Revealing Adverse Outcome Pathways from Public High-Throughput Screening Data to Evaluate New Toxicants by a Knowledge-Based Deep Neural Network Approach

Endocrine disruptor identification and multitoxicity level assessment of organic chemicals: An example of multiple machine learning models

Endocrine-disrupting chemicals (EDCs) pollution is a major global environmental issue. Assessing the multiple toxic effects of EDCs is key to managing their risks. This study successfully developed an EDCs classification and recognition model based on recursive feature elimination and random forest coupling, which passed external validation. Furthermore, the study classified the hormonal effects of EDCs and elucidated their hormonal roles. Molecular dynamics simulations were employed to investigate the toxicity of EDCs, and a regression model for such toxicity was developed using neural networks. A multi-toxicity regression model for EDCs was also developed using the XGBoost algorithm. This model can evaluate carcinogenicity, teratogenicity, and potential developmental toxicity of EDCs. The Spearman and Kendall correlation coefficient methods were used to assess the relations between toxicities. This study combines data filtering with model optimisation to ensure the use of efficient and concise methods. This allows for a comprehensive assessment of EDCs toxicity. It also helps analyse the link between EDCs molecular structure and their toxic effects, providing ideas for designing new chemicals. However, the model exhibits high complexity, and some processes are difficult to fully explain.

Perspectives on Advancing Multimodal Learning in Environmental Science and Engineering Studies

The environment faces increasing anthropogenic impacts, resulting in a rapid increase in environmental issues that undermine the natural capital essential for human wellbeing. These issues are complex and often influenced by various factors represented by data with different modalities. While machine learning (ML) provides data-driven tools for addressing the environmental issues, the current ML models in environmental science and engineering (ES&E) often neglect the utilization of multimodal data. With the advancement in deep learning, multimodal learning (MML) holds promise for comprehensive descriptions of the environmental issues by harnessing data from diverse modalities. This advancement has the potential to significantly elevate the accuracy and robustness of prediction models in ES&E studies, providing enhanced solutions for various environmental modeling tasks. This perspective summarizes MML methodologies and proposes potential applications of MML models in ES&E studies, including environmental quality assessment, prediction of chemical hazards, and optimization of pollution control techniques. Additionally, we discuss the challenges associated with implementing MML in ES&E and propose future research directions in this domain.

Knowledge-based machine learning for predicting and understanding the androgen receptor (AR)-mediated reproductive toxicity in zebrafish

Traditional methods for identifying endocrine-disrupting chemicals (EDCs) that activate androgen receptors (AR) are costly, time-consuming, and low-throughput. This study developed a knowledge-based deep neural network model (AR-DNN) to predict AR-mediated adverse outcomes on female zebrafish fertility. This model started with chemical fingerprints as the input layer and was implemented through a five-layer virtual AR-induced adverse outcome pathway (AOP). Results indicated that the AR-DNN effectively and accurately screens new reproductive toxicants (AUC = 0.94, accuracy = 0.85), providing potential toxicity pathways. Furthermore, 1477 and 2448 chemicals that could lead to infertility were identified in the plastic additives list (PLASTICMAP, n = 7112) and the Inventory of Existing Chemical Substances in China (IECSC, n = 17741), respectively. Colourants containing steroid-like structures are the major active plastic additives that might lower female zebrafish fertility through AR binding, DNA binding, and transcriptional activation. While active IECSC chemicals primarily have the same fragments, such as benzonitrile, nitrobenzene, and quinolone. The predicted toxicity pathways were consistent with existing fish evidence, demonstrating the model's applicability. This knowledge-based approach offers a promising computational toxicology strategy for predicting and characterising the endocrine-disrupting effects and toxic mechanisms of organic chemicals, potentially leading to more efficient and cost-effective screening of EDCs.

Next Generation Risk Assessment approaches for advanced nanomaterials: Current status and future perspectives

This manuscript discusses the challenges of applying New Approach Methodologies (NAMs) for safe by design and regulatory risk assessment of advanced nanomaterials (AdNMs). The authors propose a framework for Next Generation Risk Assessment of AdNMs involving NAMs that is aligned to the conventional risk assessment paradigm. This framework is exposure-driven, endpoint-specific, makes best use of pre-existing information, and can be implemented in tiers of increasing specificity and complexity of the adopted NAMs. The tiered structure of the approach, which effectively combines the use of existing data with targeted testing will allow safety to be assessed cost-effectively and as far as possible with even more limited use of vertebrates. The regulatory readiness of state-of-the-art emerging NAMs is assessed in terms of Transparency, Reliability, Accessibility, Applicability, Relevance and Completeness, and their appropriateness for AdNMs is discussed in relation to each step of the risk assessment paradigm along with providing perspectives for future developments in the respective scientific and regulatory areas.

Hybrid non-animal modeling: A mechanistic approach to predict chemical hepatotoxicity

Developing mechanistic non-animal testing methods based on the adverse outcome pathway (AOP) framework must incorporate molecular and cellular key events associated with target toxicity. Using data from an in vitro assay and chemical structures, we aimed to create a hybrid model to predict hepatotoxicants. We first curated a reference dataset of 869 compounds for hepatotoxicity modeling. Then, we profiled them against PubChem for existing in vitro toxicity data. Of the 2560 resulting assays, we selected the mitochondrial membrane potential (MMP) assay, a high-throughput screening (HTS) tool that can test chemical disruptors for mitochondrial function. Machine learning was applied to develop quantitative structure-activity relationship (QSAR) models with 2536 compounds tested in the MMP assay for screening new compounds. The MMP assay results, including QSAR model outputs, yielded hepatotoxicity predictions for reference set compounds with a Correct Classification Ratio (CCR) of 0.59. The predictivity improved by including 37 structural alerts (CCR = 0.8). We validated our model by testing 37 reference set compounds in human HepG2 hepatoma cells, and reliably predicting them for hepatotoxicity (CCR = 0.79). This study introduces a novel AOP modeling strategy that combines public HTS data, computational modeling, and experimental testing to predict chemical hepatotoxicity.

Alternatives of Animal Models for Biomedical Research: a Comprehensive Review of Modern Approaches

Biomedical research has long relied on animal models to unravel the intricacies of human physiology and pathology. However, concerns surrounding ethics, expenses, and inherent species differences have catalyzed the exploration of alternative avenues. The contemporary alternatives to traditional animal models in biomedical research delve into three main categories of alternative approaches: in vitro models, in vertebrate models, and in silico models. This unique approach to artificial intelligence and machine learning has been a keen interest to be used in different biomedical research. The main goal of this review is to serve as a guide to researchers seeking novel avenues for their investigations and underscores the importance of considering alternative models in the pursuit of scientific knowledge and medical breakthroughs, including showcasing the broad spectrum of modern approaches that are revolutionizing biomedical research and leading the way toward a more ethical, efficient, and innovative future. Models can insight into cellular processes, developmental biology, drug interaction, assessing toxicology, and understanding molecular mechanisms.

A Graph Neural Network Model with a Transparent Decision-Making Process Defines the Applicability Domain for Environmental Estrogen Screening

The application of deep learning (DL) models for screening environmental estrogens (EEs) for the sound management of chemicals has garnered significant attention. However, the currently available DL model for screening EEs lacks both a transparent decision-making process and effective applicability domain (AD) characterization, making the reliability of its prediction results uncertain and limiting its practical applications. To address this issue, a graph neural network (GNN) model was developed to screen EEs, achieving accuracy rates of 88.9% and 92.5% on the internal and external test sets, respectively. The decision-making process of the GNN model was explored through the network-like similarity graphs (NSGs) based on the model features (FT). We discovered that the accuracy of the predictions is dependent on the feature distribution of compounds in NSGs. An AD characterization method called ADFT was proposed, which excludes predictions falling outside of the model's prediction range, leading to a 15% improvement in the F1 score of the GNN model. The GNN model with the AD method may serve as an efficient tool for screening EEs, identifying 800 potential EEs in the Inventory of Existing Chemical Substances of China. Additionally, this study offers new insights into comprehending the decision-making process of DL models.

Advancing Computational Toxicology by Interpretable Machine Learning

Chemical toxicity evaluations for drugs, consumer products, and environmental chemicals have a critical impact on human health. Traditional animal models to evaluate chemical toxicity are expensive, time-consuming, and often fail to detect toxicants in humans. Computational toxicology is a promising alternative approach that utilizes machine learning (ML) and deep learning (DL) techniques to predict the toxicity potentials of chemicals. Although the applications of ML- and DL-based computational models in chemical toxicity predictions are attractive, many toxicity models are "black boxes" in nature and difficult to interpret by toxicologists, which hampers the chemical risk assessments using these models. The recent progress of interpretable ML (IML) in the computer science field meets this urgent need to unveil the underlying toxicity mechanisms and elucidate the domain knowledge of toxicity models. In this review, we focused on the applications of IML in computational toxicology, including toxicity feature data, model interpretation methods, use of knowledge base frameworks in IML development, and recent applications. The challenges and future directions of IML modeling in toxicology are also discussed. We hope this review can encourage efforts in developing interpretable models with new IML algorithms that can assist new chemical assessments by illustrating toxicity mechanisms in humans.

Advances and applications of machine learning and deep learning in environmental ecology and health

Machine learning (ML) and deep learning (DL) possess excellent advantages in data analysis (e.g., feature extraction, clustering, classification, regression, image recognition and prediction) and risk assessment and management in environmental ecology and health (EEH). Considering the rapid growth and increasing complexity of data in EEH, it is of significance to summarize recent advances and applications of ML and DL in EEH. This review summarized the basic processes and fundamental algorithms of the ML and DL modeling, and indicated the urgent needs of ML and DL in EEH. Recent research hotspots such as environmental ecology and restoration, environmental fate of new pollutants, chemical exposures and risks, chemical hazard identification and control were highlighted. Various applications of ML and DL in EEH demonstrate their versatility and technological revolution, and present some challenges. The perspective of ML and DL in EEH were further outlined to promote the innovative analysis and cultivation of the ML-driven research paradigm.

Are New Phthalate Ester Substitutes Safer than Traditional DBP and DiBP? Comparative Endocrine-Disrupting Analyses on Zebrafish Using In Vivo, Transcriptome, and In Silico Approaches

Although previous studies have confirmed the association between phthalate esters (PAEs) exposure and endocrine disorders in humans, few studies to date have systematically assessed the threats of new PAE alternatives to endocrine disruptions. Herein, zebrafish embryos were continuously exposed to two PAEs [di-n-butyl phthalate (DBP) and diisobutyl phthalate (DiBP)], two structurally related alternatives [diiononyl phthalate (DINP) and diisononyl hexahydrophthalate (DINCH)], and two non-PAE substitutes [dipropylene glycol dibenzoate (DGD) and glyceryl triacetate (GTA)], and the endocrine-disrupting effects were investigated during the early stages (8-48 hpf). For five endogenous hormones, including progesterone, testosterone, 17β-estradiol, triiodothyronine (T3), and cortisol, the tested chemicals disturbed the contents of at least one hormone at environmentally relevant concentrations (≤3.9 μM), except DINCH and GTA. Then, the concentration-dependent reduced zebrafish transcriptome analysis was performed. Thyroid hormone (TH)- and androgen/estrogen-regulated adverse outcome pathways (AOPs) were the two types of biological pathways most sensitive to PAE exposure. Notably, six compounds disrupted four TH-mediated AOPs, from the inhibition of deiodinases (molecular initiating event, MIE), a decrease in T3 levels (key event, KE), to mortality (adverse outcome, AO) with the quantitatively linear relationships between MIE-KE (|r| = 0.96, p = 0.002), KE-AO (|r| = 0.88, p = 0.02), and MIE-AO (|r| = 0.89, p = 0.02). Multiple structural analyses showed that benzoic acid is the critical toxicogenic fragment. Our data will facilitate the screening and development of green alternatives.

Identification and Prioritization of Environmental Organic Pollutants: From an Analytical and Toxicological Perspective

Exposure to environmental organic pollutants has triggered significant ecological impacts and adverse health outcomes, which have been received substantial and increasing attention. The contribution of unidentified chemical components is considered as the most significant knowledge gap in understanding the combined effects of pollutant mixtures. To address this issue, remarkable analytical breakthroughs have recently been made. In this review, the basic principles on recognition of environmental organic pollutants are overviewed. Complementary analytical methodologies (i.e., quantitative structure-activity relationship prediction, mass spectrometric nontarget screening, and effect-directed analysis) and experimental platforms are briefly described. The stages of technique development and/or essential parts of the analytical workflow for each of the methodologies are then reviewed. Finally, plausible technique paths and applications of the future nontarget screening methods, interdisciplinary techniques for achieving toxicant identification, and burgeoning strategies on risk assessment of chemical cocktails are discussed.

Integrating Concentration-Dependent Toxicity Data and Toxicokinetics To Inform Hepatotoxicity Response Pathways

Failure of animal models to predict hepatotoxicity in humans has created a push to develop biological pathway-based alternatives, such as those that use in vitro assays. Public screening programs (e.g., ToxCast/Tox21 programs) have tested thousands of chemicals using in vitro high-throughput screening (HTS) assays. Developing pathway-based models for simple biological pathways, such as endocrine disruption, has proven successful, but development remains a challenge for complex toxicities like hepatotoxicity, due to the many biological events involved. To this goal, we aimed to develop a computational strategy for developing pathway-based models for complex toxicities. Using a database of 2171 chemicals with human hepatotoxicity classifications, we identified 157 out of 1600+ ToxCast/Tox21 HTS assays to be associated with human hepatotoxicity. Then, a computational framework was used to group these assays by biological target or mechanisms into 52 key event (KE) models of hepatotoxicity. KE model output is a KE score summarizing chemical potency against a hepatotoxicity-relevant biological target or mechanism. Grouping hepatotoxic chemicals based on the chemical structure revealed chemical classes with high KE scores plausibly informing their hepatotoxicity mechanisms. Using KE scores and supervised learning to predict in vivo hepatotoxicity, including toxicokinetic information, improved the predictive performance. This new approach can be a universal computational toxicology strategy for various chemical toxicity evaluations.

Converting Nanotoxicity Data to Information Using Artificial Intelligence and Simulation

Decades of nanotoxicology research have generated extensive and diverse data sets. However, data is not equal to information. The question is how to extract critical information buried in vast data streams. Here we show that artificial intelligence (AI) and molecular simulation play key roles in transforming nanotoxicity data into critical information, i.e., constructing the quantitative nanostructure (physicochemical properties)-toxicity relationships, and elucidating the toxicity-related molecular mechanisms. For AI and molecular simulation to realize their full impacts in this mission, several obstacles must be overcome. These include the paucity of high-quality nanomaterials (NMs) and standardized nanotoxicity data, the lack of model-friendly databases, the scarcity of specific and universal nanodescriptors, and the inability to simulate NMs at realistic spatial and temporal scales. This review provides a comprehensive and representative, but not exhaustive, summary of the current capability gaps and tools required to fill these formidable gaps. Specifically, we discuss the applications of AI and molecular simulation, which can address the large-scale data challenge for nanotoxicology research. The need for model-friendly nanotoxicity databases, powerful nanodescriptors, new modeling approaches, molecular mechanism analysis, and design of the next-generation NMs are also critically discussed. Finally, we provide a perspective on future trends and challenges.

Data-Driven Quantitative Structure-Activity Relationship Modeling for Human Carcinogenicity by Chronic Oral Exposure

Traditional methodologies for assessing chemical toxicity are expensive and time-consuming. Computational modeling approaches have emerged as low-cost alternatives, especially those used to develop quantitative structure-activity relationship (QSAR) models. However, conventional QSAR models have limited training data, leading to low predictivity for new compounds. We developed a data-driven modeling approach for constructing carcinogenicity-related models and used these models to identify potential new human carcinogens. To this goal, we used a probe carcinogen dataset from the US Environmental Protection Agency's Integrated Risk Information System (IRIS) to identify relevant PubChem bioassays. Responses of 25 PubChem assays were significantly relevant to carcinogenicity. Eight assays inferred carcinogenicity predictivity and were selected for QSAR model training. Using 5 machine learning algorithms and 3 types of chemical fingerprints, 15 QSAR models were developed for each PubChem assay dataset. These models showed acceptable predictivity during 5-fold cross-validation (average CCR = 0.71). Using our QSAR models, we can correctly predict and rank 342 IRIS compounds' carcinogenic potentials (PPV = 0.72). The models predicted potential new carcinogens, which were validated by a literature search. This study portends an automated technique that can be applied to prioritize potential toxicants using validated QSAR models based on extensive training sets from public data resources.

Prediction of zebrafish embryonic developmental toxicity by integrating omics with adverse outcome pathway

New approach methodologies (NAMs), especially omics-based high-throughput bioassays have been developed rapidly, providing rich mechanistic information such as molecular initiation events (MIEs) and (sub)cellular key events (KEs) in adverse outcome pathways (AOPs). However, how to apply the knowledge of MIEs/KEs to predict adverse outcomes (AOs) induced by chemicals represents a new challenge for computational toxicology. Here, an integrated method named ScoreAOP was developed and evaluated to predict chemicals' developmental toxicity for zebrafish embryos by integrating four related AOPs and dose-dependent reduced zebrafish transcriptome (RZT). The rules of ScoreAOP included 1) sensitivity of responsive KEs demonstrated by point of departure of KEs (POD_KE), 2) evidence reliability and 3) distance between KEs and AOs. Moreover, eleven chemicals with different modes of action (MoAs) were tested to evaluate ScoreAOP. Results showed that eight of the eleven chemicals caused developmental toxicity at tested concentration in apical tests. All the tested chemicals' developmental defects were predicted using ScoreAOP, whereas eight out of the eleven chemicals predicted by ScoreMIE which was developed to score MIEs disturbed by chemicals based on in vitro bioassays data. Finally, in terms of mechanism explanation, ScoreAOP clustered chemicals with different MoAs while ScoreMIE failed, and ScoreAOP revealed the activation of aryl hydrocarbon receptor (AhR) plays a significant role in dysfunction of cardiovascular system, resulting in zebrafish developmental defects and mortality. In conclusion, ScoreAOP represents a promising approach to apply mechanism information obtained from omics to predict AOs induced by chemicals.

Estrogenic flavonoids and their molecular mechanisms of action

Flavonoids are a major group of phytoestrogens associated with physiological effects, and ecological and social impacts. Although the estrogenic activity of flavonoids was reported by researchers in the fields of medical, environmental and food studies, their molecular mechanisms of action have not been comprehensively reviewed. The estrogenic activity of the respective classes of flavonoids, anthocyanidins/anthocyanins, 2-arylbenzofurans/3-arylcoumarins/α-methyldeoxybenzoins, aurones/chalcones/dihydrochalcones, coumaronochromones, coumestans, flavans/flavan-3-ols/flavan-4-ols, flavanones/dihydroflavonols, flavones/flavonols, homoisoflavonoids, isoflavans, isoflavanones, isoflavenes, isoflavones, neoflavonoids, oligoflavonoids, pterocarpans/pterocarpenes, and rotenone/rotenoids, was summarized through a comprehensive literature search, and their structure-activity relationship, biological activities, signaling pathways, and applications were discussed. Although the respective classes of flavonoids contained at least one chemical mimicking estrogen, the mechanisms varied, such as those with estrogenic, anti-estrogenic, non-estrogenic, and biphasic activities, and additional activities through crosstalk/bypassing, which exert biological activities through cell signaling pathways. Such mechanistic variations of estrogen action are not limited to flavonoids and are observed among other broad categories of chemicals, thus this group of chemicals can be termed as the "estrogenome". This review article focuses on the connection of estrogen action mainly between the outer and the inner environments, which represent variations of chemicals and biological activities/signaling pathways, respectively, and form the basis to understand their applications. The applications of chemicals will markedly progress due to emerging technologies, such as artificial intelligence for precision medicine, which is also true of the study of the estrogenome including estrogenic flavonoids.

Machine learning and artificial intelligence in physiologically based pharmacokinetic modeling

Physiologically based pharmacokinetic (PBPK) models are useful tools in drug development and risk assessment of environmental chemicals. PBPK model development requires the collection of species-specific physiological, and chemical-specific absorption, distribution, metabolism, and excretion (ADME) parameters, which can be a time-consuming and expensive process. This raises a need to create computational models capable of predicting input parameter values for PBPK models, especially for new compounds. In this review, we summarize an emerging paradigm for integrating PBPK modeling with machine learning (ML) or artificial intelligence (AI)-based computational methods. This paradigm includes 3 steps (1) obtain time-concentration PK data and/or ADME parameters from publicly available databases, (2) develop ML/AI-based approaches to predict ADME parameters, and (3) incorporate the ML/AI models into PBPK models to predict PK summary statistics (eg, area under the curve and maximum plasma concentration). We also discuss a neural network architecture "neural ordinary differential equation (Neural-ODE)" that is capable of providing better predictive capabilities than other ML methods when used to directly predict time-series PK profiles. In order to support applications of ML/AI methods for PBPK model development, several challenges should be addressed (1) as more data become available, it is important to expand the training set by including the structural diversity of compounds to improve the prediction accuracy of ML/AI models; (2) due to the black box nature of many ML models, lack of sufficient interpretability is a limitation; (3) Neural-ODE has great potential to be used to generate time-series PK profiles for new compounds with limited ADME information, but its application remains to be explored. Despite existing challenges, ML/AI approaches will continue to facilitate the efficient development of robust PBPK models for a large number of chemicals.

Prediction of drug-induced liver injury and cardiotoxicity using chemical structure and in vitro assay data

Drug-induced liver injury (DILI) and cardiotoxicity (DICT) are major adverse effects triggered by many clinically important drugs. To provide an alternative to in vivo toxicity testing, the U.S. Tox21 consortium has screened a collection of ∼10K compounds, including drugs in clinical use, against >70 cell-based assays in a quantitative high-throughput screening (qHTS) format. In this study, we compiled reference compound lists for DILI and DICT and compared the potential of Tox21 assay data with chemical structure information in building prediction models for human in vivo hepatotoxicity and cardiotoxicity. Models were built with four different machine learning algorithms (e.g., Random Forest, Naïve Bayes, eXtreme Gradient Boosting, and Support Vector Machine) and model performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC-ROC). Chemical structure-based models showed reasonable predictive power for DILI (best AUC-ROC = 0.75 ± 0.03) and DICT (best AUC-ROC = 0.83 ± 0.03), while Tox21 assay data alone only showed better than random performance. DILI and DICT prediction models built using a combination of assay data and chemical structure information did not have a positive impact on model performance. The suboptimal predictive performance of the assay data is likely due to insufficient coverage of an adequately predictive number of toxicity mechanisms. The Tox21 consortium is currently expanding coverage of biological response space with additional assays that probe toxicologically important targets and under-represented pathways that may improve the prediction of in vivo toxicity such as DILI and DICT.

Development, Validation, and Application of a Human Reproductive Toxicity Prediction Model Based on Adverse Outcome Pathway

A growing number of environmental contaminants have been proved to have reproductive toxicity to males and females. However, the unclear toxicological mechanism of reproductive toxicants limits the development of virtual screening methods. By consolidating androgen (AR)-/estrogen receptors (ERs)-mediated adverse outcome pathways (AOPs) with more than 8000 chemical substances, we uncovered relationships between chemical features, a series of pathway-related effects, and reproductive apical outcomes─changes in sex organ weights. An AOP-based computational model named RepTox was developed and evaluated to predict and characterize chemicals' reproductive toxicity for males and females. Results showed that RepTox has three outstanding advantages. (I) Compared with the traditional models (37 and 81% accuracy, respectively), AOP significantly improved the predictive robustness of RepTox (96.3% accuracy). (II) Compared with the application domain (AD) of models based on small in vivo datasets, AOP expanded the ADs of RepTox by 1.65-fold for male and 3.77-fold for female, respectively. (III) RepTox implied that hydrophobicity, cyclopentanol substructure, and several topological indices (e.g., hydrogen-bond acceptors) were important, unbiased features associated with reproductive toxicants. Finally, RepTox was applied to the inventory of existing chemical substances of China and identified 2100 and 7281 potential toxicants to the male and female reproductive systems, respectively.

Mechanism-driven modeling of chemical hepatotoxicity using structural alerts and an in vitro screening assay

Traditional experimental approaches to evaluate hepatotoxicity are expensive and time-consuming. As an advanced framework of risk assessment, adverse outcome pathways (AOPs) describe the sequence of molecular and cellular events underlying chemical toxicities. We aimed to develop an AOP that can be used to predict hepatotoxicity by leveraging computational modeling and in vitro assays. We curated 869 compounds with known hepatotoxicity classifications as a modeling set and extracted assay data from PubChem. The antioxidant response element (ARE) assay, which quantifies transcriptional responses to oxidative stress, showed a high correlation to hepatotoxicity (PPV=0.82). Next, we developed quantitative structure-activity relationship (QSAR) models to predict ARE activation for compounds lacking testing results. Potential toxicity alerts were identified and used to construct a mechanistic hepatotoxicity model. For experimental validation, 16 compounds in the modeling set and 12 new compounds were selected and tested using an in-house ARE-luciferase assay in HepG2-C8 cells. The mechanistic model showed good hepatotoxicity predictivity (accuracy = 0.82) for these compounds. Potential false positive hepatotoxicity predictions by only using ARE results can be corrected by incorporating structural alerts and vice versa. This mechanistic model illustrates a potential toxicity pathway for hepatotoxicity, and this strategy can be expanded to develop predictive models for other complex toxicities.

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.

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.

Graph Attention Network Model with Defined Applicability Domains for Screening PBT Chemicals

In silico models for screening environmentally persistent, bio-accumulative, and toxic (PBT) substances are necessary for sound management of chemicals. Due to the complex structure-activity landscapes (SALs) on the PBT attributes, previous models for screening PBT chemicals lack either applicability domain (AD) characterizations or interpretability, restricting their applications. Herein, graph attention networks (GATs), a novel neural network architecture, were introduced to construct models for screening PBT chemicals. Results show that the GAT model not only outperformed those in previous studies but also exhibited interpretability since it optimizes attention weight parameters (P_AW) that indicate contributions of each atom to the PBT attributes. An AD characterization termed AD_FP-AC, which considers both molecular fingerprint (FP) similarities and compounds at activity cliffs (ACs) of SALs, was proposed to describe the ADs, which further assured the performance of the GAT model. Eight previously unidentified classes of compounds were identified as PBT chemicals from the Inventory of Existing Chemical Substances in China. The GAT model together with the AD_FP-AC characterization may serve as efficient tools for screening PBT chemicals, and the modeling methodology can be applied to other physicochemical, environmental, behavioral, and toxicological parameters of chemicals that are necessary for their risk assessment and management.

Predicting Prenatal Developmental Toxicity Based On the Combination of Chemical Structures and Biological Data

For hazard identification, classification, and labeling purposes, animal testing guidelines are required by law to evaluate the developmental toxicity potential of new and existing chemical products. However, guideline developmental toxicity studies are costly, time-consuming, and require many laboratory animals. Computational modeling has emerged as a promising, animal-sparing, and cost-effective method for evaluating the developmental toxicity potential of chemicals, such as endocrine disruptors, without the use of animals. We aimed to develop a predictive and explainable computational model for developmental toxicants. To this end, a comprehensive dataset of 1244 chemicals with developmental toxicity classifications was curated from public repositories and literature sources. Data from 2140 toxicological high-throughput screening assays were extracted from PubChem and the ToxCast program for this dataset and combined with information about 834 chemical fragments to group assays based on their chemical-mechanistic relationships. This effort revealed two assay clusters containing 83 and 76 assays, respectively, with high positive predictive rates for developmental toxicants identified with animal testing guidelines (PPV = 72.4 and 77.3% during cross-validation). These two assay clusters can be used as developmental toxicity models and were applied to predict new chemicals for external validation. This study provides a new strategy for constructing alternative chemical developmental toxicity evaluations that can be replicated for other toxicity modeling studies.

High throughput data-based, toxicity pathway-oriented development of a quantitative adverse outcome pathway network linking AHR activation to lung damages

The quantitative adverse outcome pathway (qAOP) is proposed to inform dose-responses at multiple biological levels for the purpose of toxicity prediction. So far, qAOP models concerning human health are scarce. Previously, we proposed 5 key molecular pathways that led aryl hydrogen receptor (AHR) activation to lung damages. The present study assembled an AOP network based on the gene expression signatures of these toxicity pathways, and validated the network using publicly available high throughput data combined with machine learning models. In addition, the AOP network was quantitatively evaluated with omics approaches and bioassays, using 16HBE-CYP1A1 cells exposed to benzo(a)pyrene (BaP), a prototypical AHR activator. Benchmark dose (BMD) analysis of transcriptomics revealed that AHR gene held the lowest BMD value, whereas AHR pathway held the lowest point of departure (PoD) compared to the other 4 pathways. Targeted bioassays were further performed to quantitatively understand the cellular responses, including ROS generation, DNA damage, interleukin-6 production, and extracellular matrix increase marked by collagen expression. Eventually, response-response relationships were plotted using nonlinear model fitting. The present study developed a highly reliable AOP model concerning human health, and validated as well as quantitatively evaluated it, and such a method is likely to be adoptable for risk assessment.