hERG Classification Model Based on a Combination of Support Vector Machine Method and GRIND Descriptors

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

Toxicity prediction is a critical step in the drug discovery process that helps identify and prioritize compounds with the greatest potential for safe and effective use in humans, while also reducing the risk of costly late-stage failures. It is estimated that over 30% of drug candidates are discarded owing to toxicity. Recently, artificial intelligence (AI) has been used to improve drug toxicity prediction as it provides more accurate and efficient methods for identifying the potentially toxic effects of new compounds before they are tested in human clinical trials, thus saving time and money. In this review, we present an overview of recent advances in AI-based drug toxicity prediction, including the use of various machine learning algorithms and deep learning architectures, of six major toxicity properties and Tox21 assay end points. Additionally, we provide a list of public data sources and useful toxicity prediction tools for the research community and highlight the challenges that must be addressed to enhance model performance. Finally, we discuss future perspectives for AI-based drug toxicity prediction. This review can aid researchers in understanding toxicity prediction and pave the way for new methods of drug discovery.

Machine-learning technique, QSAR and molecular dynamics for hERG-drug interactions

One of the most well-known anti-targets defining medication cardiotoxicity is the voltage-dependent hERG K + channel, which is well-known for its crucial involvement in cardiac action potential repolarization. Torsades de Pointes, QT prolongation, and sudden death are all caused by hERG (the human Ether-à-go-go-Related Gene) inhibition. There is great interest in creating predictive computational (in silico) tools to identify and weed out potential hERG blockers early in the drug discovery process because testing for hERG liability and the traditional experimental screening are complicated, expensive and time-consuming. This study used 2D descriptors of a large curated dataset of 6766 compounds and machine learning approaches to build robust descriptor-based QSAR and predictive classification models for KCNH2 liability. Decision Tree, Random Forest, Logistic Regression, Ada Boosting, kNN, SVM, Naïve Bayes, neural network and stochastic gradient classification classifier algorithms were used to build classification models. If a compound's IC50 value was between 10 μM and less, it was classified as a blocker (hERG-positive), and if it was more, it was classified as a non-blocker (hERG-negative). Matthew's correlation coefficient formula and F1score were applied to compare and track the developed models' performance. Molecular docking and dynamics studies were performed to understand the cardiotoxicity relating to the hERG-gene. The hERG residues interacting after 100 ns are LEU:697, THR:708, PHE:656, HIS:674, HIS:703, TRP:705 and ASN:709 and the hERG-ligand-16 complex trajectory showed stable behaviour with lesser fluctuations in the entire simulation of 200 ns.Communicated by Ramaswamy H. Sarma.

TSSF-hERG: A machine-learning-based hERG potassium channel-specific scoring function for chemical cardiotoxicity prediction

The human ether-à-go-go-related gene (hERG) encodes the Kv11.1 voltage-gated potassium ion (K⁺) channel that conducts the rapidly activating delayed rectifier current (I_Kr) in cardiomyocytes to regulate the repolarization process. Some drugs, as blockers of hERG potassium channels, cannot be marketed due to prolonged QT intervals, as well known as cardiotoxicity. Predetermining the binding affinity values between drugs and hERG through in silico methods can greatly reduce the time and cost required for experimental verification. In this study, we collected 9,215 compounds with AutoDock Vina's docking structures as training set, and collected compounds from four references as test sets. A series of models for predicting the binding affinities of hERG blockers were built based on five machine learning algorithms and combinations of interaction features and ligand features. The model built by support vector regression (SVR) using the combination of all features achieved the best performance on both tenfold cross-validation and external verification, which was selected and named as TSSF-hERG (target-specific scoring function for hERG). TSSF-hERG is more accurate than the classic scoring function of AutoDock Vina and the machine-learning-based generic scoring function RF-Score, with a Pearson's correlation coefficient (Rp) of 0.765, a Spearman's rank correlation coefficient (Rs) of 0.757, a root-mean-square error (RMSE) of 0.585 in a tenfold cross-validation study. All results demonstrated that TSSF-hERG would be useful for improving the power of binding affinity prediction between hERG and compounds, which can be further used for prediction or virtual screening of the hERG-related cardiotoxicity of drug candidates.

Assessing hERG1 Blockade from Bayesian Machine-Learning-Optimized Site Identification by Ligand Competitive Saturation Simulations

Drug-induced cardiotoxicity is a potentially lethal and yet one of the most common side effects with the drugs in clinical use. Most of the drug-induced cardiotoxicity is associated with an off-target pharmacological blockade of K+ currents carried out by the cardiac Human-Ether-a-go-go-Related (hERG1) potassium channel. There is a compulsory preclinical stage safety assessment for the hERG1 blockade for all classes of drugs, which adds substantially to the cost of drug development. The availability of a high-resolution cryogenic electron microscopy (cryo-EM) structure for the channel in its open/depolarized state solved in 2017 enabled the application of molecular modeling for rapid assessment of drug blockade by molecular docking and simulation techniques. More importantly, if successful, in silico methods may allow a path to lead-compound salvaging by mapping out key block determinants. Here, we report the blind application of the site identification by the ligand competitive saturation (SILCS) protocol to map out druggable/regulatory hotspots in the hERG1 channel available for blockers and activators. The SILCS simulations use small solutes representative of common functional groups to sample the chemical space for the entire protein and its environment using all-atom simulations. The resulting chemical maps, FragMaps, explicitly account for receptor flexibility, protein-fragment interactions, and fragment desolvation penalty allowing for rapid ranking of potential ligands as blockers or nonblockers of hERG1. To illustrate the power of the approach, SILCS was applied to a test set of 55 blockers with diverse chemical scaffolds and pIC50 values measured under uniform conditions. The original SILCS model was based on the all-atom modeling of the hERG1 channel in an explicit lipid bilayer and was further augmented with a Bayesian-optimization/machine-learning (BML) stage employing an independent literature-derived training set of 163 molecules. BML approach was used to determine weighting factors for the FragMaps contributions to the scoring function. pIC50 predictions from the combined SILCS/BML approach to the 55 blockers showed a Pearson correlation (PC) coefficient of >0.535 relative to the experimental data. SILCS/BML model was shown to yield substantially improved performance as compared to commonly used rigid and flexible molecular docking methods for a well-established cohort of hERG1 blockers, where no correlation with experimental data was recorded. SILCS/BML results also suggest that a proper weighting of protonation states of common blockers present at physiological pH is essential for accurate predictions of blocker potency. The precalculated and optimized SILCS FragMaps can now be used for the rapid screening of small molecules for their cardiotoxic potential as well as for exploring alternative binding pockets in the hERG1 channel with applications to the rational design of activators.

Prediction of hERG potassium channel blockage using ensemble learning methods and molecular fingerprints

The human ether-a-go-go-related gene (hERG) encodes a tetrameric potassium channel called Kv11.1. This channel can be blocked by certain drugs, which leads to long QT syndrome, causing cardiotoxicity. This is a significant problem during drug development. Using computer models to predict compound cardiotoxicity during the early stages of drug design will help to solve this problem. In this study, we used a dataset of 1865 compounds exhibiting known hERG inhibitory activities as a training set. Thirty cardiotoxicity classification models were established using three machine learning algorithms based on molecular fingerprints and molecular descriptors. Through using these models as the base classifier, a new cardiotoxicity classification model with better predictive performance was developed using ensemble learning method. The accuracy of the best base classifier, which was generated using the XGBoost method with molecular descriptors, was 84.8 %, and the area under the receiver-operating characteristic curve (AUC) was 0.876 in the five fold cross-validation. However, all of the ensemble models that we developed had higher predictive performance than the base classifiers in the five fold cross-validation. The best predictive performance was achieved by the Ensemble-Top7 model, with accuracy of 84.9 % and AUC of 0.887. We also tested the ensemble model using external validation data and achieved accuracy of 85.0 % and AUC of 0.786. Furthermore, we identified several hERG-related substructures, which provide valuable information for designing drug candidates.

Benchmarking Data Sets from PubChem BioAssay Data: Current Scenario and Room for Improvement

Developing realistic data sets for evaluating virtual screening methods is a task that has been tackled by the cheminformatics community for many years. Numerous artificially constructed data collections were developed, such as DUD, DUD-E, or DEKOIS. However, they all suffer from multiple drawbacks, one of which is the absence of experimental results confirming the impotence of presumably inactive molecules, leading to possible false negatives in the ligand sets. In light of this problem, the PubChem BioAssay database, an open-access repository providing the bioactivity information of compounds that were already tested on a biological target, is now a recommended source for data set construction. Nevertheless, there exist several issues with the use of such data that need to be properly addressed. In this article, an overview of benchmarking data collections built upon experimental PubChem BioAssay input is provided, along with a thorough discussion of noteworthy issues that one must consider during the design of new ligand sets from this database. The points raised in this review are expected to guide future developments in this regard, in hopes of offering better evaluation tools for novel in silico screening procedures.

Prediction of hERG K+ channel blockage using deep neural networks

Human ether-a-go-go-related gene (hERG) K+ channel blockage may cause severe cardiac side-effects and has become a serious issue in safety evaluation of drug candidates. Therefore, improving the ability to avoid undesirable hERG activity in the early stage of drug discovery is of significant importance. The purpose of this study was to build predictive models of hERG activity by deep neural networks. For each combination of sampling methods and descriptors, deep neural networks with different architectures were implemented to build classification models. The optimal model M15 with three hidden layers, undersampling method, and 2D descriptors yielded the prediction accuracy of 0.78 and F1 score of 0.75 on the test set as well as accuracy of 0.77 and F1 score of 0.34 on the external validation set, outperforming the other 35 models including 9 random forest models. Particularly, the optimal model M15 achieved the highest F1 score and the second highest accuracy when compared with other five methods from four groups using different machine learning algorithms with the same external validation set. It can be believed that this model has powerful capability on prediction of hERG toxicity, which is of great benefit for developing novel drug candidates.

Open-Access Activity Prediction Tools for Natural Products. Case Study: hERG Blockers

Interference with the hERG potassium ion channel may cause cardiac arrhythmia and can even lead to death. Over the last few decades, several drugs, already on the market, and many more investigational drugs in various development stages, have had to be discontinued because of their hERG-associated toxicity. To recognize potential hERG activity in the early stages of drug development, a wide array of computational tools, based on different principles, such as 3D QSAR, 2D and 3D similarity, and machine learning, have been developed and are reviewed in this chapter. The various available prediction tools Similarity Ensemble Approach, SuperPred, SwissTargetPrediction, HitPick, admetSAR, PASSonline, Pred-hERG, and VirtualToxLab™ were used to screen a dataset of known hERG synthetic and natural product actives and inactives to quantify and compare their predictive power. This contribution will allow the reader to evaluate the suitability of these computational methods for their own related projects. There is an unmet need for natural product-specific prediction tools in this field.

Experimentally Validated Pharmacoinformatics Approach to Predict hERG Inhibition Potential of New Chemical Entities

The hERG (human ether-a-go-go-related gene) encoded potassium ion (K⁺) channel plays a major role in cardiac repolarization. Drug-induced blockade of hERG has been a major cause of potentially lethal ventricular tachycardia termed Torsades de Pointes (TdPs). Therefore, we presented a pharmacoinformatics strategy using combined ligand and structure based models for the prediction of hERG inhibition potential (IC₅₀) of new chemical entities (NCEs) during early stages of drug design and development. Integrated GRid-INdependent Descriptor (GRIND) models, and lipophilic efficiency (LipE), ligand efficiency (LE) guided template selection for the structure based pharmacophore models have been used for virtual screening and subsequent hERG activity (pIC₅₀) prediction of identified hits. Finally selected two hits were experimentally evaluated for hERG inhibition potential (pIC₅₀) using whole cell patch clamp assay. Overall, our results demonstrate a difference of less than ±1.6 log unit between experimentally determined and predicted hERG inhibition potential (IC₅₀) of the selected hits. This revealed predictive ability and robustness of our models and could help in correctly rank the potency order (lower μM to higher nM range) against hERG.

The Catch-22 of Predicting hERG Blockade Using Publicly Accessible Bioactivity Data

Drug-induced inhibition of the human ether-à-go-go-related gene (hERG)-encoded potassium ion channels can lead to fatal cardiotoxicity. Several marketed drugs and promising drug candidates were recalled because of this concern. Diverse modeling methods ranging from molecular similarity assessment to quantitative structure-activity relationship analysis employing machine learning techniques have been applied to data sets of varying size and composition (number of blockers and nonblockers). In this study, we highlight the challenges involved in the development of a robust classifier for predicting the hERG end point using bioactivity data extracted from the public domain. To this end, three different modeling methods, nearest neighbors, random forests, and support vector machines, were employed to develop predictive models using different molecular descriptors, activity thresholds, and training set compositions. Our models demonstrated superior performance in external validations in comparison with those reported in the previous studies from which the data sets were extracted. The choice of descriptors had little influence on the model performance, with minor exceptions. The criteria used to filter bioactivity data, the activity threshold settings used to separate blockers from nonblockers, and the structural diversity of blockers in training data set were found to be the crucial indicators of model performance. Training sets based on a binary threshold of 1 μM/10 μM to separate blockers (IC₅₀/ K_i ≤ 1 μM) from nonblockers (IC₅₀/ K_i > 10 μM) provided superior performance in comparison with those defined using a single threshold (1 μM or 10 μM). A major limitation in using the public domain hERG activity data is the abundance of blockers in comparison with nonblockers at usual activity thresholds, since not many studies report the latter.

Efficiency of different measures for defining the applicability domain of classification models

The goal of defining an applicability domain for a predictive classification model is to identify the region in chemical space where the model's predictions are reliable. The boundary of the applicability domain is defined with the help of a measure that shall reflect the reliability of an individual prediction. Here, the available measures are differentiated into those that flag unusual objects and which are independent of the original classifier and those that use information of the trained classifier. The former set of techniques is referred to as novelty detection while the latter is designated as confidence estimation. A review of the available confidence estimators shows that most of these measures estimate the probability of class membership of the predicted objects which is inversely related to the error probability. Thus, class probability estimates are natural candidates for defining the applicability domain but were not comprehensively included in previous benchmark studies. The focus of the present study is to find the best measure for defining the applicability domain for a given binary classification technique and to determine the performance of novelty detection versus confidence estimation. Six different binary classification techniques in combination with ten data sets were studied to benchmark the various measures. The area under the receiver operating characteristic curve (AUC ROC) was employed as main benchmark criterion. It is shown that class probability estimates constantly perform best to differentiate between reliable and unreliable predictions. Previously proposed alternatives to class probability estimates do not perform better than the latter and are inferior in most cases. Interestingly, the impact of defining an applicability domain depends on the observed area under the receiver operator characteristic curve. That means that it depends on the level of difficulty of the classification problem (expressed as AUC ROC) and will be largest for intermediately difficult problems (range AUC ROC 0.7-0.9). In the ranking of classifiers, classification random forests performed best on average. Hence, classification random forests in combination with the respective class probability estimate are a good starting point for predictive binary chemoinformatic classifiers with applicability domain. Graphical abstract .

3D-SDAR modeling of hERG potassium channel affinity: A case study in model design and toxicophore identification

A dataset of 237 human Ether-à-go-go Related Gene (hERG) potassium channel inhibitors (180 of which were used for model building and validation, whereas 57 constituted the "true" external prediction set) collected from 22 literature sources was modeled by 3D-SDAR. To produce reliable and reproducible classification models for hERG blocking, the initial set of 180 chemicals was split into two subsets: a balanced modeling set consisting of 118 compounds and an unbalanced validation set comprised of 62 compounds. A PLS bagging-like algorithm written in Matlab was used to process the data and assign each compound to one of the two (hERG+ or hERG-) activity classes. The best predictive model evaluated on the basis of a fully randomized hold-out test set (comprising 20% of the modeling set) used 4 latent variables and a grid of 6ppm×6ppm×1Å in the C-C region, 6ppm×30ppm×1Å in the C-N region, and 30ppm×30ppm×1Å in the N-N region. An overall accuracy of 0.84 was obtained for both the hold-out test set and the validation set. Further, an external prediction set consisting of 57 drugs and drug derivatives was used to estimate the true predictive power of the reported 3D-SDAR model - a slight reduction of the overall accuracy down to 0.77 was observed. 3D-SDAR map of the most frequently occurring bins and their projection on the standard coordinate space of the chemical structures allowed identification of a three-center toxicophore composed of two aromatic rings and an amino group. A U test along the distance axis of the most frequently occurring 3D-SDAR bins was used to set the distance limits of the toxicophore. This toxicophore was found to be similar to an earlier reported phospholipidosis (PLD) toxicophore.

Getting the most out of PubChem for virtual screening

INTRODUCTION

With the emergence of the 'big data' era, the biomedical research community has great interest in exploiting publicly available chemical information for drug discovery. PubChem is an example of public databases that provide a large amount of chemical information free of charge.

AREAS COVERED

This article provides an overview of how PubChem's data, tools, and services can be used for virtual screening and reviews recent publications that discuss important aspects of exploiting PubChem for drug discovery.

EXPERT OPINION

PubChem offers comprehensive chemical information useful for drug discovery. It also provides multiple programmatic access routes, which are essential to build automated virtual screening pipelines that exploit PubChem data. In addition, PubChemRDF allows users to download PubChem data and load them into a local computing facility, facilitating data integration between PubChem and other resources. PubChem resources have been used in many studies for developing bioactivity and toxicity prediction models, discovering polypharmacologic (multi-target) ligands, and identifying new macromolecule targets of compounds (for drug-repurposing or off-target side effect prediction). These studies demonstrate the usefulness of PubChem as a key resource for computer-aided drug discovery and related area.

Alarms about structural alerts

Structural alerts are widely accepted in chemical toxicology and regulatory decision support as a simple and transparent means to flag potential chemical hazards or group compounds into categories for read-across. However, there has been a growing concern that alerts disproportionally flag too many chemicals as toxic, which questions their reliability as toxicity markers. Conversely, the rigorously developed and properly validated statistical QSAR models can accurately and reliably predict the toxicity of a chemical; however, their use in regulatory toxicology has been hampered by the lack of transparency and interpretability. We demonstrate that contrary to the common perception of QSAR models as "black boxes" they can be used to identify statistically significant chemical substructures (QSAR-based alerts) that influence toxicity. We show through several case studies, however, that the mere presence of structural alerts in a chemical, irrespective of the derivation method (expert-based or QSAR-based), should be perceived only as hypotheses of possible toxicological effect. We propose a new approach that synergistically integrates structural alerts and rigorously validated QSAR models for a more transparent and accurate safety assessment of new chemicals.

ADMET Evaluation in Drug Discovery. 16. Predicting hERG Blockers by Combining Multiple Pharmacophores and Machine Learning Approaches

Blockade of human ether-à-go-go related gene (hERG) channel by compounds may lead to drug-induced QT prolongation, arrhythmia, and Torsades de Pointes (TdP), and therefore reliable prediction of hERG liability in the early stages of drug design is quite important to reduce the risk of cardiotoxicity-related attritions in the later development stages. In this study, pharmacophore modeling and machine learning approaches were combined to construct classification models to distinguish hERG active from inactive compounds based on a diverse data set. First, an optimal ensemble of pharmacophore hypotheses that had good capability to differentiate hERG active from inactive compounds was identified by the recursive partitioning (RP) approach. Then, the naive Bayesian classification (NBC) and support vector machine (SVM) approaches were employed to construct classification models by integrating multiple important pharmacophore hypotheses. The integrated classification models showed improved predictive capability over any single pharmacophore hypothesis, suggesting that the broad binding polyspecificity of hERG can only be well characterized by multiple pharmacophores. The best SVM model achieved the prediction accuracies of 84.7% for the training set and 82.1% for the external test set. Notably, the accuracies for the hERG blockers and nonblockers in the test set reached 83.6% and 78.2%, respectively. Analysis of significant pharmacophores helps to understand the multimechanisms of action of hERG blockers. We believe that the combination of pharmacophore modeling and SVM is a powerful strategy to develop reliable theoretical models for the prediction of potential hERG liability.

ChemProt-3.0: a global chemical biology diseases mapping

ChemProt is a publicly available compilation of chemical-protein-disease annotation resources that enables the study of systems pharmacology for a small molecule across multiple layers of complexity from molecular to clinical levels. In this third version, ChemProt has been updated to more than 1.7 million compounds with 7.8 million bioactivity measurements for 19 504 proteins. Here, we report the implementation of global pharmacological heatmap, supporting a user-friendly navigation of chemogenomics space. This facilitates the visualization and selection of chemicals that share similar structural properties. In addition, the user has the possibility to search by compound, target, pathway, disease and clinical effect. Genetic variations associated to target proteins were integrated, making it possible to plan pharmacogenetic studies and to suggest human response variability to drug. Finally, Quantitative Structure–Activity Relationship models for 850 proteins having sufficient data were implemented, enabling secondary pharmacological profiling predictions from molecular structure.

Database URL: http://potentia.cbs.dtu.dk/ChemProt/

A k-nearest neighbor classification of hERG K(+) channel blockers

A series of 172 molecular structures that block the hERG K⁺ channel were used to develop a classification model where, initially, eight types of PaDEL fingerprints were used for k-nearest neighbor model development. A consensus model constructed using Extended-CDK, PubChem and Substructure count fingerprint-based models was found to be a robust predictor of hERG activity. This consensus model demonstrated sensitivity and specificity values of 0.78 and 0.61 for the internal dataset compounds and 0.63 and 0.54 for the external (PubChem) dataset compounds, respectively. This model has identified the highest number of true positives (i.e. 140) from the PubChem dataset so far, as compared to other published models, and can potentially serve as a basis for the prediction of hERG active compounds. Validating this model against FDA-withdrawn substances indicated that it may even be useful for differentiating between mechanisms underlying QT prolongation.

In silico prediction of hERG potassium channel blockage by chemical category approaches

The human ether-a-go-go related gene (hERG) plays an important role in cardiac action potential. It encodes an ion channel protein named Kv11.1, which is related to long QT syndrome and may cause avoidable sudden cardiac death. Therefore, it is important to assess the hERG channel blockage of lead compounds in an early drug discovery process. In this study, we collected a large data set containing 1163 diverse compounds with IC₅₀ values determined by the patch clamp method on mammalian cell lines. The whole data set was divided into 80% as the training set and 20% as the test set. Then, five machine learning methods were applied to build a series of binary classification models based on 13 molecular descriptors, five fingerprints and molecular descriptors combining fingerprints at four IC₅₀ thresholds to discriminate hERG blockers from nonblockers, respectively. Models built by molecular descriptors combining fingerprints were validated by using an external validation set containing 407 compounds collected from the hERGCentral database. The performance indicated that the model built by molecular descriptors combining fingerprints yielded the best results and each threshold had its best suitable method, which means that hERG blockage assessment might depend on threshold values. Meanwhile, kNN and SVM methods were better than the others for model building. Furthermore, six privileged substructures were identified using information gain and frequency analysis methods, which could be regarded as structural alerts of cardiac toxicity mediated by hERG channel blockage.

Toward a unifying strategy for the structure-based prediction of toxicological endpoints

Most computational methods used for the prediction of toxicity endpoints are based on the assumption that similar compounds have similar biological properties. This principle can be exploited using computational methods like read across or quantitative structure-activity relationships. However, there is no general agreement about which method is the most appropriate for quantifying compound similarity neither for exploiting the similarity principle in order to obtain reliable estimations of the compound properties. Moreover, optimal similarity metrics and modeling methods might depend on the characteristics of the endpoints and training series used in each case. This study describes a comparative analysis of the predictive performance of diverse similarity metrics and modeling methods in toxicological applications. A collection of two quantitative (n = 660, n = 1114) and three qualitative (n = 447, n = 905, n = 1220) datasets representing very different endpoints of interest in drug safety evaluation and rigorous methods were used to estimate the external predictive ability in each case. The results confirm that no single approach produces the best results in all instances, and the best predictions were obtained using different tools in different situations. The trends observed in this study were exploited to propose a unifying strategy allowing the use of the most suitable method for every compound. A comparison of the quality of the predictions obtained by the unifying strategy with those obtained by standard prediction methods confirmed the usefulness of the proposed approach.

Computational investigations of hERG channel blockers: New insights and current predictive models

Identification of potential human Ether-a-go-go Related-Gene (hERG) potassium channel blockers is an essential part of the drug development and drug safety process in pharmaceutical industries or academic drug discovery centers, as they may lead to drug-induced QT prolongation, arrhythmia and Torsade de Pointes. Recent reports also suggest starting to address such issues at the hit selection stage. In order to prioritize molecules during the early drug discovery phase and to reduce the risk of drug attrition due to cardiotoxicity during pre-clinical and clinical stages, computational approaches have been developed to predict the potential hERG blockage of new drug candidates. In this review, we will describe the current in silico methods developed and applied to predict and to understand the mechanism of actions of hERG blockers, including ligand-based and structure-based approaches. We then discuss ongoing research on other ion channels and hERG polymorphism susceptible to be involved in LQTS and how systemic approaches can help in the drug safety decision.

Checking the STEP-Associated Trafficking and Internalization of Glutamate Receptors for Reduced Cognitive Deficits: A Machine Learning Approach-Based Cheminformatics Study and Its Application for Drug Repurposing

BACKGROUND

Alzheimer's disease, a lethal neurodegenerative disorder that leads to progressive memory loss, is the most common form of dementia. Owing to the complexity of the disease, its root cause still remains unclear. The existing anti-Alzheimer's drugs are unable to cure the disease while the current therapeutic options have provided only limited help in restoring moderate memory and remain ineffective at restricting the disease's progression. The striatal-enriched protein tyrosine phosphatase (STEP) has been shown to be involved in the internalization of the receptor, N-methyl D-aspartate (NMDR) and thus is associated with the disease. The present study was performed using machine learning algorithms, docking protocol and molecular dynamics (MD) simulations to develop STEP inhibitors, which could be novel anti-Alzheimer's molecules.

METHODS

The present study deals with the generation of computational predictive models based on chemical descriptors of compounds using machine learning approaches followed by substructure fragment analysis. To perform this analysis, the 2D molecular descriptors were generated and machine learning algorithms (Naïve Bayes, Random Forest and Sequential Minimization Optimization) were utilized. The binding mechanisms and the molecular interactions between the predicted active compounds and the target protein were modelled using docking methods. Further, the stability of the protein-ligand complex was evaluated using MD simulation studies. The substructure fragment analysis was performed using Substructure fingerprint (SubFp), which was further explored using a predefined dictionary.

RESULTS

The present study demonstrates that the computational methodology used can be employed to examine the biological activities of small molecules and prioritize them for experimental screening. Large unscreened chemical libraries can be screened to identify potential novel hits and accelerate the drug discovery process. Additionally, the chemical libraries can be searched for significant substructure patterns as reported in the present study, thus possibly contributing to the activity of these molecules.

In silico prediction of hERG inhibition

The voltage-gated potassium channel encoded by hERG carries a delayed rectifying potassium current (IKr) underlying repolarization of the cardiac action potential. Pharmacological blockade of the hERG channel results in slowed repolarization and therefore prolongation of action potential duration and an increase in the QT interval as measured on an electrocardiogram. Those are possible to cause sudden death, leading to the withdrawals of many drugs, which is the reason for hERG screening. Computational in silico prediction models provide a rapid, economic way to screen compounds during early drug discovery. In this review, hERG prediction models are classified as 2D and 3D quantitative structure–activity relationship models, pharmacophore models, classification models, and structure based models (using homology models of hERG).

Global analysis reveals families of chemical motifs enriched for HERG inhibitors

Promiscuous inhibition of the human ether-à-go-go-related gene (hERG) potassium channel by drugs poses a major risk for life threatening arrhythmia and costly drug withdrawals. Current knowledge of this phenomenon is derived from a limited number of known drugs and tool compounds. However, in a diverse, naïve chemical library, it remains unclear which and to what degree chemical motifs or scaffolds might be enriched for hERG inhibition. Here we report electrophysiology measurements of hERG inhibition and computational analyses of >300,000 diverse small molecules. We identify chemical ‘communities’ with high hERG liability, containing both canonical scaffolds and structurally distinctive molecules. These data enable the development of more effective classifiers to computationally assess hERG risk. The resultant predictive models now accurately classify naïve compound libraries for tendency of hERG inhibition. Together these results provide a more complete reference map of characteristic chemical motifs for hERG liability and advance a systematic approach to rank chemical collections for cardiotoxicity risk.

Novel Bayesian classification models for predicting compounds blocking hERG potassium channels

AIM

A large number of drug-induced long QT syndromes are ascribed to blockage of hERG potassium channels. The aim of this study was to construct novel computational models to predict compounds blocking hERG channels.

METHODS

Doddareddy's hERG blockage data containing 2644 compounds were used, which divided into training (2389) and test (255) sets. Laplacian-corrected Bayesian classification models were constructed using Discovery Studio. The models were internally validated with the training set of compounds, and then applied to the test set for validation. Doddareddy's experimentally validated dataset with 60 compounds was used for external test set validation.

RESULTS

A Bayesian classification model considering the effects of four molecular properties (Mw, PPSA, ALogP and pKa_basic) as well as extended-connectivity fingerprints (ECFP_14) exhibited a global accuracy (91%), parameter sensitivity (90%) and specificity (92%) in the test set validation, and a global accuracy (58%), parameter sensitivity (61%) and specificity (57%) in the external test set validation.

CONCLUSION

The novel model is better than those in the literatures for predicting compounds blocking hERG channels, and can be used for large-scale prediction.

Machine learning methods in chemoinformatics

Machine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion. Though particular machine learning methods are popular in chemoinformatics and quantitative structure-activity relationships (QSAR), many others exist in the technical literature. This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive. We concentrate on methods for supervised learning, predicting the unknown property values of a test set of instances, usually molecules, based on the known values for a training set. Particularly relevant approaches include Artificial Neural Networks, Random Forest, Support Vector Machine, k-Nearest Neighbors and naïve Bayes classifiers.

Integrated analysis of drug-induced gene expression profiles predicts novel hERG inhibitors

Growing evidence suggests that drugs interact with diverse molecular targets mediating both therapeutic and toxic effects. Prediction of these complex interactions from chemical structures alone remains challenging, as compounds with different structures may possess similar toxicity profiles. In contrast, predictions based on systems-level measurements of drug effect may reveal pharmacologic similarities not evident from structure or known therapeutic indications. Here we utilized drug-induced transcriptional responses in the Connectivity Map (CMap) to discover such similarities among diverse antagonists of the human ether-à-go-go related (hERG) potassium channel, a common target of promiscuous inhibition by small molecules. Analysis of transcriptional profiles generated in three independent cell lines revealed clusters enriched for hERG inhibitors annotated using a database of experimental measurements (hERGcentral) and clinical indications. As a validation, we experimentally identified novel hERG inhibitors among the unannotated drugs in these enriched clusters, suggesting transcriptional responses may serve as predictive surrogates of cardiotoxicity complementing existing functional assays.

Fast rule-based bioactivity prediction using associative classification mining

Relating chemical features to bioactivities is critical in molecular design and is used extensively in the lead discovery and optimization process. A variety of techniques from statistics, data mining and machine learning have been applied to this process. In this study, we utilize a collection of methods, called associative classification mining (ACM), which are popular in the data mining community, but so far have not been applied widely in cheminformatics. More specifically, classification based on predictive association rules (CPAR), classification based on multiple association rules (CMAR) and classification based on association rules (CBA) are employed on three datasets using various descriptor sets. Experimental evaluations on anti-tuberculosis (antiTB), mutagenicity and hERG (the human Ether-a-go-go-Related Gene) blocker datasets show that these three methods are computationally scalable and appropriate for high speed mining. Additionally, they provide comparable accuracy and efficiency to the commonly used Bayesian and support vector machines (SVM) methods, and produce highly interpretable models.

Towards in silico identification of the human ether-a-go-go-related gene channel blockers: discriminative vs. generative classification models

HERG potassium channels have a critical role in the normal electrical activity of the heart. The blockade of hERG channels in heart cells can result in a potentially fatal disorder called long QT syndrome. HERG channels can be blocked by compounds with diverse structures belonging to several drug classes. Presented herein are generative (Generative Topographic Maps) and discriminative (Support Vector Machines) classification models to categorize the compounds in silico into active and inactive classes by using different types of descriptors. The predictive performance of discriminative and generative classification models has been compared. Here, the possibility of using Generative Topographic Maps as an approach for applicability domain analysis and to generate probability-based descriptors was demonstrated to our knowledge for the first time. Comparison of obtained results with the models developed by other teams on the same data set has been performed.

QSAR modeling and data mining link Torsades de Pointes risk to the interplay of extent of metabolism, active transport, and HERG liability

We collected 1173 hERG patch clamp (PC) data (IC50) from the literature to derive twelve classification models for hERG inhibition, covering a large variety of chemical descriptors and classification algorithms. Models were generated using 545 molecules and validated through 258 external molecules tested in PC experiments. We also evaluated the suitability of the best models to predict the activity of 26 proprietary compounds tested in radioligand binding displacement (RBD). Results proved the necessity to use multiple validation sets for a true estimation of model accuracy and demonstrated that using various descriptors and algorithms improves the performance of ligand-based models. Intriguingly, one of the most accurate models uncovered an unexpected link between extent of metabolism and hERG liability. This hypothesis was fairly reinforced by using the Biopharmaceutics Drug Disposition Classification System (BDDCS) that recognized 94% of the hERG inhibitors as extensively metabolized in vivo. Data mining suggested that high Torsades de Pointes (TdP) risk results from an interplay of hERG inhibition, extent of metabolism, active transport, and possibly solubility. Overall, these new findings might improve both the decision making skills of pharmaceutical scientists to mitigate hERG liability during the drug discovery process and the TdP risk assessment during drug development.

hERG K+ Channels: Structure, Function, and Clinical Significance

The human ether-a-go-go related gene (hERG) encodes the pore-forming subunit of the rapid component of the delayed rectifier K+ channel, Kv11.1, which are expressed in the heart, various brain regions, smooth muscle cells, endocrine cells, and a wide range of tumor cell lines. However, it is the role that Kv11.1 channels play in the heart that has been best characterized, for two main reasons. First, it is the gene product involved in chromosome 7-associated long QT syndrome (LQTS), an inherited disorder associated with a markedly increased risk of ventricular arrhythmias and sudden cardiac death. Second, blockade of Kv11.1, by a wide range of prescription medications, causes drug-induced QT prolongation with an increase in risk of sudden cardiac arrest. In the first part of this review, the properties of Kv11.1 channels, including biogenesis, trafficking, gating, and pharmacology are discussed, while the second part focuses on the pathophysiology of Kv11.1 channels.

ADMET evaluation in drug discovery. 12. Development of binary classification models for prediction of hERG potassium channel blockage

Inhibition of the human ether-a-go-go related gene (hERG) potassium channel may result in QT interval prolongation, which causes severe cardiac side effects and is a major problem in clinical studies of drug candidates. The development of in silico tools to filter out potential hERG potassium channel blockers in early stages of the drug discovery process is of considerable interest. Here, a diverse set of 806 compounds with hERG inhibition data was assembled, and the binary hERG classification models using naive Bayesian classification and recursive partitioning (RP) techniques were established and evaluated. The naive Bayesian classifier based on molecular properties and the ECFP_8 fingerprints yielded 84.8% accuracy for the training set using the leave-one-out (LOO) cross-validation procedure and 85% accuracy for the test set of 120 molecules. For the two additional test sets, the model achieved 89.4% accuracy for the WOMBAT-PK test set, and 86.1% accuracy for the PubChem test set. The naive Bayesian classifiers gave better predictions than the RP classifiers. Moreover, the Bayesian classifier, employing molecular fingerprints, highlights the important structural fragments favorable or unfavorable for hERG potassium channel blockage, which offers extra valuable information for the design of compounds avoiding undesirable hERG activity.

Accessing, using, and creating chemical property databases for computational toxicology modeling

Toxicity data is expensive to generate, is increasingly seen as precompetitive, and is frequently used for the generation of computational models in a discipline known as computational toxicology. Repositories of chemical property data are valuable for supporting computational toxicologists by providing access to data regarding potential toxicity issues with compounds as well as for the purpose of building structure-toxicity relationships and associated prediction models. These relationships use mathematical, statistical, and modeling computational approaches and can be used to understand the mechanisms by which chemicals cause harm and, ultimately, enable prediction of adverse effects of these chemicals to human health and/or the environment. Such approaches are of value as they offer an opportunity to prioritize chemicals for testing. An increasing amount of data used by computational toxicologists is being published into the public domain and, in parallel, there is a greater availability of Open Source software for the generation of computational models. This chapter provides an overview of the types of data and software available and how these may be used to produce predictive toxicology models for the community.

A critical assessment of combined ligand- and structure-based approaches to HERG channel blocker modeling

Blockade of human ether-à-go-go related gene (hERG) channel prolongs the duration of the cardiac action potential and is a common reason for drug failure in preclinical safety trials. Therefore, it is of great importance to develop robust in silico tools to predict potential hERG blockers in the early stages of drug discovery and development. Herein we described comprehensive approaches to assess the discrimination of hERG-active and -inactive compounds by combining quantitative structure-activity relationship (QSAR) modeling, pharmacophore analysis, and molecular docking. Our consensus models demonstrated high-predictive capacity and improved enrichment and could correctly classify 91.8% of 147 hERG blockers from 351 inactives. To further enhance our modeling effort, hERG homology models were constructed, and molecular docking studies were conducted, resulting in high correlations (R² = 0.81) between predicted and experimental pIC₅₀s. We expect our unique models can be applied to efficient screening for hERG blockades, and our extensive understanding of the hERG-inhibitor interactions will facilitate the rational design of drugs devoid of hERG channel activity and hence with reduced cardiac toxicities.