Cancer immunotherapy has revolutionized both the oncology research and treatment. Many of these treatment modalities have rapidly grown and gained approval over the last several years. Despite the durable and robust response to this outstanding class, the majority of patients remain resistant to such treatments. Hence, a crucial goal of on-going research is to broaden the scope of treatable tumors and patients and provide clinicians with tools that can predict patients’ responses to selected treatments. In this chapter, we shed the light on the importance of applying integrated molecular and computational approaches to address those research needs and potentially enhance the personalized medicine strategies. Numerous molecular high-throughput platforms are currently available and provide the means to perform a comprehensive immune profiling in the context of tumor immunotherapies. This allows the researchers to understand the reasons underlying the success or failure of these therapies and design strategies to mitigate any potential side effects. In addition, mathematical models have been used to predict the efficacy of therapies by recognizing and correlating specific immune features at the diagnosis time, which is crucial for selecting candidate patients who are more likely to benefit from specific immunotherapeutic treatments. Both experimental and computational tools complement each other and should be among the arsenal of tools in developing and optimizing immunotherapy approaches. The cutting-edge molecular and computational technologies exploited to predict the patients’ response to immunotherapy will be discussed throughout this chapter.