Abstract

In bladder cancer (BLCA) there are, to date, no reliable diagnostics available to predict the potential benefit of a therapeutic approach. The extraordinarily high molecular heterogeneity of BLCA might explain its wide range of therapy responses to empiric treatments. To better stratify patients for treatment response, we present a highly automated workflow for in-silico drug response prediction based on a tumors individual multi-omic profile. Within the TCGA-BLCA cohort, the algorithm identified a panel of 21 genes and 72 drugs, that suggested personalized treatment for 94,7% of patients - including five genes not yet reported as biomarkers for clinical testing in BLCA. The automated predictions were complemented by manually curated data, thus allowing for accurate sensitivity- or resistance-directed drug response predictions. Manual curation revealed pitfalls of current, and potential of future drug-gene interaction databases. Functional testing in patient derived models and/or clinical trials are next steps to validate our in-silico drug predictions.