A Causal Discovery Approach to Streamline Ionic Currents Selection to Improve Drug-Induced TdP Risk Assessment.

Causality is of paramount importance in bio-medical data analysis: assessing the causal relationships between the observed variables allows to improve our understanding of the tackled condition and better support decisionmaking. Torsade de Pointes (TdP) is a serious druginduced cardiac side effect which can lead to sudden death. TdP is related to abnormal repolarizations in single cells, and the minimum set of ion channels needed to correctly assess TdP risk is still an open question. In this work, we propose to apply the causal discovery method ICA-Linear Non-Gaussian Acyclic Model (ICA-LiNGAM) to uncover the relations across the 7 ion channels identified by the Comprehensive in vitro Pro-arrhythmia Assay (CiPA) initiative as potentially related to the induction of TdP: I Kr, I Na , I Na , I cal , I kl , I Ks and I to . We consider 109 drugs of known torsadogenic risk listed by CredibleMeds. We identify I NaL and.I CaL as the ones that directly affect TdPrisk assessment, and suggest that I Na perturbations could potentially have a high impact on pro-arrhythmic risk induction. Our causality-based results were further confirmed by independently performing binary drug risk classification, which shows that the combination of the 3 selected ionic currents maximizes the classification accuracy and specificity, outperforming state-of-the-art approaches based on alternative ion channel combinations.