A live-cell image-based machine learning strategy for reducing variability in PSC differentiation systems.

The differentiation of pluripotent stem cells (PSCs) into diverse functional cell types provides a promising solution to support drug discovery, disease modeling, and regenerative medicine. However, functional cell differentiation is currently limited by the substantial line-to-line and batch-to-batch variabilities, which severely impede the progress of scientific research and the manufacturing of cell products. For instance, PSC-to-cardiomyocyte (CM) differentiation is vulnerable to inappropriate doses of CHIR99021 (CHIR) that are applied in the initial stage of mesoderm differentiation. Here, by harnessing live-cell bright-field imaging and machine learning (ML), we realize real-time cell recognition in the entire differentiation process, e.g., CMs, cardiac progenitor cells (CPCs), PSC clones, and even misdifferentiated cells. This enables non-invasive prediction of differentiation efficiency, purification of ML-recognized CMs and CPCs for reducing cell contamination, early assessment of the CHIR dose for correcting the misdifferentiation trajectory, and evaluation of initial PSC colonies for controlling the start point of differentiation, all of which provide a more invulnerable differentiation method with resistance to variability. Moreover, with the established ML models as a readout for the chemical screen, we identify a CDK8 inhibitor that can further improve the cell resistance to the overdose of CHIR. Together, this study indicates that artificial intelligence is able to guide and iteratively optimize PSC differentiation to achieve consistently high efficiency across cell lines and batches, providing a better understanding and rational modulation of the differentiation process for functional cell manufacturing in biomedical applications.