Prediction of clinical prognosis in cutaneous melanoma using an immune-related gene pair signature

Abstract

Cutaneous melanoma (CM) is a malignant and aggressive skin cancer that is the leading cause of skin cancer-related deaths. Increasing evidence shows that immunity plays a vital role in the prognosis of CM. In this study, we developed an immune-related gene pair (IRGP) signature to predict the clinical prognosis of patients with CM. Immune-related genes from The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO) databases were selected to construct the IRGPs, and patients with CM in these two cohorts were assigned to low- and high-risk subgroups. Moreover, we investigated the IRGPs and their individualized prognostic signatures using Kaplan-Meier survival analysis, univariate and multivariate Cox analyses, and analysis of immune cell infiltration in CM. A 41-IRGP signature was constructed from 2498 immune genes that could significantly predict the overall survival of patients with CM in both the TCGA and GEO cohorts. Immune infiltration analysis indicated that several immune cells, especially M1 macrophages and activated CD4 T cells, were significantly associated with the prognostic effect of the IRGP signature in patients with CM. Overall, the IRGP signature constructed in this study was useful for determining the prognosis of patients with CM and for providing further understanding of CM immunotherapy.

Keywords: Cutaneous melanoma; immune-related gene pairs; prognosis.

Graphical abstract

Figure 1.

Time-dependent ROC curve for IRGPI at 5 years in the TCGA-CM cohort

Figure 2.

Efficacy evaluation of constructed IRGPI risk model. (a) Kaplan-Meier survival curve of TCGA cohort. (b) Kaplan-Meier survival curve of GSE65904 cohort. Univariate and multivariate Cox regression analysis of the clinicopathological features in TCGA (c) and GSE65904 (d) cohorts

Figure 3.

The infiltration level of immune cells in the constructed IRGPI risk model. (a) Summary of the 22 tumor-infiltrating immune cells’ abundance estimated by CIBERSORT analysis. p-values are based on t-test (*p< 0.05, ***p< 0.001). (b) The boxplot shows the distribution of specific immune cells in two risk subgroups from the TCGA cohort

Figure 4.

Gene set enrichment analysis (GSEA) between high- and low- IRGPI risk subgroups. The results show that 13 cancer hallmark gene sets are enriched in the low IRGPI risk subgroup (FDR < 0.002)

Figure 5.

Functional enrichment analysis of 82 immune signature genes. (a) Top 10 classes of GO enrichment terms in biological process (BP), cellular component (CC), and molecular function (MF). (b) Top 10 classes of KEGG enrichment terms. In each bubble plot, the size of the dot represents the number of enriched genes