Leveraging high-throughput screening data, deep neural networks, and conditional generative adversarial networks to advance predictive toxicology

Bridging organ transcriptomics for advancing multiple organ toxicity assessment with a generative AI approach

Translational research in toxicology has significantly benefited from transcriptomic profiling, particularly in drug safety. However, its application has predominantly focused on limited organs, notably the liver, due to resource constraints. This paper presents TransTox, an innovative AI model using a generative adversarial network (GAN) method to facilitate the bidirectional translation of transcriptomic profiles between the liver and kidney under drug treatment. TransTox demonstrates robust performance, validated across independent datasets and laboratories. First, the concordance between real experimental data and synthetic data generated by TransTox was demonstrated in characterizing toxicity mechanisms compared to real experimental settings. Second, TransTox proved valuable in gene expression predictive models, where synthetic data could be used to develop gene expression predictive models or serve as "digital twins" for diagnostic applications. The TransTox approach holds the potential for multi-organ toxicity assessment with AI and advancing the field of precision toxicology.

Deep learning in water protection of resources, environment, and ecology: achievement and challenges

The breathtaking economic development put a heavy toll on ecology, especially on water pollution. Efficient water resource management has a long-term influence on the sustainable development of the economy and society. Economic development and ecology preservation are tangled together, and the growth of one is not possible without the other. Deep learning (DL) is ubiquitous in autonomous driving, medical imaging, speech recognition, etc. The spectacular success of deep learning comes from its power of richer representation of data. In view of the bright prospects of DL, this review comprehensively focuses on the development of DL applications in water resources management, water environment protection, and water ecology. First, the concept and modeling steps of DL are briefly introduced, including data preparation, algorithm selection, and model evaluation. Finally, the advantages and disadvantages of commonly used algorithms are analyzed according to their structures and mechanisms, and recommendations on the selection of DL algorithms for different studies, as well as prospects for the application and development of DL in water science are proposed. This review provides references for solving a wider range of water-related problems and brings further insights into the intelligent development of water science.

Deep Learning-Enabled Morphometric Analysis for Toxicity Screening Using Zebrafish Larvae

Toxicology studies heavily rely on morphometric analysis to detect abnormalities and diagnose disease processes. The emergence of ever-increasing varieties of environmental pollutants makes it difficult to perform timely assessments, especially using in vivo models. Herein, we propose a deep learning-based morphometric analysis (DLMA) to quantitatively identify eight abnormal phenotypes (head hemorrhage, jaw malformation, uninflated swim bladder, pericardial edema, yolk edema, bent spine, dead, unhatched) and eight vital organ features (eye, head, jaw, heart, yolk, swim bladder, body length, and curvature) of zebrafish larvae. A data set composed of 2532 bright-field micrographs of zebrafish larvae at 120 h post fertilization was generated from toxicity screening of three categories of chemicals, i.e., endocrine disruptors (perfluorooctanesulfonate and bisphenol A), heavy metals (CdCl2 and PbI2), and emerging organic pollutants (acetaminophen, 2,7-dibromocarbazole, 3-monobromocarbazo, 3,6-dibromocarbazole, and 1,3,6,8-tetrabromocarbazo). Two typical deep learning models, one-stage and two-stage models (TensorMask, Mask R-CNN), were trained to implement phenotypic feature classification and segmentation. The accuracy was statistically validated with a mean average precision >0.93 in unlabeled data sets and a mean accuracy >0.86 in previously published data sets. Such a method effectively enables subjective morphometric analysis of zebrafish larvae to achieve efficient hazard identification of both chemicals and environmental pollutants.

Recent Advances in Toxicity Prediction: Applications of Deep Graph Learning

The development of new drugs is time-consuming and expensive, and as such, accurately predicting the potential toxicity of a drug candidate is crucial in ensuring its safety and efficacy. Recently, deep graph learning has become prevalent in this field due to its computational power and cost efficiency. Many novel deep graph learning methods aid toxicity prediction and further prompt drug development. This review aims to connect fundamental knowledge with burgeoning deep graph learning methods. We first summarize the essential components of deep graph learning models for toxicity prediction, including molecular descriptors, molecular representations, evaluation metrics, validation methods, and data sets. Furthermore, based on various graph-related representations of molecules, we introduce several representative studies and methods for toxicity prediction from the perspective of GNN architectures and graph pretrained models. Compared to other types of models, deep graph models not only advance in higher accuracy and efficiency but also provide more intuitive insights, which is significant in the development of model interpretation and generalization ability. The graph pretrained models are emerging as they can extract prominent features from large-scale unlabeled molecular graph data and improve the performance of downstream toxicity prediction tasks. We hope this survey can serve as a handbook for individuals interested in exploring deep graph learning for toxicity prediction.

TransOrGAN: An Artificial Intelligence Mapping of Rat Transcriptomic Profiles between Organs, Ages, and Sexes

Animal studies are required for the evaluation of candidate drugs to ensure patient and volunteer safety. Toxicogenomics is often applied in these studies to gain understanding of the underlying mechanisms of toxicity, which is usually focused on critical organs such as the liver or kidney in young male rats. There is a strong ethical reason to reduce, refine and replace animal use (the 3Rs), where the mapping of data between organs, sexes and ages could reduce the cost and time of drug development. Herein, we proposed a generative adversarial network (GAN)-based framework entitled TransOrGAN that allowed the molecular mapping of gene expression profiles in different rodent organ systems and across sex and age groups. We carried out a proof-of-concept study based on rat RNA-seq data from 288 samples in 9 different organs of both sexes and 4 developmental stages. First, we demonstrated that TransOrGAN could infer transcriptomic profiles between any 2 of the 9 organs studied, yielding an average cosine similarity of 0.984 between synthetic transcriptomic profiles and their corresponding real profiles. Second, we found that TransOrGAN could infer transcriptomic profiles observed in females from males, with an average cosine similarity of 0.984. Third, we found that TransOrGAN could infer transcriptomic profiles in juvenile, adult, and aged animals from adolescent animals with an average cosine similarity of 0.981, 0.983, and 0.989, respectively. Altogether, TransOrGAN is an innovative approach to infer transcriptomic profiles between ages, sexes, and organ systems, offering the opportunity to reduce animal usage and to provide an integrated assessment of toxicity in the whole organism irrespective of sex or age.

Navigating the bridge between wet and dry lab toxicology research to address current challenges with high-dimensional data

Toxicology research has rapidly evolved, leveraging increasingly advanced technologies in high-throughput approaches to yield important information on toxicological mechanisms and health outcomes. Data produced through toxicology studies are consequently becoming larger, often producing high-dimensional data. These types of data hold promise for imparting new knowledge, yet inherently have complexities causing them to be a rate-limiting element for researchers, particularly those that are housed in "wet lab" settings (i.e., researchers that use liquids to analyze various chemicals and biomarkers as opposed to more computationally focused, "dry lab" researchers). These types of challenges represent topics of ongoing conversation amongst our team and researchers in the field. The aim of this perspective is to i) summarize hurdles in analyzing high-dimensional data in toxicology that require improved training and translation for wet lab researchers, ii) highlight example methods that have aided in translating data analysis techniques to wet lab researchers; and iii) describe challenges that remain to be effectively addressed, to date, in toxicology research. Specific aspects include methodologies that could be introduced to wet lab researchers, including data pre-processing, machine learning, and data reduction. Current challenges discussed include model interpretability, study biases, and data analysis training. Example efforts implemented to translate these data analysis techniques are also mentioned, including online data analysis resources and hands-on workshops. Questions are also posed to continue conversation in the toxicology community. Contents of this perspective represent timely issues broadly occurring in the fields of bioinformatics and toxicology that require ongoing dialogue between wet and dry lab researchers.

Integrating high-throughput exposure assessment and in vitro screening data to prioritize endocrine-active potential and dietary risks of pesticides and veterinary drug residues in animal products

New approach methodologies in toxicology, such as in vitro high-throughput screening (HTS), can minimize the use of experimental animals and allow mechanism-based predictions of in vivo toxicity. HTS data has been increasingly used in the regulatory context; however, only a few studies integrated dietary exposure and HTS data to foster chemical prioritization in food. Additionally, the endocrine-associated risk of veterinary drug residues in food is yet to be fully characterized. This study aims to systematically compare the translated HTS data with the acceptable daily intake (ADI) values and prioritize the pesticides and veterinary drug residues (n = 294) in food using the exposure-activity ratio (EAR) and Toxicological Prioritization index (ToxPi). The dietary exposure assessment was accomplished using a stochastic human exposure and dose simulation high-throughput model (SHEDS-HT). We selected 76 HTS assays from 12 nuclear receptors to represent the molecular initiating event (MIE) of endocrine-disrupting phenotypes. Chemical prioritization was achieved using 4 methods (i.e., EAR-OED, EAR-ADI, ToxPi-exposure + ADI, and ToxPi-exposure + endocrine score), where the consensus prioritized chemicals were fipronil, furazolidone, oxolinic acid, and oxytetracycline for the Taiwanese population. This case study demonstrates the utility of HTS data in fostering regulatory decisions on chemicals, especially for those lacking comprehensive toxicity data.

Assessing chemical hazard and unraveling binding affinity of priority pollutants to lignin modifying enzymes for environmental remediation

Lignin-modifying enzymes (LMEs) are impactful biocatalysts in environmental remediation applications. However, LMEs-assisted experimental degradation neglects the molecular basis of pollutant degradation. Furthermore, throughout the remediation process, the inherent hazards of environmental pollutants remain untapped for in-depth toxicological endpoints. In this investigation, a predictive toxicological framework and a computational framework adopting LMEs were employed to assess the hazards of Priority Pollutants (PP) and its possible LMEs-assisted catalytic screening. The potential hazardous outcomes of PP were assessed using Quantitative structure-activity relationship (QSARs)-based techniques including Toxtree, ECOSAR, and T.E.S.T. tools. Toxicological findings revealed positive outcomes in a multitude of endpoints for all PP. The PP compound 2,3,7,8-TCDD (dioxin) was found to exhibit the lowest concentration of aquatic toxicity implementing aquatic model systems; LC₅₀ as 0.01, 0.01, 0.04 (mg L^-1) for Fish (96 H), Daphnid (48 H), Green algae (96 H) respectively. T.E.S.T. results revealed that chloroform, and 2-chlorophenol both seem to be developmental toxicants. Subsequently, LMEs-assisted docking procedure was employed in predictive mitigation of PP. The docking approach as predicted degradation revealed the far lowest docking energy score for Versatile peroxidase (VP)- 2,3,7,8-TCDD docked complex with a binding energy of -9.2 (kcal mol^-1), involved PHE-46, PRO-139, PRO-141, ILE-148, LEU-165, HIS-169, LEU-228, MET-262, and MET-265 as key interacting amino acid residues. Second most ranked but lesser than VP, Lignin peroxidase (LiP)- 2,3,7,8-TCDD docked complex exhibited a rather lower binding affinity score (-8.8 kcal mol^-1). Predictive degradation screening employing comparative docking revealed varying binding affinities, portraying that each LMEs member has independent feasibility to bind PP as substrate. Predictive findings endorsed the hazardous nature of associated PP in a multitude of endpoints, which could be attenuated by undertaking LMEs as a predictive approach to protect the environment and implement it in regulatory considerations.

Zebrafish as a Mainstream Model for In Vivo Systems Pharmacology and Toxicology

Pharmacology and toxicology are part of a much broader effort to understand the relationship between chemistry and biology. While biomedicine has necessarily focused on specific cases, typically of direct human relevance, there are real advantages in pursuing more systematic approaches to characterizing how health and disease are influenced by small molecules and other interventions. In this context, the zebrafish is now established as the representative screenable vertebrate and, through ongoing advances in the available scale of genome editing and automated phenotyping, is beginning to address systems-level solutions to some biomedical problems. The addition of broader efforts to integrate information content across preclinical model organisms and the incorporation of rigorous analytics, including closed-loop deep learning, will facilitate efforts to create systems pharmacology and toxicology with the ability to continuously optimize chemical biological interactions around societal needs. In this review, we outline progress toward this goal.

Machine learning and structure-based modeling for the prediction of UDP-glucuronosyltransferase inhibition

UDP-glucuronosyltransferases (UGTs) are responsible for 35% of the phase II drug metabolism. In this study, we focused on UGT1A1, which is a key UGT isoform. Strong inhibition of UGT1A1 may trigger adverse drug/herb-drug interactions, or result in disorders of endobiotic metabolism. Most of the current machine learning methods predicting the inhibition of drug metabolizing enzymes neglect protein structure and dynamics, both being essential for the recognition of various substrates and inhibitors. We performed molecular dynamics simulations on a homology model of the human UGT1A1 structure containing both the cofactor- (UDP-glucuronic acid) and substrate-binding domains to explore UGT conformational changes. Then, we created models for the prediction of UGT1A1 inhibitors by integrating information on UGT1A1 structure and dynamics, interactions with diverse ligands, and machine learning. These models can be helpful for further prediction of drug-drug interactions of drug candidates and safety treatments.

•

UGTs are responsible for 35% of the phase II drug metabolism reactions

•

We created machine learning models for prediction of UGT1A1 inhibitors

•

Our simulations suggested key residues of UGT1A1 involved in the substrate binding

High-throughput screening paradigms in ecotoxicity testing: Emerging prospects and ongoing challenges

The rapidly increasing number of new production chemicals coupled with stringent implementation of global chemical management programs necessities a paradigm shift towards boarder uses of low-cost and high-throughput ecotoxicity testing strategies as well as deeper understanding of cellular and sub-cellular mechanisms of ecotoxicity that can be used in effective risk assessment. The latter will require automated acquisition of biological data, new capabilities for big data analysis as well as computational simulations capable of translating new data into in vivo relevance. However, very few efforts have been so far devoted into the development of automated bioanalytical systems in ecotoxicology. This is in stark contrast to standardized and high-throughput chemical screening and prioritization routines found in modern drug discovery pipelines. As a result, the high-throughput and high-content data acquisition in ecotoxicology is still in its infancy with limited examples focused on cell-free and cell-based assays. In this work we outline recent developments and emerging prospects of high-throughput bioanalytical approaches in ecotoxicology that reach beyond in vitro biotests. We discuss future importance of automated quantitative data acquisition for cell-free, cell-based as well as developments in phytotoxicity and in vivo biotests utilizing small aquatic model organisms. We also discuss recent innovations such as organs-on-a-chip technologies and existing challenges for emerging high-throughput ecotoxicity testing strategies. Lastly, we provide seminal examples of the small number of successful high-throughput implementations that have been employed in prioritization of chemicals and accelerated environmental risk assessment.

Application of ToxCast/Tox21 data for toxicity mechanism-based evaluation and prioritization of environmental chemicals: Perspective and limitations

In response to the need to minimize the use of experimental animals, new approach methodologies (NAMs) using advanced technology have emerged in the 21st century. ToxCast/Tox21 aims to evaluate the adverse effects of chemicals quickly and efficiently using a high-throughput screening and to transform the paradigm of toxicity assessment into mechanism-based toxicity prediction. The ToxCast/Tox21 database, which contains extensive data from over 1400 assays with numerous biological targets and activity data for over 9000 chemicals, can be used for various purposes in the field of chemical prioritization and toxicity prediction. In this study, an overview of the database was explored to aid mechanism-based chemical prioritization and toxicity prediction. Implications for the utilization of the ToxCast/Tox21 database in chemical prioritization and toxicity prediction were derived. The research trends in ToxCast/Tox21 assay data were reviewed in the context of toxicity mechanism identification, chemical priority, environmental monitoring, assay development, and toxicity prediction. Finally, the potential applications and limitations of using ToxCast/Tox21 assay data in chemical risk assessment were discussed. The analysis of the toxicity mechanism-based assays of ToxCast/Tox21 will help in chemical prioritization and regulatory applications without the use of laboratory animals.

Development of the InTelligence And Machine LEarning (TAME) Toolkit for Introductory Data Science, Chemical-Biological Analyses, Predictive Modeling, and Database Mining for Environmental Health Research

Research in environmental health is becoming increasingly reliant upon data science and computational methods that can more efficiently extract information from complex datasets. Data science and computational methods can be leveraged to better identify relationships between exposures to stressors in the environment and human disease outcomes, representing critical information needed to protect and improve global public health. Still, there remains a critical gap surrounding the training of researchers on these in silico methods. We aimed to address this gap by developing the inTelligence And Machine lEarning (TAME) Toolkit, promoting trainee-driven data generation, management, and analysis methods to “TAME” data in environmental health studies. Training modules were developed to provide applications-driven examples of data organization and analysis methods that can be used to address environmental health questions. Target audiences for these modules include students, post-baccalaureate and post-doctorate trainees, and professionals that are interested in expanding their skillset to include recent advances in data analysis methods relevant to environmental health, toxicology, exposure science, epidemiology, and bioinformatics/cheminformatics. Modules were developed by study coauthors using annotated script and were organized into three chapters within a GitHub Bookdown site. The first chapter of modules focuses on introductory data science, which includes the following topics: setting up R/RStudio and coding in the R environment; data organization basics; finding and visualizing data trends; high-dimensional data visualizations; and Findability, Accessibility, Interoperability, and Reusability (FAIR) data management practices. The second chapter of modules incorporates chemical-biological analyses and predictive modeling, spanning the following methods: dose-response modeling; machine learning and predictive modeling; mixtures analyses; -omics analyses; toxicokinetic modeling; and read-across toxicity predictions. The last chapter of modules was organized to provide examples on environmental health database mining and integration, including chemical exposure, health outcome, and environmental justice indicators. Training modules and associated data are publicly available online (https://uncsrp.github.io/Data-Analysis-Training-Modules/). Together, this resource provides unique opportunities to obtain introductory-level training on current data analysis methods applicable to 21st century science and environmental health.

Chemical Mixtures in Household Environments: In Silico Predictions and In Vitro Testing of Potential Joint Action on PPARγ in Human Liver Cells

There are thousands of chemicals that humans can be exposed to in their everyday environments, the majority of which are currently understudied and lack substantial testing for potential exposure and toxicity. This study aimed to implement in silico methods to characterize the chemicals that co-occur across chemical and product uses in our everyday household environments that also target a common molecular mediator, thus representing understudied mixtures that may exacerbate toxicity in humans. To detail, the Chemical and Products Database (CPDat) was queried to identify which chemicals co-occur across common exposure sources. Chemicals were preselected to include those that target an important mediator of cell health and toxicity, the peroxisome proliferator activated receptor gamma (PPARγ), in liver cells that were identified through query of the ToxCast/Tox21 database. These co-occurring chemicals were thus hypothesized to exert potential joint effects on PPARγ. To test this hypothesis, five commonly co-occurring chemicals (namely, benzyl cinnamate, butyl paraben, decanoic acid, eugenol, and sodium dodecyl sulfate) were tested individually and in combination for changes in the expression of PPARγ and its downstream target, insulin receptor (INSR), in human liver HepG2 cells. Results showed that these likely co-occurring chemicals in household environments increased both PPARγ and INSR expression more significantly when the exposures occurred as mixtures vs. as individual chemicals. Future studies will evaluate such chemical combinations across more doses, allowing for further quantification of the types of joint action while leveraging this method of chemical combination prioritization. This study demonstrates the utility of in silico-based methods to identify chemicals that co-occur in the environment for mixtures toxicity testing and highlights relationships between understudied chemicals and changes in PPARγ-associated signaling.

Machine learning-driven identification of drugs inhibiting cytochrome P450 2C9

Cytochrome P450 2C9 (CYP2C9) is a major drug-metabolizing enzyme that represents 20% of the hepatic CYPs and is responsible for the metabolism of 15% of drugs. A general concern in drug discovery is to avoid the inhibition of CYP leading to toxic drug accumulation and adverse drug-drug interactions. However, the prediction of CYP inhibition remains challenging due to its complexity. We developed an original machine learning approach for the prediction of drug-like molecules inhibiting CYP2C9. We created new predictive models by integrating CYP2C9 protein structure and dynamics knowledge, an original selection of physicochemical properties of CYP2C9 inhibitors, and machine learning modeling. We tested the machine learning models on publicly available data and demonstrated that our models successfully predicted CYP2C9 inhibitors with an accuracy, sensitivity and specificity of approximately 80%. We experimentally validated the developed approach and provided the first identification of the drugs vatalanib, piriqualone, ticagrelor and cloperidone as strong inhibitors of CYP2C9 with IC values <18 μM and sertindole, asapiprant, duvelisib and dasatinib as moderate inhibitors with IC50 values between 40 and 85 μM. Vatalanib was identified as the strongest inhibitor with an IC50 value of 0.067 μM. Metabolism assays allowed the characterization of specific metabolites of abemaciclib, cloperidone, vatalanib and tarafenacin produced by CYP2C9. The obtained results demonstrate that such a strategy could improve the prediction of drug-drug interactions in clinical practice and could be utilized to prioritize drug candidates in drug discovery pipelines.

Tox-GAN: An AI Approach Alternative to Animal Studies-a Case Study with Toxicogenomics

Animal studies are a critical component in biomedical research, pharmaceutical product development, and regulatory submissions. There is a worldwide effort in toxicology towards "reducing, refining and replacing" (3Rs) animal use. Here, we proposed a deep generative adversarial network (GAN)-based framework capable of deriving new animal results from existing animal studies without additional experiments. To prove the concept, we employed this Tox-GAN framework to generate both gene activities and expression profiles for multiple doses and treatment durations in toxicogenomics (TGx). Using the pre-existing rat liver TGx data from the Open TG-GATEs, we generated Tox-GAN transcriptomic profiles with high similarity (0.997 ± 0.002 in intensity and 0.740 ± 0.082 in fold change) to the corresponding real gene expression profiles. Consequently, Tox-GAN showed an outstanding performance in two critical TGx applications, gaining a molecular understanding of underlying toxicological mechanisms and gene expression-based biomarker development. For the former, over 87% agreement in Gene Ontology was found between Tox-GAN results and real gene expression data. For the latter, the concordance of biomarkers between real and generated data was high in both predictive performance and biomarker genes. We also demonstrated that the Tox-GAN models constructed with TG-GATEs data were capable of generating transcriptomic profiles reported in DrugMatrix. Finally, we demonstrated potential utility for Tox-GAN in aiding chemical-based read-across. To the best of our knowledge, the proposed Tox-GAN model is novel in its ability to generate in vivo transcriptomic profiles at different treatment conditions from chemical structures. Overall, Tox-GAN holds great promise for generating high-quality toxicogenomic profiles without animal experimentation.

Artificial intelligence unifies knowledge and actions in drug repositioning

Drug repositioning aims to reuse existing drugs, shelved drugs, or drug candidates that failed clinical trials for other medical indications. Its attraction is sprung from the reduction in risk associated with safety testing of new medications and the time to get a known drug into the clinics. Artificial Intelligence (AI) has been recently pursued to speed up drug repositioning and discovery. The essence of AI in drug repositioning is to unify the knowledge and actions, i.e. incorporating real-world and experimental data to map out the best way forward to identify effective therapeutics against a disease. In this review, we share positive expectations for the evolution of AI and drug repositioning and summarize the role of AI in several methods of drug repositioning.

Quantum semi-supervised generative adversarial network for enhanced data classification

In this paper, we propose the quantum semi-supervised generative adversarial network (qSGAN). The system is composed of a quantum generator and a classical discriminator/classifier (D/C). The goal is to train both the generator and the D/C, so that the latter may get a high classification accuracy for a given dataset. Hence the qSGAN needs neither any data loading nor to generate a pure quantum state, implying that qSGAN is much easier to implement than many existing quantum algorithms. Also the generator can serve as a stronger adversary than a classical one thanks to its rich expressibility, and it is expected to be robust against noise. These advantages are demonstrated in a numerical simulation.