Classification and virtual screening of androgen receptor antagonists

Deriving general structure-activity/selectivity relationship patterns for different subfamilies of cyclin-dependent kinase inhibitors using machine learning methods

Cyclin-dependent kinases (CDKs) play essential roles in regulating the cell cycle and are among the most critical targets for cancer therapy and drug discovery. The primary objective of this research is to derive general structure-activity relationship (SAR) patterns for modeling the selectivity and activity levels of CDK inhibitors using machine learning methods. To accomplish this, 8592 small molecules with different binding affinities to CDK1, CDK2, CDK4, CDK5, and CDK9 were collected from Binding DB, and a diverse set of descriptors was calculated for each molecule. The supervised Kohonen networks (SKN) and counter propagation artificial neural networks (CPANN) models were trained to predict the activity levels and therapeutic targets of the molecules. The validity of models was confirmed through tenfold cross-validation and external test sets. Using selected sets of molecular descriptors (e.g. hydrophilicity and total polar surface area) we derived activity and selectivity maps to elucidate local regions in chemical space for active and selective CDK inhibitors. The SKN models exhibited prediction accuracies ranging from 0.75 to 0.94 for the external test sets. The developed multivariate classifiers were used for ligand-based virtual screening of 2 million random molecules of the PubChem database, yielding areas under the receiver operating characteristic curves ranging from 0.72 to 1.00 for the SKN model. Considering the persistent challenge of achieving CDK selectivity, this research significantly contributes to addressing the issue and underscores the paramount importance of developing drugs with minimized side effects.

Machine Learning Methods for Endocrine Disrupting Potential Identification Based on Single-Cell Data

Humans are continuously exposed to a variety of toxicants and chemicals which is exacerbated during and after environmental catastrophes such as floods, earthquakes, and hurricanes. The hazardous chemical mixtures generated during these events threaten the health and safety of humans and other living organisms. This necessitates the development of rapid decision-making tools to facilitate mitigating the adverse effects of exposure on the key modulators of the endocrine system, such as the estrogen receptor alpha (ERα), for example. The mechanistic stages of the estrogenic transcriptional activity can be measured with high content/high throughput microscopy-based biosensor assays at the single-cell level, which generates millions of object-based minable data points. By combining computational modeling and experimental analysis, we built a highly accurate data-driven classification framework to assess the endocrine disrupting potential of environmental compounds. The effects of these compounds on the ERα pathway are predicted as being receptor agonists or antagonists using the principal component analysis (PCA) projections of high throughput, high content image analysis descriptors. The framework also combines rigorous preprocessing steps and nonlinear machine learning algorithms, such as the Support Vector Machines and Random Forest classifiers, to develop highly accurate mathematical representations of the separation between ERα agonists and antagonists. The results show that Support Vector Machines classify the unseen chemicals correctly with more than 96% accuracy using the proposed framework, where the preprocessing and the PCA steps play a key role in suppressing experimental noise and unraveling hidden patterns in the dataset.

Review of in silico studies dedicated to the nuclear receptor family: Therapeutic prospects and toxicological concerns

Being in the center of both therapeutic and toxicological concerns, NRs are widely studied for drug discovery application but also to unravel the potential toxicity of environmental compounds such as pesticides, cosmetics or additives. High throughput screening campaigns (HTS) are largely used to detect compounds able to interact with this protein family for both therapeutic and toxicological purposes. These methods lead to a large amount of data requiring the use of computational approaches for a robust and correct analysis and interpretation. The output data can be used to build predictive models to forecast the behavior of new chemicals based on their in vitro activities. This atrticle is a review of the studies published in the last decade and dedicated to NR ligands in silico prediction for both therapeutic and toxicological purposes. Over 100 articles concerning 14 NR subfamilies were carefully read and analyzed in order to retrieve the most commonly used computational methods to develop predictive models, to retrieve the databases deployed in the model building process and to pinpoint some of the limitations they faced.

Combined Naïve Bayesian, Chemical Fingerprints and Molecular Docking Classifiers to Model and Predict Androgen Receptor Binding Data for Environmentally- and Health-Sensitive Substances

Many chemicals that enter the environment, food chain, and the human body can disrupt androgen-dependent pathways and mimic hormones and therefore, may be responsible for multiple diseases from reproductive to tumor. Thus, modeling and predicting androgen receptor activity is an important area of research. The aim of the current study was to find a method or combination of methods to predict compounds that can bind to and/or disrupt the androgen receptor, and thereby guide decision making and further analysis. A stepwise procedure proceeded from analysis of protein structures from human, chimp, and rat, followed by docking and subsequent ligand, and statistics based techniques that improved classification gradually. The best methods used multivariate logistic regression of combinations of chimpanzee protein structural docking scores, extended connectivity fingerprints, and naïve Bayesians of known binders and non-binders. Combination or consensus methods included data from a variety of procedures to improve the final model accuracy.

Classification of estrogenic compounds by coupling high content analysis and machine learning algorithms

Environmental toxicants affect human health in various ways. Of the thousands of chemicals present in the environment, those with adverse effects on the endocrine system are referred to as endocrine-disrupting chemicals (EDCs). Here, we focused on a subclass of EDCs that impacts the estrogen receptor (ER), a pivotal transcriptional regulator in health and disease. Estrogenic activity of compounds can be measured by many in vitro or cell-based high throughput assays that record various endpoints from large pools of cells, and increasingly at the single-cell level. To simultaneously capture multiple mechanistic ER endpoints in individual cells that are affected by EDCs, we previously developed a sensitive high throughput/high content imaging assay that is based upon a stable cell line harboring a visible multicopy ER responsive transcription unit and expressing a green fluorescent protein (GFP) fusion of ER. High content analysis generates voluminous multiplex data comprised of minable features that describe numerous mechanistic endpoints. In this study, we present a machine learning pipeline for rapid, accurate, and sensitive assessment of the endocrine-disrupting potential of benchmark chemicals based on data generated from high content analysis. The multidimensional imaging data was used to train a classification model to ultimately predict the impact of unknown compounds on the ER, either as agonists or antagonists. To this end, both linear logistic regression and nonlinear Random Forest classifiers were benchmarked and evaluated for predicting the estrogenic activity of unknown compounds. Furthermore, through feature selection, data visualization, and model discrimination, the most informative features were identified for the classification of ER agonists/antagonists. The results of this data-driven study showed that highly accurate and generalized classification models with a minimum number of features can be constructed without loss of generality, where these machine learning models serve as a means for rapid mechanistic/phenotypic evaluation of the estrogenic potential of many chemicals.

Chemical contaminants or toxicants pose environmental and health-related risks for exposure. The ability to rapidly understand their biological impact, specifically on a key modulator of important physiological and pathological states in the human body is essential for diagnosing and avoiding undesirable health outcomes during environmental emergencies. In this study, we use advanced data analytics for creating statistical models that can accurately predict the endocrinological activity of toxic chemicals based on high throughput/high content image analysis data. We focus on a subclass of chemicals that affect the estrogen receptor (ER), which is a pivotal transcriptional regulator in health and disease. The multidimensional imaging data of these benchmark chemicals are used to train a classification model to ultimately predict the impact of unknown compounds on the ER, either as agonists or antagonists. To this end, we evaluate linear and nonlinear classifiers for predicting the estrogenic activity of unknown compounds and use feature selection, data visualization, and model discrimination methodologies to identify the most informative features for the classification of ER agonists/antagonists.

Principles of QSAR Modeling

At the end of her academic career, the author summarizes the main aspects of QSAR modeling, giving comments and suggestions according to her 23 years' experience in QSAR research on environmental topics. The focus is mainly on Multiple Linear Regression, particularly Ordinary Least Squares, using a Genetic Algorithm for variable selection from various theoretical molecular descriptors, but the comments can be useful also for other QSAR methods. The need for rigorous validation, also external, and for applicability domain check to guarantee predictivity and reliability of QSAR models is particularly highlighted. The commented approach is the “predictive” one, based on chemometrics, and is usefully applied to the prioritization of environmental pollutants. All the discussed points and the author's ideas are implemented in the software QSARINS, as a legacy to the QSAR community.

Value of p-Value

The goal of this manuscript is to discuss important aspects of external validation of classification and category Quantitative Structure - Activity/Property/Toxicity Relationship QS/A/P/T/R models that to the best of author's knowledge are not addressed in publications. Statistical significance (in terms of p-value) and accuracy of prediction (in terms of Correct Classification Rate (CCR)) of external validation set compounds are among most important characteristics of the models. We assert that in most cases the models built for classification or category response variable should be statistically significant and predictive for each class or category. We show that three thresholds of the number of compounds in each class or category of the external validation sets should be satisfied. 1) The p-value criterion can never be satisfied, if the number of compounds is below the first threshold. 2) If the number of compounds is between the first and the second thresholds, p-value criterion should be used. 3) If it is higher than the third threshold, classification or category accuracy criterion should be used. 4) If the number of compounds is between second and third thresholds, either one or the other criterion should be used depending on the value of p-value. 5) When the number of compounds in the class approaches infinity, the maximum relative error of prediction approaches the relative expected error. The results are of interest in other areas of multidimensional data analysis.

Development, validation and integration of in silico models to identify androgen active chemicals

Humans are exposed to large numbers of environmental chemicals, some of which potentially interfere with the endocrine system. The identification of potential endocrine disrupting chemicals (EDCs) has gained increasing priority in the assessment of environmental hazards. The U.S. Environmental Protection Agency (U.S. EPA) has developed the Endocrine Disruptor Screening Program (EDSP) which aims to prioritize and screen potential EDCs. The Toxicity Forecaster (ToxCast) program has generated data using in vitro high-throughput screening (HTS) assays measuring activity of chemicals at multiple points along the androgen receptor (AR) activity pathway. In the present study, using a large and diverse data set of 1667 chemicals provided by the U.S. EPA from the combined ToxCast AR assays in the framework of the Collaborative Modeling Project for Androgen Receptor Activity (CoMPARA). Two models were built using ADMET Predictor™; one is based on Artificial Neural Networks (ANNs) technology and the other uses a Support Vector Machine (SVM) algorithm; one model is a Decision Tree (DT) developed in R; and two models make use of differently combined sets of structural alerts (SAs) automatically extracted by SARpy. We used two strategies to integrate predictions from single models; one is based on a majority vote approach and the other on prediction convergence. These strategies led to enhanced statistical performance in most cases. Moreover, the majority vote approach improved prediction coverage when one or more single models were not able to provide any estimations. This study integrates multiple in silico approaches as a virtual screening tool for use in risk assessment of endocrine disrupting chemicals.

Computational QSAR model combined molecular descriptors and fingerprints to predict HDAC1 inhibitors

The dynamic balance between acetylation and deacetylation of histones plays a crucial role in the epigenetic regulation of gene expression. It is equilibrated by two families of enzymes: histone acetyltransferases and histone deacetylases (HDACs). HDACs repress transcription by regulating the conformation of the higher-order chromatin structure. HDAC inhibitors have recently become a class of chemical agents for potential treatment of the abnormal chromatin remodeling process involved in certain cancers. In this study, we constructed a large dataset to predict the activity value of HDAC1 inhibitors. Each compound was represented with seven fingerprints, and computational models were subsequently developed to predict HDAC1 inhibitors via five machine learning methods. These methods include naïve Bayes, κ-nearest neighbor, C4.5 decision tree, random forest, and support vector machine (SVM) algorithms. The best predicting model was CDK fingerprint with SVM, which exhibited an accuracy of 0.89. This model also performed best in five-fold cross-validation. Some representative substructure alerts responsible for HDAC1 inhibitors were identified by using MoSS in KNIME, which could facilitate the identification of HDAC1 inhibitors.

Guidance for the identification of endocrine disruptors in the context of Regulations (EU) No 528/2012 and (EC) No 1107/2009

This Guidance describes how to perform hazard identification for endocrine-disrupting properties by following the scientific criteria which are outlined in Commission Delegated Regulation (EU) 2017/2100 and Commission Regulation (EU) 2018/605 for biocidal products and plant protection products, respectively.

Predictive Structure-Based Toxicology Approaches To Assess the Androgenic Potential of Chemicals

We present a practical and easy-to-run in silico workflow exploiting a structure-based strategy making use of docking simulations to derive highly predictive classification models of the androgenic potential of chemicals. Models were trained on a high-quality chemical collection comprising 1689 curated compounds made available within the CoMPARA consortium from the US Environmental Protection Agency and were integrated with a two-step applicability domain whose implementation had the effect of improving both the confidence in prediction and statistics by reducing the number of false negatives. Among the nine androgen receptor X-ray solved structures, the crystal 2PNU (entry code from the Protein Data Bank) was associated with the best performing structure-based classification model. Three validation sets comprising each 2590 compounds extracted by the DUD-E collection were used to challenge model performance and the effectiveness of Applicability Domain implementation. Next, the 2PNU model was applied to screen and prioritize two collections of chemicals. The first is a small pool of 12 representative androgenic compounds that were accurately classified based on outstanding rationale at the molecular level. The second is a large external blind set of 55450 chemicals with potential for human exposure. We show how the use of molecular docking provides highly interpretable models and can represent a real-life option as an alternative nontesting method for predictive toxicology.

Integration of in silico methods and computational systems biology to explore endocrine-disrupting chemical binding with nuclear hormone receptors

Thousands of potential endocrine-disrupting chemicals present difficult regulatory challenges. Endocrine-disrupting chemicals can interfere with several nuclear hormone receptors associated with a variety of adverse health effects. The U.S. Environmental Protection Agency (U.S. EPA) has released its reviews of Tier 1 screening assay results for a set of pesticides in the Endocrine Disruptor Screening Program (EDSP), and recently, the Collaborative Estrogen Receptor Activity Prediction Project (CERAPP) data. In this study, the predictive ability of QSAR and docking approaches is evaluated using these data sets. This study also presents a computational systems biology approach using carbaryl (1-naphthyl methylcarbamate) as a case study. For estrogen receptor and androgen receptor binding predictions, two commercial and two open source QSAR tools were used, as was the publicly available docking tool Endocrine Disruptome. For estrogen receptor binding predictions, the ADMET Predictor, VEGA, and OCHEM models (specificity: 0.88, 0.88, and 0.86, and accuracy: 0.81, 0.84, and 0.88, respectively) were each more reliable than the MetaDrug™ model (specificity 0.81 and accuracy 0.77). For androgen receptor binding predictions, the Endocrine Disruptome and ADMET Predictor models (specificity: 0.94 and 0.8, and accuracy: 0.78 and 0.71, respectively) were more reliable than the MetaDrug™ model (specificity 0.33 and accuracy 0.4). A consensus approach is proposed that reaches general agreement among the models (specificity 0.94 and accuracy 0.89). This study integrates QSAR, docking, and systems biology approaches as a virtual screening tool for use in risk assessment. As such, this systems biology pathways and network analysis approach provides a means to more critically assess the potential effects of endocrine-disrupting chemicals.

Systematic evaluation of supervised classifiers for fecal microbiota-based prediction of colorectal cancer

Predicting colorectal cancer (CRC) based on fecal microbiota presents a promising method for non-invasive screening of CRC, but the optimization of classification models remains an unaddressed question. The purpose of this study was to systematically evaluate the effectiveness of different supervised machine-learning models in predicting CRC in two independent eastern and western populations. The structures of intestinal microflora in feces in Chinese population (N = 141) were determined by 454 FLX pyrosequencing, and different supervised classifiers were employed to predict CRC based on fecal microbiota operational taxonomic unit (OTUs). As a result, Bayes Net and Random Forest displayed higher accuracies than other algorithms in both populations, although Bayes Net was found with a lower false negative rate than that of Random Forest. Gut microbiota-based prediction was more accurate than the standard fecal occult blood test (FOBT), and the combination of both approaches further improved the prediction accuracy. Moreover, when unclassified OTUs were used as input, the BayesDMNB text algorithm achieved higher accuracy in the Chinese population (AUC=0.994). Taken together, our results suggest that Bayes Net classification model combined with unclassified OTUs may present an accurate method for predicting CRC based on the compositions of gut microbiota.

Conformal prediction to define applicability domain - A case study on predicting ER and AR binding

A fundamental element when deriving a robust and predictive in silico model is not only the statistical quality of the model in question but, equally important, the estimate of its predictive boundaries. This work presents a new method, conformal prediction, for applicability domain estimation in the field of endocrine disruptors. The method is applied to binders and non-binders related to the oestrogen and androgen receptors. Ensembles of decision trees are used as statistical method and three different sets (dragon, rdkit and signature fingerprints) are investigated as chemical descriptors. The conformal prediction method results in valid models where there is an excellent balance in quality between the internally validated training set and the corresponding external test set, both in terms of validity and with respect to sensitivity and specificity. With this method the level of confidence can be readily altered by the user and the consequences thereof immediately inspected. Furthermore, the predictive boundaries for the derived models are rigorously defined by using the conformal prediction framework, thus no ambiguity exists as to the level of similarity needed for new compounds to be in or out of the predictive boundaries of the derived models where reliable predictions can be expected.

Prediction of in vitro and in vivo oestrogen receptor activity using hierarchical clustering

In this study, hierarchical clustering classification models were developed to predict in vitro and in vivo oestrogen receptor (ER) activity. Classification models were developed for binding, agonist, and antagonist in vitro ER activity and for mouse in vivo uterotrophic ER binding. In vitro classification models yielded balanced accuracies ranging from 0.65 to 0.85 for the external prediction set. In vivo ER classification models yielded balanced accuracies ranging from 0.72 to 0.83. If used as additional biological descriptors for in vivo models, in vitro scores were found to increase the prediction accuracy of in vivo ER models. If in vitro activity was used directly as a surrogate for in vivo activity, the results were poor (balanced accuracy ranged from 0.49 to 0.72). Under-sampling negative compounds in the training set was found to increase the coverage (fraction of chemicals which can be predicted) and increase prediction sensitivity.

Prediction of the endocrine disruption profile of pesticides

Numerous manmade chemicals released into the environment can interfere with normal, hormonally regulated biological processes to adversely affect the development and reproductive functions of living species. Various in vivo and in vitro tests have been designed for detecting endocrine disruptors, but the number of chemicals to test is so high that to save time and money, (quantitative) structure-activity relationship ((Q)SAR) models are increasingly used as a surrogate for these laboratory assays. However, most of them focus only on a specific target (e.g. estrogenic or androgenic receptor) while, to be more efficient, endocrine disruption modelling should preferentially consider profiles of activities to better gauge this complex phenomenon. In this context, an attempt was made to evaluate the endocrine disruption profile of 220 structurally diverse pesticides using the Endocrine Disruptome simulation (EDS) tool, which simultaneously predicts the probability of binding of chemicals on 12 nuclear receptors. In a first step, the EDS web-based system was successfully applied to 16 pharmaceutical compounds known to target at least one of the studied receptors. About 13% of the studied pesticides were estimated to be potential disruptors of the endocrine system due to their high predicted affinity for at least one receptor. In contrast, about 55% of them were unlikely to be endocrine disruptors. The simulation results are discussed and some comments on the use of the EDS tool are made.

Reprint of "In silico methods in the discovery of endocrine disrupting chemicals"

The prevalence of sex hormone-dependent cancers, reproductive problems, obesity, and cardiovascular complications has risen especially in the Western world. It has been suggested, that the exposure to various endocrine disrupting chemicals (EDCs) contributes to the development and progression of these diseases. EDCs can interfere with various proteins: nuclear steroid hormone receptors, such as estrogen-, androgen-, glucocorticoid- and mineralocorticoid receptors (ER, AR, GR, MR), and enzymes that are involved in steroid hormone synthesis and metabolism, for example hydroxysteroid dehydrogenases (HSDs). Numerous chemicals are known as endocrine disruptors. However, the mechanism of action for most of these EDCs is still unknown. It is exhaustive and time consuming to test in vitro all chemicals - potential EDCs - used in industry, agriculture or as food preservatives against their effects on the endocrine system. Computational methods, such as virtual screening, quantitative structure activity relationships and docking, are already well recognized and used in drug development. The same methods could also aid the research on EDCs. So far, the computational methods in the search of EDCs have been retrospective. There are, however, some prospective studies reporting the use of in silico methods: five studies reporting the identification of previously unknown 17β-HSD3 inhibitors, MR agonists, and ER antagonists/agonists. This review provides an overview of case studies and in silico methods that are used in the search of EDCs. This article is part of a Special Issue entitled 'CSR 2013'.

Computational models to predict endocrine-disrupting chemical binding with androgen or oestrogen receptors

Rapidly and correctly identifying endocrine-disrupting chemicals (EDCs) is an important issue in environmental risk assessment. Major EDCs are associated with the androgen receptor (AR) and oestrogen receptors (ERs). Because of the high cost and time-consuming nature of experimental tests, in silico methods are valuable alternative tools for the identification of EDCs. In this study, a large dataset related to EDCs was constructed. Each molecule was represented with seven fingerprints, and computational models were subsequently developed to predict AR and ER binders via machine learning methods including k-nearest neighbour (kNN), C4.5 decision tree (C4.5 DT), naïve Bayes (NB), and support vector machine (SVM) algorithms. The best model for predicting AR binders was PubChem Fingerprint-SVM, which exhibited an accuracy of 0.84. For ER binders, the best method was Extended Fingerprint-SVM with an accuracy of 0.79. Moreover, several representative substructure alerts for characterizing EDCs, such as phenol, trifluoromethyl, and annelated rings, were identified using the combination of information gain and substructure frequency analysis. Our study involved a systematic computational assessment of EDCs related to AR and ERs, and provides significant information on the structural characteristics of these chemicals, which are a great help in identifying EDCs.

In silico methods in the discovery of endocrine disrupting chemicals

The prevalence of sex hormone-dependent cancers, reproductive problems, obesity, and cardiovascular complications has risen especially in the Western world. It has been suggested, that the exposure to various endocrine disrupting chemicals (EDCs) contributes to the development and progression of these diseases. EDCs can interfere with various proteins: nuclear steroid hormone receptors, such as estrogen-, androgen-, glucocorticoid- and mineralocorticoid receptors (ER, AR, GR, MR), and enzymes that are involved in steroid hormone synthesis and metabolism, for example hydroxysteroid dehydrogenases (HSDs). Numerous chemicals are known as endocrine disruptors. However, the mechanism of action for most of these EDCs is still unknown. It is exhaustive and time consuming to test in vitro all chemicals - potential EDCs - used in industry, agriculture or as food preservatives against their effects on the endocrine system. Computational methods, such as virtual screening, quantitative structure activity relationships and docking, are already well recognized and used in drug development. The same methods could also aid the research on EDCs. So far, the computational methods in the search of EDCs have been retrospective. There are, however, some prospective studies reporting the use of in silico methods: five studies reporting the identification of previously unknown 17β-HSD3 inhibitors, MR agonists, and ER antagonists/agonists. This review provides an overview of case studies and in silico methods that are used in the search of EDCs. This article is part of a Special Issue entitled 'CSR 2013'.

In silico study on hydroxylated polychlorinated biphenyls as androgen receptor antagonists

Hydroxylated polychlorinated biphenyls (HO-PCBs), major metabolites of PCBs, may have the potential to disrupt androgen hormone homeostasis. However, there is a lack of systematic investigation into the intermolecular interaction mechanism between HO-PCBs and the androgen receptor (AR). In this study, the combination of three-dimensional quantitative structure-activity relationship (3D-QSAR), molecular docking, and molecular dynamics (MD) simulations was performed to elucidate structural characteristics that influence the anti-androgen activity of HO-PCBs, and to provide a better understanding of the binding modes between HO-PCBs and AR. A predictive comparative molecular field analysis (CoMFA) model was developed with good robustness and predictive ability. Graphical interpretation of the model provided some insights into the structural features that affect the anti-androgen activity of HO-PCBs. The hydrogen bond interaction with Gln711, and hydrophobic interactions with residues in the hydrophobic pocket played important roles in the binding of ligand with receptor. These results are expected to be beneficial to predict anti-androgen activities of other HO-PCBs and provided possible clues for further elucidation of the binding mechanism of HO-PCBs with AR.

On the development and validation of QSAR models

The fundamental and more critical steps that are necessary for the development and validation of QSAR models are presented in this chapter as best practices in the field. These procedures are discussed in the context of predictive QSAR modelling that is focused on achieving models of the highest statistical quality and with external predictive power. The most important and most used statistical parameters needed to verify the real performances of QSAR models (of both linear regression and classification) are presented. Special emphasis is placed on the validation of models, both internally and externally, as well as on the need to define model applicability domains, which should be done when models are employed for the prediction of new external compounds.

Prediction of acute mammalian toxicity using QSAR methods: a case study of sulfur mustard and its breakdown products

Predicting toxicity quantitatively, using Quantitative Structure Activity Relationships (QSAR), has matured over recent years to the point that the predictions can be used to help identify missing comparison values in a substance's database. In this manuscript we investigate using the lethal dose that kills fifty percent of a test population (LD₅₀) for determining relative toxicity of a number of substances. In general, the smaller the LD₅₀ value, the more toxic the chemical, and the larger the LD₅₀ value, the lower the toxicity. When systemic toxicity and other specific toxicity data are unavailable for the chemical(s) of interest, during emergency responses, LD₅₀ values may be employed to determine the relative toxicity of a series of chemicals. In the present study, a group of chemical warfare agents and their breakdown products have been evaluated using four available rat oral QSAR LD₅₀ models. The QSAR analysis shows that the breakdown products of Sulfur Mustard (HD) are predicted to be less toxic than the parent compound as well as other known breakdown products that have known toxicities. The QSAR estimated break down products LD₅₀ values ranged from 299 mg/kg to 5,764 mg/kg. This evaluation allows for the ranking and toxicity estimation of compounds for which little toxicity information existed; thus leading to better risk decision making in the field.

Identification and characterization of MEL-3, a novel AR antagonist that suppresses prostate cancer cell growth

Antiandrogens are an important component of prostate cancer therapy as the androgen receptor (AR) is the key regulator of prostate cancer growth and survival. Current AR antagonists, such as bicalutamide and hydroxyflutamide, have a low affinity for the AR and as a result block AR signaling insufficiently. Moreover, many patients develop a resistance for bicalutamide or hydroxyflutamide during therapy or show a clinical improvement after withdrawal of the antiandrogen. New and more effective AR antagonists are needed to ensure follow-up of these patients. We therefore developed a screening system to identify novel AR antagonists from a collection of compounds. MEL-3 [8-(propan-2-yl)-5,6-dihydro-4H-pyrazino[3,2,1-jk]carbazole] was selected as potent inhibitor of the AR and was further characterized in vitro. On different prostate cancer cell lines MEL-3 displayed an improved therapeutic profile compared with bicalutamide. Not only cell growth was inhibited but also the expression of androgen-regulated genes: PSA and FKBP5. Prostate cancer is often associated with mutated ARs that respond to a broadened spectrum of ligands including the current antiandrogens used in the clinic, hydroxyflutamide and bicalutamide. The activity of two mutant receptors (AR T877A and AR W741C) was shown to be reduced in presence of MEL-3, providing evidence that MEL-3 can potentially be a follow-up treatment for bicalutamide- and hydroxyflutamide-resistant patients. The mechanism of action of MEL-3 on the molecular level was further explored by comparing the structure-activity relationship of different chemical derivatives of MEL-3 with the in silico docking of MEL-3 derivatives in the binding pocket of the AR.

QSAR classification models for the screening of the endocrine-disrupting activity of perfluorinated compounds

Perfluorinated compounds (PFCs) are a class of emerging pollutants still widely used in different materials as non-adhesives, waterproof fabrics, fire-fighting foams, etc. Their toxic effects include potential for endocrine-disrupting activity, but the amount of experimental data available for these pollutants is limited. The use of predictive strategies such as quantitative structure-activity relationships (QSARs) is recommended under the REACH regulation, to fill data gaps and to screen and prioritize chemicals for further experimentation, with a consequent reduction of costs and number of tested animals. In this study, local classification models for PFCs were developed to predict their T4-TTR (thyroxin-transthyretin) competing potency. The best models were selected by maximizing the sensitivity and external predictive ability. These models, characterized by robustness, good predictive power and a defined applicability domain, were applied to predict the activity of 33 other PFCs of environmental concern. Finally, classification models recently published by our research group for T4-TTR binding of brominated flame retardants and for estrogenic and anti-androgenic activity were applied to the studied perfluorinated chemicals to compare results and to further evaluate the potential for these PFCs to cause endocrine disruption.

QSAR classification models for the prediction of endocrine disrupting activity of brominated flame retardants

The identification of potential endocrine disrupting (ED) chemicals is an important task for the scientific community due to their diffusion in the environment; the production and use of such compounds will be strictly regulated through the authorization process of the REACH regulation. To overcome the problem of insufficient experimental data, the quantitative structure-activity relationship (QSAR) approach is applied to predict the ED activity of new chemicals. In the present study QSAR classification models are developed, according to the OECD principles, to predict the ED potency for a class of emerging ubiquitary pollutants, viz. brominated flame retardants (BFRs). Different endpoints related to ED activity (i.e. aryl hydrocarbon receptor agonism and antagonism, estrogen receptor agonism and antagonism, androgen and progesterone receptor antagonism, T4-TTR competition, E2SULT inhibition) are modeled using the k-NN classification method. The best models are selected by maximizing the sensitivity and external predictive ability. We propose simple QSARs (based on few descriptors) characterized by internal stability, good predictive power and with a verified applicability domain. These models are simple tools that are applicable to screen BFRs in relation to their ED activity, and also to design safer alternatives, in agreement with the requirements of REACH regulation at the authorization step.

QSAR classification of estrogen receptor binders and pre-screening of potential pleiotropic EDCs

Endocrine disrupting chemicals (EDCs) are suspected of posing serious threats to human and wildlife health through a variety of mechanisms, these being mainly receptor-mediated modes of action. It is reported that some EDCs exhibit dual activities as estrogen receptor (ER) and androgen receptor (AR) binders. Indeed, such compounds can affect the normal endocrine system through a dual complex mechanism, so steps should be taken not only to identify them a priori from their chemical structure, but also to prioritize them for experimental tests in order to reduce and even forbid their usage. To date, very few EDCs with dual activities have been identified. The present research uses QSARs, to investigate what, so far, is the largest and most heterogeneous ER binder data set (combined METI and EDKB databases). New predictive classification models were derived using different modelling methods and a consensus approach, and these were used to virtually screen a large AR binder data set after strict validation. As a result, 46 AR antagonists were predicted from their chemical structure to also have potential ER binding activities, i.e. pleiotropic EDCs. In addition, 48 not yet recognized ER binders were in silico identified, which increases the number of potential EDCs that are substances of very high concern (SVHC) in REACH. Thus, the proposed screening models, based only on structure information, have the main aim to prioritize experimental tests for the highlighted compounds with potential estrogenic activities and also to design safer alternatives.

Virtual screening of selective multitarget kinase inhibitors by combinatorial support vector machines

Multitarget agents have been increasingly explored for enhancing efficacy and reducing countertarget activities and toxicities. Efficient virtual screening (VS) tools for searching selective multitarget agents are desired. Combinatorial support vector machines (C-SVM) were tested as VS tools for searching dual-inhibitors of 11 combinations of 9 anticancer kinase targets (EGFR, VEGFR, PDGFR, Src, FGFR, Lck, CDK1, CDK2, GSK3). C-SVM trained on 233-1,316 non-dual-inhibitors correctly identified 26.8%-57.3% (majority >36%) of the 56-230 intra-kinase-group dual-inhibitors (equivalent to the 50-70% yields of two independent individual target VS tools), and 12.2% of the 41 inter-kinase-group dual-inhibitors. C-SVM were fairly selective in misidentifying as dual-inhibitors 3.7%-48.1% (majority <20%) of the 233-1,316 non-dual-inhibitors of the same kinase pairs and 0.98%-4.77% of the 3,971-5,180 inhibitors of other kinases. C-SVM produced low false-hit rates in misidentifying as dual-inhibitors 1,746-4,817 (0.013%-0.036%) of the 13.56 M PubChem compounds, 12-175 (0.007%-0.104%) of the 168 K MDDR compounds, and 0-84 (0.0%-2.9%) of the 19,495-38,483 MDDR compounds similar to the known dual-inhibitors. C-SVM was compared to other VS methods Surflex-Dock, DOCK Blaster, kNN and PNN against the same sets of kinase inhibitors and the full set or subset of the 1.02 M Zinc clean-leads data set. C-SVM produced comparable dual-inhibitor yields, slightly better false-hit rates for kinase inhibitors, and significantly lower false-hit rates for the Zinc clean-leads data set. Combinatorial SVM showed promising potential for searching selective multitarget agents against intra-kinase-group kinases without explicit knowledge of multitarget agents.