A quantitative system for discriminating induced pluripotent stem cells, embryonic stem cells and somatic cells

TL;DR

This paper presents a robust, quantitative DNA methylation-based system using machine learning models to accurately discriminate between induced pluripotent stem cells, embryonic stem cells, and somatic cells across various platforms and subtypes.

Contribution

The study introduces a novel, unbiased DNA methylation biomarker-based framework combined with neural networks and SVMs for precise cell type discrimination.

Findings

Achieves nearly 100% accuracy in distinguishing SCs from ESCs and iPSCs with minimal biomarkers.

Discriminates ESCs from iPSCs with 95% accuracy using around 100 biomarkers.

Effective across different data platforms and cell subtypes, including gender and developmental stages.

Abstract

Embryonic stem cells (ESCs) and induced pluripotent stem cells (iPSCs) derived from somatic cells (SCs) provide promising resources for regenerative medicine and medical research, leading to a daily identification of new cell lines. However, an efficient system to discriminate the cell lines is lacking. Here, we developed a quantitative system to discriminate the three cell types, iPSCs, ESCs and SCs. The system contains DNA-methylation biomarkers and mathematical models, including an artificial neural network and support vector machines. All biomarkers were unbiasedly selected by calculating an eigengene score derived from analysis of genome-wide DNA methylations. With 30 biomarkers, or even with as few as 3 top biomarkers, this system can discriminate SCs from ESCs and iPSCs with almost 100% accuracy, and with approximately 100 biomarkers, the system can distinguish ESCs from iPSCs with an accuracy of 95%. This robust system performs precisely with raw data without normalization as well as with converted data in which the continuous methylation levels are accounted. Strikingly, this system can even accurately predict new samples generated from different microarray platforms and the next-generation sequencing. The subtypes of cells, such as female and male iPSCs and fetal and adult SCs, can also be discriminated with this system. Thus, this quantitative system works as a novel general and accurate framework for discriminating the three cell types, iPSCs, ESCs, and SCs and this strategy supports the notion that DNA-methylation generally varies among the three cell types.