A ternary classification using machine learning methods of distinct estrogen receptor activities within a large collection of environmental chemicals

Computational modeling approaches for developing a synergistic effect prediction model of estrogen agonistic activity

The concerns regarding the potential health threats caused by estrogenic endocrine-disrupting chemicals (EDCs) and their mixtures manufactured by the chemical industry are increasing worldwide. Conventional experimental tests for understanding the estrogenic activity of mixtures are expensive and time-consuming. Although non-testing methods using computational modeling approaches have been developed to reduce the number of traditional tests, they are unsuitable for predicting synergistic effects because current prediction models consider only a single chemical. Thus, the development of predictive models is essential for predicting the mixture toxicity, including chemical interactions. However, selecting suitable computational modeling approaches to develop a high-performance prediction model requires considerable time and effort. In this study, we provide a suitable computational approach to develop a predictive model for the synergistic effects of estrogenic activity. We collected datasets on mixture toxicity based on the synergistic effect of estrogen agonistic activity in binary mixtures. Using the model deviation ratio approach, we classified the labels of the binary mixtures as synergistic or non-synergistic effects. We assessed five molecular descriptors, four machine learning-based algorithms, and a deep learning-based algorithm to provide a suitable computational modeling approach. Compared with other modeling approaches, the prediction model using the deep learning-based algorithm and chemical-protein network descriptors exhibited the best performance in predicting the synergistic effects. In conclusion, we developed a new high-performance binary classification model using a deep neural network and chemical-protein network-based descriptors. The developed model will be helpful for the preliminary screening of the synergistic effects of binary mixtures during the development process of chemical products.

Machine learning models based on residue interaction network for ABCG2 transportable compounds recognition

As the one of the most important protein of placental transport of environmental substances, the identification of ABCG2 transport molecules is the key step for assessing the risk of placental exposure to environmental chemicals. Here, residue interaction network (RIN) was used to explore the difference of ABCG2 binding conformations between transportable and non-transportable compounds. The RIN were treated as a kind of special quantitative data of protein conformation, which not only reflected the changes of single amino acid conformation in protein, but also indicated the changes of distance and action type between amino acids. Based on the quantitative RIN, four machine learning algorithms were applied to establish the classification and recognition model for 1100 compounds with transported by ABCG2 potential. The random forest (RF) models constructed with RIN presented the best and satisfied predictive ability with an accuracy of training set of 0.97 and the test set of 0.96 respectively. In conclusion, the construction of residue interaction network provided a new perspective for the quantitative characterization of protein conformation and the establishment of prediction models for transporter molecular recognition. The ABCG2 transport molecular recognition model based on residue interaction network provides a possible way for screening environmental chemistry transported through placenta.

ER/AR Multi-Conformational Docking Server: A Tool for Discovering and Studying Estrogen and Androgen Receptor Modulators

The prediction of the estrogen receptor (ER) and androgen receptor (AR) activity of a compound is quite important to avoid the environmental exposures of endocrine-disrupting chemicals. The Estrogen and Androgen Receptor Database (EARDB, http://eardb.schanglab.org.cn/) provides a unique collection of reported ERα, ERβ, or AR protein structures and known small molecule modulators. With the user-uploaded query molecules, molecular docking based on multi-conformations of a single target will be performed. Moreover, the 2D similarity search against known modulators is also provided. Molecules predicted with a low binding energy or high similarity to known ERα, ERβ, or AR modulators may be potential endocrine-disrupting chemicals or new modulators. The server provides a tool to predict the endocrine activity for compounds of interests, benefiting for the ER and AR drug design and endocrine-disrupting chemical identification.

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.

Toxicity and endocrine-disrupting potential of PM2.5: Association with particulate polycyclic aromatic hydrocarbons, phthalate esters, and heavy metals

The adverse effects of fine atmospheric particulate matter with aerodynamic diameters of ≤2.5 μm (PM_2.5) are closely associated with particulate chemicals. In this study, PM_2.5 samples were collected from highway and industry sites in Hangzhou, China, during the autumn and winter, and their cytotoxicity and pulmonary toxicity and endocrine-disrupting potential (EDP) were evaluated in vitro and in vivo; the particulate polycyclic aromatic hydrocarbons (PAHs), phthalate esters (PAEs), and heavy metals were then characterized. The toxicological results suggested that the PM_2.5 from highway site induced higher cytotoxicity (cell viability inhibition, intracellular oxidative stress, and cell membrane injury) and pulmonary toxicity (inflammatory response (IR) and oxidative stress (OS)) than the samples from industry site, while the PM_2.5 from industry site exhibited higher EDP (estrogenic and anti-androgenic activity). The cytotoxicity and pulmonary toxicity of PM_2.5 in the winter were higher than those in the autumn, while no seasonal difference in the endocrine-disrupting potential was observed (p > 0.05). The Pearson correlation analysis between the biological effects and particulate chemicals revealed that the PM_2.5-induced inflammatory response and oxidative stress were closely associated with the particulate PAHs and heavy metals (Pearson correlation coefficients: r_{IR, PAHs} = 0.822-0.988, r_{IR, heavy metals} = 0.895-0.971, r_{OS, PAHs} = 0.843-0.986, and r_{OS, heavy metals} = 0.887-0.933), while particulate di (2-ethylhexyl)phthalate (DEHP) substantially contributed to the EDP of PM_2.5 (r_{EDP, DEHP} = 0.981). This study indicated that the toxicity and EDP of PM_2.5 could vary with the surrounding environment and season, which was closely associated with the variations of particulate chemicals. Further studies are needed to clarify the associations between the harmful effects of PM_2.5 and other contributing factors.

Assessing the chemical-induced estrogenicity using in silico and in vitro methods

Multiple substances are considered endocrine disrupting chemicals (EDCs). However, there is a significant gap in the early prioritization of EDC's effects. In this work, in silico and in vitro methods were used to model estrogenicity. Two Quantitative Structure-Activity Relationship (QSAR) models based on Logistic Regression and REPTree algorithms were built using a large and diverse database of estrogen receptor (ESR) agonism. A 10-fold external validation demonstrated their robustness and predictive capacity. Mechanistic interpretations of the molecular descriptors (C-026, nArOH,PW5, B06[Br-Br]) used for modelling suggested that the heteroatomic fragments, aromatic hydroxyls, and bromines, and the relative bond accessibility areas of molecules, are structural determinants in estrogenicity. As validation of the QSARs, ESR transactivity of thirteen persistent organic pollutants (POPs) and suspected EDCs was tested in vitro using the MMV-Luc cell line. A good correspondence between predictions and experimental bioassays demonstrated the value of the QSARs for prioritization of ESR agonist compounds.

Identification of active and inactive agonists/antagonists of estrogen receptor based on Tox21 10K compound library: Binomial analysis and structure alert

Endocrine disrupting chemicals can mimic, block, or interfere with hormones in organisms and subsequently affect their development and reproduction, which has raised significant public concern over the past several decades. To investigate (quantitative) structure-activity relationship, 8280 compounds were compiled from the Tox21 10K compound library. The results show that 50% activity concentrations of agonists are poorly related to that of antagonists because many compounds have considerably different activity concentrations between the agonists and antagonists. Analysis on the chemical classes based on mode of action (MOA) reveals that estrogen receptor (ER) is not the main target site in the acute toxicity to aquatic organisms. Binomial analysis of active and inactive ER agonists/antagonists reveals that ER activity of compounds is dominated by octanol/water partition coefficient and excess molar refraction. The binomial equation developed from the two descriptors can classify well active and inactive ER chemicals with an overall prediction accuracy of 73%. The classification equation developed from the molecular descriptors indicates that estrogens react with the receptor through hydrophobic and π-n electron interactions. At the same time, molecular ionization, polarity, and hydrogen bonding ability can also affect the chemical ER activity. A decision tree developed from chemical structures and their applications reveals that many hormones, proton pump inhibitors, PAHs, progestin, insecticides, fungicides, steroid and chemotherapy medications are active ER agonists/antagonists. On the other hand, many monocyclic/nonaromatic chain compounds and herbicides are inactive ER compounds. The decision tree and binomial equation developed here are valuable tools to predict active and inactive ER compounds.

Screening of potential oestrogen receptor α agonists in pesticides via in silico, in vitro and in vivo methods

In modern agricultural management, the use of pesticides is indispensable. Due to their massive use worldwide, pesticides represent a latent risk to both humans and the environment. In the present study, 1056 frequently used pesticides were screened for oestrogen receptor (ER) agonistic activity by using in silico methods. We found that 72 and 47 pesticides potentially have ER agonistic activity by the machine learning methods random forest (RF) and deep neural network (DNN), respectively. Among endocrine-disrupting chemicals (EDCs), 14 have been reported as EDCs or ER agonists by previous studies. We selected 3 reported and 7 previously unreported pesticides from 76 potential ER agonists to further assess ERα agonistic activity. All 10 selected pesticides exhibited ERα agonistic activity in human cells or zebrafish. In the dual-luciferase reporter gene assays, six pesticides exhibited ERα agonistic activity. Additionally, nine pesticides could induce mRNA expression of the pS2 and NRF1 genes in MCF-7 cells, and seven pesticides could induce mRNA expression of the vtg1 and vtg2 genes in zebrafish. Importantly, the remaining 48 out of 76 potential ER agonists, none of which have previously been reported to have endocrine-disrupting effects or oestrogenic activity, should be of great concern. Our screening results can inform environmental protection goals and play an important role in environmental protection and early warnings to human health.

Discriminant models on mitochondrial toxicity improved by consensus modeling and resolving imbalance in training

Humans and animals may be exposed to tens of thousands of natural and synthetic chemicals during their lifespan. It is difficult to assess risk for all the chemicals with experimental toxicity tests. An alternative approach is to use computational toxicology methods such as quantitative structure-activity relationship (QSAR) modeling. Mitochondrial toxicity is involved in many diseases such as cancer, neurodegeneration, type 2 diabetes, cardiovascular diseases and autoimmune diseases. Thus, it is important to rapidly and efficiently identify chemicals with mitochondrial toxicity. In this study, five machine learning algorithms and twelve types of molecular fingerprints were employed to generate QSAR discriminant models for mitochondrial toxicity. A threshold moving method was adopted to resolve the imbalance issue in the training data. Consensus of the models by an averaging probability strategy improved prediction performance. The best model has correct classification rates of 81.8% and 88.3% in ten-fold cross validation and external validation, respectively. Substructures such as phenol, carboxylic acid, nitro and arylchloride were found informative through analysis of information gain and frequency of substructures. The results demonstrate that resolving imbalance in training and building consensus models can improve classification rates for mitochondrial toxicity prediction.

The potential endocrine disruption of pesticide transformation products (TPs): The blind spot of pesticide risk assessment

The ecological and health risk assessment of environmental pesticide residues have attracted ever-growing attention; however, their transformation products (TPs) have seldom been considered. Herein, we examined the endocrine-disrupting effects of 4 widely used pesticides as pyriproxyfen (Pyr), malathion (ML), benalaxyl (BX), and fenoxaprop-ethyl (FE), together with their 21 TPs through in vitro and in silico approaches, and found approximately 50% of the TPs exhibited stronger endocrine-disrupting effects than their corresponding parent compounds. Specifically, Pyr and 9 TPs (five TPs of Pyr, one of ML, one of BX, and two of FE) exhibited estrogen-disrupting effects, which were also confirmed by results of E-screen and pS2 expression assays, and molecular docking showed that certain hydroxylated TPs could well mimic the binding mode of estrogen with ERα. Meanwhile, two TPs of Pyr, ML and its TP demonstrated weak glucocorticoid antagonistic activities partially contributed by hydrogen bonds. We also discovered that in H295R cells, all the endocrine disruptors increased hormone secretion and the related gene expression levels. Conclusively, since an increasing number of pesticide TPs have been being detected in various environmental media, a more comprehensive understanding of the ecological risk of pesticide TPs is imperative for risk assessments more extensively and regulatory policy-making on pesticide restriction in the future.

In Silico Predictions of Endocrine Disruptors Properties

Endocrine-disrupting chemicals (EDCs) are a broad class of molecules present in our environment that are suspected to cause adverse effects in the endocrine system by interfering with the synthesis, transport, degradation, or action of endogenous ligands. The characterization of the harmful interaction between environmental compounds and their potential cellular targets and the development of robust in vivo, in vitro, and in silico screening methods are important for assessment of the toxic potential of large numbers of chemicals. In this context, computer-aided technologies that will allow for activity prediction of endocrine disruptors and environmental risk assessments are being developed. These technologies must be able to cope with diverse data and connect chemistry at the atomic level with the biological activity at the cellular, organ, and organism levels. Quantitative structure-activity relationship methods became popular for toxicity issues. They correlate the chemical structure of compounds with biological activity through a number of molecular descriptors (e.g., molecular weight and parameters to account for hydrophobicity, topology, or electronic properties). Chemical structure analysis is a first step; however, modeling intermolecular interactions and cellular behavior will also be essential. The increasing number of three-dimensional crystal structures of EDCs' targets has provided a wealth of structural information that can be used to predict their interactions with EDCs using docking and scoring procedures. In the present review, we have described the various computer-assisted approaches that use ligands and targets properties to predict endocrine disruptor activities.

Classification of drug molecules for oxidative stress signalling pathway

In humans, oxidative stress is involved in the development of diabetes, cancer, hypertension, Alzheimers’ disease, and heart failure. One of the mechanisms in the cellular defence against oxidative stress is the activation of the Nrf2‐antioxidant response element (ARE) signalling pathway. Computation of activity, efficacy, and potency score of ARE signalling pathway and to propose a multi‐level prediction scheme for the same is the main aim of the study as it contributes in a big amount to the improvement of oxidative stress in humans. Applying the process of knowledge discovery from data, required knowledge is gathered and then machine learning techniques are applied to propose a multi‐level scheme. The validation of the proposed scheme is done using the K‐fold cross‐validation method and an accuracy of 90% is achieved for prediction of activity score for ARE molecules which determine their power to refine oxidative stress.

A combination of ternary classification models and reporter gene assays for the comprehensive thyroid hormone disruption profiles of 209 polychlorinated biphenyls

Computational toxicology is widely applied to screen tens and thousands of potential environmental endocrine disruptors (EDCs) for its great efficiency and rapid evaluation in recent years. Polychlorinated biphenyls (PCBs) with 209 congeners have not been comprehensively tested for their ability to interact with the thyroid receptor (TR), which is one of the most extensively studied targets related to the effects of EDCs. In this study, we aimed to determine the thyroid-disrupting mechanisms of 209 PCBs through the combination of a novel computational ternary classification model and luciferase reporter gene assay. The reporter gene assay was performed to examine the hormone activities of 22 PCBs via TR to classify their profiles as agonistic, antagonistic or inactive. Thus, six agonists, eleven antagonists and seven inactive chemicals against TR were identified in in vitro assays. Then, six relevant variables, including molecular structural descriptors and molecular docking scores, were selected for describing compounds. Machine learning methods (i.e., linear discriminant analysis (LDA) and support vector machines (SVM)) were used to build classification models. The optimal model was obtained by using SVM, with an accuracy of 88.24% in the training set, 80.0% in the test set and 75.0% in 10-fold cross-validation. The remaining 187 PCB congeners' hormone activities were predicted using the obtained models. Out of these PCBs, the SVM model predicted 38 agonists and 81 antagonists. The findings revealed that higher chlorinated PCBs tended to have TR-antagonistic activities, whereas lower chlorinated PCBs were agonists. This study provided a reference for further exploring PCBs' thyroid effect.

Implementing QM in docking calculations: is it a waste of computational time?

The greatest challenge in molecular docking (MD) is the deficiency of scoring functions (SFs), which limits their reliability. SFs are too simplified to represent the true features of the complex free energy of protein-ligand interactions. Investigations of docking functions have traded accuracy for speed through the use of approximations and simplifications. Consequently, there has been an increase in the popularity of quantum-mechanical (QM)-based methods as reference points for the development of fast, reliable, valuable, yet inexpensive, tools. As we discuss here, one significant QM-based parameter used to predict docking is the accuracy of atomic partial charges, which is strongly related to the accuracy of the SF prediction.