Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

A greedy classifier optimisation strategy to assess ion channel blocking activity and pro-arrhythmia in hiPSC-cardiomyocytes

Abstract : Novel studies conducting cardiac safety assessment using human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) are promising but might be limited by their specificity and predictivity. It is often challenging to correctly classify ion channel blockers or to sufficiently predict the risk for Torsade de Pointes (TdP). In this study, we developed a method combining in vitro and in silico experiments to improve machine learning approaches in delivering fast and reliable prediction of drug-induced ion-channel blockade and proarrhythmic behaviour. The algorithm is based on the construction of a dictionary and a greedy optimisation, leading to the definition of optimal classifiers. Finally, we present a numerical tool that can accurately predict compound-induced pro-arrhythmic risk and involvement of sodium, calcium and potassium channels, based on hiPSC-CM field potential data. 2 Introduction 1 The Comprehensive in vitro Proarrhythmia Assay (CiPA) is an initiative for a new 2 paradigm in safety pharmacology to redefine the non-clinical evaluation of Torsade de 3 Pointes (TdP) [1-3]. 4 It aims to more precisely assess TdP risk in vitro by using a multifaceted approach 5 that combines in vitro evaluations of electrophysiologic responses in human-induced 6 pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) and in silico models 7 providing reconstructions of drug effects on ventricular electrical activity [4, 5]. 8 Since CiPA, in vitro studies using hiPSC-CMs become an increasingly integrated 9 part of today's cardiac safety assessment. While encouraging, adequately predicting 10 TdP risk of unknown drugs based on in vitro studies alone is challenging. Besides, the 11 analysis of the large data sets derived from those studies is often far from being 12 automated. 13 The main focus of the present study is to address these issues by investigating a 14 computational tool that combines statistical analysis and machine learning approaches 15 (used in this context in [6]) to the mathematical modeling and the numerical 16 simulations (in silico experiments) of the drug effects on the field potential (FP) of 17 hiPSC-CMs obtained by multi-electrode array (MEA) technology.
Complete list of metadatas

Cited literature [49 references]  Display  Hide  Download

https://hal.inria.fr/hal-02276945
Contributor : Damiano Lombardi <>
Submitted on : Tuesday, September 3, 2019 - 11:23:29 AM
Last modification on : Friday, April 10, 2020 - 5:10:41 PM
Document(s) archivé(s) le : Wednesday, February 5, 2020 - 6:32:43 PM

File

toSubmit_Plos.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02276945, version 1

Citation

Fabien Raphel, Tessa de Korte, Damiano Lombardi, Stefan Braam, Jean-Frédéric Gerbeau. A greedy classifier optimisation strategy to assess ion channel blocking activity and pro-arrhythmia in hiPSC-cardiomyocytes. 2019. ⟨hal-02276945⟩

Share

Metrics

Record views

297

Files downloads

655