Cancer Personalized Drug Recommendation (CPDR)

A recommendation tool of personalized drugs for patients with cancer by reversing individual disease signatures

Installation

Before library installation install required Bioconductor and CRAN packages through this code:

bioconductor_packages=c('edgeR','RUVSeq','DESeq2','limma','rhdf5')

#For R version 3.5> use BiocManager to install required bioconductor packages: 
if (length(setdiff(bioconductor_packages, rownames(installed.packages()))) > 0) {
  if (!requireNamespace("BiocManager", quietly = TRUE))
    install.packages("BiocManager")
  BiocManager::install(setdiff(bioconductor_packages, rownames(installed.packages())))
}

packages=c('magrittr','dplyr','ggplot2','doParallel','foreach','Rfast','data.table')
if (length(setdiff(packages, rownames(installed.packages()))) > 0) {
  install.packages(setdiff(packages, rownames(installed.packages())))  
}

Now you can install the development version of CPDR with:

install.packages('devtools')
devtools::install_github("AllenSpike/CPDR", build_vignettes = TRUE)

Additional data

By default, CPDR uses LINCS_978 from octad.db. To acquire reliable results, It is suggested to download the LINCS_all_processed data (6.5Gb) manually from https://zenodo.org/record/5880026#.YgZos9--uUl.

Example and user manual

A Example shows the usecase of screening effective compounds targeting individual patient with colorectal cancer. Please check the 'CPDR_user_manual.pdf' for guidance. The example data can be downloaded from the 'viginitte/images' folder.