An Appearance Data-Driven Model Visualizes Cell State and Predicts Mesenchymal Stem Cell Regenerative Capacity.

Mesenchymal stem cells (MSCs) are widely used in treating various diseases. However, lack of a reliable evaluation approach to characterize the potency of MSCs has dampened their clinical applications. Here, a function-oriented mathematical model is established to evaluate and predict the regenerative capacity (RC) of MSCs. Processed by exhaustive testing, the model excavates four optimal fitted indices, including nucleus roundness, nucleus/cytoplasm ratio, side-scatter height, and ERK1/2 from the given index combinations. Notably, three of them except ERK1/2 are cell appearance-associated features. The predictive power of the model is validated via screening experiments of these indices by predicting the RC of newly enrolled and chemical inhibitor-treated MSCs. Further RNA-sequencing analysis reveals that cell appearance-based indices may serve as major indicators to visualize the results of integration-weighted signals in and out of cells and reflect MSC stemness. In general, this study proposes an appearance data-driven predictive model for the RC and stemness of MSCs.