Automated Grouping of Action Potentials of Human Embryonic Stem Cell-Derived Cardiomyocytes

Abstract

Methods for obtaining cardiomyocytes from human embryonic stem cells (hESCs) are improving at a significant rate. However, the characterization of these cardiomyocytes is evolving at a relatively slower rate. In particular, there is still uncertainty in classifying the phenotype (ventricular-like, atrial-like, nodal-like, etc.) of an hESC-derived cardiomyocyte (hESC-CM). While previous studies identified the phenotype of a cardiomyocyte based on electrophysiological features of its action potential, the criteria for classification were typically subjective and differed across studies. In this paper, we use techniques from signal processing and machine learning to develop an automated approach to discriminate the electrophysiological differences between hESC-CMs. Specifically, we propose a spectral grouping-based algorithm to separate a population of cardiomyocytes into distinct groups based on the similarity of their action potential shapes. We applied this method to a dataset of optical maps of cardiac cell clusters dissected from human embryoid bodies (hEBs). While some of the 9 cell clusters in the dataset presented with just one phenotype, the majority of the cell clusters presented with multiple phenotypes. The proposed algorithm is generally applicable to other action potential datasets and could prove useful in investigating the purification of specific types of cardiomyocytes from an electrophysiological perspective.

Variability of Action Potentials Within and Among Cardiac Cell Clusters Derived from Human Embryonic Stem Cells

“…Analysis of the entire data set of APs (recorded across 32 hEBs) by an automated machine learning algorithm 47 divided the APs into different groups based on their shape and similarity to one another. This method also produced the most distinctive differences in AP waveforms between groups ( Fig.…”

Concise Review: Criteria for Chamber-Specific Categorization of Human Cardiac Myocytes Derived from Pluripotent Stem Cells

“…PSC‐CMs themselves also pose a challenge to classification on this basis. While numerous reports have detailed the presence of nodal‐like, atrial‐like, and ventricular‐like APs in unguided differentiations of iPSC‐CMs , recent work by our group and others has shown that the AP morphologies of iPSC‐CMs do not robustly discriminate between multiple subpopulations of cells . While the question of whether different cell populations are present remains to be answered, if it is the case then they are not sufficiently distinct to be classified on the basis of their AP properties.…”

The Fallacy of Assigning Chamber Specificity to iPSC Cardiac Myocytes from Action Potential Morphology

“…We were not the first to consider this weakness of work to date, with Gorospe et al (6) turning to computational methods to perform more quantitative comparisons of optically recorded AP waveforms with typical chamberlike morphologies, albeit in embryonic stem cell-derived cardiomyocytes. Tellingly, while this approach was able to distinguish a number of discrete AP phenotypes, this varied from just one to four or more distinct sets of morphologies depending on how the data was interpreted.…”