Skip to content

Leveraging genes known to be associated with gene of interest for target gene expression

Notifications You must be signed in to change notification settings

aarthivenkat/Gene-Network-Graphs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Refine gene interaction network using graph attention networks

Aarthi Venkat, Mamie Wang, Sabrina Su, Jeremy Gygi

Each cell represents a graph of genes. The task we want to perform is node prediction for each cell - predicting the gene expression value of a gene that does not have a value due to sc-RNASeq dropout. Features are expressions of other genes for each cell, where the set of other genes can be defined as the first-degree neighbors in the gene network graph

As an attempt to refine networks for data-specific analysis, we aim to leverage Graph Attention Network architecture to perform gene expression imputation on single-cell RNA-sequencing data from a single cell type Cd8, which will in turn elucidate refined functional networks within Cd8 T cells in our datasets.

About

Leveraging genes known to be associated with gene of interest for target gene expression

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages