Machine learning prediction of cancer cell sensitivity to drugs based on genomic and chemical properties

Predicting the response of a specific cancer to a therapy is a major goal in modern oncology that should ultimately lead to a personalised treatment. High-throughput screenings of potentially active compounds against a panel of genomically heterogeneous cancer cell lines 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 orthogonal but complementary approaches, we developed machine learning models to predict the response of cancer cell lines to drug treatment, quantified through IC50 values, based on both the genomic features of the cell lines and the chemical properties of the considered drugs. Models predicted IC50 values in a 8-fold cross-validation and an independent blind test with Pearson correlations of 0.85 and 0.79 respectively. Furthermore, models were able to predict with comparable accuracy (Pearson correlation 0.79) IC50s of cell lines from a tissue not used in the training stage. As they stand, our in silico models can be used to optimise the experimental design of drug-cell screenings by accurately predicting a large proportion of missing IC50 values rather than experimentally measure them. The implications of our results go beyond virtual drug screening design: thousands of drugs could be probed in silico to systematically test their potential efficacy as anti-tumour agents based on their structure, thus providing a computational framework for identifying new drug repositioning opportunities.