Accurately build cell trajectories in time course single cell RNA-Seq data are crucial for understanding cellular development dynamics. However, most of the available methods only apply for static single cell RNA-seq data. They thus fail to identify the essential cell development trend across time. Recently, a few existing analysis frameworks focus on individual cell development trajectories at multiple time points. Those methods are based on low-dimensional space computed by the dimension reduction technics. Reducing the dimensionality will lose the dynamics pathway expression patterns over time. In this talk, I will present a novel machine learning method called cell optimal transport (CellOT) to identify individual cell development behavior in time course single cell RNA-Seq data. The CellOT builds individual cell trajectories and utilizes the gene features on high-dimensional space. We further cluster the gene expressions within a cell trajectory to reflect the correct pathway expression patterns over time. The proposed method CellOT is powerful and efficient in constructing cell trajectories and detecting biologically pathway patterns in time course single cell RNA-Seq data.