Abstract P2109: Elaborating Safety Margins To Predict Drug Proarrhythmia Using Deep Learning And Patient-derived IPSCs

Introduction: Drug-induced arrhythmias are a common cause for drug attrition during development and for restricted use or withdrawal from the market. Cell based assays to assess arrhythmia risk typically rely on the quantification of waveform features - e.g. action potential prolongation and after depolarizations - in the cells’ action potential. However, the predictive power of these approaches is limited.

Hypothesis: We hypothesize that deep learning can extract features relevant to discriminating input classes in a systematic and unbiased manner, effectively removing the need for human-defined metrics. This can lead to a new model to estimate torsadogenic risk of drugs and evaluate the influence of myopathic gene variants on drug-induced arrhythmia.

Methods: We optically recorded action potentials optically recorded for 40 drugs - characterized high, intermediate, and low or no torsadogenic risk in patients- at 8 concentrations in hiPSC-CMs from 3 healthy donors and 5 hiPSC-CMs isogenic lines carrying 5 gene variants that cause dilated and hypertrophic cardiomyopathies. We designed a convolutional neural network (CNN) to classify non-arrhythmic, arrhythmic and asystolic traces in hiPSC-CMs. Using the class probabilities measured by the CNN, we created torsadogenic and asystolic safety margins for each drug and cell line.

Results: The arrhythmic class probability computed by the CNN, provided a continuous, dose-dependent metric of the proarrhythmic risk of drugs in healthy and cardiomyopathic hiPSC-CMs. We used this metric to estimate safety margins for drug-induced arrhythmia and achieved a 0.942 AUC in classifying drugs of high-intermediate risk from safe ones. We used this approach to discern the contribution of putative genetic risk factors to arrhythmia susceptibility by comparing the risk profiles of the same drugs in healthy and isogenic hiPSC-CMs carrying causal HCM and DCM gene variants that are associated with arrhythmia in patients.

Conclusions: We conclude that deep learning algorithms can effectively evaluate proarrhythmic risk of small molecules. Moreover, they can also be used to discern heightened arrhythmic risk caused by genetic mutations that increase the propensity for drug-induced arrhythmia in patients.

Abstract P3105: Improving Cardiovascular Toxicity Of Chronic Myeloid Leukemia Therapy

Introduction: Ponatinib is one of the most cardiotoxic Tyrosine Kinase Inhibitors (TKIs), but continues to be used in clinical practice as it is the only TKI effective against the most common ABL T315I mutation in Chronic Myeloid Leukemia (CML). Long-term exposure to ponatinib increases cardiovascular events including myocardial infarction, heart failure, stroke, peripheral vascular disease and venous thrombosis. Novel therapeutics are needed to provide treatment for this common form of CML while avoiding cardiovascular side effects.

Hypothesis: Chemical reengineering can create novel TKIs effective against T315I mutant CML but with reduced cardiovascular toxicity.

Methods: Using fragment-based approach, we generated new, safer analogues of ponatinib. The anti-tumor efficacy of these analogues was tested in 2 different CML cell lines (K562 T315I and KCL22 T315I) and in CML patient samples. We assayed for myocardial toxicity by measuring contractile function in human iPSC-cardiomyocytes (hiPSC-CMs) using high-throughput functional imaging, and assayed for vascular toxicity by measuring vasculogenesis in human microvascular endothelial cells (HMVECs). Finally, we confirmed the safer cardiovascular profile and adequate anti-tumor efficacy in an in vivo xenograft mouse model of CML.

Results: The new analogues inhibited T315I BCR-ABL kinase activity similar to ponatinib and suppressed T315I mutant CML tumor growth in vitro and in vivo . Compared to ponatinib, the new compounds showed markedly decreased adverse effects on contractility of hiPSC-CMs and vasculogenesis in HMVECs in vitro . The therapeutic window was increased in vivo , leading to regression of human T315I mutant CML xenografts comparable to ponatinib but without increased levels of cardiac troponin. Additionally, we identified multiple kinases, including FGFR1, that were inhibited by ponatinib but not the analogues, suggesting that there is a specific set of kinases responsible for ponatinib toxicity.

Conclusions: This study demonstrates that chemical reengineering can generate novel, cardiovascular-safe TKIs that retain effective therapeutic properties against CML carrying ABL T315I mutation, but that exhibit minimal cardiovascular toxicity compared to ponatinib.