Currently, cancer therapy trial-and-error methodology is inefficient and unsustainable. Oncology is the worst therapeutic area for drug trial success; only 3.4% of drugs that enter phase I end up being FDA approved, and 57% fail due to poor drug efficacy in trials. Building tools that may aid in predicting an individual’s response to a specific therapy may help in reducing costs, guesswork, and importantly improve the outcome of patients and accelerate new drug development.