Skip to content

FraBer95/MultiOmicPDA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MultiOmicPDA

New: Check our last work on genetic mutation predictions in PDA with pathomic and transcriptomic data! -> https://github.com/FraBer95/MultimodalMutationsPDAC

This is the repository of the "A time-dependent explainable radiomic analysis from the multi-omic cohort of CPTAC-Pancreatic Ductal Adenocarcinoma" paper.

The code is written in R and Python and it is composed by the following parts:

  1. data folder, that should contains all data in a csv format and the pyradiomics configuration .yaml file in
  2. python_scripts folder, containing all pre-processing operations for merging different data, extraction and validation of the radiomic signature
  3. R_scripts folder, containing the feature selection in UV, feature dicotomizing and survival models training and test

Preprocessing part: Data Reading and formatting, dropping of non relevant features, categorization, statistical analysis and feature selection. Analysis part: Survival Curves, Models Training and Validation, XAI(t). The python libraries requested are:

-pandas, torch, pycox, reticulate, numpy, seaborn, scipy, statsmodels, scikit-learn

The R libraries requested are:

-survival, surviminer, survex, randomForestSRC, gbm, survivalsvm, ggsurvfit, ggplot2, pec, caret, SurvMetrics, mlr3proba, mlr3extralearners, mlr3pipelines, survivalmodels, reticulate

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published