High-throughput molecular profiling has revolutionized our understanding of molecular mechanisms involved in disease progression and treatment response. As more information from patients' high-throughput molecular and clinical profiles (i.e., Big Data) becomes accessible, there is a significant shift in personalized and precision-based patient-centric approaches, allowing for an individualized therapeutic planning and more accurate prediction of therapeutic success or failure. Here, we discuss the most commonly utilized Big Data types (touching on most recent advances), including genome, DNA methylome, and transcriptome (i.e., RNA abundance and alternative splicing), alongside computational methods for their effective analysis. Further, we discuss how Big Data integration helps in unveiling complex molecular relationships involved in treatment response in oncology, including identification of biological pathways as markers of treatment resistance, and how its utilization builds a foundation for improved clinical decision making and precision medicine.