Predicting the response of a patient to a therapy is a major goal in modern oncology and a requisite to develop a personalised treatment. To model the heterogeneous response of patients to treatment, high-throughput screenings of therapeutic compounds against a panel of heterogeneous cancer cell lines have been performed. These studies have unveiled multiple relationships between genomic alterations and drug responses. Various computational approaches have been proposed to predict sensitivity based on genomic features, while others have used the chemical properties of the drugs to ascertain their effect. In an effort to integrate these complementary approaches, we have developed machine learning models to predict the response of cancer cell lines to drug treatment based on both the genomic features of the cell lines and the chemical properties of the considered drugs. Genomic data is integrated with various sources of prior knowledge whenever possible. These computational models can be used to optimise the experimental design of drug-cell screenings as well as to screen in silico novel compounds, thus identifying novel new drug repositioning opportunities. They also point at molecular processes involved in resistance mechanisms, thus proposing systems to analyse in a mechanistic fashion. These mechanisms can then be characterised in detail using pathway models. Specifically, we build logic models based on phosphoproteomic measurements upon ligand stimulation and perturbation with drugs, and use these models to dissect biochemically the mechanism of action of targeted therapeutics, and understand the molecular basis of drug resistance.