Machine learning identifies abnormal Ca2+transients in human induced pluripotent stem cell-derived cardiomyocytes

• Type of Material: Article
• Authors: Hyun Hwang, Emory University; Rui Liu, Emory University; Joshua Maxwell, Emory University; Jingjing Yang, Emory University; Chunhui Xu, Emory University
• Language: English
• Date: 2020-10-12
• Publisher: Nature Publishing Group
• Publication Version: Final Published Version
• Copyright Statement: © The Author(s) 2020
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1038/s41598-020-73801-x
• Title of Journal or Parent Work: Scientific Reports
• Volume: 10
• Grant/Funding Information: This study was supported by the Center for Pediatric Technology at Emory University and Georgia Institute of Technology; Imagine, Innovate and Impact (I3) Funds from the Emory School of Medicine and through the Georgia CTSA NIH award [UL1-TR002378]; Biolocity at Emory University & Georgia Institute of Technology; National Science Foundation-Center for the Advancement of Science in Space [CBET 1926387]; and the National Institutes of Health [R21AA025723 and R01HL136345].
• Keywords: Induced pluripotent stem cells; Machine learning
• Research Categories: Biology, Cell

Abstract

Human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) provide an excellent platform for potential clinical and research applications. Identifying abnormal Ca2+ transients is crucial for evaluating cardiomyocyte function that requires labor-intensive manual effort. Therefore, we develop an analytical pipeline for automatic assessment of Ca2+ transient abnormality, by employing advanced machine learning methods together with an Analytical Algorithm. First, we adapt an existing Analytical Algorithm to identify Ca2+ transient peaks and determine peak abnormality based on quantified peak characteristics. Second, we train a peak-level Support Vector Machine (SVM) classifier by using human-expert assessment of peak abnormality as outcome and profiled peak variables as predictive features. Third, we train another cell-level SVM classifier by using human-expert assessment of cell abnormality as outcome and quantified cell-level variables as predictive features. This cell-level SVM classifier can be used to assess additional Ca2+ transient signals. By applying this pipeline to our Ca2+ transient data, we trained a cell-level SVM classifier using 200 cells as training data, then tested its accuracy in an independent dataset of 54 cells. As a result, we obtained 88% training accuracy and 87% test accuracy. Further, we provide a free R package to implement our pipeline for high-throughput CM Ca2+ analysis.