Precision cancer medicine promises better treatments to a disease as complex and heterogenous as cancer. Many anti-cancer therapies are beneficial to only a subset of patients due to the variability in patient genetic and tumor heterogeneity. Thus, we need better frameworks for understanding underlying genomic and transcriptomic patterns influencing differential patient outcomes, yet our understanding of how genetic alterations connect to treatment in in vivo and in vitro models remains understudied. To address this gap, I utilized human patient data from The Cancer Genome Atlas (TCGA), hepatocellular carcinoma (HCC) models, prostate cancer (PCa) models, and chronic myelogenous leukemia (CML) cell lines. Through the integration of multi-omic data, I identified parallel features of human and model organism data that could reveal disease specific characteristics. Additionally, I characterized the landscape of acquired resistance for a panel of chemotherapeutic treatments and revealed potential alleles and genes that mediate the process. The analyses I conducted expose the role of genetic information and suggest future applications for development of precision medicine.