Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 142 - Recent Development in Computational Biology and Bioinformatics
Type: Invited
Date/Time: Tuesday, August 10, 2021 : 10:00 AM to 11:50 AM
Sponsor: Section on Statistics in Genomics and Genetics
Abstract #316763
Title: Cell-to-Cell Trajectories and Pathway Construction for Time-Course Single Cell RNA-Seq Data
Author(s): Ping Ma*
Companies: University of Georgia
Keywords: Optimal Transport; Cell Trajectory; Time Course Data

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.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program