AutoEncoder-Based Computational Framework for Tumor Microenvironment Decomposition and Biomarker Identification in Metastatic Melanoma.

Melanoma is one of the most aggressive cancer types whose prognosis is determined by both the tumor cell-intrinsic and -extrinsic features as well as their interactions. In this study, we performed systematic and unbiased analysis using The Cancer Genome Atlas (TCGA) melanoma RNA-seq data and identified two gene signatures that captured the intrinsic and extrinsic features, respectively. Specifically, we selected genes that best reflected the expression signals from tumor cells and immune infiltrate cells. Then, we applied an AutoEncoder-based method to decompose the expression of these genes into a small number of representative nodes. Many of these nodes were found to be significantly associated with patient prognosis. From them, we selected two most prognostic nodes and defined a tumor-intrinsic (TI) signature and a tumor-extrinsic (TE) signature. Pathway analysis confirmed that the TE signature recapitulated cytotoxic immune cell related pathways while the TI signature reflected MYC pathway activity. We leveraged these two signatures to investigate six independent melanoma microarray datasets and found that they were able to predict the prognosis of patients under standard care. Furthermore, we showed that the TE signature was also positively associated with patients' response to immunotherapies, including tumor vaccine therapy and checkpoint blockade immunotherapy. This study developed a novel computational framework to capture the tumor-intrinsic and -extrinsic features and identified robust prognostic and predictive biomarkers in melanoma.