Curated chemogenomics datasets for drug sensitivity prediction

Two files are provided: 'rma_data_Dec2025.pkl' and 'sensitivity_data_Dec2025.pkl' 'rma_data_Dec2025.pkl' - rma gene expression data extracted and curated from the Genomics of Drug Sensitivity in Cancer (GDSC) repository, reporting the cosmic ID, the cell line name, the tissue site and the spesific histology type. 'sensitivity_data_Dec2025.pkl' - sensitivity data expressed as LN IC50, AUC and Z-score normalized IC50 values. Each cell line-drug interaction is annotated with the the additional following information: cell line cosmic ID, cell line name, drug id, drug name, putative drug target, pathway involved, nonstereo aromatic smile of the drug.