In the last two years we have become actively engaged in collaborative studies in cancer immunotherapy, ranging from studying the role of urea cycle dysregulation in modulating the response to checkpoint inhibitors in different cancer types, studying the role of intratumor heterogeneity in shaping the immune response and its effectiveness, and very recently, building machine learning based predictors of patients' response to checkpoint therapies in melanoma. We also found CAPN1 is a novel binding partner and regulator of the tumor suppressor Neurofibromin 1 (NF1) in melanoma. We also found robust prediction of response to immune checkpoint blockade therapy in metastatic melanoma. Analyzing gene expression data from patients with neuroblastoma, we identified 15 checkpoint-related pairs of genes whose relative activity could be used to predict the effectiveness of the immune system's anticancer response, which we used to develop a predictive tool. When we applied this predictor to available data from patients with melanoma, it outperformed all other predictors of immunotherapy drug outcomes that had been reported so far.
