Fluorescence-based live-cell reporter assays provide a powerful platform for quantitatively investigating complex cell-cycle signaling dynamics and cellular fate transitions with high spatiotemporal resolution. By capturing real-time data, these assays offer unparalleled insights into cellular processes, enabling the visualization of key events such as cell division, motility, and signal transduction. Integrating live-cell imaging with advanced image analysis methods allows for precise quantification of cell behaviors over extended periods, overcoming limitations imposed by endpoint assays that obscure potentially critical information about the cellular process of interest. For this reason, our lab and many others seek to establish turnkey methods for collecting robust live-cell imaging data over extended periods and customizable, machine learning-based analytical tools for robustly and rapidly quantifying these data in order to facilitate the discovery process. Here, we employed time-lapse microscopy to directly visualize cell-cycle dynamics in individual living cells using fluorescence-based reporters, including the fluorescence ubiquitination cell-cycle indicator (FUCCI) and cyclin-dependent kinase translocation reporters. Using this approach, we automated real-time monitoring of the behaviors of thousands of individual cells across multiple days and multiple conditions. We quantified the data obtained from these investigations using deep learning models to assess the accuracy and predictive power of automated quantitative analyses. Our goal is to further develop this pipeline to facilitate real time investigations of cell-cycle dynamics to enable faster, more accurate disease characterization.
Kilic et al. (Sun,) studied this question.