|
Activity Number:
|
308
- Statistical Methods for Studying Spatial Transcriptomics, Tissue Heterogeneity, and Pleiotropy
|
|
Type:
|
Topic-Contributed
|
|
Date/Time:
|
Wednesday, August 11, 2021 : 3:30 PM to 5:20 PM
|
|
Sponsor:
|
Section on Statistics in Genomics and Genetics
|
|
Abstract #317620
|
|
|
Title:
|
Unsupervised Gene Selection for Predicting Cell Spatial Positions in the Drosophila Embryo
|
|
Author(s):
|
Yang Chen and Disheng Mao and Yuping Zhang and Zhengqing Ouyang*
|
|
Companies:
|
University of Massachusetts, Amherst and University of Connecticut and University of Connecticut and University of Massachusetts, Amherst
|
|
Keywords:
|
scRNA-seq;
spatial positioin;
gene selection;
unsupervised learning;
DREAM Challenge
|
|
Abstract:
|
Analyzing single cell RNA-seq data is important for deciphering the spatial relationships, expression patterns, and developmental processes of cells. Combining in situ hybridization-based gene expression atlas images, some works have successfully recovered spatial locations of cells in zebrafish and Drosophila embryos. Here, we describe a highly ranked method in the DREAM Single Cell Transcriptomics Challenge for predicting cell positions in the Drosophila embryo. The method uses unsupervised feature extraction for selecting a small number of driver genes and then uses them to predict gene expression and spatial position of each individual cell. Our method is evaluated on a benchmark dataset based on genes from the reference atlas of the Berkeley Drosophila Transcription Network Project. The results suggest that our method is effective on selecting genes for reconstructing cell spatial positions and gene expression patterns in tissues.
|
Authors who are presenting talks have a * after their name.
