The best treatment for every patient: New algorithms to predict treatment benefit in cancer using genomics and transcriptomics

Many cancer drugs only benefit a subset of the patients that receive them. Because these drugs are often associated with serious side effects, it is very important to be able to predict who will benefit and who will not. This thesis presents several algorithms that can build models that can predict whether a patient will benefit more from a drug of interest than an alternative treatment. We show these algorithms can be used for various types of cancer and different datatypes