Deep Learning-Based Prediction of Drug-Induced Cardiotoxicity

CardioDPi: An explainable deep-learning model for identifying cardiotoxic chemicals targeting hERG, Cav1.2, and Nav1.5 channels

The cardiotoxic effects of various pollutants have been a growing concern in environmental and material science. These effects encompass arrhythmias, myocardial injury, cardiac insufficiency, and pericardial inflammation. Compounds such as organic solvents and air pollutants disrupt the potassium, sodium, and calcium ion channels cardiac cell membranes, leading to the dysregulation of cardiac function. However, current cardiotoxicity models have disadvantages of incomplete data, ion channels, interpretability issues, and inability of toxic structure visualization. Herein, an interpretable deep-learning model known as CardioDPi was developed, which is capable of discriminating cardiotoxicity induced by the human Ether-à-go-go-related gene (hERG) channel, sodium channel (Na_v1.5), and calcium channel (Ca_v1.5) blockade. External validation yielded promising area under the ROC curve (AUC) values of 0.89, 0.89, and 0.94 for the hERG, Na_v1.5, and Ca_v1.5 channels, respectively. The CardioDPi can be freely accessed on the web server CardioDPipredictor (http://cardiodpi.sapredictor.cn/). Furthermore, the structural characteristics of cardiotoxic compounds were analyzed and structural alerts (SAs) can be extracted using the user-friendly CardioDPi-SAdetector web service (http://cardiosa.sapredictor.cn/). CardioDPi is a valuable tool for identifying cardiotoxic chemicals that are environmental and health risks. Moreover, the SA system provides essential insights for mode-of-action studies concerning cardiotoxic compounds.

MultiCBlo: Enhancing predictions of compound-induced inhibition of cardiac ion channels with advanced multimodal learning

Predicting compound-induced inhibition of cardiac ion channels is crucial and challenging, significantly impacting cardiac drug efficacy and safety assessments. Despite the development of various computational methods for compound-induced inhibition prediction in cardiac ion channels, their performance remains limited. Most methods struggle to fuse multi-source data, relying solely on specific dataset training, leading to poor accuracy and generalization. We introduce MultiCBlo, a model that fuses multimodal information through a progressive learning approach, designed to predict compound-induced inhibition of cardiac ion channels with high accuracy. MultiCBlo employs progressive multimodal information fusion technology to integrate the compound's SMILES sequence, graph structure, and fingerprint, enhancing its representation. This is the first application of progressive multimodal learning for predicting compound-induced inhibition of cardiac ion channels, to our knowledge. The objective of this study was to predict the compound-induced inhibition of three major cardiac ion channels: hERG, Cav1.2, and Nav1.5. The results indicate that MultiCBlo significantly outperforms current models in predicting compound-induced inhibition of cardiac ion channels. We hope that MultiCBlo will facilitate cardiac drug development and reduce compound toxicity risks. Code and data are accessible at: https://github.com/taowang11/MultiCBlo. The online prediction platform is freely accessible at: https://huggingface.co/spaces/wtttt/PCICB.

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

BACKGROUND

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

STUDY DESIGN AND METHOD

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

RESULTS

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

CONCLUSIONS

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

Two-Dimensional Deep Learning Frameworks for Drug-Induced Cardiotoxicity Detection

The identification of drug-induced cardiotoxicity remains a pressing challenge with far-reaching clinical and economic ramifications, often leading to patient harm and resource-intensive drug recalls. Current methodologies, including in vivo and in vitro models, have severe limitations in accurate identification of cardiotoxic substances. Pioneering a paradigm shift from these conventional techniques, our study presents two deep learning-based frameworks, STFT-CNN and SST-CNN, to assess cardiotoxicity with markedly improved accuracy and reliability. Leveraging the power of induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) as a more human-relevant cell model, we record mechanical beating signals through impedance measurements. These temporal signals were converted into enriched two-dimensional representations through advanced transformation techniques, specifically short-time Fourier transform (STFT) and synchro-squeezing transform (SST). These transformed data are fed into the proposed frameworks for comprehensive analysis, including drug type classification, concentration classification, cardiotoxicity classification, and new drug identification. Compared to traditional models like recurrent neural network (RNN) and 1-dimensional convolutional neural network (1D-CNN), SST-CNN delivered an impressive test accuracy of 98.55% in drug type classification and 99% in distinguishing cardiotoxic and noncardiotoxic drugs. Its feasibility is further highlighted with a stellar 98.5% average accuracy for classification of various concentrations, and the superiority of our proposed frameworks underscores their promise in revolutionizing drug safety assessments. With a potential for scalability, they represent a major leap in drug safety assessments, offering a pathway to more robust, efficient, and human-relevant cardiotoxicity evaluations.

Advancing Drug Safety in Drug Development: Bridging Computational Predictions for Enhanced Toxicity Prediction

The attrition rate of drugs in clinical trials is generally quite high, with estimates suggesting that approximately 90% of drugs fail to make it through the process. The identification of unexpected toxicity issues during preclinical stages is a significant factor contributing to this high rate of failure. These issues can have a major impact on the success of a drug and must be carefully considered throughout the development process. These late-stage rejections or withdrawals of drug candidates significantly increase the costs associated with drug development, particularly when toxicity is detected during clinical trials or after market release. Understanding drug-biological target interactions is essential for evaluating compound toxicity and safety, as well as predicting therapeutic effects and potential off-target effects that could lead to toxicity. This will enable scientists to predict and assess the safety profiles of drug candidates more accurately. Evaluation of toxicity and safety is a critical aspect of drug development, and biomolecules, particularly proteins, play vital roles in complex biological networks and often serve as targets for various chemicals. Therefore, a better understanding of these interactions is crucial for the advancement of drug development. The development of computational methods for evaluating protein-ligand interactions and predicting toxicity is emerging as a promising approach that adheres to the 3Rs principles (replace, reduce, and refine) and has garnered significant attention in recent years. In this review, we present a thorough examination of the latest breakthroughs in drug toxicity prediction, highlighting the significance of drug-target binding affinity in anticipating and mitigating possible adverse effects. In doing so, we aim to contribute to the development of more effective and secure drugs.

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.

Expanding Predictive Capacities in Toxicology: Insights from Hackathon-Enhanced Data and Model Aggregation

In the realm of predictive toxicology for small molecules, the applicability domain of QSAR models is often limited by the coverage of the chemical space in the training set. Consequently, classical models fail to provide reliable predictions for wide classes of molecules. However, the emergence of innovative data collection methods such as intensive hackathons have promise to quickly expand the available chemical space for model construction. Combined with algorithmic refinement methods, these tools can address the challenges of toxicity prediction, enhancing both the robustness and applicability of the corresponding models. This study aimed to investigate the roles of gradient boosting and strategic data aggregation in enhancing the predictivity ability of models for the toxicity of small organic molecules. We focused on evaluating the impact of incorporating fragment features and expanding the chemical space, facilitated by a comprehensive dataset procured in an open hackathon. We used gradient boosting techniques, accounting for critical features such as the structural fragments or functional groups often associated with manifestations of toxicity.

Benchmarking of Small Molecule Feature Representations for hERG, Nav1.5, and Cav1.2 Cardiotoxicity Prediction

In the field of drug discovery, there is a substantial challenge in seeking out chemical structures that possess desirable pharmacological, toxicological, and pharmacokinetic properties. Complications arise when drugs interfere with the functioning of cardiac ion channels, leading to serious cardiovascular consequences. The discontinuation and removal of numerous approved drugs from the market or at late development stages in the pipeline due to such inhibitory effects further highlight the urgency of addressing this issue. Consequently, the early prediction of potential blockers targeting cardiac ion channels during the drug discovery process is of paramount importance. This study introduces a deep learning framework that computationally determines the cardiotoxicity associated with the voltage-gated potassium channel (hERG), the voltage-gated calcium channel (Cav1.2), and the voltage-gated sodium channel (Nav1.5) for drug candidates. The predictive capabilities of three feature representations─molecular fingerprints, descriptors, and graph-based numerical representations─are rigorously benchmarked. Additionally, a novel training and evaluation data set framework is presented, enabling predictive model training of drug off-target cardiotoxicity using a comprehensive and large curated data set covering these three cardiac ion channels. To facilitate these predictions, a robust and comprehensive small molecule cardiotoxicity prediction tool named CToxPred has been developed. It is made available as open source under the permissive MIT license at https://github.com/issararab/CToxPred.

Enhancing property and activity prediction and interpretation using multiple molecular graph representations with MMGX

Graph Neural Networks (GNNs) excel in compound property and activity prediction, but the choice of molecular graph representations significantly influences model learning and interpretation. While atom-level molecular graphs resemble natural topology, they overlook key substructures or functional groups and their interpretation partially aligns with chemical intuition. Recent research suggests alternative representations using reduced molecular graphs to integrate higher-level chemical information and leverages both representations for model. However, there is a lack of studies about applicability and impact of different molecular graphs on model learning and interpretation. Here, we introduce MMGX (Multiple Molecular Graph eXplainable discovery), investigating the effects of multiple molecular graphs, including Atom, Pharmacophore, JunctionTree, and FunctionalGroup, on model learning and interpretation with various perspectives. Our findings indicate that multiple graphs relatively improve model performance, but in varying degrees depending on datasets. Interpretation from multiple graphs in different views provides more comprehensive features and potential substructures consistent with background knowledge. These results help to understand model decisions and offer valuable insights for subsequent tasks. The concept of multiple molecular graph representations and diverse interpretation perspectives has broad applicability across tasks, architectures, and explanation techniques, enhancing model learning and interpretation for relevant applications in drug discovery.

Predicting Cardiotoxicity of Molecules Using Attention-Based Graph Neural Networks

In drug discovery, the search for new and effective medications is often hindered by concerns about toxicity. Numerous promising molecules fail to pass the later phases of drug development due to strict toxicity assessments. This challenge significantly increases the cost, time, and human effort needed to discover new therapeutic molecules. Additionally, a considerable number of drugs already on the market have been withdrawn or re-evaluated because of their unwanted side effects. Among the various types of toxicity, drug-induced heart damage is a severe adverse effect commonly associated with several medications, especially those used in cancer treatments. Although a number of computational approaches have been proposed to identify the cardiotoxicity of molecules, the performance and interpretability of the existing approaches are limited. In our study, we proposed a more effective computational framework to predict the cardiotoxicity of molecules using an attention-based graph neural network. Experimental results indicated that the proposed framework outperformed the other methods. The stability of the model was also confirmed by our experiments. To assist researchers in evaluating the cardiotoxicity of molecules, we have developed an easy-to-use online web server that incorporates our model.

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.

Derivation of Highly Predictive 3D-QSAR Models for hERG Channel Blockers Based on the Quantum Artificial Neural Network Algorithm

The hERG potassium channel serves as an annexed target for drug discovery because the associated off-target inhibitory activity may cause serious cardiotoxicity. Quantitative structure-activity relationship (QSAR) models were developed to predict inhibitory activities against the hERG potassium channel, utilizing the three-dimensional (3D) distribution of quantum mechanical electrostatic potential (ESP) as the molecular descriptor. To prepare the optimal atomic coordinates of dataset molecules, pairwise 3D structural alignments were carried out in order for the quantum mechanical cross correlation between the template and other molecules to be maximized. This alignment method stands out from the common atom-by-atom matching technique, as it can handle structurally diverse molecules as effectively as chemical derivatives that share an identical scaffold. The alignment problem prevalent in 3D-QSAR methods was ameliorated substantially by dividing the dataset molecules into seven subsets, each of which contained molecules with similar molecular weights. Using an artificial neural network algorithm to find the functional relationship between the quantum mechanical ESP descriptors and the experimental hERG inhibitory activities, highly predictive 3D-QSAR models were derived for all seven molecular subsets to the extent that the squared correlation coefficients exceeded 0.79. Given their simplicity in model development and strong predictability, the 3D-QSAR models developed in this study are expected to function as an effective virtual screening tool for assessing the potential cardiotoxicity of drug candidate molecules.

Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery

Artificial intelligence (AI) has permeated various sectors, including the pharmaceutical industry and research, where it has been utilized to efficiently identify new chemical entities with desirable properties. The application of AI algorithms to drug discovery presents both remarkable opportunities and challenges. This review article focuses on the transformative role of AI in medicinal chemistry. We delve into the applications of machine learning and deep learning techniques in drug screening and design, discussing their potential to expedite the early drug discovery process. In particular, we provide a comprehensive overview of the use of AI algorithms in predicting protein structures, drug-target interactions, and molecular properties such as drug toxicity. While AI has accelerated the drug discovery process, data quality issues and technological constraints remain challenges. Nonetheless, new relationships and methods have been unveiled, demonstrating AI's expanding potential in predicting and understanding drug interactions and properties. For its full potential to be realized, interdisciplinary collaboration is essential. This review underscores AI's growing influence on the future trajectory of medicinal chemistry and stresses the importance of ongoing synergies between computational and domain experts.

Bio-activity prediction of drug candidate compounds targeting SARS-Cov-2 using machine learning approaches

The SARS-CoV-2 3CLpro protein is one of the key therapeutic targets of interest for COVID-19 due to its critical role in viral replication, various high-quality protein crystal structures, and as a basis for computationally screening for compounds with improved inhibitory activity, bioavailability, and ADMETox properties. The ChEMBL and PubChem database contains experimental data from screening small molecules against SARS-CoV-2 3CLpro, which expands the opportunity to learn the pattern and design a computational model that can predict the potency of any drug compound against coronavirus before in-vitro and in-vivo testing. In this study, Utilizing several descriptors, we evaluated 27 machine learning classifiers. We also developed a neural network model that can correctly identify bioactive and inactive chemicals with 91% accuracy, on CheMBL data and 93% accuracy on combined data on both CheMBL and Pubchem. The F1-score for inactive and active compounds was 93% and 94%, respectively. SHAP (SHapley Additive exPlanations) on XGB classifier to find important fingerprints from the PaDEL descriptors for this task. The results indicated that the PaDEL descriptors were effective in predicting bioactivity, the proposed neural network design was efficient, and the Explanatory factor through SHAP correctly identified the important fingertips. In addition, we validated the effectiveness of our proposed model using a large dataset encompassing over 100,000 molecules. This research employed various molecular descriptors to discover the optimal one for this task. To evaluate the effectiveness of these possible medications against SARS-CoV-2, more in-vitro and in-vivo research is required.

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.

hERG-toxicity prediction using traditional machine learning and advanced deep learning techniques

The rise of artificial intelligence (AI) based algorithms has gained a lot of interest in the pharmaceutical development field. Our study demonstrates utilization of traditional machine learning techniques such as random forest (RF), support-vector machine (SVM), extreme gradient boosting (XGBoost), deep neural network (DNN) as well as advanced deep learning techniques like gated recurrent unit-based DNN (GRU-DNN) and graph neural network (GNN), towards predicting human ether-á-go-go related gene (hERG) derived toxicity. Using the largest hERG dataset derived to date, we have utilized 203,853 and 87,366 compounds for training and testing the models, respectively. The results show that GNN, SVM, XGBoost, DNN, RF, and GRU-DNN all performed well, with validation set AUC ROC scores equals 0.96, 0.95, 0.95, 0.94, 0.94 and 0.94, respectively. The GNN was found to be the top performing model based on predictive power and generalizability. The GNN technique is free of any feature engineering steps while having a minimal human intervention. The GNN approach may serve as a basis for comprehensive automation in predictive toxicology. We believe that the models presented here may serve as a promising tool, both for academic institutes as well as pharmaceutical industries, in predicting hERG-liability in new molecular structures.

Prospective Validation of Machine Learning Algorithms for Absorption, Distribution, Metabolism, and Excretion Prediction: An Industrial Perspective

Absorption, distribution, metabolism, and excretion (ADME), which collectively define the concentration profile of a drug at the site of action, are of critical importance to the success of a drug candidate. Recent advances in machine learning algorithms and the availability of larger proprietary as well as public ADME data sets have generated renewed interest within the academic and pharmaceutical science communities in predicting pharmacokinetic and physicochemical endpoints in early drug discovery. In this study, we collected 120 internal prospective data sets over 20 months across six ADME in vitro endpoints: human and rat liver microsomal stability, MDR1-MDCK efflux ratio, solubility, and human and rat plasma protein binding. A variety of machine learning algorithms in combination with different molecular representations were evaluated. Our results suggest that gradient boosting decision tree and deep learning models consistently outperformed random forest over time. We also observed better performance when models were retrained on a fixed schedule, and the more frequent retraining generally resulted in increased accuracy, while hyperparameters tuning only improved the prospective predictions marginally.

Hydroxychloroquine Attenuates hERG Channel by Promoting the Membrane Channel Degradation: Computational Simulation and Experimental Evidence for QT-Interval Prolongation with Hydroxychloroquine Treatment

INTRODUCTION

The coronavirus disease 2019 (COVID-19) pandemic has led to millions of confirmed cases and deaths worldwide and has no approved therapy. Currently, more than 700 drugs are tested in the COVID-19 clinical trials, and full evaluation of their cardiotoxicity risks is in high demand.

METHODS

We mainly focused on hydroxychloroquine (HCQ), one of the most concerned drugs for COVID-19 therapy, and investigated the effects and underlying mechanisms of HCQ on hERG channel via molecular docking simulations. We further applied the HEK293 cell line stably expressing hERG-wild-type channel (hERG-HEK) and HEK293 cells transiently expressing hERG-p.Y652A or hERG-p.F656A mutants to validate our predictions. Western blot analysis was used to determine the hERG channel, and the whole-cell patch clamp was utilized to record hERG current (IhERG).

RESULTS

HCQ reduced the mature hERG protein in a time- and concentration-dependent manner. Correspondingly, chronic and acute treatment of HCQ decreased the hERG current. Treatment with brefeldin A (BFA) and HCQ combination reduced hERG protein to a greater extent than BFA alone. Moreover, disruption of the typical hERG binding site (hERG-p.Y652A or hERG-p.F656A) rescued HCQ-mediated hERG protein and IhERG reduction.

CONCLUSION

HCQ can reduce the mature hERG channel expression and IhERG via enhancing channel degradation. The QT prolongation effect of HCQ is mediated by typical hERG binding sites involving residues Tyr652 and Phe656.

On QSAR-based cardiotoxicity modeling with the expressiveness-enhanced graph learning model and dual-threshold scheme

Introduction: Given the direct association with malignant ventricular arrhythmias, cardiotoxicity is a major concern in drug design. In the past decades, computational models based on the quantitative structure-activity relationship have been proposed to screen out cardiotoxic compounds and have shown promising results. The combination of molecular fingerprint and the machine learning model shows stable performance for a wide spectrum of problems; however, not long after the advent of the graph neural network (GNN) deep learning model and its variant (e.g., graph transformer), it has become the principal way of quantitative structure-activity relationship-based modeling for its high flexibility in feature extraction and decision rule generation. Despite all these progresses, the expressiveness (the ability of a program to identify non-isomorphic graph structures) of the GNN model is bounded by the WL isomorphism test, and a suitable thresholding scheme that relates directly to the sensitivity and credibility of a model is still an open question. Methods: In this research, we further improved the expressiveness of the GNN model by introducing the substructure-aware bias by the graph subgraph transformer network model. Moreover, to propose the most appropriate thresholding scheme, a comprehensive comparison of the thresholding schemes was conducted. Results: Based on these improvements, the best model attains performance with 90.4% precision, 90.4% recall, and 90.5% F1-score with a dual-threshold scheme (active: < 1 μ M ; non-active: > 30 μ M ). The improved pipeline (graph subgraph transformer network model and thresholding scheme) also shows its advantages in terms of the activity cliff problem and model interpretability.

Structural analysis of hERG channel blockers and the implications for drug design

The repolarizing current (I_kr) produced by the hERG potassium channel forms a major component of the cardiac action potential and blocking this current by small molecule drugs can lead to life-threatening cardiotoxicity. Understanding the mechanisms of drug-mediated hERG inhibition is essential to develop a second generation of safe drugs, with minimal cardiotoxic effects. Although various computational tools and drug design guidelines have been developed to avoid binding of drugs to the hERG pore domain, there are many other aspects that are still open for investigation. This includes the use computational modelling to study the implications of hERG mutations on hERG structure and trafficking, the interactions of hERG with hERG chaperone proteins and with membrane-soluble molecules, the mechanisms of drugs that inhibit hERG trafficking and drugs that rescue hERG mutations. The plethora of available experimental data regarding all these aspects can guide the construction of much needed robust computational structural models to study these mechanisms for the rational design of safe drugs.

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.

Unraveling Structural Alerts in Marketed Drugs for Improving Adverse Outcome Pathway Framework of Drug-Induced QT Prolongation

In pharmaceutical treatment, many non-cardiac drugs carry the risk of prolonging the QT interval, which can lead to fatal cardiac complications such as torsades de points (TdP). Although the unexpected blockade of ion channels has been widely considered to be one of the main reasons for affecting the repolarization phase of the cardiac action potential and leading to QT interval prolongation, the lack of knowledge regarding chemical structures in drugs that may induce the prolongation of the QT interval remains a barrier to further understanding the underlying mechanism and developing an effective prediction strategy. In this study, we thoroughly investigated the differences in chemical structures between QT-prolonging drugs and drugs with no drug-induced QT prolongation (DIQT) concerns, based on the Drug-Induced QT Prolongation Atlas (DIQTA) dataset. Three categories of structural alerts (SAs), namely amines, ethers, and aromatic compounds, appeared in large quantities in QT-prolonging drugs, but rarely in drugs with no DIQT concerns, indicating a close association between SAs and the risk of DIQT. Moreover, using the molecular descriptors associated with these three categories of SAs as features, the structure–activity relationship (SAR) model for predicting the high risk of inducing QT interval prolongation of marketed drugs achieved recall rates of 72.5% and 80.0% for the DIQTA dataset and the FDA Adverse Event Reporting System (FAERS) dataset, respectively. Our findings may promote a better understanding of the mechanism of DIQT and facilitate research on cardiac adverse drug reactions in drug development.

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.

Application of machine learning to improve the efficiency of electrophysiological simulations used for the prediction of drug-induced ventricular arrhythmia

BACKGROUND AND OBJECTIVE

In silico prediction of drug-induced ventricular arrhythmia often requires computationally intensive simulations, making its application tedious and non-interactive. This inconvenience can be mitigated using matrices of precomputed simulation results, allowing instantaneous computation of biomarkers such as action potential duration at 90% of the repolarisation (APD₉₀). However, preparing such matrices can be computationally intensive for the method developers, limiting the range of simulated conditions. In this work, we aim to optimise the generation of these matrices so that they can be obtained with less effort and for a broader range of input values.

METHODS

Machine learning methods were applied, building models trained with only a small fraction of the originally simulated results. The predictive performances of the models were assessed by comparing their predicted values with the actual simulation results, using percentual mean absolute error and mean relative error, as well as the percentage of data with a relative error below 5%.

RESULTS

Our method obtained highly accurate estimations of the original values, leading to a nearly one hundred-fold decrease in computation time. This method also allows precomputing more complex matrices, describing the effect of more ion channels on the APD_90. The best results were obtained by applying Support Vector Machine models, which yielded errors below 1% in most cases. This approach was further validated by predicting the APD₉₀ of a set of 12 CiPA compounds and exporting the optimal settings for predicting APD₉₀ using a different set of ion channels, always with satisfactory results.

CONCLUSIONS

The proposed method effectively reduces the computational effort required to generate matrices of precomputed electrophysiological simulation values. The same approach can be applied in other fields where computationally costly simulations are applied repeatedly using slightly different input values.

A biosensing system employing nonlinear dynamic analysis-assisted neural network for drug-induced cardiotoxicity assessment

Preclinical investigation of drug-induced cardiotoxicity is of importance for drug development. To evaluate such cardiotoxicity, in vitro high-throughput interdigitated electrode-based recording of cardiomyocytes mechanical beating is widely used. To automatically analyze the features from the beating signals for drug-induced cardiotoxicity assessment, artificial neural network analysis is conventionally employed and signals are segmented into cycles and feature points are located in the cycles. However, signal segmentation and location of feature points for different signal shapes require design of specific algorithms. Consequently, this may lower the efficiency of research and the applications of such algorithms in signals with different morphologies are limited. Here, we present a biosensing system that employs nonlinear dynamic analysis-assisted neural network (NDANN) to avoid the signal segmentation process and directly extract features from beating signal time series. By processing beating time series with fixed time duration to avoid the signal segmentation process, this NDANN-based biosensing system can identify drug-induced cardiotoxicity with accuracy over 0.99. The individual drugs were classified with high accuracies over 0.94 and drug-induced cardiotoxicity levels were accurately predicted. We also evaluated the generalization performance of the NDANN-based biosensing system in assessing drug-induced cardiotoxicity through an independent dataset. This system achieved accuracy of 0.85-0.95 for different drug concentrations in identification of drug-induced cardiotoxicity. This result demonstrates that our NDANN-based biosensing system has the capacity of screening newly developed drugs, which is crucial in practical applications. This NDANN-based biosensing system can work as a new screening platform for drug-induced cardiotoxicity and improve the efficiency of bio-signal processing.

Investigating cardiotoxicity related with hERG channel blockers using molecular fingerprints and graph attention mechanism

Human ether-a-go-go-related gene (hERG) channel blockade by small molecules is a big concern during drug development in the pharmaceutical industry. Failure or inhibition of hERG channel activity caused by drug molecules can lead to prolonging QT interval, which will result in serious cardiotoxicity. Thus, evaluating the hERG blocking activity of all these small molecular compounds is technically challenging, and the relevant procedures are expensive and time-consuming. In this study, we develop a novel deep learning predictive model named DMFGAM for predicting hERG blockers. In order to characterize the molecule more comprehensively, we first consider the fusion of multiple molecular fingerprint features to characterize its final molecular fingerprint features. Then, we use the multi-head attention mechanism to extract the molecular graph features. Both molecular fingerprint features and molecular graph features are fused as the final features of the compounds to make the feature expression of compounds more comprehensive. Finally, the molecules are classified into hERG blockers or hERG non-blockers through the fully connected neural network. We conduct 5-fold cross-validation experiment to evaluate the performance of DMFGAM, and verify the robustness of DMFGAM on external validation datasets. We believe DMFGAM can serve as a powerful tool to predict hERG channel blockers in the early stages of drug discovery and development.

Virtual screening of DrugBank database for hERG blockers using topological Laplacian-assisted AI models

The human ether-a-go-go (hERG) potassium channel (Kv11.1) plays a critical role in mediating cardiac action potential. The blockade of this ion channel can potentially lead fatal disorder and/or long QT syndrome. Many drugs have been withdrawn because of their serious hERG-cardiotoxicity. It is crucial to assess the hERG blockade activity in the early stage of drug discovery. We are particularly interested in the hERG-cardiotoxicity of compounds collected in the DrugBank database considering that many DrugBank compounds have been approved for therapeutic treatments or have high potential to become drugs. Machine learning-based in silico tools offer a rapid and economical platform to virtually screen DrugBank compounds. We design accurate and robust classifiers for blockers/non-blockers and then build regressors to quantitatively analyze the binding potency of the DrugBank compounds on the hERG channel. Molecular sequences are embedded with two natural language processing (NLP) methods, namely, autoencoder and transformer. Complementary three-dimensional (3D) molecular structures are embedded with two advanced mathematical approaches, i.e., topological Laplacians and algebraic graphs. With our state-of-the-art tools, we reveal that 227 out of the 8641 DrugBank compounds are potential hERG blockers, suggesting serious drug safety problems. Our predictions provide guidance for the further experimental interrogation of DrugBank compounds' hERG-cardiotoxicity.

Application of Convolutional Neural Networks Using Action Potential Shape for In-Silico Proarrhythmic Risk Assessment

This study proposes a convolutional neural network (CNN) model using action potential (AP) shapes as input for proarrhythmic risk assessment, considering the hypothesis that machine-learning features automatically extracted from AP shapes contain more meaningful information than do manually extracted indicators. We used 28 drugs listed in the comprehensive in vitro proarrhythmia assay (CiPA), consisting of eight high-risk, eleven intermediate-risk, and nine low-risk torsadogenic drugs. We performed drug simulations to generate AP shapes using experimental drug data, obtaining 2000 AP shapes per drug. The proposed CNN model was trained to classify the TdP risk into three levels, high-, intermediate-, and low-risk, based on in silico AP shapes generated using 12 drugs. We then evaluated the performance of the proposed model for 16 drugs. The classification accuracy of the proposed CNN model was excellent for high- and low-risk drugs, with AUCs of 0.914 and 0.951, respectively. The model performance for intermediate-risk drugs was good, at 0.814. Our proposed model can accurately assess the TdP risks of drugs from in silico AP shapes, reflecting the pharmacokinetics of ionic currents. We need to secure more drugs for future studies to improve the TdP-risk-assessment robustness.

Prediction of inotropic effect based on calcium transients in human iPSC-derived cardiomyocytes and machine learning

Functional changes to cardiomyocytes are undesirable during drug discovery and identifying the inotropic effects of compounds is hence necessary to decrease the risk of cardiovascular adverse effects in the clinic. Recently, approaches leveraging calcium transients in human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) have been developed to detect contractility changes, induced by a variety of mechanisms early during drug discovery projects. Although these approaches have been able to provide some predictive ability, we hypothesised that using additional waveform parameters could offer improved insights, as well as predictivity. In this study, we derived 25 parameters from each calcium transient waveform and developed a modified Random Forest method to predict the inotropic effects of the compounds. In total annotated data for 48 compounds were available for modelling, out of which 31 were inotropes. The results show that the Random Forest model with a modified purity criterion performed slightly better than an unmodified algorithm in terms of the Area Under the Curve, giving values of 0.84 vs 0.81 in a cross-validation, and outperformed the ToxCast Pipeline model, for which the highest value was 0.76 when using the best-performing parameter, PW10. Our study hence demonstrates that more advanced parameters derived from waveforms, in combination with additional machine learning methods, provide improved predictivity of cardiovascular risk associated with inotropic effects.

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.

Machine Learning Toxicity Prediction: Latest Advances by Toxicity End Point

Machine learning (ML) models to predict the toxicity of small molecules have garnered great attention and have become widely used in recent years. Computational toxicity prediction is particularly advantageous in the early stages of drug discovery in order to filter out molecules with high probability of failing in clinical trials. This has been helped by the increase in the number of large toxicology databases available. However, being an area of recent application, a greater understanding of the scope and applicability of ML methods is still necessary. There are various kinds of toxic end points that have been predicted in silico. Acute oral toxicity, hepatotoxicity, cardiotoxicity, mutagenicity, and the 12 Tox21 data end points are among the most commonly investigated. Machine learning methods exhibit different performances on different data sets due to dissimilar complexity, class distributions, or chemical space covered, which makes it hard to compare the performance of algorithms over different toxic end points. The general pipeline to predict toxicity using ML has already been analyzed in various reviews. In this contribution, we focus on the recent progress in the area and the outstanding challenges, making a detailed description of the state-of-the-art models implemented for each toxic end point. The type of molecular representation, the algorithm, and the evaluation metric used in each research work are explained and analyzed. A detailed description of end points that are usually predicted, their clinical relevance, the available databases, and the challenges they bring to the field are also highlighted.

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.

Intersection of stem cell biology and engineering towards next generation in vitro models of human fibrosis

Human fibrotic diseases constitute a major health problem worldwide. Fibrosis involves significant etiological heterogeneity and encompasses a wide spectrum of diseases affecting various organs. To date, many fibrosis targeted therapeutic agents failed due to inadequate efficacy and poor prognosis. In order to dissect disease mechanisms and develop therapeutic solutions for fibrosis patients, in vitro disease models have gone a long way in terms of platform development. The introduction of engineered organ-on-a-chip platforms has brought a revolutionary dimension to the current fibrosis studies and discovery of anti-fibrotic therapeutics. Advances in human induced pluripotent stem cells and tissue engineering technologies are enabling significant progress in this field. Some of the most recent breakthroughs and emerging challenges are discussed, with an emphasis on engineering strategies for platform design, development, and application of machine learning on these models for anti-fibrotic drug discovery. In this review, we discuss engineered designs to model fibrosis and how biosensor and machine learning technologies combine to facilitate mechanistic studies of fibrosis and pre-clinical drug testing.

A multi-task FP-GNN framework enables accurate prediction of selective PARP inhibitors

PARP (poly ADP-ribose polymerase) family is a crucial DNA repair enzyme that responds to DNA damage, regulates apoptosis, and maintains genome stability; therefore, PARP inhibitors represent a promising therapeutic strategy for the treatment of various human diseases including COVID-19. In this study, a multi-task FP-GNN (Fingerprint and Graph Neural Networks) deep learning framework was proposed to predict the inhibitory activity of molecules against four PARP isoforms (PARP-1, PARP-2, PARP-5A, and PARP-5B). Compared with baseline predictive models based on four conventional machine learning methods such as RF, SVM, XGBoost, and LR as well as six deep learning algorithms such as DNN, Attentive FP, MPNN, GAT, GCN, and D-MPNN, the evaluation results indicate that the multi-task FP-GNN method achieves the best performance with the highest average BA, F1, and AUC values of 0.753 ± 0.033, 0.910 ± 0.045, and 0.888 ± 0.016 for the test set. In addition, Y-scrambling testing successfully verified that the model was not results of chance correlation. More importantly, the interpretability of the multi-task FP-GNN model enabled the identification of key structural fragments associated with the inhibition of each PARP isoform. To facilitate the use of the multi-task FP-GNN model in the field, an online webserver called PARPi-Predict and its local version software were created to predict whether compounds bear potential inhibitory activity against PARPs, thereby contributing to design and discover better selective PARP inhibitors.

cardioToxCSM: A Web Server for Predicting Cardiotoxicity of Small Molecules

The design of novel, safe, and effective drugs to treat human diseases is a challenging venture, with toxicity being one of the main sources of attrition at later stages of development. Failure due to toxicity incurs a significant increase in costs and time to market, with multiple drugs being withdrawn from the market due to their adverse effects. Cardiotoxicity, for instance, was responsible for the failure of drugs such as fenspiride, propoxyphene, and valdecoxib. While significant effort has been dedicated to mitigate this issue by developing computational approaches that aim to identify molecules likely to be toxic, including quantitative structure-activity relationship models and machine learning methods, current approaches present limited performance and interpretability. To overcome these, we propose a new web-based computational method, cardioToxCSM, which can predict six types of cardiac toxicity outcomes, including arrhythmia, cardiac failure, heart block, hERG toxicity, hypertension, and myocardial infarction, efficiently and accurately. cardioToxCSM was developed using the concept of graph-based signatures, molecular descriptors, toxicophore matchings, and molecular fingerprints, leveraging explainable machine learning, and was validated internally via different cross validation schemes and externally via low-redundancy blind sets. The models presented robust performances with areas under ROC curves of up to 0.898 on 5-fold cross-validation, consistent with metrics on blind tests. Additionally, our models provide interpretation of the predictions by identifying whether substructures that are commonly enriched in toxic compounds were present. We believe cardioToxCSM will provide valuable insight into the potential cardiotoxicity of small molecules early on drug screening efforts. The method is made freely available as a web server at https://biosig.lab.uq.edu.au/cardiotoxcsm.

Deep learning and machine intelligence: New computational modeling techniques for discovery of the combination rules and pharmacodynamic characteristics of Traditional Chinese Medicine

It has been increasingly accepted that Multi-Ingredient-Based interventions provide advantages over single-target therapy for complex diseases. With the growing development of Traditional Chinese Medicine (TCM) and continually being refined of a holistic view, "multi-target" and "multi-pathway" integration characteristics of which are being accepted. However, its effector substances, efficacy targets, especially the combination rules and mechanisms remain unclear, and more powerful strategies to interpret the synergy are urgently needed. Artificial intelligence (AI) and computer vision lead to a rapidly expanding in many fields, including diagnosis and treatment of TCM. AI technology significantly improves the reliability and accuracy of diagnostics, target screening, and new drug research. While all AI techniques are capable of matching models to biological big data, the specific methods are complex and varied. Retrieves literature by the keywords such as "artificial intelligence", "machine learning", "deep learning", "traditional Chinese medicine" and "Chinese medicine". Search the application of computer algorithms of TCM between 2000 and 2021 in PubMed, Web of Science, China National Knowledge Infrastructure (CNKI), Elsevier and Springer. This review concentrates on the application of computational in herb quality evaluation, drug target discovery, optimized compatibility and medical diagnoses of TCM. We describe the characteristics of biological data for which different AI techniques are applicable, and discuss some of the best data mining methods and the problems faced by deep learning and machine learning methods applied to Chinese medicine.

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.

Large-scale comparison of machine learning algorithms for target prediction of natural products

Natural products (NPs) and their derivatives are important resources for drug discovery. There are many in silico target prediction methods that have been reported, however, very few of them distinguish NPs from synthetic molecules. Considering the fact that NPs and synthetic molecules are very different in many characteristics, it is necessary to build specific target prediction models of NPs. Therefore, we collected the activity data of NPs and their derivatives from the public databases and constructed four datasets, including the NP dataset, the NPs and its first-class derivatives dataset, the NPs and all its derivatives and the ChEMBL26 compounds dataset. Conditions, including activity thresholds and input features, were explored to access the performance of eight machine learning methods of target prediction of NPs, including support vector machines (SVM), extreme gradient boosting, random forests, K-nearest neighbor, naive Bayes, feedforward neural networks (FNN), convolutional neural networks and recurrent neural networks. As a result, the NPs and all their derivatives datasets were selected to build the best NP-specific models. Furthermore, the consensus models, as well as the voting models, were additionally applied to improve the prediction performance. More evaluations were made on the external validation set and the results demonstrated that (1) the NP-specific model performed better on the target prediction of NPs than the traditional models training on the whole compounds of ChEMBL26. (2) The consensus model of FNN + SVM possessed the best overall performance, and the voting model can significantly improve recall and specificity.

Shared Genetic Risk Factors Between Cancer and Cardiovascular Diseases

Cancer and cardiovascular diseases (CVD) account for approximately 27.5 million deaths every year. While they share some common environmental risk factors, their shared genetic risk factors are not yet fully understood. The aim of the present study was to aggregate genetic risk factors associated with the comorbidity of cancer and CVDs. For this purpose, we: (1) created a catalog of genes associated with cancer and CVDs, (2) visualized retrieved data as a gene-disease network, and (3) performed a pathway enrichment analysis. We performed screening of PubMed database for literature reporting genetic risk factors in patients with both cancer and CVD. The gene-disease network was visualized using Cytoscape and the enrichment analysis was conducted using Enrichr software. We manually reviewed the 181 articles fitting the search criteria and included 13 articles in the study. Data visualization revealed a highly interconnected network containing a single subnetwork with 56 nodes and 146 edges. Genes in the network with the highest number of disease interactions were JAK2, TTN, TET2, and ATM. The pathway enrichment analysis revealed that genes included in the study were significantly enriched in DNA damage repair (DDR) pathways, such as homologous recombination. The role of DDR mechanisms in the development of CVDs has been studied in previously published research; however, additional functional studies are required to elucidate their contribution to the pathophysiology to CVDs.

A biosensing system employing nanowell microelectrode arrays to record the intracellular potential of a single cardiomyocyte

Electrophysiological recording is a widely used method to investigate cardiovascular pathology, pharmacology and developmental biology. Microelectrode arrays record the electrical potential of cells in a minimally invasive and high-throughput way. However, commonly used microelectrode arrays primarily employ planar microelectrodes and cannot work in applications that require a recording of the intracellular action potential of a single cell. In this study, we proposed a novel measuring method that is able to record the intracellular action potential of a single cardiomyocyte by using a nanowell patterned microelectrode array (NWMEA). The NWMEA consists of five nanoscale wells at the center of each circular planar microelectrode. Biphasic pulse electroporation was applied to the NWMEA to penetrate the cardiomyocyte membrane, and the intracellular action potential was continuously recorded. The intracellular potential recording of cardiomyocytes by the NWMEA measured a potential signal with a higher quality (213.76 ± 25.85%), reduced noise root-mean-square (~33%), and higher signal-to-noise ratio (254.36 ± 12.61%) when compared to those of the extracellular recording. Compared to previously reported nanopillar microelectrodes, the NWMEA could ensure single cell electroporation and acquire high-quality action potential of cardiomyocytes with reduced fabrication processes. This NWMEA-based biosensing system is a promising tool to record the intracellular action potential of a single cell to broaden the usage of microelectrode arrays in electrophysiological investigation.

BayeshERG: a robust, reliable and interpretable deep learning model for predicting hERG channel blockers

Unintended inhibition of the human ether-à-go-go-related gene (hERG) ion channel by small molecules leads to severe cardiotoxicity. Thus, hERG channel blockage is a significant concern in the development of new drugs. Several computational models have been developed to predict hERG channel blockage, including deep learning models; however, they lack robustness, reliability and interpretability. Here, we developed a graph-based Bayesian deep learning model for hERG channel blocker prediction, named BayeshERG, which has robust predictive power, high reliability and high resolution of interpretability. First, we applied transfer learning with 300 000 large data in initial pre-training to increase the predictive performance. Second, we implemented a Bayesian neural network with Monte Carlo dropout to calibrate the uncertainty of the prediction. Third, we utilized global multihead attentive pooling to augment the high resolution of structural interpretability for the hERG channel blockers and nonblockers. We conducted both internal and external validations for stringent evaluation; in particular, we benchmarked most of the publicly available hERG channel blocker prediction models. We showed that our proposed model outperformed predictive performance and uncertainty calibration performance. Furthermore, we found that our model learned to focus on the essential substructures of hERG channel blockers via an attention mechanism. Finally, we validated the prediction results of our model by conducting in vitro experiments and confirmed its high validity. In summary, BayeshERG could serve as a versatile tool for discovering hERG channel blockers and helping maximize the possibility of successful drug discovery. The data and source code are available at our GitHub repository (https://github.com/GIST-CSBL/BayeshERG).

PregTox: A Resource of Knowledge about Drug Fetal Toxicity

Background

It is of vital importance to determine the safety of drugs. Pregnant women, as a special group, need to evaluate the effects of drugs on pregnant women as well as the fetus. The use of drugs during pregnancy may be subject to fetal toxicity, thus affecting the development of the fetus or even leading to stillbirth. The U.S. Food and Drug Administration (FDA) issued a toxicity rating for drugs used during pregnancy in 1979. These toxicity ratings are denoted by the letters A, B, C, D, and X. However, the query of drug pregnancy category has yet to be well established as electronic service.

Results

Here, we presented PregTox, a publicly accessible resource for pregnancy category information of 1114 drugs. The PregTox database also included chemical structures, important physico-chemical properties, protein targets, and relevant signaling pathways. An advantage of the database is multiple search options which allow systematic analyses. In a case study, we demonstrated that a set of chemical descriptors could effectively discriminate high-risk drugs from others (area under ROC curve reached 0.81).

Conclusions

PregTox can serve as a unique drug safety data source for drug development and pharmacological research.

Machine learning-based predictive models for identifying high active compounds against HIV-1 integrase

HIV-integrase is an important drug target because it catalyzes chromosomal integration of proviral DNA towards establishing latent infection. Computer-aided drug design has immensely contributed to identifying and developing novel antiviral drugs. We have developed various machine learning-based predictive models for identifying high activity compounds against HIV-integrase. Multiclass models were built using support vector machine with reasonable accuracy on the test and evaluation sets. The developed models were evaluated by rigorous validation approaches and the best features were selected by Boruta method. As compared to the model developed from all descriptors set, a slight improvement was observed among the selected descriptors. Validated models were further used for virtual screening of potential compounds from ChemBridge library. Of the six high active compounds predicted from selected models, compounds 9103124, 6642917 and 9082952 showed the most reasonable binding-affinity and stable-interaction with HIV-integrase active-site residues Asp64, Glu152 and Asn155. This was in agreement with previous reports on the essentiality of these residues against a wide range of inhibitors. We therefore highlight the rigorosity of validated classification models for accurate prediction and ranking of high active lead drugs against HIV-integrase.

Identification and New Indication of Melanin-Concentrating Hormone Receptor 1 (MCHR1) Antagonist Derived from Machine Learning and Transcriptome-Based Drug Repositioning Approaches

Melanin-concentrating hormone receptor 1 (MCHR1) has been a target for appetite suppressants, which are helpful in treating obesity. However, it is challenging to develop an MCHR1 antagonist because its binding site is similar to that of the human Ether-à-go-go-Related Gene (hERG) channel, whose inhibition may cause cardiotoxicity. Most drugs developed as MCHR1 antagonists have failed in clinical development due to cardiotoxicity caused by hERG inhibition. Machine learning-based prediction models can overcome these difficulties and provide new opportunities for drug discovery. In this study, we identified KRX-104130 with potent MCHR1 antagonistic activity and no cardiotoxicity through virtual screening using two MCHR1 binding affinity prediction models and an hERG-induced cardiotoxicity prediction model. In addition, we explored other possibilities for expanding the new indications for KRX-104130 using a transcriptome-based drug repositioning approach. KRX-104130 increased the expression of low-density lipoprotein receptor (LDLR), which induced cholesterol reduction in the gene expression analysis. This was confirmed by comparison with gene expression in a nonalcoholic steatohepatitis (NASH) patient group. In a NASH mouse model, the administration of KRX-104130 showed a protective effect by reducing hepatic lipid accumulation, liver injury, and histopathological changes, indicating a promising prospect for the therapeutic effect of NASH as a new indication for MCHR1 antagonists.

Molecular Design Learned from the Natural Product Porphyra-334: Molecular Generation via Chemical Variational Autoencoder versus Database Mining via Similarity Search, A Comparative Study

A comparative study is presented. The method via chemical variational autoencoder (VAE) and the method via similarity search are compared, focusing on their generation ability for new functional molecular design. Focusing on the natural porphyra-334 as a model molecule, we generated three groups: molecules of mycosporine-like amino acids (MAAs) as seeds (G _SEEDS ), molecules generated via chemical VAE (G _VAE ) and molecules gathered via similarity search (G _SIM ). The number of molecules that satisfy the condition for the light absorption ability of porphyra-334 in G _SEEDS , G _VAE , and G _SIM are 52, 138, and 6, respectively. The method via chemical VAE shows a promising potential for future molecular design. By using quantum chemistry wave function properties for chemical VAE, we find new molecules that are comparable to porphyra-334, including some with unexpected geometries. At the end, we show a group of molecules found with this method.

Multimodality Advanced Cardiovascular and Molecular Imaging for Early Detection and Monitoring of Cancer Therapy-Associated Cardiotoxicity and the Role of Artificial Intelligence and Big Data

Cancer mortality has improved due to earlier detection via screening, as well as due to novel cancer therapies such as tyrosine kinase inhibitors and immune checkpoint inhibitions. However, similarly to older cancer therapies such as anthracyclines, these therapies have also been documented to cause cardiotoxic events including cardiomyopathy, myocardial infarction, myocarditis, arrhythmia, hypertension, and thrombosis. Imaging modalities such as echocardiography and magnetic resonance imaging (MRI) are critical in monitoring and evaluating for cardiotoxicity from these treatments, as well as in providing information for the assessment of function and wall motion abnormalities. MRI also allows for additional tissue characterization using T1, T2, extracellular volume (ECV), and delayed gadolinium enhancement (DGE) assessment. Furthermore, emerging technologies may be able to assist with these efforts. Nuclear imaging using targeted radiotracers, some of which are already clinically used, may have more specificity and help provide information on the mechanisms of cardiotoxicity, including in anthracycline mediated cardiomyopathy and checkpoint inhibitor myocarditis. Hyperpolarized MRI may be used to evaluate the effects of oncologic therapy on cardiac metabolism. Lastly, artificial intelligence and big data of imaging modalities may help predict and detect early signs of cardiotoxicity and response to cardioprotective medications as well as provide insights on the added value of molecular imaging and correlations with cardiovascular outcomes. In this review, the current imaging modalities used to assess for cardiotoxicity from cancer treatments are discussed, in addition to ongoing research on targeted molecular radiotracers, hyperpolarized MRI, as well as the role of artificial intelligence (AI) and big data in imaging that would help improve the detection and prognostication of cancer-treatment cardiotoxicity.

Transfer inhibitory potency prediction to binary classification: A model only needs a small training set

One of the most laborious for drug discovery is to select compounds from a library for experimental evaluation. Hence, we propose a machine learning model only needs to be trained on a small dataset to predict the inhibition constant (Ki) and half maximal inhibitory concentration (IC50) for a compound. We transfer the prediction task to a simpler binary classification task based on a naive but effective idea that we only need the related rank of a compound to determine whether to take it for further examination. To achieve this, we design a data augmentation strategy to effectively leverage the relationship between the compounds in the training set. After that, we formulate a new reward function for deep reinforcement learning to balance the feature selection and the accuracy. We employ a particle swarm optimized support vector machine for the binary classification task. Finally, a soft voting mechanism is introduced to solve the contradiction from the binary classification. Sufficient experiments show that our model achieves high and reliable accuracy, and is capable of ranking compounds based on a selected set of molecular descriptors. The current results show that our model provides a potential ligand-based in silico approach for prioritizing chemicals for experimental studies.