Table 1 Summary of data sets used in the study.

From: Multitask learning improves prediction of cancer drug sensitivity

  CCLE CTD2 NCI60
Feature matrix size (N×P) 436 × 43971 228 × 43971 59 × 18134
Features Expression, copy number variation and mutation Expression, copy number variation and mutation Expression
Response matrix size (N×T) 436 × 24 228 × 354 59 × 255
Response measurements Activity area Area under the concentration-response curve −LOG10(GI50)