Prediction of response to anti-cancer drugs becomes robust via network integration of molecular data

In order to tackle heterogeneity of cancer samples and high data space dimensionality, we propose finding sensitive and robust biomarkers at the pathway level. Scores from network enrichment analysis transform the original space of altered genes into a lower-dimensional space of pathways, which is then correlated with phenotype variables. The analysis was first done on in vitro anti-cancer drug screen datasets and then on clinical data. In parallel, we tested a panel of state-of-the-art enrichment methods. In this comparison, our method proved superior in terms of 1) universal applicability to different data types with possibility of cross-platform integration, 2) consistency of the discovered correlates in independent drug screens, and 3) ability to explain differential survival of patients. Our new screen validated performance of the discovered multivariate models. Only the network-based method could discover markers that predict both response in vitro and patient survival given administration of the same drug.