Key result
The deep CNN model using dVm/dt shapes classified TdP risk with AUCs of 0.98 for high-risk, 0.94 for intermediate-risk, and 0.89 for low-risk test drugs, with 81% overall accuracy.
Why the study?
A single in silico feature such as qNet cannot reflect all TdP-related characteristics across the entire action potential shape.
Does a deep convolutional neural network (CNN) using differential action potential (dVm/dt) waveforms improve the classification of drug-induced Torsades de Pointes (TdP) risk compared to traditional logistic regression using qNet in in silico CiPA drug simulations?
Does a deep convolutional neural network (CNN) using differential action potential (dVm/dt) waveforms improve the classification of drug-induced Torsades de Pointes (TdP) risk compared to traditional logistic regression using qNet in in silico CiPA drug simulations?
A deep CNN analyzing the full differential action potential waveform (dVm/dt) from in silico simulations accurately classifies drug-induced Torsades de Pointes risk into three tiers without requiring complex hERG dynamic modeling.
Comprehensive in vitro Proarrhythmia Assay (CiPA) projects for assessing proarrhythmic drugs suggested a logistic regression model using qNet as the Torsades de Pointes (TdP) risk assessment biomarker, obtained from in silico simulation. However, using a single in silico feature, such as qNet, cannot reflect whole characteristics related to TdP in the entire action potential (AP) shape. Thus, this study proposed a deep convolutional neural network (CNN) model using differential action potential shapes to classify three proarrhythmic risk levels: high, intermediate, and low, considering both characteristics related to TdP not only in the depolarization phase but also the repolarization phase of AP shape. We performed an in silico simulation and got AP shapes with drug effects using half-maximal inhibitory concentration and Hill coefficients of 28 drugs released by CiPA groups. Then, we trained the deep CNN model with the differential AP shapes of 12 drugs and tested it with those of 16 drugs. Our model had a better performance for classifying the proarrhythmic risk of drugs than the traditional logistic regression model using qNet. The classification accuracy was 98% for high-risk level drugs, 94% for intermediate-risk level drugs, and 89% for low-risk level drugs.
No takes yet. Share an insight, caveat, or question.
Jeong et al. (2022) studied Drug-induced Torsades de Pointes (TdP) proarrhythmic risk (n=28). Deep convolutional neural network (CNN) model using differential action potential (dVm/dt) shapes vs. Traditional logistic regression model using qNet (with and without hERG dynamics) was evaluated on Classification performance (AUC) for high-risk Torsades de Pointes (TdP) drugs in the 16-drug test set (95% CI 0.94-1.0). The deep CNN model using dVm/dt shapes classified TdP risk with AUCs of 0.98 for high-risk, 0.94 for intermediate-risk, and 0.89 for low-risk test drugs, with 81% overall accuracy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: