Identification of an epigenetic signature in human induced pluripotent stem cells using a linear machine learning model
- PDF / 2,731,306 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 87 Downloads / 143 Views
RESEARCH ARTICLE
Identification of an epigenetic signature in human induced pluripotent stem cells using a linear machine learning model Koichiro Nishino1,2 · Ken Takasawa1 · Kohji Okamura3 · Yoshikazu Arai1 · Asato Sekiya1 · Hidenori Akutsu4 · Akihiro Umezawa4 Received: 24 June 2020 / Accepted: 2 October 2020 © The Author(s) 2020
Abstract The use of human induced pluripotent stem cells (iPSCs), used as an alternative to human embryonic stem cells (ESCs), is a potential solution to challenges, such as immune rejection, and does not involve the ethical issues concerning the use of ESCs in regenerative medicine, thereby enabling developments in biological research. However, comparative analyses from previous studies have not indicated any specific feature that distinguishes iPSCs from ESCs. Therefore, in this study, we established a linear classification-based learning model to distinguish among ESCs, iPSCs, embryonal carcinoma cells (ECCs), and somatic cells on the basis of their DNA methylation profiles. The highest accuracy achieved by the learned models in identifying the cell type was 94.23%. In addition, the epigenetic signature of iPSCs, which is distinct from that of ESCs, was identified by component analysis of the learned models. The iPSC-specific regions with methylation fluctuations were abundant on chromosomes 7, 8, 12, and 22. The method developed in this study can be utilized with comprehensive data and widely applied to many aspects of molecular biology research. Keywords Machine learning · Human iPSCs · Human ESCs · DNA methylation · Epigenetic signature of hiPSCs
Introduction The application of human induced pluripotent stem cells (iPSCs) in medicine requires prior assessment of the cells with respect to quality, including identity, equivalence, and safety. For evaluation of the iPSCs, comprehensive Electronic supplementary material The online version of this article (https://doi.org/10.1007/s13577-020-00446-3) contains supplementary material, which is available to authorized users. * Koichiro Nishino [email protected]‑u.ac.jp 1
Laboratory of Veterinary Biochemistry and Molecular Biology, Graduate School of Medicine and Veterinary Medicine/Faculty of Agriculture, University of Miyazaki, Miyazaki, Japan
2
Center for Animal Disease Control, University of Miyazaki, Miyazaki, Japan
3
Department of Systems BioMedicine, National Research Institute for Child Health and Development, Tokyo, Japan
4
Department of Reproductive Biology, Center for Regenerative Medicine, National Research Institute for Child Health and Development, Tokyo, Japan
molecular analysis of characteristics, such as DNA methylation, rather than tests based on a few marker genes, is considered to be more useful. DNA methylation is an epigenetic modification with important roles in normal development and differentiation [1–6]. DNA methylation profiles vary depending on tissue types and cell lineage [5, 7]; therefore, the DNA methylation profile of a cell can be useful for the identification and validation of it
Data Loading...
