Assessment of Drug Proarrhythmicity Using Artificial Neural Networks With in silico Deterministic Model Outputs.

Yedam Yoo,Ki-Suk Kim,Aroli Marcellinus,Ki Moo Lim,Da Un Jeong

doi:10.3389/fphys.2021.761691

Abstract

As part of the Comprehensive in vitro Proarrhythmia Assay initiative, methodologies for predicting the occurrence of drug-induced torsade de pointes via computer simulations have been developed and verified recently. However, their predictive performance still requires improvement. Herein, we propose an artificial neural networks (ANN) model that uses nine multiple input features, considering the action potential morphology, calcium transient morphology, and charge features to further improve the performance of drug toxicity evaluation. The voltage clamp experimental data for 28 drugs were augmented to 2,000 data entries using an uncertainty quantification technique. By applying these data to the modified O’Hara Rudy in silico model, nine features (dVm/dtmax, APresting, APD90, APD50, Caresting, CaD90, CaD50, qNet, and qInward) were calculated. These nine features were used as inputs to an ANN model to classify drug toxicity into high-risk, intermediate-risk, and low-risk groups. The model was trained with data from 12 drugs and tested using the data of the remaining 16 drugs. The proposed ANN model demonstrated an AUC of 0.92 in the high-risk group, 0.83 in the intermediate-risk group, and 0.98 in the low-risk group. This was higher than the classification performance of the method proposed in previous studies.

Highlights

In 1999, the gastroprokinetic agent cisapride was recalled from the European pharmaceutical market because it was associated with torsades de pointes (TdP) (World health Organizations, 2001; Roden, 2008)
In this study, to increase the accuracy of drug toxicity assessments, we propose a drug TdP induced risk level classification model based on an artificial neural network (ANN)
The representative values of the area under the curve (AUC) obtained after 10,000 tests using the learned artificial neural networks (ANN) classifier developed in this study were 0.92 for the high-risk level, 0.83 for the intermediate-risk level, and 0.98 for the low-risk level

Summary

Introduction

In 1999, the gastroprokinetic agent cisapride was recalled from the European pharmaceutical market because it was associated with torsades de pointes (TdP) (World health Organizations, 2001; Roden, 2008). In 2005, the International Council for Harmonization (ICH) established guidelines for the proarrhythmic assessment of drugs (Cavero and Crumb, 2005). This guideline suggests that the cardiotoxicity assessment for drugs should be conducted according to the S7B non-clinical evaluation and the E14 clinical evaluation guidelines. This conventional guideline requires extensive trials and has high sensitivity but low specificity for the risk classification of drugs. This means that even drugs that do not cause TdP are strictly regulated, negatively affecting drug development (Colatsky et al, 2016)

Methods

Results

Conclusion