Pharmacogenomics Datasets for Cancer Cell Lines from CellMiner Cross-Database (CellMinerCDB)

If you use this data, please cite: Luna A, Elloumi F, Varma S et al. NAR. 2021. PMID: 33196823

Cell line pharmacogenomics datasets for cancer biology and machine learning studies. The datasets are compatible with rcellminer and CellMinerCDB (see publications for details) and data can be extracted for use with Python-based projects.

An example for extracting data from the rcellminer and CellMinerCDB compatible packages: 

# INSTALL ----
if (!require("BiocManager", quietly = TRUE))
    install.packages("BiocManager")

BiocManager::install("rcellminer")

# Replace path_to_file with the data package filename
install.packages(path_to_file, repos = NULL, type="source")

# GET DATA ----
## Replace nciSarcomaData with name of dataset through code 
library(nciSarcomaData)

## DRUG DATA ----
drugAct <- exprs(getAct(nciSarcomaData::drugData))
drugAnnot <- getFeatureAnnot(nciSarcomaData::drugData)[["drug"]]

## MOLECULAR DATA ----
### List available datasets
names(getAllFeatureData(nciSarcomaData::molData))

### Extract data and annotations
expData <- exprs(nciSarcomaData::molData[["exp"]])
mirData <- exprs(nciSarcomaData::molData[["mir"]])

expAnnot <- getFeatureAnnot(nciSarcomaData::molData)[["exp"]]
mirAnnot <- getFeatureAnnot(nciSarcomaData::molData)[["mir"]]

## SAMPLE DATA ----
sampleAnnot <- getSampleData(nciSarcomaData::molData)