Proarrhythmic risk assessment of drugs by dVm /dt shapes using the convolutional neural network

A stacking ensemble machine learning model for evaluating cardiac toxicity of drugs based on in silico biomarkers

This study addresses the critical issue of drug-induced torsades de pointes (TdP) risk assessment, a vital aspect of new drug development due to its association with arrhythmia and sudden cardiac death. Existing methodologies, particularly those reliant on a single biomarker derived from CiPA O'Hara-Rudy (CiPAORdv1.0) ventricular cell model without the hERG dynamic as input to the individual machine learning model, have limitations in capturing the complexity inherent in the comprehensive range of factors influencing drug-induced TdP risk. This study aims to overcome these limitations by proposing a stacking ensemble machine learning approach by integrating multiple in silico biomarkers derived from the CiPAORdv1.0 with hERG dynamic characteristics. The ensemble machine learning model consisted of three artificial neural network (ANN) models as baseline model and support vector machine (SVM), logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) models as meta-classifier. The highest AUC score of 1.00 (0.90-1.00) for high risk, 0.97 (0.84-1.00) for intermediate risk, and 1.00 (0.87-1.00) for low risk were obtained using seven biomarkers derived from the CiPAORdv1.0 with hERG dynamic characteristics. Furthering our investigation, we explored the model's robustness by incorporating interindividual variability into the generation of in silico biomarkers from a population of human ventricular cell models. This study also enabled an analysis of TdP risk classification under high clinical exposure and therapeutic scenarios for several drugs. Additionally, from a sensitivity analysis, we revealed four important ion channels, namely, CaL, NaL, Na, and Kr channels that affect significantly the important biomarkers for TdP risk prediction.

Neural network emulation of the human ventricular cardiomyocyte action potential for more efficient computations in pharmacological studies

Computer models of the human ventricular cardiomyocyte action potential (AP) have reached a level of detail and maturity that has led to an increasing number of applications in the pharmaceutical sector. However, interfacing the models with experimental data can become a significant computational burden. To mitigate the computational burden, the present study introduces a neural network (NN) that emulates the AP for given maximum conductances of selected ion channels, pumps, and exchangers. Its applicability in pharmacological studies was tested on synthetic and experimental data. The NN emulator potentially enables massive speed-ups compared to regular simulations and the forward problem (find drugged AP for pharmacological parameters defined as scaling factors of control maximum conductances) on synthetic data could be solved with average root-mean-square errors (RMSE) of 0.47 mV in normal APs and of 14.5 mV in abnormal APs exhibiting early afterdepolarizations (72.5% of the emulated APs were alining with the abnormality, and the substantial majority of the remaining APs demonstrated pronounced proximity). This demonstrates not only very fast and mostly very accurate AP emulations but also the capability of accounting for discontinuities, a major advantage over existing emulation strategies. Furthermore, the inverse problem (find pharmacological parameters for control and drugged APs through optimization) on synthetic data could be solved with high accuracy shown by a maximum RMSE of 0.22 in the estimated pharmacological parameters. However, notable mismatches were observed between pharmacological parameters estimated from experimental data and distributions obtained from the Comprehensive in vitro Proarrhythmia Assay initiative. This reveals larger inaccuracies which can be attributed particularly to the fact that small tissue preparations were studied while the emulator was trained on single cardiomyocyte data. Overall, our study highlights the potential of NN emulators as powerful tool for an increased efficiency in future quantitative systems pharmacology studies.

Assessment of the proarrhythmic effects of repurposed antimalarials for COVID-19 treatment using a comprehensive in vitro proarrhythmia assay (CiPA)

Due to the outbreak of the SARS-CoV-2 virus, drug repurposing and Emergency Use Authorization have been proposed to treat the coronavirus disease 2019 (COVID-19) during the pandemic. While the efficiency of the drugs has been discussed, it was identified that certain compounds, such as chloroquine and hydroxychloroquine, cause QT interval prolongation and potential cardiotoxic effects. Drug-induced cardiotoxicity and QT prolongation may lead to life-threatening arrhythmias such as torsades de pointes (TdP), a potentially fatal arrhythmic symptom. Here, we evaluated the risk of repurposed pyronaridine or artesunate-mediated cardiac arrhythmias alone and in combination for COVID-19 treatment through in vitro and in silico investigations using the Comprehensive in vitro Proarrhythmia Assay (CiPA) initiative. The potential effects of each drug or in combinations on cardiac action potential (AP) and ion channels were explored using human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) and Chinese hamster ovary (CHO) cells transiently expressing cardiac ion channels (Nav1.5, Cav1.2, and hERG). We also performed in silico computer simulation using the optimized O'Hara-Rudy human ventricular myocyte model (ORd model) to classify TdP risk. Artesunate and dihydroartemisinin (DHA), the active metabolite of artesunate, are classified as a low risk of inducing TdP based on the torsade metric score (TMS). Moreover, artesunate does not significantly affect the cardiac APs of hiPSC-CMs even at concentrations up to 100 times the maximum serum concentration (Cmax). DHA modestly prolonged at APD90 (10.16%) at 100 times the Cmax. When considering Cmax, pyronaridine, and the combination of both drugs (pyronaridine and artesunate) are classified as having an intermediate risk of inducing TdP. However, when considering the unbound concentration (the free fraction not bound to carrier proteins or other tissues inducing pharmacological activity), both drugs are classified as having a low risk of inducing TdP. In summary, pyronaridine, artesunate, and a combination of both drugs have been confirmed to pose a low proarrhythmogenic risk at therapeutic and supratherapeutic (up to 4 times) free Cmax. Additionally, the CiPA initiative may be suitable for regulatory use and provide novel insights for evaluating drug-induced cardiotoxicity.

qInward variability-based in-silico proarrhythmic risk assessment of drugs using deep learning model

Many researchers have suggested evaluation methods and Torsades de Pointes (TdP) metrics to assess the proarrhythmic risk of a drug based on the in silico simulation, as part of the Comprehensive in-vitro Proarrhythmia Assay (CiPA) project. In the previous study, we validated the robustness of 12 in silico features using the ordinal logistic regression (OLR) model by comparing the classification performances of metrics according to the in-vitro experimental datasets used; however, the OLR model using 12 in silico features did not provide desirable results. This study proposed a convolutional neural network (CNN) model using the variability of promising in silico TdP metrics hypothesizing that the variability of in silico features based on beats has more information than the single value of in silico features. We performed the action potential (AP) simulation using a human ventricular myocyte model to calculate seven in silico features representing the electrophysiological cell states of drug effects over 1,000 beats: qNet, qInward, intracellular calcium duration at returning to 50% baseline (CaD50) and 90% baseline (CaD90), AP duration at 50% repolarization (APD50) and 90% repolarization (APD90), and dVm/dtMax_repol. The proposed CNN classifier was trained using 12 train drugs and tested using 16 test drugs among CiPA drugs. The torsadogenic risk of drugs was classified as high, intermediate, and low risks. We determined the CNN classifier by comparing the classification performance according to the variabilities of seven in silico biomarkers computed from the in silico drug simulation using the Chantest dataset. The proposed CNN classifier performed the best when using qInward variability to classify the TdP-risk drugs with 0.94 AUC for high risk and 0.93 AUC for low risk. In addition, the final CNN classifier was validated using the qInward variability obtained after merging three in-vitro datasets, but the model performance decreased to a moderate level of 0.75 and 0.78 AUC. These results suggest the need for the proposed CNN model to be trained and tested using various types of drugs.