On the Separation of Normal and Abnormal Stem Cell-Derived Cardiomyocytes' Calcium Transient Signals

On the Separation of Normal and Abnormal Stem Cell-Derived Cardiomyocytes' Calcium Transient Signals

Martti Juhola (Tampere University, Tampere, Finland), Henry Joutsijoki (Tampere University, Tampere, Finland), Kirsi Varpa (Tampere University, Tampere, Finland), Kirsi Penttinen (Tampere University, Tampere, Finland) and Katriina Aalto-Setälä (Tampere University, Tampere, Finland)
DOI: 10.4018/IJEACH.2019070102

Abstract

A data set of 438 calcium transient signals measured from induced pluripotent stem cell derived cardiomyocytes was collected to analyze and separate abnormal signals corresponding to aberrant cardiomyocytes from normal signals corresponding to normally developed cells. After the calcium transient peak detection, the authors computed peak variable values. Each signal peak was determined to be either normal or abnormal. The peak variables were used for machine learning algorithms to classify entire calcium transient signals into normal or abnormal types. The authors evaluated the classification power of 10 variables to separate normal signals from abnormal ones. This article obtained classification accuracies of up to 85-95%, around 5% better than the results in the preliminary research. The correctness of the classification of the signals was inferred either by a biotechnology expert or by an algorithm. The new results are promising for the continuity of this area of study in identifying aberrant calcium transients.
Article Preview
Top

Introduction

Calcium cycling refers to the release and reuptake of intracellular calcium, and it is the central regulator of cardiac contraction and relaxation. Cardiac contractility is determined by the amplitude and kinetics of calcium cycling and therefore it has a great impact on the functionality of cardiomyocytes. It is initiated by action potential, and leads to the excitation-contraction coupling of the cardiomyocytes (Marks, 2013). Aberrant calcium cycling due to cardiac diseases or different drugs can lead to abnormal calcium transients, which can cause impaired contractility and fatal cardiac arrhythmias. It is therefore important to understand and analyze cellular calcium cycling.

Calcium imaging of cardiomyocytes is a method for monitoring calcium cycling activity in vitro. In recent years, the calcium cycling functionality of cardiomyocytes has been studied widely with induced pluripotent stem cell (iPSC) (Marks, 2013) -derived cardiomyocytes. Typically, the cells are generated from patients carrying different genetic cardiac disorders, and they offer a promising platform for studying the pathophysiology of various disorders and drug responses in human cells. These previous studies have offered new insights into different cardiac diseases by revealing substantial defects and abnormalities in the calcium cycling of these cardiomyocytes, reflecting the cardiac phenotype observed in patients (Takahashi et al., 2007; Penttinen et al., 2015a; Fatima et al., 2011; Jung et al., 2012; Kujala et al., 2012; Lan et al., 2013; Kiviaho et al., 2015; Ojala et al., 2016; Penttinen et al., 2015b). Recently studied diseases revealing calcium cycling abnormalities include catecholaminergic polymorphic ventricular tachycardia (CPVT), an exercise-induced malignant arrhythmogenic disorder (Penttinen et al., 2015a; Kujala et al., 2012), long QT syndrome 1 (LQT1), an electric disorder of the heart that predisposes patients to arrhythmias and sudden cardiac death (Kiviaho et al., 2015), and hypertrophic cardiac myopathy (HCM), a disorder that affects the structure of heart muscle tissue leading to arrhythmias and progressive heart failure (Ojala et al., 2016).

To accelerate the development, application, research, and innovations of stem cell-derived cardiomyocytes, we study the automatic separation of CPVT-, LQT1-, HCM-specific and control (WT) iPSC-derived cardiomyocytes into normal and abnormal groupings to distinguish aberrant cells from normally developed cells. This can be implemented by separating individual cells according to their calcium cycling. Thus far, this separation has been performed manually by biotechnologists or medical laboratory personnel. To gradually enable progress from theoretical research to medical practice, appropriate software based on signal analysis, pattern recognition, and machine learning algorithms is needed to automatize some of the routine-like but very demanding work of biotechnological experts.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 2: 2 Issues (2020): Forthcoming, Available for Pre-Order
Volume 1: 2 Issues (2019)
View Complete Journal Contents Listing