Agency (EPA) is faced with the challenge of efficiently and credibly evaluating chemical safety often with limited or no available toxicity data. The expanding number of chemicals found in commerce and the environment, coupled with time and resource requirements for traditional toxicity testing and exposure characterization, continue to underscore the need for new approaches. In 2005, EPA charted a new course to address this challenge by embracing computational toxicology (CompTox) and investing in the technologies and capabilities to push the field forward. The return on this investment has been demonstrated through results and applications across a range of human and environmental health problems, as well as initial application to regulatory decision-making within programs such as the EPA's Endocrine Disruptor Screening Program. The CompTox initiative at EPA is more than a decade old. This manuscript presents a blueprint to guide the strategic and operational direction over the next 5 years. The primary goal is to obtain broader acceptance of the CompTox approaches for application to higher tier regulatory decisions, such as chemical assessments. To achieve this goal, the blueprint expands and refines the use of high-throughput and computational modeling approaches to transform the components in chemical risk assessment, while systematically addressing key challenges that have hindered progress. In addition, the blueprint outlines additional investments in cross-cutting efforts to characterize uncertainty and variability, develop software and information technology tools, provide outreach and training, and establish scientific confidence for application to different public health and environmental regulatory decisions.

Using the concordance of in vitro and in vivo data to evaluate extrapolation assumptions

Linking in vitro bioactivity and in vivo toxicity on a dose basis enables the use of high-throughput in vitro assays as an alternative to traditional animal studies. In this study, we evaluated assumptions in the use of a high-throughput, physiologically based toxicokinetic (PBTK) model to relate in vitro bioactivity and rat in vivo toxicity data. The fraction unbound in plasma (f_up) and intrinsic hepatic clearance (Cl_int) were measured for rats (for 67 and 77 chemicals, respectively), combined with f_up and Cl_int literature data for 97 chemicals, and incorporated in the PBTK model. Of these chemicals, 84 had corresponding in vitro ToxCast bioactivity data and in vivo toxicity data. For each possible comparison of in vitro and in vivo endpoint, the concordance between the in vivo and in vitro data was evaluated by a regression analysis. For a base set of assumptions, the PBTK results were more frequently better associated than either the results from a “random” model parameterization or direct comparison of the “untransformed” values of AC₅₀ and dose (performed best in 51%, 28%, and 21% of cases, respectively). We also investigated several assumptions in the application of PBTK for IVIVE, including clearance and internal dose selection. One of the better assumptions sets–restrictive clearance and comparing free in vivo venous plasma concentration with free in vitro concentration–outperformed the random and untransformed results in 71% of the in vitro-in vivo endpoint comparisons. These results demonstrate that applying PBTK improves our ability to observe the association between in vitro bioactivity and in vivo toxicity data in general. This suggests that potency values from in vitro screening should be transformed using in vitro-in vivo extrapolation (IVIVE) to build potentially better machine learning and other statistical models for predicting in vivo toxicity in humans.

Improving the Utility of the Tox21 Dataset by Deep Metadata Annotations and Constructing Reusable Benchmarked Chemical Reference Signatures

The Toxicology in the 21st Century (Tox21) project seeks to develop and test methods for high-throughput examination of the effect certain chemical compounds have on biological systems. Although primary and toxicity assay data were readily available for multiple reporter gene modified cell lines, extensive annotation and curation was required to improve these datasets with respect to how FAIR (Findable, Accessible, Interoperable, and Reusable) they are. In this study, we fully annotated the Tox21 published data with relevant and accepted controlled vocabularies. After removing unreliable data points, we aggregated the results and created three sets of signatures reflecting activity in the reporter gene assays, cytotoxicity, and selective reporter gene activity, respectively. We benchmarked these signatures using the chemical structures of the tested compounds and obtained generally high receiver operating characteristic (ROC) scores, suggesting good quality and utility of these signatures and the underlying data. We analyzed the results to identify promiscuous individual compounds and chemotypes for the three signature categories and interpreted the results to illustrate the utility and re-usability of the datasets. With this study, we aimed to demonstrate the importance of data standards in reporting screening results and high-quality annotations to enable re-use and interpretation of these data. To improve the data with respect to all FAIR criteria, all assay annotations, cleaned and aggregate datasets, and signatures were made available as standardized dataset packages (Aggregated Tox21 bioactivity data, 2019).

Development of quantitative structure-activity relationship models to predict potential nephrotoxic ingredients in traditional Chinese medicines

The broad use of traditional Chinese medicines (TCMs) and the accompanied incidences of kidney injury have attracted considerable interest in investigating the responsible toxic ingredients. It is challenging to evaluate toxicity of TCMs since they contain complex mixtures of phytochemicals. Quantitative structure-activity relationship (QSAR) is an efficient tool to predict toxicity and QSAR study on TCMs-induced nephrotoxicity remains lacked. We developed QSAR models using three datasets of 609 compounds: natural products, drugs, and mixed (contained both kinds of data) datasets. Each dataset was used for modelling by utilizing artificial neural networks (ANN) and support vector machines (SVM) algorithms separately. Both internal and external validations were performed on each model. Six QSAR models were developed and yielded reliable performance in the internal validation. For external validation, 30 ingredients in the TCMs were predicted well by the natural product models (accuracy: ANN 96.7%, SVM 93.3%). The mixed models (accuracy: ANN 76.7%, SVM 66.7%) showed a better performance than the drug models (accuracy: ANN 50%, SVM 53.3%). Particularly, natural product models produced the most reliable results. It has the application not only on screening the nephrotoxic ingredients in TCMs, but it is also helpful at prioritizing the subsequent toxicity testing of natural products.

Stacked Generalization with Applicability Domain Outperforms Simple QSAR on in Vitro Toxicological Data

The development of in silico tools able to predict bioactivity and toxicity of chemical substances is a powerful solution envisioned to assess toxicity as early as possible. To enable the development of such tools, the ToxCast program has generated and made publicly available in vitro bioactivity data for thousands of compounds. The goal of the present study is to characterize and explore the data from ToxCast in terms of Machine Learning capability. For this, a large scale analysis on the entire database has been performed to build models to predict bioactivities measured in in vitro assays. Simple classical QSAR algorithms (ANN, SVM, LDA, random forest, and Bayesian) were first applied on the data, and the results of these algorithms suggested that they do not seem to be well-suited for data sets with a high proportion of inactive compounds. The study then showed for the first time that the use of an ensemble method named "Stacked generalization" could improve the model performance on this type of data. Indeed, for 61% of 483 models, the Stacked method led to models with higher performance. Moreover, the combination of this ensemble method with an applicability domain filter allows one to assess the reliability of the predictions for further compound prioritization. In particular we showed that for 50% of the models, the ROC score is better if we do not consider the compounds that are not within the applicability domain.

In Silico Prediction of Chemical-Induced Hepatocellular Hypertrophy Using Molecular Descriptors

In silico prediction for toxicity of chemicals is required to reduce cost, time, and animal testing. However, predicting hepatocellular hypertrophy, which often affects the derivation of the No-Observed-Adverse-Effect Level in repeated dose toxicity studies, is difficult because pathological findings are diverse, mechanisms are largely unknown, and a wide variety of chemical structures exists. Therefore, a method for predicting the hepatocellular hypertrophy of diverse chemicals without complete understanding of their mechanisms is necessary. In this study, we developed predictive classification models of hepatocellular hypertrophy using machine learning-specifically, deep learning, random forest, and support vector machine. We extracted hepatocellular hypertrophy data on rats from 2 toxicological databases, our original database developed from risk assessment reports such as pesticides, and the Hazard Evaluation Support System Integrated Platform. Then, we constructed prediction models based on molecular descriptors and evaluated their performance using independent test chemicals datasets, which differed from the training chemicals datasets. Further, we defined the applicability domain (AD), which generally limits the application for chemicals, as structurally similar to the training chemicals dataset. The best model was found to be the support vector machine model using the Hazard Evaluation Support System Integrated Platform dataset, which was trained with 251 chemicals and predicted 214 test chemicals inside the applicability domain. It afforded a prediction accuracy of 0.76, sensitivity of 0.90, and area under the curve of 0.81. These in silico predictive classification models could be reliable tools for hepatocellular hypertrophy assessments and can facilitate the development of in silico models for toxicity prediction.