Development and Validation of Decision Forest Model for Estrogen Receptor Binding Prediction of Chemicals Using Large Data Sets

Machine learning and deep learning approaches for enhanced prediction of hERG blockade: a comprehensive QSAR modeling study

BACKGROUND

Cardiotoxicity is a major cause of drug withdrawal. The hERG channel, regulating ion flow, is pivotal for heart and nervous system function. Its blockade is a concern in drug development. Predicting hERG blockade is essential for identifying cardiac safety issues. Various QSAR models exist, but their performance varies. Ongoing improvements show promise, necessitating continued efforts to enhance accuracy using emerging deep learning algorithms in predicting potential hERG blockade.

STUDY DESIGN AND METHOD

Using a large training dataset, six individual QSAR models were developed. Additionally, three ensemble models were constructed. All models were evaluated using 10-fold cross-validations and two external datasets.

RESULTS

The 10-fold cross-validations resulted in Mathews correlation coefficient (MCC) values from 0.682 to 0.730, surpassing the best-reported model on the same dataset (0.689). External validations yielded MCC values from 0.520 to 0.715 for the first dataset, exceeding those of previously reported models (0-0.599). For the second dataset, MCC values fell between 0.025 and 0.215, aligning with those of reported models (0.112-0.220).

CONCLUSIONS

The developed models can assist the pharmaceutical industry and regulatory agencies in predicting hERG blockage activity, thereby enhancing safety assessments and reducing the risk of adverse cardiac events associated with new drug candidates.

BERT-based language model for accurate drug adverse event extraction from social media: implementation, evaluation, and contributions to pharmacovigilance practices

Introduction

Social media platforms serve as a valuable resource for users to share health-related information, aiding in the monitoring of adverse events linked to medications and treatments in drug safety surveillance. However, extracting drug-related adverse events accurately and efficiently from social media poses challenges in both natural language processing research and the pharmacovigilance domain.

Method

Recognizing the lack of detailed implementation and evaluation of Bidirectional Encoder Representations from Transformers (BERT)-based models for drug adverse event extraction on social media, we developed a BERT-based language model tailored to identifying drug adverse events in this context. Our model utilized publicly available labeled adverse event data from the ADE-Corpus-V2. Constructing the BERT-based model involved optimizing key hyperparameters, such as the number of training epochs, batch size, and learning rate. Through ten hold-out evaluations on ADE-Corpus-V2 data and external social media datasets, our model consistently demonstrated high accuracy in drug adverse event detection.

Result

The hold-out evaluations resulted in average F1 scores of 0.8575, 0.9049, and 0.9813 for detecting words of adverse events, words in adverse events, and words not in adverse events, respectively. External validation using human-labeled adverse event tweets data from SMM4H further substantiated the effectiveness of our model, yielding F1 scores 0.8127, 0.8068, and 0.9790 for detecting words of adverse events, words in adverse events, and words not in adverse events, respectively.

Discussion

This study not only showcases the effectiveness of BERT-based language models in accurately identifying drug-related adverse events in the dynamic landscape of social media data, but also addresses the need for the implementation of a comprehensive study design and evaluation. By doing so, we contribute to the advancement of pharmacovigilance practices and methodologies in the context of emerging information sources like social media.

Machine learning and deep learning for brain tumor MRI image segmentation

Brain tumors are often fatal. Therefore, accurate brain tumor image segmentation is critical for the diagnosis, treatment, and monitoring of patients with these tumors. Magnetic resonance imaging (MRI) is a commonly used imaging technique for capturing brain images. Both machine learning and deep learning techniques are popular in analyzing MRI images. This article reviews some commonly used machine learning and deep learning techniques for brain tumor MRI image segmentation. The limitations and advantages of the reviewed machine learning and deep learning methods are discussed. Even though each of these methods has a well-established status in their individual domains, the combination of two or more techniques is currently an emerging trend.

Review of machine learning and deep learning models for toxicity prediction

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

Machine learning models for rat multigeneration reproductive toxicity prediction

Reproductive toxicity is one of the prominent endpoints in the risk assessment of environmental and industrial chemicals. Due to the complexity of the reproductive system, traditional reproductive toxicity testing in animals, especially guideline multigeneration reproductive toxicity studies, take a long time and are expensive. Therefore, machine learning, as a promising alternative approach, should be considered when evaluating the reproductive toxicity of chemicals. We curated rat multigeneration reproductive toxicity testing data of 275 chemicals from ToxRefDB (Toxicity Reference Database) and developed predictive models using seven machine learning algorithms (decision tree, decision forest, random forest, k-nearest neighbors, support vector machine, linear discriminant analysis, and logistic regression). A consensus model was built based on the seven individual models. An external validation set was curated from the COSMOS database and the literature. The performances of individual and consensus models were evaluated using 500 iterations of 5-fold cross-validations and the external validation data set. The balanced accuracy of the models ranged from 58% to 65% in the 5-fold cross-validations and 45%–61% in the external validations. Prediction confidence analysis was conducted to provide additional information for more appropriate applications of the developed models. The impact of our findings is in increasing confidence in machine learning models. We demonstrate the importance of using consensus models for harnessing the benefits of multiple machine learning models (i.e., using redundant systems to check validity of outcomes). While we continue to build upon the models to better characterize weak toxicants, there is current utility in saving resources by being able to screen out strong reproductive toxicants before investing in vivo testing. The modeling approach (machine learning models) is offered for assessing the rat multigeneration reproductive toxicity of chemicals. Our results suggest that machine learning may be a promising alternative approach to evaluate the potential reproductive toxicity of chemicals.

Deep Learning Models for Predicting Gas Adsorption Capacity of Nanomaterials

Metal-organic frameworks (MOFs), a class of porous nanomaterials, have been widely used in gas adsorption-based applications due to their high porosities and chemical tunability. To facilitate the discovery of high-performance MOFs for different applications, a variety of machine learning models have been developed to predict the gas adsorption capacities of MOFs. Most of the predictive models are developed using traditional machine learning algorithms. However, the continuously increasing sizes of MOF datasets and the complicated relationships between MOFs and their gas adsorption capacities make deep learning a suitable candidate to handle such big data with increased computational power and accuracy. In this study, we developed models for predicting gas adsorption capacities of MOFs using two deep learning algorithms, multilayer perceptron (MLP) and long short-term memory (LSTM) networks, with a hypothetical set of about 130,000 structures of MOFs with methane and carbon dioxide adsorption data at different pressures. The models were evaluated using 10 iterations of 10-fold cross validations and 100 holdout validations. The MLP and LSTM models performed similarly with high prediction accuracy. The models for predicting gas adsorption at a higher pressure outperformed the models for predicting gas adsorption at a lower pressure. The deep learning models are more accurate than the random forest models reported in the literature, especially for predicting gas adsorption capacities at low pressures. Our results demonstrated that deep learning algorithms have a great potential to generate models that can accurately predict the gas adsorption capacities of MOFs.

Machine Learning Models for Predicting Cytotoxicity of Nanomaterials

The wide application of nanomaterials in consumer and medical products has raised concerns about their potential adverse effects on human health. Thus, more and more biological assessments regarding the toxicity of nanomaterials have been performed. However, the different ways the evaluations were performed, such as the utilized assays, cell lines, and the differences of the produced nanoparticles, make it difficult for scientists to analyze and effectively compare toxicities of nanomaterials. Fortunately, machine learning has emerged as a powerful tool for the prediction of nanotoxicity based on the available data. Among different types of toxicity assessments, nanomaterial cytotoxicity was the focus here because of the high sensitivity of cytotoxicity assessment to different treatments without the need for complicated and time-consuming procedures. In this review, we summarized recent studies that focused on the development of machine learning models for prediction of cytotoxicity of nanomaterials. The goal was to provide insight into predicting potential nanomaterial toxicity and promoting the development of safe nanomaterials.

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.

Machine Learning Models for Predicting Liver Toxicity

Liver toxicity is a major adverse drug reaction that accounts for drug failure in clinical trials and withdrawal from the market. Therefore, predicting potential liver toxicity at an early stage in drug discovery is crucial to reduce costs and the potential for drug failure. However, current in vivo animal toxicity testing is very expensive and time consuming. As an alternative approach, various machine learning models have been developed to predict potential liver toxicity in humans. This chapter reviews current advances in the development and application of machine learning models for prediction of potential liver toxicity in humans and discusses possible improvements to liver toxicity prediction.

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.

Elucidation of Agonist and Antagonist Dynamic Binding Patterns in ER-α by Integration of Molecular Docking, Molecular Dynamics Simulations and Quantum Mechanical Calculations

Estrogen receptor alpha (ERα) is a ligand-dependent transcriptional factor in the nuclear receptor superfamily. Many structures of ERα bound with agonists and antagonists have been determined. However, the dynamic binding patterns of agonists and antagonists in the binding site of ERα remains unclear. Therefore, we performed molecular docking, molecular dynamics (MD) simulations, and quantum mechanical calculations to elucidate agonist and antagonist dynamic binding patterns in ERα. 17β-estradiol (E2) and 4-hydroxytamoxifen (OHT) were docked in the ligand binding pockets of the agonist and antagonist bound ERα. The best complex conformations from molecular docking were subjected to 100 nanosecond MD simulations. Hierarchical clustering was conducted to group the structures in the trajectory from MD simulations. The representative structure from each cluster was selected to calculate the binding interaction energy value for elucidation of the dynamic binding patterns of agonists and antagonists in the binding site of ERα. The binding interaction energy analysis revealed that OHT binds ERα more tightly in the antagonist conformer, while E2 prefers the agonist conformer. The results may help identify ERα antagonists as drug candidates and facilitate risk assessment of chemicals through ER-mediated responses.

High-Throughput Screening to Identify Chemical Cardiotoxic Potential

Cardiovascular (CV) disease is one of the most prevalent public health concerns, and mounting evidence supports the contribution of environmental chemicals to CV disease burden. In this study, we performed cardiotoxicity profiling for the Tox21 chemical library by focusing on high-throughput screening (HTS) assays whose targets are associated with adverse events related to CV failure modes. Our objective was to develop new hypotheses around environmental chemicals of potential interest for adverse CV outcomes using Tox21/ToxCast HTS data. Molecular and cellular events linked to six failure modes of CV toxicity were cross-referenced with 1399 Tox21/ToxCast assays to identify cardio-relevant bioactivity signatures. The resulting 40 targets, measured in 314 assays, were integrated via a ToxPi visualization tool and ranking system to prioritize 1138 chemicals based upon formal integration across multiple domains of information. Filtering was performed based on cytotoxicity and generalized cell stress endpoints to try and isolate chemicals with effects specific to CV biology, and bioactivity- and structure-based clustering identified subgroups of chemicals preferentially affecting targets such as ion channels and vascular tissue biology. Our approach identified drugs with known cardiotoxic effects, such as estrogenic modulators like clomiphene and raloxifene, anti-arrhythmic drugs like amiodarone and haloperidol, and antipsychotic drugs like chlorpromazine. Several classes of environmental chemicals such as organotins, bisphenol-like chemicals, pesticides, and quaternary ammonium compounds demonstrated strong bioactivity against CV targets; these were compared to existing data in the literature (e.g., from cardiomyocytes, animal data, or human epidemiological studies) and prioritized for further testing.

Development of a Nicotinic Acetylcholine Receptor nAChR α7 Binding Activity Prediction Model

Despite the well-known adverse health effects associated with tobacco use, addiction to nicotine found in tobacco products causes difficulty in quitting among users. Nicotinic acetylcholine receptors (nAChRs) are the physiological targets of nicotine and facilitate addiction to tobacco products. The nAChR-α7 subtype plays an important role in addiction; therefore, predicting the binding activity of tobacco constituents to nAChR-α7 is an important component for assessing addictive potential of tobacco constituents. We developed an α7 binding activity prediction model based on a large training data set of 843 chemicals with human α7 binding activity data extracted from PubChem and ChEMBL. The model was tested using 1215 chemicals with rat α7 binding activity data from the same databases. Based on the competitive docking results, the docking scores were partitioned to the key residues that play important roles in the receptor-ligand binding. A decision forest was used to train the human α7 binding activity prediction model based on the partition of docking scores. Five-fold cross validations were conducted to estimate the performance of the decision forest models. The developed model was used to predict the potential human α7 binding activity for 5275 tobacco constituents. The human α7 binding activity data for 84 of the 5275 tobacco constituents were experimentally measured to confirm and empirically validate the prediction results. The prediction accuracy, sensitivity, and specificity were 64.3, 40.0, and 81.6%, respectively. The developed prediction model of human α7 may be a useful tool for high-throughput screening of potential addictive tobacco constituents.

Artificial Intelligence for Drug Toxicity and Safety

Interventional pharmacology is one of medicine's most potent weapons against disease. These drugs, however, can result in damaging side effects and must be closely monitored. Pharmacovigilance is the field of science that monitors, detects, and prevents adverse drug reactions (ADRs). Safety efforts begin during the development process, using in vivo and in vitro studies, continue through clinical trials, and extend to postmarketing surveillance of ADRs in real-world populations. Future toxicity and safety challenges, including increased polypharmacy and patient diversity, stress the limits of these traditional tools. Massive amounts of newly available data present an opportunity for using artificial intelligence (AI) and machine learning to improve drug safety science. Here, we explore recent advances as applied to preclinical drug safety and postmarketing surveillance with a specific focus on machine and deep learning (DL) approaches.

Stacked Generalization with Applicability Domain Outperforms Simple QSAR on in Vitro Toxicological Data

The development of in silico tools able to predict bioactivity and toxicity of chemical substances is a powerful solution envisioned to assess toxicity as early as possible. To enable the development of such tools, the ToxCast program has generated and made publicly available in vitro bioactivity data for thousands of compounds. The goal of the present study is to characterize and explore the data from ToxCast in terms of Machine Learning capability. For this, a large scale analysis on the entire database has been performed to build models to predict bioactivities measured in in vitro assays. Simple classical QSAR algorithms (ANN, SVM, LDA, random forest, and Bayesian) were first applied on the data, and the results of these algorithms suggested that they do not seem to be well-suited for data sets with a high proportion of inactive compounds. The study then showed for the first time that the use of an ensemble method named "Stacked generalization" could improve the model performance on this type of data. Indeed, for 61% of 483 models, the Stacked method led to models with higher performance. Moreover, the combination of this ensemble method with an applicability domain filter allows one to assess the reliability of the predictions for further compound prioritization. In particular we showed that for 50% of the models, the ROC score is better if we do not consider the compounds that are not within the applicability domain.

Computational prediction models for assessing endocrine disrupting potential of chemicals

Endocrine disrupting chemicals (EDCs) mimic natural hormones and disrupt endocrine function. Humans and wildlife are exposed to EDCs might alter endocrine functions through various mechanisms and lead to an adverse effects. Hence, EDCs identification is important to protect the ecosystem and to promote the public health. Leveraging in-vitro and in-vivo experiments to identify potential EDCs is time consuming and expensive. Hence, quantitative structure-activity relationship is applied to screen the potential EDCs. Here, we summarize the predictive models developed using various algorithms to forecast the binding activity of chemicals to the estrogen and androgen receptors, alpha-fetoprotein, and sex hormone binding globulin.

Structural Changes Due to Antagonist Binding in Ligand Binding Pocket of Androgen Receptor Elucidated Through Molecular Dynamics Simulations

When a small molecule binds to the androgen receptor (AR), a conformational change can occur which impacts subsequent binding of co-regulator proteins and DNA. In order to accurately study this mechanism, the scientific community needs a crystal structure of the Wild type AR (WT-AR) ligand binding domain, bound with antagonist. To address this open need, we leveraged molecular docking and molecular dynamics (MD) simulations to construct a structure of the WT-AR ligand binding domain bound with antagonist bicalutamide. The structure of mutant AR (Mut-AR) bound with this same antagonist informed this study. After molecular docking analysis pinpointed the suitable binding orientation of a ligand in AR, the model was further optimized through 1 μs of MD simulations. Using this approach, three molecular systems were studied: (1) WT-AR bound with agonist R1881, (2) WT-AR bound with antagonist bicalutamide, and (3) Mut-AR bound with bicalutamide. Our structures were very similar to the experimentally determined structures of both WT-AR with R1881 and Mut-AR with bicalutamide, demonstrating the trustworthiness of this approach. In our model, when WT-AR is bound with bicalutamide, Val716/Lys720/Gln733, or Met734/Gln738/Glu897 move and thus disturb the positive and negative charge clumps of the AF2 site. This disruption of the AF2 site is key for understanding the impact of antagonist binding on subsequent co-regulator binding. In conclusion, the antagonist induced structural changes in WT-AR detailed in this study will enable further AR research and will facilitate AR targeting drug discovery.

Advancing Predictive Hepatotoxicity at the Intersection of Experimental, in Silico, and Artificial Intelligence Technologies

Adverse drug reactions, particularly those that result in drug-induced liver injury (DILI), are a major cause of drug failure in clinical trials and drug withdrawals. Hepatotoxicity-mediated drug attrition occurs despite substantial investments of time and money in developing cellular assays, animal models, and computational models to predict its occurrence in humans. Underperformance in predicting hepatotoxicity associated with drugs and drug candidates has been attributed to existing gaps in our understanding of the mechanisms involved in driving hepatic injury after these compounds perfuse and are metabolized by the liver. Herein we assess in vitro, in vivo (animal), and in silico strategies used to develop predictive DILI models. We address the effectiveness of several two- and three-dimensional in vitro cellular methods that are frequently employed in hepatotoxicity screens and how they can be used to predict DILI in humans. We also explore how humanized animal models can recapitulate human drug metabolic profiles and associated liver injury. Finally, we highlight the maturation of computational methods for predicting hepatotoxicity, the untapped potential of artificial intelligence for improving in silico DILI screens, and how knowledge acquired from these predictions can shape the refinement of experimental methods.

Competitive docking model for prediction of the human nicotinic acetylcholine receptor α7 binding of tobacco constituents

The detrimental health effects associated with tobacco use constitute a major public health concern. The addiction associated with nicotine found in tobacco products has led to difficulty in quitting among users. Nicotinic acetylcholine receptors (nAChRs) are the targets of nicotine and are responsible for addiction to tobacco products. However, it is unknown if the other >8000 tobacco constituents are addictive. Since it is time-consuming and costly to experimentally assess addictive potential of such larger number of chemicals, computationally predicting human nAChRs binding is important for in silico evaluation of addiction potential of tobacco constituents and needs structures of human nAChRs. Therefore, we constructed three-dimensional structures of the ligand binding domain of human nAChR α7 subtype and then developed a predictive model based on the constructed structures to predict human nAChR α7 binding activity of tobacco constituents. The predictive model correctly predicted 11 out of 12 test compounds to be binders of nAChR α7. The model is a useful tool for high-throughput screening of potential addictive tobacco constituents. These results could inform regulatory science research by providing a new validated predictive tool using cutting-edge computational methodology to high-throughput screen tobacco additives and constituents for their binding interaction with the human α7 nicotinic receptor. The tool represents a prediction model capable of screening thousands of chemicals found in tobacco products for addiction potential, which improves the understanding of the potential effects of additives.

Channel Interactions and Robust Inference for Ratiometric β-lactamase Assay Data: a Tox21 Library Analysis

Ratiometric β-lactamase (BLA) reporters are widely used to study transcriptional responses in a high-throughput screening (HTS) format. Typically, a ratio readout (background/target fluorescence) is used for toxicity assessment and structure-activity modeling efforts from BLA HTS data. This ratio readout may be confounded by channel-specific artifacts. To maximize the utility of BLA HTS data, we analyzed the relationship between individual channels and ratio readouts after fitting 10,000 chemical titration series screened in seven BLA stress-response assays from the Tox21 initiative. Similar to previous observations, we found that activity classifications based on BLA ratio readout alone are confounded by interference patterns for up to 85% (50 % on average) of active chemicals. Most Tox21 analyses adjust for this issue by evaluating target and ratio readout direction. In addition, we found that the potency and efficacy estimates derived from the ratio readouts may not represent the target channel effects and thus complicates chemical activity comparison. From these analyses we recommend a simpler approach using a direct evaluation of the target and background channels as well as the respective noise levels when using BLA data for toxicity assessment. This approach eliminates the channel interference issues and allows for straightforward chemical assessment and comparisons.

Endocrine Disrupting Chemicals Mediated through Binding Androgen Receptor Are Associated with Diabetes Mellitus

Endocrine disrupting chemicals (EDCs) can mimic natural hormone to interact with receptors in the endocrine system and thus disrupt the functions of the endocrine system, raising concerns on the public health. In addition to disruption of the endocrine system, some EDCs have been found associated with many diseases such as breast cancer, prostate cancer, infertility, asthma, stroke, Alzheimer’s disease, obesity, and diabetes mellitus. EDCs that binding androgen receptor have been reported associated with diabetes mellitus in in vitro, animal, and clinical studies. In this review, we summarize the structural basis and interactions between androgen receptor and EDCs as well as the associations of various types of diabetes mellitus with the EDCs mediated through androgen receptor binding. We also discuss the perspective research for further understanding the impact and mechanisms of EDCs on the risk of diabetes mellitus.

Development of Decision Forest Models for Prediction of Drug-Induced Liver Injury in Humans Using A Large Set of FDA-approved Drugs

Drug-induced liver injury (DILI) presents a significant challenge to drug development and regulatory science. The FDA’s Liver Toxicity Knowledge Base (LTKB) evaluated >1000 drugs for their likelihood of causing DILI in humans, of which >700 drugs were classified into three categories (most-DILI, less-DILI, and no-DILI). Based on this dataset, we developed and compared 2-class and 3-class DILI prediction models using the machine learning algorithm of Decision Forest (DF) with Mold2 structural descriptors. The models were evaluated through 1000 iterations of 5-fold cross-validations, 1000 bootstrapping validations and 1000 permutation tests (that assessed the chance correlation). Furthermore, prediction confidence analysis was conducted, which provides an additional parameter for proper interpretation of prediction results. We revealed that the 3-class model not only had a higher resolution to estimate DILI risk but also showed an improved capability to differentiate most-DILI drugs from no-DILI drugs in comparison with the 2-class DILI model. We demonstrated the utility of the models for drug ingredients with warnings very recently issued by the FDA. Moreover, we identified informative molecular features important for assessing DILI risk. Our results suggested that the 3-class model presents a better option than the binary model (which most publications are focused on) for drug safety evaluation.

Development of estrogen receptor beta binding prediction model using large sets of chemicals

We developed an ER_β binding prediction model to facilitate identification of chemicals specifically bind ER_β or ER_α together with our previously developed ER_α binding model. Decision Forest was used to train ER_β binding prediction model based on a large set of compounds obtained from EADB. Model performance was estimated through 1000 iterations of 5-fold cross validations. Prediction confidence was analyzed using predictions from the cross validations. Informative chemical features for ER_β binding were identified through analysis of the frequency data of chemical descriptors used in the models in the 5-fold cross validations. 1000 permutations were conducted to assess the chance correlation. The average accuracy of 5-fold cross validations was 93.14% with a standard deviation of 0.64%. Prediction confidence analysis indicated that the higher the prediction confidence the more accurate the predictions. Permutation testing results revealed that the prediction model is unlikely generated by chance. Eighteen informative descriptors were identified to be important to ER_β binding prediction. Application of the prediction model to the data from ToxCast project yielded very high sensitivity of 90-92%. Our results demonstrated ER_β binding of chemicals could be accurately predicted using the developed model. Coupling with our previously developed ER_α prediction model, this model could be expected to facilitate drug development through identification of chemicals that specifically bind ER_β or ER_α.

Molecular dynamics simulations and applications in computational toxicology and nanotoxicology

Nanotoxicology studies toxicity of nanomaterials and has been widely applied in biomedical researches to explore toxicity of various biological systems. Investigating biological systems through in vivo and in vitro methods is expensive and time taking. Therefore, computational toxicology, a multi-discipline field that utilizes computational power and algorithms to examine toxicology of biological systems, has gained attractions to scientists. Molecular dynamics (MD) simulations of biomolecules such as proteins and DNA are popular for understanding of interactions between biological systems and chemicals in computational toxicology. In this paper, we review MD simulation methods, protocol for running MD simulations and their applications in studies of toxicity and nanotechnology. We also briefly summarize some popular software tools for execution of MD simulations.

In Silico Prediction of Chemicals Binding to Aromatase with Machine Learning Methods

Environmental chemicals may affect endocrine systems through multiple mechanisms, one of which is via effects on aromatase (also known as CYP19A1), an enzyme critical for maintaining the normal balance of estrogens and androgens in the body. Therefore, rapid and efficient identification of aromatase-related endocrine disrupting chemicals (EDCs) is important for toxicology and environment risk assessment. In this study, on the basis of the Tox21 10K compound library, in silico classification models for predicting aromatase binders/nonbinders were constructed by machine learning methods. To improve the prediction ability of the models, a combined classifier (CC) strategy that combines different independent machine learning methods was adopted. Performances of the models were measured by test and external validation sets containing 1336 and 216 chemicals, respectively. The best model was obtained with the MACCS (Molecular Access System) fingerprint and CC method, which exhibited an accuracy of 0.84 for the test set and 0.91 for the external validation set. Additionally, several representative substructures for characterizing aromatase binders, such as ketone, lactone, and nitrogen-containing derivatives, were identified using information gain and substructure frequency analysis. Our study provided a systematic assessment of chemicals binding to aromatase. The built models can be helpful to rapidly identify potential EDCs targeting aromatase.

Consensus Modeling for Prediction of Estrogenic Activity of Ingredients Commonly Used in Sunscreen Products

Sunscreen products are predominantly regulated as over-the-counter (OTC) drugs by the US FDA. The "active" ingredients function as ultraviolet filters. Once a sunscreen product is generally recognized as safe and effective (GRASE) via an OTC drug review process, new formulations using these ingredients do not require FDA review and approval, however, the majority of ingredients have never been tested to uncover any potential endocrine activity and their ability to interact with the estrogen receptor (ER) is unknown, despite the fact that this is a very extensively studied target related to endocrine activity. Consequently, we have developed an in silico model to prioritize single ingredient estrogen receptor activity for use when actual animal data are inadequate, equivocal, or absent. It relies on consensus modeling to qualitatively and quantitatively predict ER binding activity. As proof of concept, the model was applied to ingredients commonly used in sunscreen products worldwide and a few reference chemicals. Of the 32 chemicals with unknown ER binding activity that were evaluated, seven were predicted to be active estrogenic compounds. Five of the seven were confirmed by the published data. Further experimental data is needed to confirm the other two predictions.

sNebula, a network-based algorithm to predict binding between human leukocyte antigens and peptides

Understanding the binding between human leukocyte antigens (HLAs) and peptides is important to understand the functioning of the immune system. Since it is time-consuming and costly to measure the binding between large numbers of HLAs and peptides, computational methods including machine learning models and network approaches have been developed to predict HLA-peptide binding. However, there are several limitations for the existing methods. We developed a network-based algorithm called sNebula to address these limitations. We curated qualitative Class I HLA-peptide binding data and demonstrated the prediction performance of sNebula on this dataset using leave-one-out cross-validation and five-fold cross-validations. This algorithm can predict not only peptides of different lengths and different types of HLAs, but also the peptides or HLAs that have no existing binding data. We believe sNebula is an effective method to predict HLA-peptide binding and thus improve our understanding of the immune system.

Prediction of selective estrogen receptor beta agonist using open data and machine learning approach

Background

Estrogen receptors (ERs) are nuclear transcription factors that are involved in the regulation of many complex physiological processes in humans. ERs have been validated as important drug targets for the treatment of various diseases, including breast cancer, ovarian cancer, osteoporosis, and cardiovascular disease. ERs have two subtypes, ER-α and ER-β. Emerging data suggest that the development of subtype-selective ligands that specifically target ER-β could be a more optimal approach to elicit beneficial estrogen-like activities and reduce side effects.

Methods

Herein, we focused on ER-β and developed its in silico quantitative structure-activity relationship models using machine learning (ML) methods.

Results

The chemical structures and ER-β bioactivity data were extracted from public chemogenomics databases. Four types of popular fingerprint generation methods including MACCS fingerprint, PubChem fingerprint, 2D atom pairs, and Chemistry Development Kit extended fingerprint were used as descriptors. Four ML methods including Naïve Bayesian classifier, k-nearest neighbor, random forest, and support vector machine were used to train the models. The range of classification accuracies was 77.10% to 88.34%, and the range of area under the ROC (receiver operating characteristic) curve values was 0.8151 to 0.9475, evaluated by the 5-fold cross-validation. Comparison analysis suggests that both the random forest and the support vector machine are superior for the classification of selective ER-β agonists. Chemistry Development Kit extended fingerprints and MACCS fingerprint performed better in structural representation between active and inactive agonists.

Conclusion

These results demonstrate that combining the fingerprint and ML approaches leads to robust ER-β agonist prediction models, which are potentially applicable to the identification of selective ER-β agonists.

Experimental Data Extraction and in Silico Prediction of the Estrogenic Activity of Renewable Replacements for Bisphenol A

Bisphenol A (BPA) is a ubiquitous compound used in polymer manufacturing for a wide array of applications; however, increasing evidence has shown that BPA causes significant endocrine disruption and this has raised public concerns over safety and exposure limits. The use of renewable materials as polymer feedstocks provides an opportunity to develop replacement compounds for BPA that are sustainable and exhibit unique properties due to their diverse structures. As new bio-based materials are developed and tested, it is important to consider the impacts of both monomers and polymers on human health. Molecular docking simulations using the Estrogenic Activity Database in conjunction with the decision forest were performed as part of a two-tier in silico model to predict the activity of 29 bio-based platform chemicals in the estrogen receptor-α (ERα). Fifteen of the candidates were predicted as ER binders and fifteen as non-binders. Gaining insight into the estrogenic activity of the bio-based BPA replacements aids in the sustainable development of new polymeric materials.

Structures of androgen receptor bound with ligands: advancing understanding of biological functions and drug discovery

INTRODUCTION

Androgen receptor (AR) is a ligand-dependent transcription factor and a member of the nuclear receptor superfamily. It plays a vital role in male sexual development and regulates gene expression in various tissues, including prostate. Androgens are compounds that exert their biological effects via interaction with AR. Binding of androgens to AR initiates conformational changes in AR that affect binding of co-regulator proteins and DNA. AR agonists and antagonists are widely used in a variety of clinical applications (i.e. hypogonadism and prostate cancer therapy).

AREAS COVERED

This review provides a close look at structures of AR-ligand complexes and mutations in the receptor that have been revealed, discusses current challenges in the field, and sheds light on future directions.

EXPERT OPINION

AR is one of the primary targets for the treatment of prostate cancer, as AR antagonists inhibit prostate cancer growth. However, these drugs are not effective for long-term treatment and lead to castration-resistant prostate cancer. The structures of AR-ligand complexes are an invaluable scientific asset that enhances our understanding of biological functions and mechanisms of androgenic and anti-androgenic chemicals as well as promotes the discovery of superior drug candidates.

Applying network analysis and Nebula (neighbor-edges based and unbiased leverage algorithm) to ToxCast data

BACKGROUND

ToxCast data have been used to develop models for predicting in vivo toxicity. To predict the in vivo toxicity of a new chemical using a ToxCast data based model, its ToxCast bioactivity data are needed but not normally available. The capability of predicting ToxCast bioactivity data is necessary to fully utilize ToxCast data in the risk assessment of chemicals.

OBJECTIVES

We aimed to understand and elucidate the relationships between the chemicals and bioactivity data of the assays in ToxCast and to develop a network analysis based method for predicting ToxCast bioactivity data.

METHODS

We conducted modularity analysis on a quantitative network constructed from ToxCast data to explore the relationships between the assays and chemicals. We further developed Nebula (neighbor-edges based and unbiased leverage algorithm) for predicting ToxCast bioactivity data.

RESULTS

Modularity analysis on the network constructed from ToxCast data yielded seven modules. Assays and chemicals in the seven modules were distinct. Leave-one-out cross-validation yielded a Q(2) of 0.5416, indicating ToxCast bioactivity data can be predicted by Nebula. Prediction domain analysis showed some types of ToxCast assay data could be more reliably predicted by Nebula than others.

CONCLUSIONS

Network analysis is a promising approach to understand ToxCast data. Nebula is an effective algorithm for predicting ToxCast bioactivity data, helping fully utilize ToxCast data in the risk assessment of chemicals.

A Rat α-Fetoprotein Binding Activity Prediction Model to Facilitate Assessment of the Endocrine Disruption Potential of Environmental Chemicals

Endocrine disruptors such as polychlorinated biphenyls (PCBs), diethylstilbestrol (DES) and dichlorodiphenyltrichloroethane (DDT) are agents that interfere with the endocrine system and cause adverse health effects. Huge public health concern about endocrine disruptors has arisen. One of the mechanisms of endocrine disruption is through binding of endocrine disruptors with the hormone receptors in the target cells. Entrance of endocrine disruptors into target cells is the precondition of endocrine disruption. The binding capability of a chemical with proteins in the blood affects its entrance into the target cells and, thus, is very informative for the assessment of potential endocrine disruption of chemicals. α-fetoprotein is one of the major serum proteins that binds to a variety of chemicals such as estrogens. To better facilitate assessment of endocrine disruption of environmental chemicals, we developed a model for α-fetoprotein binding activity prediction using the novel pattern recognition method (Decision Forest) and the molecular descriptors calculated from two-dimensional structures by Mold² software. The predictive capability of the model has been evaluated through internal validation using 125 training chemicals (average balanced accuracy of 69%) and external validations using 22 chemicals (balanced accuracy of 71%). Prediction confidence analysis revealed the model performed much better at high prediction confidence. Our results indicate that the model is useful (when predictions are in high confidence) in endocrine disruption risk assessment of environmental chemicals though improvement by increasing number of training chemicals is needed.

Predictive Modeling of Estrogen Receptor Binding Agents Using Advanced Cheminformatics Tools and Massive Public Data

Estrogen receptors (ERα) are a critical target for drug design as well as a potential source of toxicity when activated unintentionally. Thus, evaluating potential ERα binding agents is critical in both drug discovery and chemical toxicity areas. Using computational tools, e.g., Quantitative Structure-Activity Relationship (QSAR) models, can predict potential ERα binding agents before chemical synthesis. The purpose of this project was to develop enhanced predictive models of ERα binding agents by utilizing advanced cheminformatics tools that can integrate publicly available bioassay data. The initial ERα binding agent data set, consisting of 446 binders and 8307 non-binders, was obtained from the Tox21 Challenge project organized by the NIH Chemical Genomics Center (NCGC). After removing the duplicates and inorganic compounds, this data set was used to create a training set (259 binders and 259 non-binders). This training set was used to develop QSAR models using chemical descriptors. The resulting models were then used to predict the binding activity of 264 external compounds, which were available to us after the models were developed. The cross-validation results of training set [Correct Classification Rate (CCR) = 0.72] were much higher than the external predictivity of the unknown compounds (CCR = 0.59). To improve the conventional QSAR models, all compounds in the training set were used to search PubChem and generate a profile of their biological responses across thousands of bioassays. The most important bioassays were prioritized to generate a similarity index that was used to calculate the biosimilarity score between each two compounds. The nearest neighbors for each compound within the set were then identified and its ERα binding potential was predicted by its nearest neighbors in the training set. The hybrid model performance (CCR = 0.94 for cross validation; CCR = 0.68 for external prediction) showed significant improvement over the original QSAR models, particularly for the activity cliffs that induce prediction errors. The results of this study indicate that the response profile of chemicals from public data provides useful information for modeling and evaluation purposes. The public big data resources should be considered along with chemical structure information when predicting new compounds, such as unknown ERα binding agents.