In silico models for evaluating proarrhythmic risk of drugs

In Silico Human Cardiomyocyte Action Potential Modeling: Exploring Ion Channel Input Combinations

In silico modeling offers an opportunity to supplement and accelerate cardiac safety testing. With in silico modeling, computational simulation methods are used to predict electrophysiological interactions and pharmacological effects of novel drugs on critical physiological processes. The O'Hara-Rudy's model was developed to predict the response to different ion channel inhibition levels on cardiac action potential duration (APD) which is known to directly correlate with the QT interval. APD data at 30% 60% and 90% inhibition were derived from the model to delineate possible ventricular arrhythmia scenarios and the marginal contribution of each ion channel to the model. Action potential values were calculated for epicardial, myocardial, and endocardial cells, with action potential curve modeling. This study assessed cardiac ion channel inhibition data combinations to consider when undertaking in silico modeling of proarrhythmic effects as stipulated in the Comprehensive in Vitro Proarrhythmia Assay (CiPA). As expected, our data highlight the importance of the delayed rectifier potassium channel (IKr) as the most impactful channel for APD prolongation. The impact of the transient outward potassium channel (Ito) inhibition on APD was minimal while the inward rectifier (IK1) and slow component of the delayed rectifier potassium channel (IKs) also had limited APD effects. In contrast, the contribution of fast sodium channel (INa) and/or L-type calcium channel (ICa) inhibition resulted in substantial APD alterations supporting the pharmacological relevance of in silico modeling using input from a limited number of cardiac ion channels including IKr, INa, and ICa, at least at an early stage of drug development.

Machine learning approach to evaluate TdP risk of drugs using cardiac electrophysiological model including inter-individual variability

Introduction: Predicting ventricular arrhythmia Torsade de Pointes (TdP) caused by drug-induced cardiotoxicity is essential in drug development. Several studies used single biomarkers such as qNet and Repolarization Abnormality (RA) in a single cardiac cell model to evaluate TdP risk. However, a single biomarker may not encompass the full range of factors contributing to TdP risk, leading to divergent TdP risk prediction outcomes, mainly when evaluated using unseen data. We addressed this issue by utilizing multi-in silico features from a population of human ventricular cell models that could capture a representation of the underlying mechanisms contributing to TdP risk to provide a more reliable assessment of drug-induced cardiotoxicity. Method: We generated a virtual population of human ventricular cell models using a modified O'Hara-Rudy model, allowing inter-individual variation. IC 50 and Hill coefficients from 67 drugs were used as input to simulate drug effects on cardiac cells. Fourteen features (dVm dt repol , dVm dt max , Vm peak , Vm resting , APD tri , APD 90 , APD 50 , Ca peak , Ca diastole , Ca tri , CaD 90 , CaD 50 , qNet, qInward) could be generated from the simulation and used as input to several machine learning models, including k-nearest neighbor (KNN), Random Forest (RF), XGBoost, and Artificial Neural Networks (ANN). Optimization of the machine learning model was performed using a grid search to select the best parameter of the proposed model. We applied five-fold cross-validation while training the model with 42 drugs and evaluated the model's performance with test data from 25 drugs. Result: The proposed ANN model showed the highest performance in predicting the TdP risk of drugs by providing an accuracy of 0.923 (0.908-0.937), sensitivity of 0.926 (0.909-0.942), specificity of 0.921 (0.906-0.935), and AUC score of 0.964 (0.954-0.975). Discussion and conclusion: According to the performance results, combining the electrophysiological model including inter-individual variation and optimization of machine learning showed good generalization ability when evaluated using the unseen dataset and produced a reliable drug-induced TdP risk prediction system.

Uncertainty assessment of proarrhythmia predictions derived from multi-level in silico models

In silico methods can be used for an early assessment of arrhythmogenic properties of drug candidates. However, their use for decision-making is conditioned by the possibility to estimate the predictions' uncertainty. This work describes our efforts to develop uncertainty quantification methods for the predictions produced by multi-level proarrhythmia models. In silico models used in this field usually start with experimental or predicted IC50 values that describe drug-induced ion channel blockade. Using such inputs, an electrophysiological model computes how the ion channel inhibition, exerted by a drug in a certain concentration, translates to an altered shape and duration of the action potential in cardiac cells, which can be represented as arrhythmogenic risk biomarkers such as the APD90. Using this framework, we identify the main sources of aleatory and epistemic uncertainties and propose a method based on probabilistic simulations that replaces single-point estimates predicted using multiple input values, including the IC50s and the electrophysiological parameters, by distributions of values. Two selected variability types associated with these inputs are then propagated through the multi-level model to estimate their impact on the uncertainty levels in the output, expressed by means of intervals. The proposed approach yields single predictions of arrhythmogenic risk biomarkers together with value intervals, providing a more comprehensive and realistic description of drug effects on a human population. The methodology was tested by predicting arrhythmogenic biomarkers on a series of twelve well-characterised marketed drugs, belonging to different arrhythmogenic risk classes.

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.

Brain physiome: A concept bridging in vitro 3D brain models and in silico models for predicting drug toxicity in the brain

In the last few decades, adverse reactions to pharmaceuticals have been evaluated using 2D in vitro models and animal models. However, with increasing computational power, and as the key drivers of cellular behavior have been identified, in silico models have emerged. These models are time-efficient and cost-effective, but the prediction of adverse reactions to unknown drugs using these models requires relevant experimental input. Accordingly, the physiome concept has emerged to bridge experimental datasets with in silico models. The brain physiome describes the systemic interactions of its components, which are organized into a multilevel hierarchy. Because of the limitations in obtaining experimental data corresponding to each physiome component from 2D in vitro models and animal models, 3D in vitro brain models, including brain organoids and brain-on-a-chip, have been developed. In this review, we present the concept of the brain physiome and its hierarchical organization, including cell- and tissue-level organizations. We also summarize recently developed 3D in vitro brain models and link them with the elements of the brain physiome as a guideline for dataset collection. The connection between in vitro 3D brain models and in silico modeling will lead to the establishment of cost-effective and time-efficient in silico models for the prediction of the safety of unknown drugs.

Kinase inhibitor-induced cardiotoxicity assessed in vitro with human pluripotent stem cell derived cardiomyocytes

Many small molecule kinase inhibitors (SMKIs), used predominately in cancer therapy, have been implicated in serious clinical cardiac adverse events, which means that traditional preclinical drug development assays were not sufficient for identifying these cardiac liabilities. To improve clinical cardiac safety predictions, the effects of SMKIs targeting many different signaling pathways were studied using human pluripotent stem cell derived cardiomyocytes (hPSC-CMs) in combined assays designed for the detection of both electrophysiological (proarrhythmic) and non-electrophysiological (non-proarrhythmic) drug-induced cardiotoxicity. Several microplate-based assays were used to quantitate cell death, apoptosis, mitochondrial damage, energy depletion, and oxidative stress as mechanism-based non-electrophysiological cardiomyocyte toxicities. Microelectrode arrays (MEA) were used to quantitate vitro arrhythmic events (iAEs), field potential duration (FPD) prolongation, and spike amplitude suppression (SAS) as electrophysiological effects. To enhance the clinical relevance, SMKIs induced cardiotoxicities were compared by converting dug concentrations into multiples of reported clinical maximum therapeutic plasma concentration, "FoldC_max", for each assay. The results support the conclusion that the combination of the hPSC-CMs based electrophysiological and non-electrophysiological assays have significantly more predictive value than either assay alone, and significantly more than the current FDA-recommended hERG assay. In addition, the combination of these assays provided mechanistic information relevant to cardiomyocyte toxicities, thus providing valuable information on potential drug-induced cardiotoxicities early in drug development prior to animal and clinical testing. We believe that this early information will be helpful to guide the development of safer and more cost-effective drugs.

In vitro and In silico Models to Study SARS-CoV-2 Infection: Integrating Experimental and Computational Tools to Mimic "COVID-19 Cardiomyocyte"

The rapid dissemination of SARS-CoV-2 has made COVID-19 a tremendous social, economic, and health burden. Despite the efforts to understand the virus and treat the disease, many questions remain unanswered about COVID-19 mechanisms of infection and progression. Severe Acute Respiratory Syndrome (SARS) infection can affect several organs in the body including the heart, which can result in thromboembolism, myocardial injury, acute coronary syndromes, and arrhythmias. Numerous cardiac adverse events, from cardiomyocyte death to secondary effects caused by exaggerated immunological response against the virus, have been clinically reported. In addition to the disease itself, repurposing of treatments by using "off label" drugs can also contribute to cardiotoxicity. Over the past several decades, animal models and more recently, stem cell-derived cardiomyocytes have been proposed for studying diseases and testing treatments in vitro. In addition, mechanistic in silico models have been widely used for disease and drug studies. In these models, several characteristics such as gender, electrolyte imbalance, and comorbidities can be implemented to study pathophysiology of cardiac diseases and to predict cardiotoxicity of drug treatments. In this Mini Review, we (1) present the state of the art of in vitro and in silico cardiomyocyte modeling currently in use to study COVID-19, (2) review in vitro and in silico models that can be adopted to mimic the effects of SARS-CoV-2 infection on cardiac function, and (3) provide a perspective on how to combine some of these models to mimic "COVID-19 cardiomyocytes environment.".