Protein kinases are a diverse family of about 500 proteins that all share the common ability to catalyze phosphorylation of the side chains of amino acids in proteins. Kinases play a vital role across diverse biological functions including proliferation, differentiation, cell migration, and cell-cycle control. Moreover, they are frequently altered across most cancers types and have been a focus for development of anti- cancer drugs, which has led to the development of 38 approved kinase inhibitors as of 2018. In this thesis, I developed two orthogonal computational approaches for investigating kinase function and deregulation. Starting with data from a large cohort of mouse triple negative breast cancer (TNBC) tumors, I use a combination of whole exome sequencing (WES) and RNA-seq to identify somatic alterations that drive individual tumors. I discovered that a large number of these alterations involve protein kinases and subsequent therapeutic targeting led to tumor regression. For my second approach, I utilized a large peptide library dataset from about 300 kinases. Which kinase phosphorylate which phosphorylation site is determined by both kinase- intrinsic and contextual factors. Peptide library approaches provide kinase-intrinsic amino acid specificity, which I used to predict novel kinase substrates and map out kinase phosphorylation networks. In summary, I developed methods using next-generation sequencing and peptide library data to generate novel insights into protein kinase function and deregulation.