jupytext

kernelspec

formats

text_representation

md:myst

extension	format_name	format_version	jupytext_version
.md	myst	0.13	1.11.5

display_name	language	name
Python 3	python	python3

Processing in R

Step 1 - Preprocessing

Create a folder called for the dataset e.g. TCGA, and within this folder create a folder for each project.

Run the R script Preprocessing.R specifying the phenotypical trait and project, checking to ensure the paths point to the created data folder.

Save each modalities processed folder with naming convention modality_processed.RData.

The options are
BRCA :
project = 'BRCA'
trait = 'paper_paper_BRCA_Subtype_PAM50'

LGG :
project = 'LGG'
trait = 'paper_Grade'

KIPAN :
project = 'KIPAN'
trait = 'subtype'

Point the knn_graph_generation.R to the project folder containing the processed modalities.

Create a folder called raw. This is the folder from which MOGDx will be run.

Use the R script knn_graph_generation.R specifying the phenotypical trait, project and modalities downloaded in the for loop.

Create a folder called Network outside data
Copy each modalities modality_graph.csv to this folder \

Specify the modalities of interest in the list mod_list

Point the SNF script to the new Network folder

Run the R script SNF.R