COSMOS next generation - A public knowledge base leveraging chemical and biological data to support the regulatory assessment of chemicals

In Silico Prediction of Skin Sensitization for Compounds via Flexible Evidence Combination Based on Machine Learning and Dempster-Shafer Theory

Skin sensitization is increasingly becoming a significant concern in the development of drugs and cosmetics due to consumer safety and occupational health problems. In silico methods have emerged as alternatives to traditional in vivo animal testing due to ethical and economic considerations. In this study, machine learning methods were used to build quantitative structure-activity relationship (QSAR) models on five skin sensitization data sets (GPMT, LLNA, DPRA, KeratinoSens, and h-CLAT), achieving effective predictive accuracies (correct classification rates of 0.688-0.764 on test sets). To address the complex mechanisms of human skin sensitization, the Dempster-Shafer theory was applied to merge multiple QSAR models, resulting in an evidence-based integrated decision model. Various evidence combinations and combination rules were explored, with the self-defined Q3 rule showing superior balance. The combination of evidence such as GPMT and KeratinoSens and h-CLAT achieved a correct classification rate (CCR) of 0.880 and coverage of 0.893 while maintaining the competitiveness of other combinations. Additionally, the Shapley additive explanations (SHAP) method was used to interpret important features and substructures related to skin sensitization. A comparative analysis of an external human test set demonstrated the superior performance of the proposed method. Finally, to enhance accessibility, the workflow was implemented into a user-friendly software named HSkinSensDS.

New approaches build upon historical studies in dermal toxicology

These are my personal reflections on the history of approaches to understanding dermal toxicology brought together for the Paton Prize Award. This is not a comprehensive account of all publications from in vivo studies in humans to development of in vitro and in silico approaches but highlghts important progress. I will consider what is needed now to influence approaches to understanding dermal exposure with the current development and use of NAMs (new approach methodologies).

Update of the Cancer Potency Database (CPDB) to enable derivations of Thresholds of Toxicological Concern (TTC) for cancer potency

The purpose of this study was to update the existing Cancer Potency Database (CPDB) in order to support the development of a dataset of compounds, with associated points of departure (PoDs), to enable a review and update of currently applied values for the Threshold of Toxicological Concern (TTC) for cancer endpoints. This update of the current CPDB, last reviewed in 2012, includes the addition of new data (44 compounds and 158 studies leading to additional 359 dose-response curves). Strict inclusion criteria were established and applied to select compounds and studies with relevant cancer potency data. PoDs were calculated from dose-response modeling, including the benchmark dose (BMD) and the lower 90% confidence limits (BMDL) at a specified benchmark response (BMR) of 10%. The updated full CPDB database resulted in a total of 421 chemicals which had dose-response data that could be used to calculate PoDs. This candidate dataset for cancer TTC is provided in a transparent and adaptable format for further analysis of TTC to derive cancer potency thresholds.

High Throughput Read-Across for Screening a Large Inventory of Related Structures by Balancing Artificial Intelligence/Machine Learning and Human Knowledge

Read-across is an in silico method applied in chemical risk assessment for data-poor chemicals. The read-across outcomes for repeated-dose toxicity end points include the no-observed-adverse-effect level (NOAEL) and estimated uncertainty for a particular category of effects. We have previously developed a new paradigm for estimating NOAELs based on chemoinformatics analysis and experimental study qualities from selected analogues, not relying on quantitative structure-activity relationships (QSARs) or rule-based SAR systems, which are not well-suited to end points for which the underpinning data are weakly grounded in specific chemical-biological interactions. The central hypothesis of this approach is that similar compounds have similar toxicity profiles and, hence, similar NOAEL values. Analogue quality (AQ) quantifies the suitability of an analogue candidate for reading across to the target by considering similarity from structure, physicochemical, ADME (absorption, distribution, metabolism, excretion), and biological perspectives. Biological similarity is based on experimental data; assay vectors derived from aggregations of ToxCast/Tox21 data are used to derive machine learning (ML) hybrid rules that serve as biological fingerprints to capture target-analogue similarity relevant to specific effects of interest, for example, hormone receptors (ER/AR/THR). Once one or more analogues have been qualified for read-across, a decision theory approach is used to estimate confidence bounds for the NOAEL of the target. The confidence interval is dramatically narrowed when analogues are constrained to biologically related profiles. Although this read-across process works well for a single target with several analogues, it can become unmanageable when, for example, screening multiple targets (e.g., virtual screening library) or handling a parent compound having numerous metabolites. To this end, we have established a digitalized framework to enable the assessment of a large number of substances, while still allowing for human decisions for filtering and prioritization. This workflow was developed and validated through a use case of a large set of bisphenols and their metabolites.

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.

Making in silico predictive models for toxicology FAIR

In silico predictive models for toxicology include quantitative structure-activity relationship (QSAR) and physiologically based kinetic (PBK) approaches to predict physico-chemical and ADME properties, toxicological effects and internal exposure. Such models are used to fill data gaps as part of chemical risk assessment. There is a growing need to ensure in silico predictive models for toxicology are available for use and reproducible. This paper describes how the FAIR (Findable, Accessible, Interoperable, Reusable) principles, developed for data sharing, have been applied to in silico predictive models. In particular, this investigation has focussed on how the FAIR principles could be applied to improved regulatory acceptance of predictions from such models. Eighteen principles have been developed that cover all aspects of FAIR. It is intended that FAIRification of in silico predictive models for toxicology will increase their use and acceptance.

Construction of an In Silico Structural Profiling Tool Facilitating Mechanistically Grounded Classification of Aquatic Toxicants

The performance of chemical safety assessment within the domain of environmental toxicology is often impeded by a shortfall of appropriate experimental data describing potential hazards across the many compounds in regular industrial use. In silico schemes for assigning aquatic-relevant modes or mechanisms of toxic action to substances, based solely on consideration of chemical structure, have seen widespread employment─including those of Verhaar, Russom, and later Bauer (MechoA). Recently, development of a further system was reported by Sapounidou, which, in common with MechoA, seeks to ground its classifications in understanding and appreciation of molecular initiating events. Until now, this Sapounidou scheme has not seen implementation as a tool for practical screening use. Accordingly, the primary purpose of this study was to create such a resource─in the form of a computational workflow. This exercise was facilitated through the formulation of 183 structural alerts/rules describing molecular features associated with narcosis, chemical reactivity, and specific mechanisms of action. Output was subsequently compared relative to that of the three aforementioned alternative systems to identify strengths and shortcomings as regards coverage of chemical space.

The chemical landscape of high-throughput new approach methodologies for exposure

The rapid characterization of risk to humans and ecosystems from exogenous chemicals requires information on both hazard and exposure. The U.S. Environmental Protection Agency's ToxCast program and the interagency Tox21 initiative have screened thousands of chemicals in various high-throughput (HT) assay systems for in vitro bioactivity. EPA's ExpoCast program is developing complementary HT methods for characterizing the human and ecological exposures necessary to interpret HT hazard data in a real-world risk context. These new approach methodologies (NAMs) for exposure include computational and analytical tools for characterizing multiple components of the complex pathways chemicals take from their source to human and ecological receptors. Here, we analyze the landscape of exposure NAMs developed in ExpoCast in the context of various chemical lists of scientific and regulatory interest, including the ToxCast and Tox21 libraries and the Toxic Substances Control Act (TSCA) inventory. We examine the landscape of traditional and exposure NAM data covering chemical use, emission, environmental fate, toxicokinetics, and ultimately external and internal exposure. We consider new chemical descriptors, machine learning models that draw inferences from existing data, high-throughput exposure models, statistical frameworks that integrate multiple model predictions, and non-targeted analytical screening methods that generate new HT monitoring information. We demonstrate that exposure NAMs drastically improve the coverage of the chemical landscape compared to traditional approaches and recommend a set of research activities to further expand the development of HT exposure data for application to risk characterization. Continuing to develop exposure NAMs to fill priority data gaps identified here will improve the availability and defensibility of risk-based metrics for use in chemical prioritization and screening. IMPACT: This analysis describes the current state of exposure assessment-based new approach methodologies across varied chemical landscapes and provides recommendations for filling key data gaps.

Virtual Extensive Read-Across: A New Open-Access Software for Chemical Read-Across and Its Application to the Carcinogenicity Assessment of Botanicals

Read-across applies the principle of similarity to identify the most similar substances to represent a given target substance in data-poor situations. However, differences between the target and the source substances exist. The present study aims to screen and assess the effect of the key components in a molecule which may escape the evaluation for read-across based only on the most similar substance(s) using a new open-access software: Virtual Extensive Read-Across (VERA). VERA provides a means to assess similarity between chemicals using structural alerts specific to the property, pre-defined molecular groups and structural similarity. The software finds the most similar compounds with a certain feature, e.g., structural alerts and molecular groups, and provides clusters of similar substances while comparing these similar substances within different clusters. Carcinogenicity is a complex endpoint with several mechanisms, requiring resource intensive experimental bioassays and a large number of animals; as such, the use of read-across as part of new approach methodologies would support carcinogenicity assessment. To test the VERA software, carcinogenicity was selected as the endpoint of interest for a range of botanicals. VERA correctly labelled 70% of the botanicals, indicating the most similar substances and the main features associated with carcinogenicity.

In Silico Models for Predicting Acute Systemic Toxicity

In this chapter, we give a brief overview of the regulatory requirements for acute systemic toxicity information in the European Union, and we review structure-based computational models that are available and potentially useful in the assessment of acute systemic toxicity. Emphasis is placed on quantitative structure-activity relationship (QSAR) models implemented by means of a range of software tools. The most recently published literature models for acute systemic toxicity are also discussed, and perspectives for future developments in this field are offered.