Abstract
Proper chromosome alignment at the spindle equator is a prerequisite for accurate chromosome segregation during cell division. However, the chromosome movement trajectories prior to alignment remain elusive. Here, we established a 4D imaging analysis framework to visualize chromosome dynamics and develop a deep-learning model for chromosome movement trajectory classification. Our data reveal that chromosomes follow at least three distinct movement trajectories (retracing, congressing, and quasi-static) to arrive at the equator. We further revealed the distinct roles of multiple kinesin superfamily proteins (KIFs) in coordinating and maintaining the chromosome movement trajectories. In summary, we have presented an efficient and unbiased approach to studying chromosome dynamics during cell division, thereby uncovering a variety of chromosome movement trajectories that precede alignment.