Metastatic melanoma remains a significant cause of death in the United States, with average survival rates below 35% just 5 years after initial diagnosis. In order to improve outcomes for patients, a growing area of research has been to focus on patient-specific biomarkers, which may enable targeted therapy or contribute to prognostic tests to determine which therapy is best for a certain patient. One important existing prognostic factor in melanoma is the sentinel lymph node biopsy (SLNB), which takes a sample of patient lymph node (LN) tissue to determine the stage of a patients’ cancer. Unfortunately, there is limited knowledge on if there are specific biomarkers present in patient LN tissue from SLNB to predict efficacy for specific melanoma treatments. This is important because recent experiments have shown that patient LN tissue is critical in mediating immune cell interactions which contribute to responses in immunotherapy treatment. These experiments suggest that there may be biomarkers present in patient LN tissue. In this study, we seek to profile patient LN tissue to determine specific biomarkers associated with response to immunotherapy in both local and metastatic melanoma. We will utilize advanced gene sequencing and imaging technology with machine learning models to determine specific immune pathways and spatial architecture of immune cells in LN tissue. This research is critical because it will definitively establish pathways and biomarkers which predict responses to immunotherapy in patient LN tissue— samples that are commonly available and extracted during routine melanoma SLNB staging procedures. In the future, researchers will be able to analyze these pathways to target specific pro- and anti-cancer pathways involved in lymph node metastasis. Melanoma physicians may be able to use information from patient SLNB to further determine which immunotherapy to give patients based on this data.