Infer the in vivo point of departure with ToxCast in vitro assay data using a robust learning approach

Predictive value of the ToxCast/Tox21 high throughput toxicity screening data for approximating in vivo ecotoxicity endpoints and ecotoxicological risk in eco- surveillance applications

Ecotoxicology has long relied on assessing the hazard potential of chemicals through traditional in vivo testing methods to understand the possible risk exposure could pose to ecological taxa. In the past decade, the development of non-animal new approach methods (NAMs) for assessing chemical hazard and risk has quickly grown. These methods are often cheaper and faster than traditional toxicity testing, and thus are amenable to high-throughput toxicity testing (HTT), resulting in large datasets. The ToxCast/Tox21 HTT programs have produced in vitro data for thousands of chemicals covering a large space of biological activity. The relevance of these data to in vivo mammalian toxicity has been much explored. Interest has also grown in using these data to evaluate the risk of environmental exposures to taxa of ecological importance such as fish, aquatic invertebrates, etc.; particularly for the purpose of estimating the risk of exposure from real-world complex mixtures. Understanding the relationship and relative sensitivity of NAMs versus standardized ecotoxicological whole organism models is a key component of performing reliable read-across from mammalian in vitro data to ecotoxicological in vivo data. In this work, we explore the relationship between in vivo ecotoxicity data from several publicly available databases and the ToxCast/Tox21 data. We also performed several case studies in which we compare how using different ecotoxicity datasets, whether traditional or ToxCast-based, affects risk conclusions based on exposure to complex mixtures derived from existing large-scale chemical monitoring data. Generally, predictive value of ToxCast data for traditional in vivo endpoints (EPs) was poor (r ≤ 0.3). Risk conclusions, including identification of different chemical risk drivers and prioritized monitoring sites, were different when using HTT data vs. traditional in vivo data.

A novel multi-omics data analysis of dose-dependent and temporal changes in regulatory pathways due to chemical perturbation: a case study on caffeine

Comprehensive analysis of multi-omics data can reveal alterations in regulatory pathways induced by cellular exposure to chemicals by characterizing biological processes at the molecular level. Data-driven omics analysis, conducted in a dose-dependent or dynamic manner, can facilitate comprehending toxicity mechanisms. This study introduces a novel multi-omics data analysis designed to concurrently examine dose-dependent and temporal patterns of cellular responses to chemical perturbations. This analysis, encompassing preliminary exploration, pattern deconstruction, and network reconstruction of multi-omics data, provides a comprehensive perspective on the dynamic behaviors of cells exposed to varying levels of chemical stimuli. Importantly, this analysis is adaptable to any number of omics layers, including site-specific phosphoproteomics. We implemented this analysis on multi-omics data obtained from HepG2 cells exposed to a range of caffeine doses over varying durations and identified six response patterns, along with their associated biomolecules and pathways. Our study demonstrates the effectiveness of the proposed multi-omics data analysis in capturing multidimensional patterns of cellular response to chemical perturbation, enhancing understanding of pathway regulation for chemical risk assessment.

Exploring the effects of experimental parameters and data modeling approaches on in vitro transcriptomic point-of-departure estimates

Multiple new approach methods (NAMs) are being developed to rapidly screen large numbers of chemicals to aid in hazard evaluation and risk assessments. High-throughput transcriptomics (HTTr) in human cell lines has been proposed as a first-tier screening approach for determining the types of bioactivity a chemical can cause (activation of specific targets vs. generalized cell stress) and for calculating transcriptional points of departure (tPODs) based on changes in gene expression. In the present study, we examine a range of computational methods to calculate tPODs from HTTr data, using six data sets in which MCF7 cells cultured in two different media formulations were treated with a panel of 44 chemicals for 3 different exposure durations (6, 12, 24 hr). The tPOD calculation methods use data at the level of individual genes and gene set signatures, and compare data processed using the ToxCast Pipeline 2 (tcplfit2), BMDExpress and PLIER (Pathway Level Information ExtractoR). Methods were evaluated by comparing to in vitro PODs from a validated set of high-throughput screening (HTS) assays for a set of estrogenic compounds. Key findings include: (1) for a given chemical and set of experimental conditions, tPODs calculated by different methods can vary by several orders of magnitude; (2) tPODs are at least as sensitive to computational methods as to experimental conditions; (3) in comparison to an external reference set of PODs, some methods give generally higher values, principally PLIER and BMDExpress; and (4) the tPODs from HTTr in this one cell type are mostly higher than the overall PODs from a broad battery of targeted in vitro ToxCast assays, reflecting the need to test chemicals in multiple cell types and readout technologies for in vitro hazard screening.

Machine Learning-Based Hazard-Driven Prioritization of Features in Nontarget Screening of Environmental High-Resolution Mass Spectrometry Data

Nontarget high-resolution mass spectrometry screening (NTS HRMS/MS) can detect thousands of organic substances in environmental samples. However, new strategies are needed to focus time-intensive identification efforts on features with the highest potential to cause adverse effects instead of the most abundant ones. To address this challenge, we developed MLinvitroTox, a machine learning framework that uses molecular fingerprints derived from fragmentation spectra (MS2) for a rapid classification of thousands of unidentified HRMS/MS features as toxic/nontoxic based on nearly 400 target-specific and over 100 cytotoxic endpoints from ToxCast/Tox21. Model development results demonstrated that using customized molecular fingerprints and models, over a quarter of toxic endpoints and the majority of the associated mechanistic targets could be accurately predicted with sensitivities exceeding 0.95. Notably, SIRIUS molecular fingerprints and xboost (Extreme Gradient Boosting) models with SMOTE (Synthetic Minority Oversampling Technique) for handling data imbalance were a universally successful and robust modeling configuration. Validation of MLinvitroTox on MassBank spectra showed that toxicity could be predicted from molecular fingerprints derived from MS2 with an average balanced accuracy of 0.75. By applying MLinvitroTox to environmental HRMS/MS data, we confirmed the experimental results obtained with target analysis and narrowed the analytical focus from tens of thousands of detected signals to 783 features linked to potential toxicity, including 109 spectral matches and 30 compounds with confirmed toxic activity.

Confirmation of high-throughput screening data and novel mechanistic insights into FXR-xenobiotic interactions by orthogonal assays

Toxicology in the 21st Century (Tox21) is a federal collaboration employing a high-throughput robotic screening system to test 10,000 environmental chemicals. One of the primary goals of the program is prioritizing toxicity evaluations through in vitro high-throughput screening (HTS) assays for large numbers of chemicals already in commercial use for which little or no toxicity data is available. Within the Tox21 screening program, disruption in nuclear receptor (NR) signaling represents a particular area of interest. Given the role of NR's in modulating a wide range of biological processes, alterations of their activity can have profound biological impacts. Farnesoid X receptor (FXR) is a member of the nuclear receptor superfamily that has demonstrated importance in bile acid homeostasis, glucose metabolism, lipid homeostasis and hepatic regeneration. In this study, we re-evaluated 24 FXR agonists and antagonists identified through Tox21 using select orthogonal assays. In transient transactivation assays, 7/8 putative agonists and 4/4 putative inactive compounds were confirmed. Likewise, we confirmed 9/12 antagonists tested. Using a mammalian two hybrid approach we demonstrate that both FXR agonists and antagonists facilitate FXRα-coregulator interactions suggesting that differential coregulator recruitment may mediate activation/repression of FXRα mediated transcription. Additionally, we tested the ability of select FXR agonists and antagonists to facilitate hepatic transcription of FXR gene targets Shp and Bsep in a teleost (Medaka) model. Through application of in vitro cell-based assays, in silico modeling and in vivo gene expressions, we demonstrated the molecular complexity of FXR:ligand interactions and confirmed the ability of diverse ligands to modulate FXRα, facilitate differential coregulator recruitment and activate/repress receptor-mediated transcription. Overall, we suggest a multiplicative approach to assessment of nuclear receptor function may facilitate a greater understanding of the biological and mechanistic complexities of nuclear receptor activities and further our ability to interpret broad HTS outcomes.

Artificial Intelligence-Based Toxicity Prediction of Environmental Chemicals: Future Directions for Chemical Management Applications

Recently, research on the development of artificial intelligence (AI)-based computational toxicology models that predict toxicity without the use of animal testing has emerged because of the rapid development of computer technology. Various computational toxicology techniques that predict toxicity based on the structure of chemical substances are gaining attention, including the quantitative structure-activity relationship. To understand the recent development of these models, we analyzed the databases, molecular descriptors, fingerprints, and algorithms considered in recent studies. Based on a selection of 96 papers published since 2014, we found that AI models have been developed to predict approximately 30 different toxicity end points using more than 20 toxicity databases. For model development, molecular access system and extended-connectivity fingerprints are the most commonly used molecular descriptors. The most used algorithm among the machine learning techniques is the random forest, while the most used algorithm among the deep learning techniques is a deep neural network. The use of AI technology in the development of toxicity prediction models is a new concept that will aid in achieving a scientific accord and meet regulatory applications. The comprehensive overview provided in this study will provide a useful guide for the further development and application of toxicity prediction models.

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.

Evaluating consumer exposure to disinfecting chemicals against coronavirus disease 2019 (COVID-19) and associated health risks

Disinfection of surfaces has been recommended as one of the most effective ways to combat the spread of novel coronavirus (SARS-CoV-2) that causes coronavirus disease 2019 (COVID-19). However, overexposure to disinfecting chemicals may lead to unintended human health risks. Here, using an indoor fate and chemical exposure model, we estimate human exposure to 22 disinfecting chemicals on the lists recommended by various governmental agencies against COVID-19, resulting from contact with disinfected surfaces and handwashing. Three near-field exposure routes, i.e., mouthing-mediated oral ingestion, inhalation, and dermal absorption, are considered to calculate the whole-body uptake doses and blood concentrations caused by single use per day for three age groups (3, 14, and 24-year-old). We also assess the health risks by comparing the predicted whole-body uptake doses with in vivo toxicological data and the predicted blood concentrations with in vitro bioactivity data. Our results indicate that both the total exposure and relative contribution of each exposure route vary considerably among the disinfecting chemicals due to their diverse physicochemical properties. 3-year-old children have consistent higher exposure than other age groups, especially in the scenario of contact with disinfected surfaces, due to their more frequent hand contact and mouthing activities. Due to the short duration of handwashing, we do not expect any health risk from the use of disinfecting chemicals in handwashing. In contrast, exposure from contact with disinfected surfaces may result in health risks for certain age groups especially children, even the surfaces are disinfected once a day. Interestingly, risk assessments based on whole-body uptake doses and in vivo toxicological data tend to give higher risk estimates than do those based on blood concentrations and in vitro bioactivity data. Our results reveal the most important exposure routes for disinfecting chemicals used in the indoor environment; they also highlight the need for more accurate data for both chemical properties and toxicity to better understand the risks associated with the increased use of disinfecting chemicals in the pandemic.

Prediction Model with High-Performance Constitutive Androstane Receptor (CAR) Using DeepSnap-Deep Learning Approach from the Tox21 10K Compound Library

The constitutive androstane receptor (CAR) plays pivotal roles in drug-induced liver injury through the transcriptional regulation of drug-metabolizing enzymes and transporters. Thus, identifying regulatory factors for CAR activation is important for understanding its mechanisms. Numerous studies conducted previously on CAR activation and its toxicity focused on in vivo or in vitro analyses, which are expensive, time consuming, and require many animals. We developed a computational model that predicts agonists for the CAR using the Toxicology in the 21st Century 10k library. Additionally, we evaluate the prediction performance of novel deep learning (DL)-based quantitative structure-activity relationship analysis called the DeepSnap-DL approach, which is a procedure of generating an omnidirectional snapshot portraying three-dimensional (3D) structures of chemical compounds. The CAR prediction model, which applies a 3D structure generator tool, called CORINA-generated and -optimized chemical structures, in the DeepSnap-DL demonstrated better performance than the existing methods using molecular descriptors. These results indicate that high performance in the prediction model using the DeepSnap-DL approach may be important to prepare suitable 3D chemical structures as input data and to enable the identification of modulators of the CAR.