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

Enhancing hERG Risk Assessment with Interpretable Classificatory and Regression Models

The human Ether-à-go-go-Related Gene (hERG) is a transmembrane protein that regulates cardiac action potential, and its inhibition can induce a potentially deadly cardiac syndrome. In vitro tests help identify hERG blockers at early stages; however, the high cost motivates searching for alternative, cost-effective methods. The primary goal of this study was to enhance the Pred-hERG tool for predicting hERG blockage. To achieve this, we developed new QSAR models that incorporated additional data, updated existing classificatory and multiclassificatory models, and introduced new regression models. Notably, we integrated SHAP (SHapley Additive exPlanations) values to offer a visual interpretation of these models. Utilizing the latest data from ChEMBL v30, encompassing over 14,364 compounds with hERG data, our binary and multiclassification models outperformed both the previous iteration of Pred-hERG and all publicly available models. Notably, the new version of our tool introduces a regression model for predicting hERG activity (pIC50). The optimal model demonstrated an R2 of 0.61 and an RMSE of 0.48, surpassing the only available regression model in the literature. Pred-hERG 5.0 now offers users a swift, reliable, and user-friendly platform for the early assessment of chemically induced cardiotoxicity through hERG blockage. The tool provides versatile outcomes, including (i) classificatory predictions of hERG blockage with prediction reliability, (ii) multiclassificatory predictions of hERG blockage with reliability, (iii) regression predictions with estimated pIC50 values, and (iv) probability maps illustrating the contribution of chemical fragments for each prediction. Furthermore, we implemented explainable AI analysis (XAI) to visualize SHAP values, providing insights into the contribution of each feature to binary classification predictions. A consensus prediction calculated based on the predictions of the three developed models is also present to assist the user's decision-making process. Pred-hERG 5.0 has been designed to be user-friendly, making it accessible to users without computational or programming expertise. The tool is freely available at http://predherg.labmol.com.br.

Role of Machine Learning and Artificial Intelligence in Arrhythmias and Electrophysiology

Machine learning (ML), a subset of artificial intelligence (AI) centered on machines learning from extensive datasets, stands at the forefront of a technological revolution shaping various facets of society. Cardiovascular medicine has emerged as a key domain for ML applications, with considerable efforts to integrate these innovations into routine clinical practice. Within cardiac electrophysiology, ML applications, especially in the automated interpretation of electrocardiograms, have garnered substantial attention in existing literature. However, less recognized are the diverse applications of ML in cardiac electrophysiology and arrhythmias, spanning basic science research on arrhythmia mechanisms, both experimental and computational, as well as contributions to enhanced techniques for mapping cardiac electrical function and translational research related to arrhythmia management. This comprehensive review delves into various ML applications within the scope of this journal, organized into 3 parts. The first section provides a fundamental understanding of general ML principles and methodologies, serving as a foundational resource for readers interested in exploring ML applications in arrhythmia research. The second part offers an in-depth review of studies in arrhythmia and electrophysiology that leverage ML methodologies, showcasing the broad potential of ML approaches. Each subject is thoroughly outlined, accompanied by a review of notable ML research advancements. Finally, the review delves into the primary challenges and future perspectives surrounding ML-driven cardiac electrophysiology and arrhythmias research.

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.

Can machine learning 'transform' peptides/peptidomimetics into small molecules? A case study with ghrelin receptor ligands

There has been considerable interest in transforming peptides into small molecules as peptide-based molecules often present poorer bioavailability and lower metabolic stability. Our studies looked into building machine learning (ML) models to investigate if ML is able to identify the 'bioactive' features of peptides and use the features to accurately discriminate between binding and non-binding small molecules. The ghrelin receptor (GR), a receptor that is implicated in various diseases, was used as an example to demonstrate whether ML models derived from a peptide library can be used to predict small molecule binders. ML models based on three different algorithms, namely random forest, support vector machine, and extreme gradient boosting, were built based on a carefully curated dataset of peptide/peptidomimetic and small molecule GR ligands. The results indicated that ML models trained with a dataset exclusively composed of peptides/peptidomimetics provide limited predictive power for small molecules, but that ML models trained with a diverse dataset composed of an array of both peptides/peptidomimetics and small molecules displayed exceptional results in terms of accuracy and false rates. The diversified models can accurately differentiate the binding small molecules from non-binding small molecules using an external validation set with new small molecules that we synthesized previously. Structural features that are the most critical contributors to binding activity were extracted and are remarkably consistent with the crystallography and mutagenesis studies.

In silico prediction of hERG blockers using machine learning and deep learning approaches

The human ether-à-go-go-related gene (hERG) is associated with drug cardiotoxicity. If the hERG channel is blocked, it will lead to prolonged QT interval and cause sudden death in severe cases. Therefore, it is important to evaluate the hERG-blocking property of compounds in early drug discovery. In this study, a dataset containing 4556 compounds with IC50 values determined by patch clamp techniques on mammalian lineage cells was collected, and hERG blockers and non-blockers were distinguished according to three single thresholds and two binary thresholds. Four machine learning (ML) algorithms combining four molecular fingerprints and molecular descriptors as well as graph convolutional neural networks (GCNs) were used to construct a series of binary classification models. The results showed that the best models varied for different thresholds. The ML models implemented by support vector machine and random forest performed well based on Morgan fingerprints and molecular descriptors, with AUCs ranging from 0.884 to 0.950. GCN showed superior prediction performance with AUCs above 0.952, which might be related to its direct extraction of molecular features from the original input. Meanwhile, the classification of binary threshold was better than that of single threshold, which could provide us with a more accurate prediction of hERG blockers. At last, the applicability domain for the model was defined, and seven structural alerts that might generate hERG blockage were identified by information gain and substructure frequency analysis. Our work would be beneficial for identifying hERG blockers in chemicals.

hERG agonists pose challenges to web-based machine learning methods for prediction of drug-hERG channel interaction

Pharmacological blockade of the IKr channel (hERG) by diverse drugs in clinical use is associated with the Long QT Syndrome that can lead to life threatening arrhythmia. Various computational tools including machine learning models (MLM) for the prediction of hERG inhibition have been developed to facilitate the throughput screening of drugs in development and optimise thus the prediction of hERG liabilities. The use of MLM relies on large libraries of training compounds for the quantitative structure-activity relationship (QSAR) modelling of hERG inhibition. The focus on inhibition omits potential effects of hERG channel agonist molecules and their associated QT shortening risk. It is instructive, therefore, to consider how known hERG agonists are handled by MLM. Here, two highly developed online computational tools for the prediction of hERG liability, Pred-hERG and HergSPred were probed for their ability to detect hERG activator drug molecules as hERG interactors. In total, 73 hERG blockers were tested with both computational tools giving overall good predictions for hERG blockers with reported IC50s below Pred-hERG and HergSPred cut-off threshold for hERG inhibition. However, for compounds with reported IC50s above this threshold such as disopyramide or sotalol discrepancies were observed. HergSPred identified all 20 hERG agonists selected as interacting with the hERG channel. Further studies are warranted to improve online MLM prediction of hERG related cardiotoxicity, by explicitly taking into account channel agonism as well as inhibition.

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.

Federated learning for molecular discovery

Federated Learning enables machine learning across multiple sources of data and alleviates the risk of leaking private information between partners thereby encouraging knowledge sharing and collaborative modelling. Hence, Federated Learning opens the ways to a new generation of improved models. Domains involving molecular informatics, like Drug Discovery, are progressively adopting Federated Learning; this review describes the main projects and applications of Federated Learning for molecular discovery with a special focus on their benefits and the remaining challenges. All the studies demonstrate a real benefit of Federated Learning, namely the improvement of the performance of models as well as their applicability domain thanks to knowledge aggregation. The selected publications also reveal several remaining challenges to be addressed to fully exploit Federated Learning.

Toward Quantitative Models in Safety Assessment: A Case Study to Show Impact of Dose-Response Inference on hERG Inhibition Models

Due to challenges with historical data and the diversity of assay formats, in silico models for safety-related endpoints are often based on discretized data instead of the data on a natural continuous scale. Models for discretized endpoints have limitations in usage and interpretation that can impact compound design. Here, we present a consistent data inference approach, exemplified on two data sets of Ether-à-go-go-Related Gene (hERG) K+ inhibition data, for dose-response and screening experiments that are generally applicable for in vitro assays. hERG inhibition has been associated with severe cardiac effects and is one of the more prominent safety targets assessed in drug development, using a wide array of in vitro and in silico screening methods. In this study, the IC₅₀ for hERG inhibition is estimated from diverse historical proprietary data. The IC₅₀ derived from a two-point proprietary screening data set demonstrated high correlation (R = 0.98, MAE = 0.08) with IC_50s derived from six-point dose-response curves. Similar IC₅₀ estimation accuracy was obtained on a public thallium flux assay data set (R = 0.90, MAE = 0.2). The IC₅₀ data were used to develop a robust quantitative model. The model's MAE (0.47) and R² (0.46) were on par with literature statistics and approached assay reproducibility. Using a continuous model has high value for pharmaceutical projects, as it enables rank ordering of compounds and evaluation of compounds against project-specific inhibition thresholds. This data inference approach can be widely applicable to assays with quantitative readouts and has the potential to impact experimental design and improve model performance, interpretation, and acceptance across many standard safety endpoints.

Physicochemical QSAR analysis of hERG inhibition revisited: towards a quantitative potency prediction

In an earlier study (Didziapetris R & Lanevskij K (2016). J Comput Aided Mol Des. 30:1175-1188) we collected a database of publicly available hERG inhibition data for almost 6700 drug-like molecules and built a probabilistic Gradient Boosting classifier with a minimal set of physicochemical descriptors (log P, pK_a, molecular size and topology parameters). This approach favored interpretability over statistical performance but still achieved an overall classification accuracy of 75%. In the current follow-up work we expanded the database (provided in Supplementary Information) to almost 9400 molecules and performed temporal validation of the model on a set of novel chemicals from recently published lead optimization projects. Validation results showed almost no performance degradation compared to the original study. Additionally, we rebuilt the model using AFT (Accelerated Failure Time) learning objective in XGBoost, which accepts both quantitative and censored data often reported in protein inhibition studies. The new model achieved a similar level of accuracy of discerning hERG blockers from non-blockers at 10 µM threshold, which can be conceived as close to the performance ceiling for methods aiming to describe only non-specific ligand interactions with hERG. Yet, this model outputs quantitative potency values (IC₅₀) and is not tied to a particular classification cut-off. pIC₅₀ from patch-clamp measurements can be predicted with R² ≈ 0.4 and MAE < 0.5, which enables ligand ranking according to their expected potency levels. The employed approach can be valuable for quantitative modeling of various ADME and drug safety endpoints with a high prevalence of censored data.

Prediction of drug-induced liver injury and cardiotoxicity using chemical structure and in vitro assay data

Drug-induced liver injury (DILI) and cardiotoxicity (DICT) are major adverse effects triggered by many clinically important drugs. To provide an alternative to in vivo toxicity testing, the U.S. Tox21 consortium has screened a collection of ∼10K compounds, including drugs in clinical use, against >70 cell-based assays in a quantitative high-throughput screening (qHTS) format. In this study, we compiled reference compound lists for DILI and DICT and compared the potential of Tox21 assay data with chemical structure information in building prediction models for human in vivo hepatotoxicity and cardiotoxicity. Models were built with four different machine learning algorithms (e.g., Random Forest, Naïve Bayes, eXtreme Gradient Boosting, and Support Vector Machine) and model performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC-ROC). Chemical structure-based models showed reasonable predictive power for DILI (best AUC-ROC = 0.75 ± 0.03) and DICT (best AUC-ROC = 0.83 ± 0.03), while Tox21 assay data alone only showed better than random performance. DILI and DICT prediction models built using a combination of assay data and chemical structure information did not have a positive impact on model performance. The suboptimal predictive performance of the assay data is likely due to insufficient coverage of an adequately predictive number of toxicity mechanisms. The Tox21 consortium is currently expanding coverage of biological response space with additional assays that probe toxicologically important targets and under-represented pathways that may improve the prediction of in vivo toxicity such as DILI and DICT.

Ligand-based prediction of hERG-mediated cardiotoxicity based on the integration of different machine learning techniques

Drug-induced cardiotoxicity is a common side effect of drugs in clinical use or under postmarket surveillance and is commonly due to off-target interactions with the cardiac human-ether-a-go-go-related (hERG) potassium channel. Therefore, prioritizing drug candidates based on their hERG blocking potential is a mandatory step in the early preclinical stage of a drug discovery program. Herein, we trained and properly validated 30 ligand-based classifiers of hERG-related cardiotoxicity based on 7,963 curated compounds extracted by the freely accessible repository ChEMBL (version 25). Different machine learning algorithms were tested, namely, random forest, K-nearest neighbors, gradient boosting, extreme gradient boosting, multilayer perceptron, and support vector machine. The application of 1) the best practices for data curation, 2) the feature selection method VSURF, and 3) the synthetic minority oversampling technique (SMOTE) to properly handle the unbalanced data, allowed for the development of highly predictive models (BAMAX = 0.91, AUCMAX = 0.95). Remarkably, the undertaken temporal validation approach not only supported the predictivity of the herein presented classifiers but also suggested their ability to outperform those models commonly used in the literature. From a more methodological point of view, the study put forward a new computational workflow, freely available in the GitHub repository (https://github.com/PDelre93/hERG-QSAR), as valuable for building highly predictive models of hERG-mediated cardiotoxicity.

hERG Blockade Prediction by Combining Site Identification by Ligand Competitive Saturation and Physicochemical Properties

Human ether-a-go-go-related gene (hERG) potassium channel is well-known contributor to drug-induced cardiotoxicity and therefore an extremely important target when performing safety assessments of drug candidates. Ligand-based approaches in connection with quantitative structure active relationships (QSAR) analyses have been developed to predict hERG toxicity. Availability of the recent published cryogenic electron microscopy (cryo-EM) structure for the hERG channel opened the prospect for using structure-based simulation and docking approaches for hERG drug liability predictions. In recent time, the idea of combining structure- and ligand-based approaches for modeling hERG drug liability has gained momentum offering improvements in predictability when compared to ligand-based QSAR practices alone. The present article demonstrates uniting the structure-based SILCS (site-identification by ligand competitive saturation) approach in conjunction with physicochemical properties to develop predictive models for hERG blockade. This combination leads to improved model predictability based on Pearson's R and percent correct (represents rank-ordering of ligands) metric for different validation sets of hERG blockers involving diverse chemical scaffold and wide range of pIC50 values. The inclusion of the SILCS structure-based approach allows determination of the hERG region to which compounds bind and the contribution of different chemical moieties in the compounds to blockade, thereby facilitating the rational ligand design to minimize hERG liability.

Simulation and Machine Learning Methods for Ion-Channel Structure Determination, Mechanistic Studies and Drug Design

Ion channels are expressed in almost all living cells, controlling the in-and-out communications, making them ideal drug targets, especially for central nervous system diseases. However, owing to their dynamic nature and the presence of a membrane environment, ion channels remain difficult targets for the past decades. Recent advancement in cryo-electron microscopy and computational methods has shed light on this issue. An explosion in high-resolution ion channel structures paved way for structure-based rational drug design and the state-of-the-art simulation and machine learning techniques dramatically improved the efficiency and effectiveness of computer-aided drug design. Here we present an overview of how simulation and machine learning-based methods fundamentally changed the ion channel-related drug design at different levels, as well as the emerging trends in the field.

High-Throughput Chemical Screening and Structure-Based Models to Predict hERG Inhibition

Simple Summary

Cardiovascular disease is the leading cause of death for people of most ethnicities in the United States. The human ether-a-go-go-related gene (hERG) potassium channel plays a pivotal role in cardiac rhythm regulation, and cardiotoxicity associated with hERG inhibition by drug molecules and environmental chemicals is a major public health concern. An evaluation of the effect of environmental chemicals on hERG channel function can help inform the potential public health risks of these compounds. To assess the cardiotoxic effect of diverse drugs and environmental compounds, the Tox21 federal research program has screened a collection of 9667 chemicals for inhibitory activity against the hERG channel. A set of molecular descriptors covering physicochemical and structural properties of chemicals, self-organizing maps, and hierarchical clustering were applied to characterize the chemicals inhibiting hERG. Machine learning approaches were applied to build robust statistical models that can predict the probability of any new chemical to cause cardiotoxicity via this mechanism.

Abstract

Chemical inhibition of the human ether-a -go-go-related gene (hERG) potassium channel leads to a prolonged QT interval that can contribute to severe cardiotoxicity. The adverse effects of hERG inhibition are one of the principal causes of drug attrition in clinical and pre-clinical development. Preliminary studies have demonstrated that a wide range of environmental chemicals and toxicants may also inhibit the hERG channel and contribute to the pathophysiology of cardiovascular (CV) diseases. As part of the US federal Tox21 program, the National Center for Advancing Translational Science (NCATS) applied a quantitative high throughput screening (qHTS) approach to screen the Tox21 library of 10,000 compounds (~7871 unique chemicals) at 14 concentrations in triplicate to identify chemicals perturbing hERG activity in the U2OS cell line thallium flux assay platform. The qHTS cell-based thallium influx assay provided a robust and reliable dataset to evaluate the ability of thousands of drugs and environmental chemicals to inhibit hERG channel protein, and the use of chemical structure-based clustering and chemotype enrichment analysis facilitated the identification of molecular features that are likely responsible for the observed hERG activity. We employed several machine-learning approaches to develop QSAR prediction models for the assessment of hERG liabilities for drug-like and environmental chemicals. The training set was compiled by integrating hERG bioactivity data from the ChEMBL database with the Tox21 qHTS thallium flux assay data. The best results were obtained with the random forest method (~92.6% balanced accuracy). The data and scripts used to generate hERG prediction models are provided in an open-access format as key in vitro and in silico tools that can be applied in a translational toxicology pipeline for drug development and environmental chemical screening.

Predicting hERG channel blockers with directed message passing neural networks

Compounds with human ether-à-go-go related gene (hERG) blockade activity may cause severe cardiotoxicity. Assessing the hERG liability in the early stages of the drug discovery process is important, and the in silico methods for predicting hERG channel blockers are actively pursued. In the present study, the directed message passing neural network (D-MPNN) was applied to construct classification models for identifying hERG blockers based on diverse datasets. Several descriptors and fingerprints were tested along with the D-MPNN model. Among all these combinations, D-MPNN with the moe206 descriptors generated from MOE (D-MPNN + moe206) showed significantly improved performances. The AUC-ROC values of the D-MPNN + moe206 model reached 0.956 ± 0.005 under random split and 0.922 ± 0.015 under scaffold split on Cai's hERG dataset, respectively. Moreover, the comparisons between our models and several recently reported machine learning models were made based on various datasets. Our results indicated that the D-MPNN + moe206 model is among the best classification models. Overall, the excellent performance of the DMPNN + moe206 model achieved in this study highlights its potential application in the discovery of novel and effective hERG blockers.

Compounds with human ether-à-go-go related gene (hERG) blockade activity may cause severe cardiotoxicity.

Structure-Based Prediction of hERG-Related Cardiotoxicity: A Benchmark Study

Drug-induced blockade of the human ether-à-go-go-related gene (hERG) channel is today considered the main cause of cardiotoxicity in postmarketing surveillance. Hence, several ligand-based approaches were developed in the last years and are currently employed in the early stages of a drug discovery process for in silico cardiac safety assessment of drug candidates. Herein, we present the first structure-based classifiers able to discern hERG binders from nonbinders. LASSO regularized support vector machines were applied to integrate docking scores and protein–ligand interaction fingerprints. A total of 396 models were trained and validated based on: (i) high-quality experimental bioactivity information returned by 8337 curated compounds extracted from ChEMBL (version 25) and (ii) structural predictor data. Molecular docking simulations were performed using GLIDE and GOLD software programs and four different hERG structural models, namely, the recently published structures obtained by cryoelectron microscopy (PDB codes: 5VA1 and 7CN1) and two published homology models selected for comparison. Interestingly, some classifiers return performances comparable to ligand-based models in terms of area under the ROC curve (AUC_MAX = 0.86 ± 0.01) and negative predictive values (NPV_MAX = 0.81 ± 0.01), thus putting forward the herein proposed computational workflow as a valuable tool for predicting hERG-related cardiotoxicity without the limitations of ligand-based models, typically affected by low interpretability and a limited applicability domain. From a methodological point of view, our study represents the first example of a successful integration of docking scores and protein–ligand interaction fingerprints (IFs) through a support vector machine (SVM) LASSO regularized strategy. Finally, the study highlights the importance of using hERG structural models accounting for ligand-induced fit effects and allowed us to select the best-performing protein conformation (made available in the Supporting Information, SI) to be employed for a reliable structure-based prediction of hERG-related cardiotoxicity.

Toward Reducing hERG Affinities for DAT Inhibitors with a Combined Machine Learning and Molecular Modeling Approach

Psychostimulant drugs, such as cocaine, inhibit dopamine reuptake via blockading the dopamine transporter (DAT), which is the primary mechanism underpinning their abuse. Atypical DAT inhibitors are dissimilar to cocaine and can block cocaine- or methamphetamine-induced behaviors, supporting their development as part of a treatment regimen for psychostimulant use disorders. When developing these atypical DAT inhibitors as medications, it is necessary to avoid off-target binding that can produce unwanted side effects or toxicities. In particular, the blockade of a potassium channel, human ether-a-go-go (hERG), can lead to potentially lethal ventricular tachycardia. In this study, we established a counter screening platform for DAT and against hERG binding by combining machine learning-based quantitative structure-activity relationship (QSAR) modeling, experimental validation, and molecular modeling and simulations. Our results show that the available data are adequate to establish robust QSAR models, as validated by chemical synthesis and pharmacological evaluation of a validation set of DAT inhibitors. Furthermore, the QSAR models based on subsets of the data according to experimental approaches used have predictive power as well, which opens the door to target specific functional states of a protein. Complementarily, our molecular modeling and simulations identified the structural elements responsible for a pair of DAT inhibitors having opposite binding affinity trends at DAT and hERG, which can be leveraged for rational optimization of lead atypical DAT inhibitors with desired pharmacological properties.

CardioTox net: a robust predictor for hERG channel blockade based on deep learning meta-feature ensembles

MOTIVATION

Ether-a-go-go-related gene (hERG) channel blockade by small molecules is a big concern during drug development in the pharmaceutical industry. Blockade of hERG channels may cause prolonged QT intervals that potentially could lead to cardiotoxicity. Various in-silico techniques including deep learning models are widely used to screen out small molecules with potential hERG related toxicity. Most of the published deep learning methods utilize a single type of features which might restrict their performance. Methods based on more than one type of features such as DeepHIT struggle with the aggregation of extracted information. DeepHIT shows better performance when evaluated against one or two accuracy metrics such as negative predictive value (NPV) and sensitivity (SEN) but struggle when evaluated against others such as Matthew correlation coefficient (MCC), accuracy (ACC), positive predictive value (PPV) and specificity (SPE). Therefore, there is a need for a method that can efficiently aggregate information gathered from models based on different chemical representations and boost hERG toxicity prediction over a range of performance metrics.

RESULTS

In this paper, we propose a deep learning framework based on step-wise training to predict hERG channel blocking activity of small molecules. Our approach utilizes five individual deep learning base models with their respective base features and a separate neural network to combine the outputs of the five base models. By using three external independent test sets with potency activity of IC50 at a threshold of 10 [Formula: see text]m, our method achieves better performance for a combination of classification metrics. We also investigate the effective aggregation of chemical information extracted for robust hERG activity prediction. In summary, CardioTox net can serve as a robust tool for screening small molecules for hERG channel blockade in drug discovery pipelines and performs better than previously reported methods on a range of classification metrics.

Machine learning models for classification tasks related to drug safety

In this review, we outline the current trends in the field of machine learning-driven classification studies related to ADME (absorption, distribution, metabolism and excretion) and toxicity endpoints from the past six years (2015-2021). The study focuses only on classification models with large datasets (i.e. more than a thousand compounds). A comprehensive literature search and meta-analysis was carried out for nine different targets: hERG-mediated cardiotoxicity, blood-brain barrier penetration, permeability glycoprotein (P-gp) substrate/inhibitor, cytochrome P450 enzyme family, acute oral toxicity, mutagenicity, carcinogenicity, respiratory toxicity and irritation/corrosion. The comparison of the best classification models was targeted to reveal the differences between machine learning algorithms and modeling types, endpoint-specific performances, dataset sizes and the different validation protocols. Based on the evaluation of the data, we can say that tree-based algorithms are (still) dominating the field, with consensus modeling being an increasing trend in drug safety predictions. Although one can already find classification models with great performances to hERG-mediated cardiotoxicity and the isoenzymes of the cytochrome P450 enzyme family, these targets are still central to ADMET-related research efforts.

Machine Learning in Arrhythmia and Electrophysiology

Machine learning (ML), a branch of artificial intelligence, where machines learn from big data, is at the crest of a technological wave of change sweeping society. Cardiovascular medicine is at the forefront of many ML applications, and there is a significant effort to bring them into mainstream clinical practice. In the field of cardiac electrophysiology, ML applications have also seen a rapid growth and popularity, particularly the use of ML in the automatic interpretation of ECGs, which has been extensively covered in the literature. Much lesser known are the other aspects of ML application in cardiac electrophysiology and arrhythmias, such as those in basic science research on arrhythmia mechanisms, both experimental and computational; in the development of better techniques for mapping of cardiac electrical function; and in translational research related to arrhythmia management. In the current review, we examine comprehensively such ML applications as they match the scope of this journal. The current review is organized in 3 parts. The first provides an overview of general ML principles and methodologies that will afford readers of the necessary information on the subject, serving as the foundation for inviting further ML applications in arrhythmia research. The basic information we provide can serve as a guide on how one might design and conduct an ML study. The second part is a review of arrhythmia and electrophysiology studies in which ML has been utilized, highlighting the broad potential of ML approaches. For each subject, we outline comprehensively the general topics, while reviewing some of the research advances utilizing ML under the subject. Finally, we discuss the main challenges and the perspectives for ML-driven cardiac electrophysiology and arrhythmia research.

Artificial Intelligence in Drug Discovery: A Comprehensive Review of Data-driven and Machine Learning Approaches

As expenditure on drug development increases exponentially, the overall drug discovery process requires a sustainable revolution. Since artificial intelligence (AI) is leading the fourth industrial revolution, AI can be considered as a viable solution for unstable drug research and development. Generally, AI is applied to fields with sufficient data such as computer vision and natural language processing, but there are many efforts to revolutionize the existing drug discovery process by applying AI. This review provides a comprehensive, organized summary of the recent research trends in AI-guided drug discovery process including target identification, hit identification, ADMET prediction, lead optimization, and drug repositioning. The main data sources in each field are also summarized in this review. In addition, an in-depth analysis of the remaining challenges and limitations will be provided, and proposals for promising future directions in each of the aforementioned areas.

Machine Learning in Predictive Toxicology: Recent Applications and Future Directions for Classification Models

In recent times, machine learning has become increasingly prominent in predictive toxicology as it has shifted from in vivo studies toward in silico studies. Currently, in vitro methods together with other computational methods such as quantitative structure-activity relationship modeling and absorption, distribution, metabolism, and excretion calculations are being used. An overview of machine learning and its applications in predictive toxicology is presented here, including support vector machines (SVMs), random forest (RF) and decision trees (DTs), neural networks, regression models, naïve Bayes, k-nearest neighbors, and ensemble learning. The recent successes of these machine learning methods in predictive toxicology are summarized, and a comparison of some models used in predictive toxicology is presented. In predictive toxicology, SVMs, RF, and DTs are the dominant machine learning methods due to the characteristics of the data available. Lastly, this review describes the current challenges facing the use of machine learning in predictive toxicology and offers insights into the possible areas of improvement in the field.

Critical Assessment of Artificial Intelligence Methods for Prediction of hERG Channel Inhibition in the "Big Data" Era

The rise of novel artificial intelligence (AI) methods necessitates their benchmarking against classical machine learning for a typical drug-discovery project. Inhibition of the potassium ion channel, whose alpha subunit is encoded by the human ether-à-go-go-related gene (hERG), leads to a prolonged QT interval of the cardiac action potential and is a significant safety pharmacology target for the development of new medicines. Several computational approaches have been employed to develop prediction models for the assessment of hERG liabilities of small molecules including recent work using deep learning methods. Here, we perform a comprehensive comparison of hERG effect prediction models based on classical approaches (random forests and gradient boosting) and modern AI methods [deep neural networks (DNNs) and recurrent neural networks (RNNs)]. The training set (∼9000 compounds) was compiled by integrating the hERG bioactivity data from the ChEMBL database with experimental data generated from an in-house, high-throughput thallium flux assay. We utilized different molecular descriptors including the latent descriptors, which are real-value continuous vectors derived from chemical autoencoders trained on a large chemical space (>1.5 million compounds). The models were prospectively validated on ∼840 in-house compounds screened in the same thallium flux assay. The best results were obtained with the XGBoost method and RDKit descriptors. The comparison of models based only on latent descriptors revealed that the DNNs performed significantly better than the classical methods. The RNNs that operate on SMILES provided the highest model sensitivity. The best models were merged into a consensus model that offered superior performance compared to reference models from academic and commercial domains. Furthermore, we shed light on the potential of AI methods to exploit the big data in chemistry and generate novel chemical representations useful in predictive modeling and tailoring a new chemical space.

hERG-Att: Self-attention-based deep neural network for predicting hERG blockers

A voltage-gated potassium channel encoded by the human ether-à-go-go-related gene (hERG) regulates cardiac action potential, and it is involved in cardiotoxicity with compounds that inhibit its activity. Therefore, the screening of hERG channel blockers is a mandatory step in the drug discovery process. The screening of hERG blockers by using conventional methods is inefficient in terms of cost and efforts. This has led to the development of many in silico hERG blocker prediction models. However, constructing a high-performance predictive model with interpretability on hERG blockage by certain compounds is a major obstacle. In this study, we developed the first, attention-based, interpretable model that predicts hERG blockers and captures important hERG-related compound substructures. To do that, we first collected various datasets, ranging from public databases to publicly available private datasets, to train and test the model. Then, we developed a precise and interpretable hERG blocker prediction model by using deep learning with a self-attention approach that has an appropriate molecular descriptor, Morgan fingerprint. The proposed prediction model was validated, and the validation result showed that the model was well-optimized and had high performance. The test set performance of the proposed model was significantly higher than that of previous fingerprint-based conventional machine learning models. In particular, the proposed model generally had high accuracy and F1 score thereby, representing the model's predictive reliability. Furthermore, we interpreted the calculated attention score vectors obtained from the proposed prediction model and demonstrated the important structural patterns that are represented in hERG blockers. In summary, we have proposed a powerful and interpretable hERG blocker prediction model that can reduce the overall cost of drug discovery by accurately screening for hERG blockers and suggesting hERG-related substructures.

Capsule Networks Showed Excellent Performance in the Classification of hERG Blockers/Nonblockers

Capsule networks (CapsNets), a new class of deep neural network architectures proposed recently by Hinton et al., have shown a great performance in many fields, particularly in image recognition and natural language processing. However, CapsNets have not yet been applied to drug discovery-related studies. As the first attempt, we in this investigation adopted CapsNets to develop classification models of hERG blockers/nonblockers; drugs with hERG blockade activity are thought to have a potential risk of cardiotoxicity. Two capsule network architectures were established: convolution-capsule network (Conv-CapsNet) and restricted Boltzmann machine-capsule networks (RBM-CapsNet), in which convolution and a restricted Boltzmann machine (RBM) were used as feature extractors, respectively. Two prediction models of hERG blockers/nonblockers were then developed by Conv-CapsNet and RBM-CapsNet with the Doddareddy's training set composed of 2,389 compounds. The established models showed excellent performance in an independent test set comprising 255 compounds, with prediction accuracies of 91.8 and 92.2% for Conv-CapsNet and RBM-CapsNet models, respectively. Various comparisons were also made between our models and those developed by other machine learning methods including deep belief network (DBN), convolutional neural network (CNN), multilayer perceptron (MLP), support vector machine (SVM), k-nearest neighbors (kNN), logistic regression (LR), and LightGBM, and with different training sets. All the results showed that the models by Conv-CapsNet and RBM-CapsNet are among the best classification models. Overall, the excellent performance of capsule networks achieved in this investigation highlights their potential in drug discovery-related studies.

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.

A combined drug discovery strategy based on machine learning and molecular docking

Data mining methods based on machine learning play an increasingly important role in drug design and discovery. In the current work, eight machine learning methods including decision trees, k-Nearest neighbor, support vector machines, random forests, extremely randomized trees, AdaBoost, gradient boosting trees, and XGBoost were evaluated comprehensively through a case study of ACC inhibitor data sets. Internal and external data sets were employed for cross-validation of the eight machine learning methods. Results showed that the extremely randomized trees model performed best and was adopted as the first step of virtual screening. Together with structure-based virtual screening in the second step, this combined strategy obtained desirable results. This work indicates that the combination of machine learning methods with traditional structure-based virtual screening can effectively strengthen the ability in finding potential hits from large compound database for a given target.

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.