Collaborative SAR Modeling and Prospective In Vitro Validation of Oxidative Stress Activation in Human HepG2 Cells.

Oxidative stress is the consequence of an abnormal increase of reactive oxygen species (ROS). ROS are generated mainly during the metabolism in both normal and pathological conditions as well as from exposure to xenobiotics. Xenobiotics can, on the one hand, disrupt molecular machinery involved in redox processes and, on the other hand, reduce the effectiveness of the antioxidant activity. Such dysregulation may lead to oxidative damage when combined with oxidative stress overpassing the cell capacity to detoxify ROS. In this work, a green fluorescent protein (GFP)-tagged nuclear factor erythroid 2-related factor 2 (NRF2)-regulated sulfiredoxin reporter (Srxn1-GFP) was used to measure the antioxidant response of HepG2 cells to a large series of drug and drug-like compounds (2230 compounds). These compounds were then classified as positive or negative depending on cellular response and distributed among different modeling groups to establish structure-activity relationship (SAR) models. A selection of models was used to prospectively predict oxidative stress induced by a new set of compounds subsequently experimentally tested to validate the model predictions. Altogether, this exercise exemplifies the different challenges of developing SAR models of a phenotypic cellular readout, model combination, chemical space selection, and results interpretation.

In Silico Methods for Carcinogenicity Assessment.

Screening compounds for potential carcinogenicity is of major importance for prevention of environmentally induced cancers. A large sequence of predictive models, ranging from short-term biological assays (e.g., mutagenicity tests) to theoretical models, has been attempted in this field. Theoretical approaches such as (Q)SAR are highly desirable for identifying carcinogens, since they actively promote the replacement, reduction, and refinement of animal tests. This chapter reports and describes some of the most noted (Q)SAR models based on human expert knowledge and statistical approaches, aiming at predicting the carcinogenicity of chemicals. Additionally, the performance of the selected models has been evaluated, and the results are interpreted in details by applying these predictive models to some pharmaceutical molecules.

Quantitative Structure-Activity Relationship Modeling of the Amplex Ultrared Assay to Predict Thyroperoxidase Inhibitory Activity.

The thyroid system plays a major role in the regulation of several physiological processes. The dysregulation of the thyroid system caused by the interference of xenobiotics and contaminants may bring to pathologies like hyper- and hypothyroidism and it has been recently correlated with adverse outcomes leading to cancer, obesity, diabetes and neurodevelopmental disorders. Thyroid disruption can occur at several levels. For example, the inhibition of thyroperoxidase (TPO) enzyme, which catalyses the synthesis of thyroid hormones, may cause dysfunctions related to hypothyroidism. The inhibition of the TPO enzyme can occur as a consequence of prolonged exposure to chemical compounds, for this reason it is of utmost importance to identify alternative methods to evaluate the large amount of pollutants and other chemicals that may pose a potential hazard to the human health. In this work, quantitative structure-activity relationship (QSAR) models to predict the TPO inhibitory potential of chemicals are presented. Models are developed by means of several machine learning and data selection approaches, and are based on data obtained in vitro with the Amplex UltraRed-thyroperoxidase (AUR-TPO) assay. Balancing methods and feature selection are applied during model development. Models are rigorously evaluated through internal and external validation. Based on validation results, two models based on Balanced Random Forest (BRF) and K-Nearest Neighbours (KNN) algorithms were selected for a further validation phase, that leads predictive performance (BA = 0.76-0.78 on external data) that is comparable with the reported experimental variability of the AUR-TPO assay (BA ∼0.70). Finally, a consensus between the two models was proposed (BA = 0.82). Based on the predictive performance, these models can be considered suitable for toxicity screening of environmental chemicals.

The index of ideality of correlation improves the predictive potential of models of the antioxidant activity of tripeptides from frog skin (Litoria rubella).

It is usually held that good-quality models for the biological activity of peptides must take into account their 3D architecture and descriptors of quantum mechanics. However, the present study shows that it is possible to build up models without these complex calculations. The structure of tripeptides represented by sequences of one-symbol abbreviations of the corresponding amino acids serves to build up quantitative structure-activity relationships for the antioxidant activity of tripeptides from frog skin. The statistical quality of the best model for the validation set is n = 27, r2 = 0.93, RMSE = 0.15.

CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity.

BACKGROUND: Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones and alter synthesis, transport, or metabolic pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being addressed using high-throughput screening (HTS) in vitro approaches and computational modeling. OBJECTIVES: In support of the Endocrine Disruptor Screening Program, the U.S. Environmental Protection Agency (EPA) led two worldwide consortiums to virtually screen chemicals for their potential estrogenic and androgenic activities. Here, we describe the Collaborative Modeling Project for Androgen Receptor Activity (CoMPARA) efforts, which follows the steps of the Collaborative Estrogen Receptor Activity Prediction Project (CERAPP). METHODS: The CoMPARA list of screened chemicals built on CERAPP's list of 32,464 chemicals to include additional chemicals of interest, as well as simulated ToxCast™ metabolites, totaling 55,450 chemical structures. Computational toxicology scientists from 25 international groups contributed 91 predictive models for binding, agonist, and antagonist activity predictions. Models were underpinned by a common training set of 1,746 chemicals compiled from a combined data set of 11 ToxCast™/Tox21 HTS in vitro assays. RESULTS: The resulting models were evaluated using curated literature data extracted from different sources. To overcome the limitations of single-model approaches, CoMPARA predictions were combined into consensus models that provided averaged predictive accuracy of approximately 80% for the evaluation set. DISCUSSION: The strengths and limitations of the consensus predictions were discussed with example chemicals; then, the models were implemented into the free and open-source OPERA application to enable screening of new chemicals with a defined applicability domain and accuracy assessment. This implementation was used to screen the entire EPA DSSTox database of ∼875,000 chemicals, and their predicted AR activities have been made available on the EPA CompTox Chemicals dashboard and National Toxicology Program's Integrated Chemical Environment. https://doi.org/10.1289/EHP5580.

QSAR Models for Human Carcinogenicity: An Assessment Based on Oral and Inhalation Slope Factors.

Carcinogenicity is a crucial endpoint for the safety assessment of chemicals and products. During the last few decades, the development of quantitative structure-activity relationship ((Q)SAR) models has gained importance for regulatory use, in combination with in vitro testing or expert-based reasoning. Several classification models can now predict both human and rat carcinogenicity, but there are few models to quantitatively assess carcinogenicity in humans. To our knowledge, slope factor (SF), a parameter describing carcinogenicity potential used especially for human risk assessment of contaminated sites, has never been modeled for both inhalation and oral exposures. In this study, we developed classification and regression models for inhalation and oral SFs using data from the Risk Assessment Information System (RAIS) and different machine learning approaches. The models performed well in classification, with accuracies for the external set of 0.76 and 0.74 for oral and inhalation exposure, respectively, and r2 values of 0.57 and 0.65 in the regression models for oral and inhalation SFs in external validation. These models might therefore support regulators in (de)prioritizing substances for regulatory action and in weighing evidence in the context of chemical safety assessments. Moreover, these models are implemented on the VEGA platform and are now freely downloadable online.

In silico model for mutagenicity (Ames test), taking into account metabolism.

Bacterial reverse mutation test is one of the most common methods used to address genotoxicity. The experimental test is designed to include a step to simulate mammalian metabolism. The most common metabolic activation system is the incubation with S9 fraction prepared from the livers of rodents. Usually, in silico models addressing this endpoint are developed on the basis of an overall call disregarding the fact that the toxic effect was observed before or after metabolic activation. Here, we present a new in silico model to predict mutagenicity as measured by activity in the bacterial reverse mutation test, bearing in mind the role of S9 activation to stimulate metabolism. We applied the software SARpy, which identifies structural alerts associated with the effect. Different rules codified by these structural alerts were found in case of positive or negative mutagenicity, observed in the presence or absence of the S9 fraction. These rules can be used to understand the role of metabolism in mutagenicity better. We also identified a possible association of the results from these models with carcinogenicity.

Impact of REACH legislation on the production and importation of CMR (carcinogen, mutagen and reproductive) and explosive chemicals in Italy from 2011 to 2015.

On 1 June 2007, the European Commission issued the Registration, Evaluation, Authorization and Restriction of Chemicals (REACH) to protect both the environment and human health. We analyzed the impact of REACH in the Italian market considering the presence of chemicals, their diversity, importation and production during the period 2011-2015, with particular attention to products with toxic or explosive properties. There was a reduction of the chemicals on the market, in terms of tons but also the absolute numbers of types of compounds. The production reduction was particularly noticeable for explosive chemicals: -14.7%. CMR products did not show any statistically significant reduction in term of tons: -2.3%.

New clues on carcinogenicity-related substructures derived from mining two large datasets of chemical compounds.

In this study, new molecular fragments associated with genotoxic and nongenotoxic carcinogens are introduced to estimate the carcinogenic potential of compounds. Two rule-based carcinogenesis models were developed with the aid of SARpy: model R (from rodents' experimental data) and model E (from human carcinogenicity data). Structural alert extraction method of SARpy uses a completely automated and unbiased manner with statistical significance. The carcinogenicity models developed in this study are collections of carcinogenic potential fragments that were extracted from two carcinogenicity databases: the ANTARES carcinogenicity dataset with information from bioassay on rats and the combination of ISSCAN and CGX datasets, which take into accounts human-based assessment. The performance of these two models was evaluated in terms of cross-validation and external validation using a 258 compound case study dataset. Combining R and H predictions and scoring a positive or negative result when both models are concordant on a prediction, increased accuracy to 72% and specificity to 79% on the external test set. The carcinogenic fragments present in the two models were compared and analyzed from the point of view of chemical class. The results of this study show that the developed rule sets will be a useful tool to identify some new structural alerts of carcinogenicity and provide effective information on the molecular structures of carcinogenic chemicals.

CERAPP: Collaborative Estrogen Receptor Activity Prediction Project.

BACKGROUND: Humans are exposed to thousands of man-made chemicals in the environment. Some chemicals mimic natural endocrine hormones and, thus, have the potential to be endocrine disruptors. Most of these chemicals have never been tested for their ability to interact with the estrogen receptor (ER). Risk assessors need tools to prioritize chemicals for evaluation in costly in vivo tests, for instance, within the U.S. EPA Endocrine Disruptor Screening Program. OBJECTIVES: We describe a large-scale modeling project called CERAPP (Collaborative Estrogen Receptor Activity Prediction Project) and demonstrate the efficacy of using predictive computational models trained on high-throughput screening data to evaluate thousands of chemicals for ER-related activity and prioritize them for further testing. METHODS: CERAPP combined multiple models developed in collaboration with 17 groups in the United States and Europe to predict ER activity of a common set of 32,464 chemical structures. Quantitative structure-activity relationship models and docking approaches were employed, mostly using a common training set of 1,677 chemical structures provided by the U.S. EPA, to build a total of 40 categorical and 8 continuous models for binding, agonist, and antagonist ER activity. All predictions were evaluated on a set of 7,522 chemicals curated from the literature. To overcome the limitations of single models, a consensus was built by weighting models on scores based on their evaluated accuracies. RESULTS: Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. Out of the 32,464 chemicals, the consensus model predicted 4,001 chemicals (12.3%) as high priority actives and 6,742 potential actives (20.8%) to be considered for further testing. CONCLUSION: This project demonstrated the possibility to screen large libraries of chemicals using a consensus of different in silico approaches. This concept will be applied in future projects related to other end points. CITATION: Mansouri K, Abdelaziz A, Rybacka A, Roncaglioni A, Tropsha A, Varnek A, Zakharov A, Worth A, Richard AM, Grulke CM, Trisciuzzi D, Fourches D, Horvath D, Benfenati E, Muratov E, Wedebye EB, Grisoni F, Mangiatordi GF, Incisivo GM, Hong H, Ng HW, Tetko IV, Balabin I, Kancherla J, Shen J, Burton J, Nicklaus M, Cassotti M, Nikolov NG, Nicolotti O, Andersson PL, Zang Q, Politi R, Beger RD, Todeschini R, Huang R, Farag S, Rosenberg SA, Slavov S, Hu X, Judson RS. 2016. CERAPP: Collaborative Estrogen Receptor Activity Prediction Project. Environ Health Perspect 124:1023-1033; http://dx.doi.org/10.1289/ehp.1510267.

Evaluation of QSAR models for the prediction of ames genotoxicity: a retrospective exercise on the chemical substances registered under the EU REACH regulation.

We evaluated the performance of seven freely available quantitative structure-activity relationship models predicting Ames genotoxicity thanks to a dataset of chemicals that were registered under the EU Registration, Evaluation, Authorization and Restriction of Chemicals (REACH) regulation. The performance of the models was estimated according to Cooper's statistics and Matthew's Correlation Coefficients (MCC). The Benigni/Bossa rule base originally implemented in Toxtree and re-implemented within the Virtual models for property Evaluation of chemicals within a Global Architecture (VEGA) platform displayed the best performance (accuracy = 92%, sensitivity = 83%, specificity = 93%, MCC = 0.68) indicating that this rule base provides a reliable tool for the identification of genotoxic chemicals. Finally, we elaborated a consensus model that outperformed the accuracy of the individual models.

A comparative survey of chemistry-driven in silico methods to identify hazardous substances under REACH.

This paper presents an inventory of in silico screening tools to identify substance properties of concern under the European chemicals' legislation REACH. The objective is to support the selection and implementation of appropriate tools as building blocks within integrated testing strategies (ITS). The relevant concerns addressed are persistence, bioaccumulation potential, acute and long-term aquatic toxicity, PBT/vPvB properties ((very) persistent, (very) bioaccumulative, toxic), CMR (carcinogenicity, mutagenicity, reproductive toxicity), endocrine disruption and skin sensitisation. The inventory offers a comparative evaluation of methods with respect to the underlying algorithms (how does the method work?) and the applicability domains (when does the method work?) as well as their limitations (when does the method not work?). The inventory explicitly addresses the reliability of predictions of different in silico models for diverse chemicals by applicability domain considerations. The confidence in predictions can be greatly improved by consensus modelling that allows for taking conflicting results into account. The inventory is complemented by a brief discussion of socio-economic tools for assessing the potential efficiency gains of using in silico methods compared to traditional in vivo testing of chemical hazards.

Evaluating the applicability domain in the case of classification predictive models for carcinogenicity based on the counter propagation artificial neural network.

The applicability domain (AD) of models developed for regulatory use has attached great attention recently. The AD of quantitative structure-activity relationship (QSAR) models is the response and chemical structure space in which the model makes predictions with a given reliability. The evaluation of AD of regressions QSAR models for congeneric sets of chemicals can be find in many papers and books while the issue about metrics for the evaluation of an AD for the non-linear models (like neural networks) for the diverse set of chemicals represents the new field of investigations in QSAR studies. The scientific society is standing before the challenge to find out reliable way for the evaluation of an AD of non linear models. The new metrics for the evaluation of the AD of the counter propagation artificial neural network (CP ANN) models are discussed in the article: the Euclidean distances between an object (molecule) and the corresponding excited neuron of the neural network and between an object (molecule) and the representative object (vector of average values of descriptors). The investigation of the training and test sets chemicals coverage in the descriptors space was made with the respect to false predicted chemicals. The leverage approach was used to compare non linear (CP ANN) models with linear ones.

Comparison and possible use of in silico tools for carcinogenicity within REACH legislation.

Seven in silico models have been used to assess the prediction accuracy of chemical compound carcinogenicity. More than 1500 compounds with experimental values have been used to evaluate the models. Here we review the application of these models for toxicity prediction and their advantages and disadvantages, discussing the different approaches underlying the models and their main critical points. Some models have fewer false negatives while others are better at avoiding false positives. Since carcinogenicity is typically evaluated using a series of studies, identification of a strategy using one, or preferably a battery of in silico models, could reduce the number of animal studies needed.

New public QSAR model for carcinogenicity.

BACKGROUND: One of the main goals of the new chemical regulation REACH (Registration, Evaluation and Authorization of Chemicals) is to fulfill the gaps in data concerned with properties of chemicals affecting the human health. (Q)SAR models are accepted as a suitable source of information. The EU funded CAESAR project aimed to develop models for prediction of 5 endpoints for regulatory purposes. Carcinogenicity is one of the endpoints under consideration. RESULTS: Models for prediction of carcinogenic potency according to specific requirements of Chemical regulation were developed. The dataset of 805 non-congeneric chemicals extracted from Carcinogenic Potency Database (CPDBAS) was used. Counter Propagation Artificial Neural Network (CP ANN) algorithm was implemented. In the article two alternative models for prediction carcinogenicity are described. The first model employed eight MDL descriptors (model A) and the second one twelve Dragon descriptors (model B). CAESAR's models have been assessed according to the OECD principles for the validation of QSAR. For the model validity we used a wide series of statistical checks. Models A and B yielded accuracy of training set (644 compounds) equal to 91% and 89% correspondingly; the accuracy of the test set (161 compounds) was 73% and 69%, while the specificity was 69% and 61%, respectively. Sensitivity in both cases was equal to 75%. The accuracy of the leave 20% out cross validation for the training set of models A and B was equal to 66% and 62% respectively. To verify if the models perform correctly on new compounds the external validation was carried out. The external test set was composed of 738 compounds. We obtained accuracy of external validation equal to 61.4% and 60.0%, sensitivity 64.0% and 61.8% and specificity equal to 58.9% and 58.4% respectively for models A and B. CONCLUSION: Carcinogenicity is a particularly important endpoint and it is expected that QSAR models will not replace the human experts opinions and conventional methods. However, we believe that combination of several methods will provide useful support to the overall evaluation of carcinogenicity. In present paper models for classification of carcinogenic compounds using MDL and Dragon descriptors were developed. Models could be used to set priorities among chemicals for further testing. The models at the CAESAR site were implemented in java and are publicly accessible.

In silico-aided prediction of biological properties of chemicals: oestrogen receptor-mediated effects.

In silico methods are a valid tool for analysing the properties of chemical compounds and interest in computational modelling techniques to predict the activity of chemicals is constantly growing. Many computational methods can be used to analyse the toxicity or biological activity of chemicals, particularly as regards their interactions with biological macromolecules (e.g. receptors) and other physico-chemical properties. An overview of these methods is provided in this tutorial review, with some examples of their application to predict oestrogen receptor (ER)-mediated effects. Nuclear receptors, particularly ER, have been studied with in silico tools since concern is growing about substances, called endocrine disrupters, that can interfere with hormone regulation. Molecular modelling techniques such as Quantitative Structure-Activity Relationships (QSAR), related methods like 3D-QSAR, and virtual docking have been used to investigate these phenomena and are described here. Implications about regulatory acceptance and use of these methods and the resulting models for identifying hazards and setting priorities are also addressed.

Identification of the structural requirements of the receptor-binding affinity of diphenolic azoles to estrogen receptors alpha and beta by three-dimensional quantitative structure-activity relationship and structure-activity relationship analysis.

Three-dimensional (3D) quantitative structure-activity relationship (QSAR) and structure-activity relationship (SAR) analyses were applied concurrently to a data set of highly selective estrogen receptor beta (ERbeta) agonists. The data set consisted of diphenolic azoles characterized by similar structural skeletons but with different binding modes to the estrogen receptor site. Models were developed separately with respect to the relative binding affinities (RBAs) to ERalpha and ERbeta. Steric and electrostatic fields were calculated for a training set of 72 compounds using comparative molecular field analysis (CoMFA). The model developed for ERalpha RBA yielded R2 of 0.91 and q(cv)2 of 0.60. The model developed for ERbeta RBA yielded R2 of 0.95 and q(cv)2 of 0.40. Both models were validated successfully using an external test set of 32 compounds. A new concept of test set evaluation based on the variability of the biological response due to the variability of the living organism has been introduced. The CoMFA analysis was supported by a SAR study. In addition to the most favorable steric and electrostatic regions identified by CoMFA, a number of structural descriptors were identified as being important for binding. These are the number of substituents attached to the main skeleton of each compound, the largest distance between the oxygen atoms of each molecule, and the angle defined by the planes that split the phenyl or the naphthyl and the benzisoxazole or the benzoxazole moiety in a morphometrically longitudinal way.

Variable selection and interpretation in structure-affinity correlation modeling of estrogen receptor binders.

A computational approach for the identification and investigation of correlations between a chemical structure and a selected biological property is described. It is based on a set of 132 compounds of known chemical structures, which were tested for their binding affinities to the estrogen receptor. Different multivariate modeling methods, i.e., partial least-squares regression, counterpropagation neural network, and error-back-propagation neural network, were applied, and the prediction ability of each model was tested in order to compare the results of the obtained models. To reduce the extensive set of calculated structural descriptors, two types of variable selection methods were applied, depending on the modeling approach used. In particular, the final partial least-squares regression model was built using the "variable importance in projection" variable selection method, while genetic algorithms were applied in neural network modeling to select the optimal set of descriptors. A thorough statistical study of the variables selected by genetic algorithms is shown. The results were assessed with the aim to get insight to the mechanisms involved in the binding of estrogenic compounds to the receptor. The variable selection on the basis of genetic algorithm was controlled with the test set of compounds, extracted from the data set available. To compare the predictive ability of all the optimized models, a leave-one-out cross-validation procedure was applied, the best model being the nonlinear neural network model based on error back-propagation algorithm, which resulted in R2= 92.2% and Q2= 70.8%.

A protocol to select high quality datasets of ecotoxicity values for pesticides.

The key to any QSAR model is the underlying dataset. In order to construct a reliable dataset to develop a QSAR model for pesticide toxicity, we have derived a protocol to critically evaluate the quality of the underlying data. In developing an appropriate protocol that would enable data to be selected in constructing a QSAR, we concentrated on one toxicity end point, the 96 h LC50 from the acute rainbow trout study. This end point is key in pesticide regulation carried out under 91/414/EEC. The dataset used for this exercise was from the US EPA-OPP database.