Additional file 1 of Predicting tumor response to drugs based on gene-expression biomarkers of sensitivity learned from cancer cell lines

Additional file 1: Table S1. The 10 most predictable drugs. Table S7. TCGA tumor types and sample size (A) and summary statistics for the distribution of the number of cancer cell lines per drug across the 573 drugs for each cancer type separately (B). Table S8. Main parameters of the GA/KNN algorithm used for the analyses of all datasets. Table S9. Training and testing performances for various combinations of k and d. Table S10. Comparison of training and testing performances between two independent runs with 100 and 1000 runs, respectively