Key result
Combining myocyte simulations and machine learning improves risk prediction for drug-induced TdP.
Why the study?
Does a computational approach combining simulations and machine learning improve the prediction of drug-induced Torsades de Pointes?
Does a computational approach combining simulations and machine learning improve the prediction of drug-induced Torsades de Pointes?
Answers are grounded in this paper and cite their sources.
A novel machine learning and simulation-based computational approach improves the prediction of drug-induced Torsades de Pointes by incorporating action potential and calcium waveform dynamics.
The ventricular arrhythmia Torsades de Pointes (TdP) is a common form of drug-induced cardiotoxicity, but prediction of this arrhythmia remains an unresolved issue in drug development. Current assays to evaluate arrhythmia risk are limited by poor specificity and a lack of mechanistic insight. We addressed this important unresolved issue through a novel computational approach that combined simulations of drug effects on dynamics with statistical analysis and machine-learning. Drugs that blocked multiple ion channels were simulated in ventricular myocyte models, and metrics computed from the action potential and intracellular (Ca(2+) ) waveform were used to construct classifiers that distinguished between arrhythmogenic and nonarrhythmogenic drugs. We found that: (1) these classifiers provide superior risk prediction; (2) drug-induced changes to both the action potential and intracellular (Ca(2+) ) influence risk; and (3) cardiac ion channels not typically assessed may significantly affect risk. Our algorithm demonstrates the value of systematic simulations in predicting pharmacological toxicity.
No takes yet. Share an insight, caveat, or question.
Lancaster et al. (2016) studied Drug-induced Torsades de Pointes (TdP). Computational simulations and machine learning algorithms vs. Current assays was evaluated on Prediction of arrhythmogenic versus nonarrhythmogenic drugs. A novel computational approach combining simulations of drug effects on ventricular myocyte dynamics with machine learning provided superior risk prediction for drug-induced Torsades de Pointes.
Synapse has enriched 10 related papers. Consider them for comparative context: