Comprehensive cancer cell line drug response prediction by machine learning based computational modelling

Assessing the best treatment option specifically for each patient is the main goal of precision medicine. The patients with the same diagnosis may display varying sensitivity to the applied treatment due to genetic heterogeneity, especially in cancers. With the aim of predicting drug response in advance, to save valuable time and prevent the administration of ineffective drugs, computational approaches that utilize genetic features of patients have been developed. In this thesis study, DeepResponse-RF is proposed, which is a machine learning-based system that predicts drug responses (sensitivity) of cancer cells. DeepResponse-RF utilizes gene expression, mutation, copy number variation and methylation profiles of different cancer cell-lines (each representing an individual tumor) obtained from large-scale profiling/screening projects, together with drugs' molecular features at the input level and process them via the random forest algorithm, to learn the relationship between multi-omics features of the tumor and its sensitivity to the drug administered. Performance results indicated DeepResponse-RF successfully predicts drug sensitivity of cancer cells, and especially the multi-omics aspect benefited the learning process and yielded better performance compared to the single-omic-based state-of-the-art. With further development, DeepResponse-RF can be used for early stage discovery of new drug candidates and for repurposing the existing ones against resistant tumors.