Automated grouping of action potentials of human embryonic stem cell-derived cardiomyocytes

Giann Gorospe, Renjun Zhu, Michal A. Millrod, Elias Zambidis, Leslie Tung, Rene Vidal

Research output: Contribution to journalArticle

Abstract

Methods for obtaining cardiomyocytes from human embryonic stem cells (hESCs) are improving at a significant rate. However, the characterization of these cardiomyocytes (CMs) 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 CM 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 CMs 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. While some of the nine cell clusters in the dataset are presented with just one phenotype, the majority of the cell clusters are 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 CMs from an electrophysiological perspective.

Original languageEnglish (US)
Article number6766211
Pages (from-to)2389-2395
Number of pages7
JournalIEEE Transactions on Biomedical Engineering
Volume61
Issue number9
DOIs
StatePublished - 2014

Fingerprint

Stem cells
Purification
Learning systems
Signal processing

Keywords

  • Cardiac electrophysiology
  • cardiomyocyte (CM)
  • spectral grouping
  • stem cells.

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Automated grouping of action potentials of human embryonic stem cell-derived cardiomyocytes. / Gorospe, Giann; Zhu, Renjun; Millrod, Michal A.; Zambidis, Elias; Tung, Leslie; Vidal, Rene.

In: IEEE Transactions on Biomedical Engineering, Vol. 61, No. 9, 6766211, 2014, p. 2389-2395.

Research output: Contribution to journalArticle

Gorospe, Giann ; Zhu, Renjun ; Millrod, Michal A. ; Zambidis, Elias ; Tung, Leslie ; Vidal, Rene. / Automated grouping of action potentials of human embryonic stem cell-derived cardiomyocytes. In: IEEE Transactions on Biomedical Engineering. 2014 ; Vol. 61, No. 9. pp. 2389-2395.
@article{47e517ef180e418e8221b13eaad41150,
title = "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 (CMs) 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 CM 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 CMs 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. While some of the nine cell clusters in the dataset are presented with just one phenotype, the majority of the cell clusters are 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 CMs from an electrophysiological perspective.",
keywords = "Cardiac electrophysiology, cardiomyocyte (CM), spectral grouping, stem cells.",
author = "Giann Gorospe and Renjun Zhu and Millrod, {Michal A.} and Elias Zambidis and Leslie Tung and Rene Vidal",
year = "2014",
doi = "10.1109/TBME.2014.2311387",
language = "English (US)",
volume = "61",
pages = "2389--2395",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "9",

}

TY - JOUR

T1 - Automated grouping of action potentials of human embryonic stem cell-derived cardiomyocytes

AU - Gorospe, Giann

AU - Zhu, Renjun

AU - Millrod, Michal A.

AU - Zambidis, Elias

AU - Tung, Leslie

AU - Vidal, Rene

PY - 2014

Y1 - 2014

N2 - Methods for obtaining cardiomyocytes from human embryonic stem cells (hESCs) are improving at a significant rate. However, the characterization of these cardiomyocytes (CMs) 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 CM 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 CMs 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. While some of the nine cell clusters in the dataset are presented with just one phenotype, the majority of the cell clusters are 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 CMs from an electrophysiological perspective.

AB - Methods for obtaining cardiomyocytes from human embryonic stem cells (hESCs) are improving at a significant rate. However, the characterization of these cardiomyocytes (CMs) 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 CM 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 CMs 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. While some of the nine cell clusters in the dataset are presented with just one phenotype, the majority of the cell clusters are 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 CMs from an electrophysiological perspective.

KW - Cardiac electrophysiology

KW - cardiomyocyte (CM)

KW - spectral grouping

KW - stem cells.

UR - http://www.scopus.com/inward/record.url?scp=84906545742&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906545742&partnerID=8YFLogxK

U2 - 10.1109/TBME.2014.2311387

DO - 10.1109/TBME.2014.2311387

M3 - Article

C2 - 25148658

AN - SCOPUS:84906545742

VL - 61

SP - 2389

EP - 2395

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 9

M1 - 6766211

ER -