Expanding Predictive Capacities in Toxicology: Insights from Hackathon-Enhanced Data and Model Aggregation.

In the realm of predictive toxicology for small molecules, the applicability domain of QSAR models is often limited by the coverage of the chemical space in the training set. Consequently, classical models fail to provide reliable predictions for wide classes of molecules. However, the emergence of innovative data collection methods such as intensive hackathons have promise to quickly expand the available chemical space for model construction. Combined with algorithmic refinement methods, these tools can address the challenges of toxicity prediction, enhancing both the robustness and applicability of the corresponding models. This study aimed to investigate the roles of gradient boosting and strategic data aggregation in enhancing the predictivity ability of models for the toxicity of small organic molecules. We focused on evaluating the impact of incorporating fragment features and expanding the chemical space, facilitated by a comprehensive dataset procured in an open hackathon. We used gradient boosting techniques, accounting for critical features such as the structural fragments or functional groups often associated with manifestations of toxicity.

Assessing the impact of a new medical toxicology service on the treatment of paracetamol overdose at a large tertiary care hospital.

BACKGROUND: Paracetamol overdose is the most common cause of acute liver failure in the United States. Administration of acetylcysteine is the standard of care for this intoxication. Laboratory values and clinical criteria are used to guide treatment duration, but decision-making is nuanced and often complex and difficult. The purpose of this study was to evaluate the effect of the introduction of a medical toxicology service on the rate of errors in the management of paracetamol overdose. METHODS: This was a single center, retrospective, cohort evaluation. Patients with suspected paracetamol overdose were divided into two groups: those attending in the 1 year period before and those in the 1 year after the introduction of the medical toxicology service. The primary outcome was the frequency of deviations from the established management of paracetamol intoxication, using international guidelines as a reference. RESULTS: Fifty-four patients were eligible for the study (20 pre-toxicology-service, 34 post-toxicology-service). The frequency of incorrect therapeutic decisions was significantly lower in the post-toxicology service implementation versus the pre-implementation group (P = 0.005). DISCUSSION: Our study suggests that a medical toxicology service reduces the incidence of management errors, including the number of missed acetylcysteine doses in patients with paracetamol overdose. The limitations include the retrospective study design and that the study was conducted at a single center, which may limit generalizability. CONCLUSIONS: The implementation of a medical toxicology service was associated with a decrease in the number of errors in the management of paracetamol overdose.

Exploring rabbit as a nonrodent species for general toxicology studies.

To avoid adverse events in humans, toxicity studies in nonclinical species have been the foundation of safety evaluation in the pharmaceutical industry. However, it is recognized that working with animals in research is a privilege, and conscientious use should always respect the 3Rs: replacement, reduction, and refinement. In the wake of the shortages in routine nonrodent species and considering that nonanimal methods are not yet sufficiently mature, the value of the rabbit as a nonrodent species is worth exploring. Historically used in vaccine, cosmetic, and medical device testing, the rabbit is seldom used today as a second species in pharmaceutical development, except for embryo-fetal development studies, ophthalmic therapeutics, some medical devices and implants, and vaccines. Although several factors affect the decision of species selection, including pharmacological relevance, pharmacokinetics, and ADME considerations, there are no perfect animal models. In this forum article, we bring together experts from veterinary medicine, industry, contract research organizations, and government to explore the pros and cons, residual concerns, and data gaps regarding the use of the rabbit for general toxicity testing.

The probable future of toxicology - probabilistic risk assessment.

Both because of the shortcomings of existing risk assessment methodologies, as well as newly available tools to predict hazard and risk with machine learning approaches, there has been an emerging emphasis on probabilistic risk assessment. Increasingly sophisticated AI models can be applied to a plethora of exposure and hazard data to obtain not only predictions for particular endpoints but also to estimate the uncertainty of the risk assessment outcome. This provides the basis for a shift from deterministic to more probabilistic approaches but comes at the cost of an increased complexity of the process as it requires more resources and human expertise. There are still challenges to overcome before a probabilistic paradigm is fully embraced by regulators. Based on an earlier white paper (Maertens et al., 2022), a workshop discussed the prospects, challenges and path forward for implementing such AI-based probabilistic hazard assessment. Moving forward, we will see the transition from categorized into probabilistic and dose-dependent hazard outcomes, the application of internal thresholds of toxicological concern for data-poor substances, the acknowledgement of user-friendly open-source software, a rise in the expertise of toxicologists required to understand and interpret artificial intelligence models, and the honest communication of uncertainty in risk assessment to the public.

Probabilistic risk assessment, initially from engineering, is applied in toxicology to understand chemical-related hazards and their consequences. In toxicology, uncertainties abound ­ unclear molecular events, varied proposed outcomes, and population-level assessments for issues like neurodevelopmental disorders. Establishing links between chemical exposures and diseases, especially rare events like birth defects, often demands extensive studies. Existing methods struggle with subtle effects or those affecting specific groups. Future risk assessments must address developmental disease origins, presenting challenges beyond current capabilities. The intricate nature of many toxicological processes, lack of consensus on mechanisms and outcomes, and the need for nuanced population-level assessments highlight the complexities in understanding and quantifying risks associated with chemical exposures in the field of toxicology.

Quantifying the Benefits of Imputation over QSAR Methods in Toxicology Data Modeling.

Imputation machine learning (ML) surpasses traditional approaches in modeling toxicity data. The method was tested on an open-source data set comprising approximately 2500 ingredients with limited in vitro and in vivo data obtained from the OECD QSAR Toolbox. By leveraging the relationships between different toxicological end points, imputation extracts more valuable information from each data point compared to well-established single end point methods, such as ML-based Quantitative Structure Activity Relationship (QSAR) approaches, providing a final improvement of up to around 0.2 in the coefficient of determination. A significant aspect of this methodology is its resilience to the inclusion of extraneous chemical or experimental data. While additional data typically introduces a considerable level of noise and can hinder performance of single end point QSAR modeling, imputation models remain unaffected. This implies a reduction in the need for laborious manual preprocessing tasks such as feature selection, thereby making data preparation for ML analysis more efficient. This successful test, conducted on open-source data, validates the efficacy of imputation approaches in toxicity data analysis. This work opens the way for applying similar methods to other types of sparse toxicological data matrices, and so we discuss the development of regulatory authority guidelines to accept imputation models, a key aspect for the wider adoption of these methods.

High-Throughput Screening to Advance In Vitro Toxicology: Accomplishments, Challenges, and Future Directions.

Traditionally, chemical toxicity is determined by in vivo animal studies, which are low throughput, expensive, and sometimes fail to predict compound toxicity in humans. Due to the increasing number of chemicals in use and the high rate of drug candidate failure due to toxicity, it is imperative to develop in vitro, high-throughput screening methods to determine toxicity. The Tox21 program, a unique research consortium of federal public health agencies, was established to address and identify toxicity concerns in a high-throughput, concentration-responsive manner using a battery of in vitro assays. In this article, we review the advancements in high-throughput robotic screening methodology and informatics processes to enable the generation of toxicological data, and their impact on the field; further, we discuss the future of assessing environmental toxicity utilizing efficient and scalable methods that better represent the corresponding biological and toxicodynamic processes in humans.

[Deductive Toxicology and Bioorganometallics].

Toxicology based on a deductive approach is called "deductive toxicology," which attempts to explain clinical and pathological findings by collecting all scientific information about the chemical substance under study and relating them to the essence of toxicity. We have introduced the method of signal toxicology into the deductive toxicology of metal and have shown that signal toxicity exists in heavy metals. Based on the results, we have proposed a new research strategy called "bioorganometallics," in which organic-inorganic hybrid molecules are used as molecular probes to analyze biological systems. This review outlines our research that has evolved from "deductive toxicology" to "bioorganometallics."

Current state-of-the-art approaches for mass spectrometry in clinical toxicology: an overview.

INTRODUCTION: Hyphenated mass spectrometry (MS) has evolved into a very powerful analytical technique of high sensitivity and specificity. It is used to analyze a very wide spectrum of analytes in classical and alternative matrices. The presented paper will provide an overview of the current state-of-the-art of hyphenated MS applications in clinical toxicology primarily based on review articles indexed in PubMed (1990 to April 2023). AREAS COVERED: A general overview of matrices, sample preparation, analytical systems, detection modes, and validation and quality control is given. Moreover, selected applications are discussed. EXPERT OPINION: A more widespread use of hyphenated MS techniques, especially in systematic toxicological analysis and drugs of abuse testing, would help overcome limitations of immunoassay-based screening strategies. This is currently hampered by high instrument cost, qualification requirements for personnel, and less favorable turnaround times, which could be overcome by more user-friendly, ideally fully automated MS instruments. This would help making hyphenated MS-based analysis available in more laboratories and expanding analysis to a large number of organic drugs, poisons, and/or metabolites. Even the most recent novel psychoactive substances (NPS) could be presumptively identified by high-resolution MS methods, their likely presence be communicated to treating physicians, and be confirmed later on.

State of the Art of Genomic Technology in Toxicology: A Review.

The rapid growth of genomics techniques has revolutionized and impacted, greatly and positively, the knowledge of toxicology, ushering it into a "new era": the era of genomic technology (GT). This great advance permits us to analyze the whole genome, to know the gene response to toxicants and environmental stressors, and to determine the specific profiles of gene expression, among many other approaches. The aim of this work was to compile and narrate the recent research on GT during the last 2 years (2020-2022). A literature search was managed using the PubMed and Medscape interfaces on the Medline database. Relevant articles published in peer-reviewed journals were retrieved and their main results and conclusions are mentioned briefly. It is quite important to form a multidisciplinary taskforce on GT with the aim of designing and implementing a comprehensive, collaborative, and a strategic work plan, prioritizing and assessing the most relevant diseases, so as to decrease human morbimortality due to exposure to environmental chemicals and stressors.

Application of toxicology in silico methods for prediction of acute toxicity (LD50) for Novichoks.

Novichoks represent the fourth generation of chemical warfare agents with paralytic and convulsive effects, produced clandestinely during the Cold War by the Soviet Union. This novel class of organophosphate compounds is characterised by severe toxicity, which, for example, we have already experienced three times (Salisbury, Amesbury, and Navalny's case) as a society. Then the public debate about the true nature of Novichoks began, realising the importance of examining the properties, especially the toxicological aspects of these compounds. The updated Chemical Warfare Agents list registers over 10,000 compounds as candidate structures for Novichoks. Consequently, conducting experimental research for each of them would be a huge challenge. Additionally, due to the enormous risk of contact with hazardous Novichoks, in silico assessments were applied to estimate their toxicity safely. In silico toxicology provides a means of identifying hazards of compounds before synthesis, helping to fill gaps and guide risk minimisation strategies. A new approach to toxicology testing first considers the prediction of toxicological parameters, eliminating unnecessary animal studies. This new generation risk assessment (NGRA) can meet the modern requirements of toxicological research. The present study explains, using QSAR models, the acute toxicity of the Novichoks studied (n = 17). The results indicate that the toxicity of Novichoks varies. The deadliest turned out to be A-232, followed by A-230 and A-234. On the other hand, the "Iranian" Novichok and C01-A038 compounds turned out to be the least toxic. Developing reliable in silico methods to predict various parameters is essential to prepare for the upcoming use of Novichoks.

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.

The Precision Toxicology initiative.

The goal of PrecisionTox is to overcome conceptual barriers to replacing traditional mammalian chemical safety testing by accelerating the discovery of evolutionarily conserved toxicity pathways that are shared by descent among humans and more distantly related animals. An international consortium is systematically testing the toxicological effects of a diverse set of chemicals on a suite of five model species comprising fruit flies, nematodes, water fleas, and embryos of clawed frogs and zebrafish along with human cell lines. Multiple forms of omics and comparative toxicology data are integrated to map the evolutionary origins of biomolecular interactions that are predictive of adverse health effects, to major branches of the animal phylogeny. These conserved elements of adverse outcome pathways (AOPs) and their biomarkers are expected to provide mechanistic insight useful for regulating groups of chemicals based on their shared modes of action. PrecisionTox also aims to quantify risk variation within populations by recognizing susceptibility as a heritable trait that varies with genetic diversity. This initiative incorporates legal experts and collaborates with risk managers to address specific needs within European chemicals legislation, including the uptake of new approach methodologies (NAMs) for setting precise regulatory limits on toxic chemicals.

Toxicology and Analytical Chemistry.

Knowing how to effectively use veterinary diagnostic toxicology laboratories is key when navigating suspect toxicoses in ruminants. This begins with establishing a causal relationship between clinical signs and potential sources of exposure, followed by collecting the appropriate samples for toxicology testing. There are times in which a successful diagnosis is hindered by not obtaining a thorough case history and not knowing what specimens to collect, or how much specimen to submit, for toxicology testing. This article is intended to offer some guidance with respect to the effective use of veterinary toxicology/analytical chemistry laboratories when navigating suspect toxicology cases in ruminants.

TOXRIC: a comprehensive database of toxicological data and benchmarks.

The toxic effects of compounds on environment, humans, and other organisms have been a major focus of many research areas, including drug discovery and ecological research. Identifying the potential toxicity in the early stage of compound/drug discovery is critical. The rapid development of computational methods for evaluating various toxicity categories has increased the need for comprehensive and system-level collection of toxicological data, associated attributes, and benchmarks. To contribute toward this goal, we proposed TOXRIC (https://toxric.bioinforai.tech/), a database with comprehensive toxicological data, standardized attribute data, practical benchmarks, informative visualization of molecular representations, and an intuitive function interface. The data stored in TOXRIC contains 113 372 compounds, 13 toxicity categories, 1474 toxicity endpoints covering in vivo/in vitro endpoints and 39 feature types, covering structural, target, transcriptome, metabolic data, and other descriptors. All the curated datasets of endpoints and features can be retrieved, downloaded and directly used as output or input to Machine Learning (ML)-based prediction models. In addition to serving as a data repository, TOXRIC also provides visualization of benchmarks and molecular representations for all endpoint datasets. Based on these results, researchers can better understand and select optimal feature types, molecular representations, and baseline algorithms for each endpoint prediction task. We believe that the rich information on compound toxicology, ML-ready datasets, benchmarks and molecular representation distribution can greatly facilitate toxicological investigations, interpretation of toxicological mechanisms, compound/drug discovery and the development of computational methods.

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.

Toxicology, Nanotoxicology and Occupational Diseases Related to Chemical Exposure.

The Special Issue "Toxicology, Nanotoxicology and Occupational Diseases" of the International Journal of Molecular Sciences includes six articles presenting the results of recent experimental studies in the fields of toxicology, nanotoxicology, and occupational health [...].

Scientific and Regulatory Policy Committee Points to Consider: Integration of Clinical Pathology Data With Anatomic Pathology Data in Nonclinical Toxicology Studies.

Integrating clinical pathology data with anatomic pathology data is a common practice when reporting findings in the context of nonclinical toxicity studies and aids in understanding and communicating the nonclinical safety profile of test articles in development. Appropriate pathology data integration requires knowledge of analyte and tissue biology, species differences, methods of specimen acquisition and analysis, study procedures, and an understanding of the potential causes and effects of a variety of pathophysiologic processes. Neglecting these factors can lead to inappropriate data integration or a missed opportunity to enhance understanding and communication of observed changes. In such cases, nonclinical safety information relevant to human safety risk assessment may be misrepresented or misunderstood. This "Points to Consider" manuscript presents general concepts regarding pathology data integration in nonclinical studies, considerations for avoiding potential oversights and errors in data integration, and focused discussion on topics relevant to data integration for several key organ systems including liver, kidney, and cardiovascular system.