Key result
A deep learning multitask network successfully translated simulated iPSC-CM action potentials into adult-CM action potentials with less than 0.003 mean-squared error and classified drug effects with approximately 90% accuracy.
Why the study?
The study was designed to address the low throughput, high variability, and immature phenotype of the induced pluripotent stem cell-derived cardiomyocyte platform.
A novel deep learning multitask network successfully translates immature iPSC-CM action potentials to adult cardiomyocyte phenotypes and classifies drug effects, overcoming a major limitation of the iPSC-CM platform.
New DL network classifies iPSC-CM drug responses; leaves open whether it improves throughput or maturity for patient-specific studies.
The development of induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) has been a critical in vitro advance in the study of patient-specific physiology, pathophysiology and pharmacology. We designed a new deep learning multitask network approach intended to address the low throughput, high variability and immature phenotype of the iPSC-CM platform. It was trained using simulated action potential (AP) data and applied to classify cells into the drug-free and drugged categories and to predict the impact of electrophysiological perturbation across the continuum of aging from the immature iPSC-CMs to the adult ventricular myocytes. The phase of the AP extremely sensitive to perturbation due to a steep rise of the membrane resistance was found to contain the key information required for successful network multitasking. We also demonstrated successful translation of both experimental and simulated iPSC-CM AP data validating our network by prediction of experimental drug-induced effects on adult cardiomyocyte APs by the latter.
No takes yet. Share an insight, caveat, or question.
Aghasafari et al. (2020) studied Cardiac electrophysiology (n=758). Deep learning multitask network was evaluated on Mean squared error of translation from iPSC-CM to adult-CM action potentials. A deep learning multitask network successfully translated simulated iPSC-CM action potentials into adult-CM action potentials with less than 0.003 mean-squared error and classified drug effects with approximately 90% accuracy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: