A Mechanistic Framework for Integrating Chemical Structure and High-Throughput Screening Results to Improve Toxicity Predictions

Computational Strategies for Assessing Adverse Outcome Pathways: Hepatic Steatosis as a Case Study

The evolving landscape of chemical risk assessment is increasingly focused on developing tiered, mechanistically driven approaches that avoid the use of animal experiments. In this context, adverse outcome pathways have gained importance for evaluating various types of chemical-induced toxicity. Using hepatic steatosis as a case study, this review explores the use of diverse computational techniques, such as structure-activity relationship models, quantitative structure-activity relationship models, read-across methods, omics data analysis, and structure-based approaches to fill data gaps within adverse outcome pathway networks. Emphasizing the regulatory acceptance of each technique, we examine how these methodologies can be integrated to provide a comprehensive understanding of chemical toxicity. This review highlights the transformative impact of in silico techniques in toxicology, proposing guidelines for their application in evidence gathering for developing and filling data gaps in adverse outcome pathway networks. These guidelines can be applied to other cases, advancing the field of toxicological risk assessment.

The ToxCast pipeline: updates to curve-fitting approaches and database structure

Introduction: The US Environmental Protection Agency Toxicity Forecaster (ToxCast) program makes in vitro medium- and high-throughput screening assay data publicly available for prioritization and hazard characterization of thousands of chemicals. The assays employ a variety of technologies to evaluate the effects of chemical exposure on diverse biological targets, from distinct proteins to more complex cellular processes like mitochondrial toxicity, nuclear receptor signaling, immune responses, and developmental toxicity. The ToxCast data pipeline (tcpl) is an open-source R package that stores, manages, curve-fits, and visualizes ToxCast data and populates the linked MySQL Database, invitrodb. Methods: Herein we describe major updates to tcpl and invitrodb to accommodate a new curve-fitting approach. The original tcpl curve-fitting models (constant, Hill, and gain-loss models) have been expanded to include Polynomial 1 (Linear), Polynomial 2 (Quadratic), Power, Exponential 2, Exponential 3, Exponential 4, and Exponential 5 based on BMDExpress and encoded by the R package dependency, tcplfit2. Inclusion of these models impacted invitrodb (beta version v4.0) and tcpl v3 in several ways: (1) long-format storage of generic modeling parameters to permit additional curve-fitting models; (2) updated logic for winning model selection; (3) continuous hit calling logic; and (4) removal of redundant endpoints as a result of bidirectional fitting. Results and discussion: Overall, the hit call and potency estimates were largely consistent between invitrodb v3.5 and 4.0. Tcpl and invitrodb provide a standard for consistent and reproducible curve-fitting and data management for diverse, targeted in vitro assay data with readily available documentation, thus enabling sharing and use of these data in myriad toxicology applications. The software and database updates described herein promote comparability across multiple tiers of data within the US Environmental Protection Agency CompTox Blueprint.

iRaPCA and SOMoC: Development and Validation of Web Applications for New Approaches for the Clustering of Small Molecules

The clustering of small molecules implies the organization of a group of chemical structures into smaller subgroups with similar features. Clustering has important applications to sample chemical datasets or libraries in a representative manner (e.g., to choose, from a virtual screening hit list, a chemically diverse subset of compounds to be submitted to experimental confirmation, or to split datasets into representative training and validation sets when implementing machine learning models). Most strategies for clustering molecules are based on molecular fingerprints and hierarchical clustering algorithms. Here, two open-source in-house methodologies for clustering of small molecules are presented: iterative Random subspace Principal Component Analysis clustering (iRaPCA), an iterative approach based on feature bagging, dimensionality reduction, and K-means optimization; and Silhouette Optimized Molecular Clustering (SOMoC), which combines molecular fingerprints with the Uniform Manifold Approximation and Projection (UMAP) and Gaussian Mixture Model algorithm (GMM). In a benchmarking exercise, the performance of both clustering methods has been examined across 29 datasets containing between 100 and 5000 small molecules, comparing these results with those given by two other well-known clustering methods, Ward and Butina. iRaPCA and SOMoC consistently showed the best performance across these 29 datasets, both in terms of within-cluster and between-cluster distances. Both iRaPCA and SOMoC have been implemented as free Web Apps and standalone applications, to allow their use to a wide audience within the scientific community.

Comparing Machine Learning Models for Aromatase (P450 19A1)

Aromatase, or cytochrome P450 19A1, catalyzes the aromatization of androgens to estrogens within the body. Changes in the activity of this enzyme can produce hormonal imbalances that can be detrimental to sexual and skeletal development. Inhibition of this enzyme can occur with drugs and natural products as well as environmental chemicals. Therefore, predicting potential endocrine disruption via exogenous chemicals requires that aromatase inhibition be considered in addition to androgen and estrogen pathway interference. Bayesian machine learning methods can be used for prospective prediction from the molecular structure without the need for experimental data. Herein, the generation and evaluation of multiple machine learning models utilizing different sources of aromatase inhibition data are described. These models are applied to two test sets for external validation with molecules relevant to drug discovery from the public domain. In addition, the performance of multiple machine learning algorithms was evaluated by comparing internal five-fold cross-validation statistics of the training data. These methods to predict aromatase inhibition from molecular structure, when used in concert with estrogen and androgen machine learning models, allow for a more holistic assessment of endocrine-disrupting potential of chemicals with limited empirical data and enable the reduction of the use of hazardous substances.

Comparison of Machine Learning Models for the Androgen Receptor

The androgen receptor (AR) is a target of interest for endocrine disruption research, as altered signaling can affect normal reproductive and neurological development for generations. In an effort to prioritize compounds with alternative methodologies, the U.S. Environmental Protection Agency (EPA) used in vitro data from 11 assays to construct models of AR agonist and antagonist signaling pathways. While these EPA ToxCast AR models require in vitro data to assign a bioactivity score, Bayesian machine learning methods can be used for prospective prediction from molecule structure alone. This approach was applied to multiple types of data corresponding to the EPA's AR signaling pathway with proprietary software, Assay Central. The training performance of all machine learning models, including six other algorithms, was evaluated by internal 5-fold cross-validation statistics. Bayesian machine learning models were also evaluated with external predictions of reference chemicals to compare prediction accuracies to published results from the EPA. The machine learning model group selected for further studies of endocrine disruption consisted of continuous AC50 data from the February 2019 release of ToxCast/Tox21. These efforts demonstrate how machine learning can be used to predict AR-mediated bioactivity and can also be applied to other targets of endocrine disruption.

Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction

The U.S. Environmental Protection Agency (EPA) periodically releases in vitro data across a variety of targets, including the estrogen receptor (ER). In 2015, the EPA used these data to construct mathematical models of ER agonist and antagonist pathways to prioritize chemicals for endocrine disruption testing. However, mathematical models require in vitro data prior to predicting estrogenic activity, but machine learning methods are capable of prospective prediction from the molecular structure alone. The current study describes the generation and evaluation of Bayesian machine learning models grouped by the EPA's ER agonist pathway model using multiple data types with proprietary software, Assay Central. External predictions with three test sets of in vitro and in vivo reference chemicals with agonist activity classifications were compared to previous mathematical model publications. Training data sets were subjected to additional machine learning algorithms and compared with rank normalized scores of internal five-fold cross-validation statistics. External predictions were found to be comparable or superior to previous studies published by the EPA. When assessing six additional algorithms for the training data sets, Assay Central performed similarly at a reduced computational cost. This study demonstrates that machine learning can prioritize chemicals for future in vitro and in vivo testing of ER agonism.

In Silico Guidance for In Vitro Androgen and Glucocorticoid Receptor ToxCast Assays

Molecular initiating events (MIEs) are key events in adverse outcome pathways that link molecular chemistry to target biology. As they are based on chemistry, these interactions are excellent targets for computational chemistry approaches to in silico modeling. In this work, we aim to link ligand chemical structures to MIEs for androgen receptor (AR) and glucocorticoid receptor (GR) binding using ToxCast data. This has been done using an automated computational algorithm to perform maximal common substructure searches on chemical binders for each target from the ToxCast dataset. The models developed show a high level of accuracy, correctly assigning 87.20% of AR binders and 96.81% of GR binders in a 25% test set using holdout cross-validation. The 2D structural alerts developed can be used as in silico models to predict these MIEs and as guidance for in vitro ToxCast assays to confirm hits. These models can target such experimental work, reducing the number of assays to be performed to gain required toxicological insight. Development of these models has also allowed some structural alerts to be identified as predictors for agonist or antagonist behavior at the receptor target. This work represents a first step in using computational methods to guide and target experimental approaches.

Internationalization of read-across as a validated new approach method (NAM) for regulatory toxicology

Read-across (RAx) translates available information from well-characterized chemicals to a substance for which there is a toxicological data gap. The OECD is working on case studies to probe general applicability of RAx, and several regulations (e.g., EU-REACH) already allow this procedure to be used to waive new in vivo tests. The decision to prepare a review on the state of the art of RAx as a tool for risk assessment for regulatory purposes was taken during a workshop with international experts in Ranco, Italy in July 2018. Three major issues were identified that need optimization to allow a higher regulatory acceptance rate of the RAx procedure: (i) the definition of similarity of source and target, (ii) the translation of biological/toxicological activity of source to target in the RAx procedure, and (iii) how to deal with issues of ADME that may differ between source and target. The use of new approach methodologies (NAM) was discussed as one of the most important innovations to improve the acceptability of RAx. At present, NAM data may be used to confirm chemical and toxicological similarity. In the future, the use of NAM may be broadened to fully characterize the hazard and toxicokinetic properties of RAx compounds. Concerning available guidance, documents on Good Read-Across Practice (GRAP) and on best practices to perform and evaluate the RAx process were identified. Here, in particular, the RAx guidance, being worked out by the European Commission’s H2020 project EU-ToxRisk together with many external partners with regulatory experience, is given.

The Next Generation Blueprint of Computational Toxicology at the U.S. Environmental Protection Agency

The U.S. Environmental Protection Agency (EPA) is faced with the challenge of efficiently and credibly evaluating chemical safety often with limited or no available toxicity data. The expanding number of chemicals found in commerce and the environment, coupled with time and resource requirements for traditional toxicity testing and exposure characterization, continue to underscore the need for new approaches. In 2005, EPA charted a new course to address this challenge by embracing computational toxicology (CompTox) and investing in the technologies and capabilities to push the field forward. The return on this investment has been demonstrated through results and applications across a range of human and environmental health problems, as well as initial application to regulatory decision-making within programs such as the EPA's Endocrine Disruptor Screening Program. The CompTox initiative at EPA is more than a decade old. This manuscript presents a blueprint to guide the strategic and operational direction over the next 5 years. The primary goal is to obtain broader acceptance of the CompTox approaches for application to higher tier regulatory decisions, such as chemical assessments. To achieve this goal, the blueprint expands and refines the use of high-throughput and computational modeling approaches to transform the components in chemical risk assessment, while systematically addressing key challenges that have hindered progress. In addition, the blueprint outlines additional investments in cross-cutting efforts to characterize uncertainty and variability, develop software and information technology tools, provide outreach and training, and establish scientific confidence for application to different public health and environmental regulatory decisions.

Unlocking the potential of in silico chemical safety assessment - A report on a cross-sector symposium on current opportunities and future challenges

In silico chemical safety assessment can support the evaluation of hazard and risk following potential exposure to a substance. A symposium identified a number of opportunities and challenges to implement in silico methods, such as quantitative structure-activity relationships (QSARs) and read-across, to assess the potential harm of a substance in a variety of exposure scenarios, e.g. pharmaceuticals, personal care products, and industrial chemicals. To initiate the process of in silico safety assessment, clear and unambiguous problem formulation is required to provide the context for these methods. These approaches must be built on data of defined quality, while acknowledging the possibility of novel data resources tapping into on-going progress with data sharing. Models need to be developed that cover appropriate toxicity and kinetic endpoints, and that are documented appropriately with defined uncertainties. The application and implementation of in silico models in chemical safety requires a flexible technological framework that enables the integration of multiple strands of data and evidence. The findings of the symposium allowed for the identification of priorities to progress in silico chemical safety assessment towards the animal-free assessment of chemicals.

Machine learning models for predicting endocrine disruption potential of environmental chemicals

We introduce here ML4Tox, a framework offering Deep Learning and Support Vector Machine models to predict agonist, antagonist, and binding activities of chemical compounds, in this case for the estrogen receptor ligand-binding domain. The ML4Tox models have been developed with a 10 × 5-fold cross-validation schema on the training portion of the CERAPP ToxCast dataset, formed by 1677 chemicals, each described by 777 molecular features. On the CERAPP "All Literature" evaluation set (agonist: 6319 compounds; antagonist 6539; binding 7283), ML4Tox significantly improved sensitivity over published results on all three tasks, with agonist: 0.78 vs 0.56; antagonist: 0.69 vs 0.11; binding: 0.66 vs 0.26.