Identification of a novel 10 immune-related genes signature as a prognostic biomarker panel for gastric cancer

Background Emerging evidence indicates that immune infiltrating cells in tumor microenvironment (TME) correlates with the development and progression of gastric cancer (GC). This study aimed to systematically investigate the immune-related genes (IRGs) to develop a prognostic signature to predict the overall survival (OS) in GC. Method The gene expression profiles of training dataset (), validation dataset I (), and validation dataset II () were retrieved from GEO and TCGA databases. In the present study, we developed a 10 IRGs prognostic signature with the combination of weighted gene co-expression network analysis (WGCNA) and least absolute shrinkage and selection operator method (LASSO) COX model. Results In the training dataset, the accuracy of the signature was 0.681, 0.741, and 0.72 in predicting 1, 3, and 5-year OS separately. The signature also had good performance in validation dataset I with the accuracy of 0.57, 0.619, and 0.694, and in validation dataset II with the accuracy of 0.559, 0.624, and 0.585. Then, we constructed a nomogram using the signature and clinical information which had strong discrimination ability with the c-index of 0.756. In the immune infiltration analysis, the signature was correlated with multiple immune infiltrating cells such as CD8 T cells, CD4 memory T cells, NK cells, and macrophages. Furthermore, several significant pathways were enriched in gene set enrichment analysis (GSEA) analysis, including TGF-beta signaling pathway and Wnt signaling pathway. Conclusion The signature of 10 IRGs we identified can effectively predict the prognosis of GC and provides new insight into discovering candidate prognostic biomarkers of GC.