Characterization of protein-based risk signature to predict prognosis and evaluate the tumor immune environment in breast cancer

BackgroundProteomics profiles have enabled a systematic insight into the prognosis of cancer. This study aimed to establish a valuable protein-based risk signature to assess the prognosis and immune status in patients with breast cancer (BC).MethodsProtein expression profile, RNA expression data, and clinical information were acquired from The Cancer Genome Atlas (TCGA). The whole cohort was randomly split into two cohorts, one for establishing the risk signature and the other for testing. Univariate Cox analysis and Least absolute shrinkage and selection operator (LASSO) Cox regression were utilized to construct the protein-based risk signature. All cohorts were divided into high- and low-risk groups, which were applied to investigate the clinical relevance, tumor microenvironment, and therapeutic response.ResultsThe prognostic proteomics signature was established based on prognostic proteins, thus categorizing patients into low-risk and high-risk groups with different prognoses. A predictive nomogram was also developed to predict 1, 3, and 5-year survival possibility for BC patients, and the calibration curves confirmed the predictive significance of this signature. Afterward, the low-risk group displayed higher immune activities, immune checkpoint expression, and immunotherapeutic response. Moreover, GSEA analysis indicated that immune-associated pathways were rich in the low-risk group. Additionally, this prognostic signature demonstrated potential predict significance for chemotherapeutic agents.ConclusionThis study established an effective prognostic proteomics signature with reliable predictive performance for survival, immune activity, and drug sensitivity. It might provide a novel perspective into the protein function in BC, and guide the individual treatment strategies for BC patients.