Skip to content

Latest commit

 

History

41 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Graph Deep Learning Over a Bipartite Graph Using a Biological Pathways Prior

This is the code for the L45 project "Incorporating biological pathways information to aid deep learning on scRNA-set data".

Run the experiments

To run the experiments in the paper, execute the benchmarking.py script.

python3 benchmarking.py 

Plots can then be created using the plot_results.py script with the name of the csv file created by the benchmarking.py script.

python3 scripts/plot_results.py experiments/all_models.csv

Run different experiments

There is no command line interface, so to change the experiment setup, you need to edit the ExperimentConfig object in the benchmarking.py script directly. For example, to change the output csv location, change the ExperimentConfig.name parameter in the instantiation.

About

Graph representation learning for single-cell transcriptomics

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages