Journal: bioRxiv

Article Title: Classifying drugs by their arrhythmogenic risk using machine learning

doi: 10.1101/545863

Figure Lengend Snippet: We characterize calcium transients in ventricular cardiomyocytes in response to drugs, both computationally (top) and experimentally (bottom) and identify the ion channels that most likely generate early afterdepolarizations (left). We then screen the concentration space of the two most relevant channels and identify the classification boundary between the arrhythmic and non-arrhythmic domains using high performance computing and machine learning (center). We validate our approach using electrocardiograms, both computationally and experimentally, in whole heart simulations and isolated Langendorff perfused hearts (right). We demonstrate the potential of our new classifier by risk stratifying 23 common drugs and comparing the result against the reported risk categories of these compounds.

Article Snippet: We excised the hearts from anesthetized rats (2.5% isoflurane in 95% oxygen and 5% carbon dioxide), immediately cannulated the aorta, connected it to a constant pressure perfusion Langendorff system (Harvard Apparatus, Massachusetts) with Krebs solution (118mM NaCl, 4.75mM KCl, 25mM NaHCO 3 , 1.2mM KH 2 PO 4 , 1.2mM MgSO 4 , 1.5mM CaCl 2 , 11mM glucose, and 2mM Pyruvate), warmed to 37° C, and bubbled with 95% oxygen and 5% carbon dioxide.

Techniques: Concentration Assay, Isolation