Tumor Immune Microenvironment Characterization Identifies Prognosis and Immunotherapy-Related Gene Signatures in Melanoma

Abstract

Background: The tumor microenvironment (TME) involves infiltration of multiple immune cell subsets, which could influence the prognosis and clinical characteristics. The increasing evidence on the role of tumor-infiltrating lymphocytes (TILs) in primary and metastatic melanomas supports that the immune system is involved in the progression and outcomes of melanoma. However, the immune infiltration landscape in melanoma has not been systematically elucidated.

Methods: In this study, we used CIBERSORT and ESTIMATE algorithms to analyze immune infiltration pattern of 993 melanoma samples. Then we screened differential expression genes (DEGs) related to immune subtypes and survival. The immune cell infiltration (ICI) score was constructed by using principal-component analysis (PCA) based on immune signature genes from DGEs. Gene set enrichment analysis (GSEA) was applied to explore high and low ICI score related pathways. Finally, the predictive ability of ICI score was evaluated in survival prognosis and immunotherapy benefit.

Result: We identified three ICI clusters and three gene clusters associated with different immune subtypes and survival outcomes. Then the ICI score was constructed, and we found that high ICI score exhibited activated immune characteristics and better prognosis. High ICI score was significantly enriched in immune pathways and highly expressed immune signature genes. More importantly, we confirmed that melanoma patients with high ICI score had longer overall survival and rate of response to immunotherapy.

Conclusion: We presented a comprehensive immune infiltration landscape in melanoma. Our results will facilitate understanding of the melanoma tumor microenvironment and provide a new immune therapy strategy.

Keywords: immune cell infiltration; immune therapy; melanoma; prognosis; tumor microenvironment.

Figure 1

Landscape of immune cells infiltration in melanoma. (A) Unsupervised clustering heatmap of immune cells infiltration for all melanoma samples. Rows represent tumor-infiltrating immune cells, and columns represent samples. (B) The correlation coefficient heatmap of immune cell interaction. (C) Kaplan-Meier curves of overall survival for ICI cluster A–C. Log rank test P = 0.007. (D) The box plot of immune cells fraction in ICI cluster A–C. *P<0.05; **P < 0.01; ***P<0.001; ****P<0.0001; ns: no significance. (E) The box plot of immune activity related signature genes expression (CXCL9, CXCL10, TNF, IFNG, CD8A, GZMA, GZMB, PRF1) between ICI cluster A–C, ****P<0.0001. (F) The box plot of immune checkpoint signature genes expression (CTLA4, PDCD1, PDCD1LG2, LAG3) between ICI cluster A-C, ****P<0.0001.

Figure 2

Immune gene subtype (A) Unsupervised clustering heatmap of differential expression genes among three ICI cluster. (B) Kaplan-Meier curves of overall survival for gene cluster A-C. Log rank test P <0.001. (C) The box plot of immune cells fraction in gene cluster A-C. **P < 0.01; ***P<0.001; ns, no significance. (D, E) GO enrichment analysis for ICI signature gene A and B.

Figure 3

Analysis of ICI score. (A) Alluvial diagram of ICI scores groups distribution in different gene cluster, and survival outcomes. (B) Kaplan-Meier curves of overall survival for high and low ICI score cluster in all sample. Log rank test P <0.001. (C) Kaplan-Meier curves of overall survival for high and low ICI score cluster in TCGA cohort. Log rank test P <0.001. (D) GSEA of high and low ICI score groups for all melanoma samples. (E) The box plot of immune activity related signature genes expression (CXCL9, CXCL10, TNF, IFNG, CD8A, GZMA, GZMB, PRF1) in high and low ICI score, ****P<0.0001. (F) The box plot of immune checkpoint signature genes expression (CTLA4, PDCD1, PDCD1LG2, LAG3) in high and low ICI score, ****P<0.0001.

Figure 4

The correlation between ICI score and cancer somatic variants. (A) TMB difference among the high and low ICI score groups. (B) The correlation Scatter plots between TMB and ICI score. (C) Kaplan-Meier curves of overall survival for high and low TMB group. Log rank test P <0.001. (D) Kaplan-Meier curves of overall survival stratified by both TMB and ICI scores. Log rank test P <0.001. (E, F) The oncoPrint of high (left) and low (right)ICI score. Individual patients represented in each column. Missense mutation: green; Nostop mutation: gray; Nonsense mutation: red; Multi-hit: black. The top bar plot represented TMB. The right bar plot shows the mutation frequency of each gene in separate ICI score groups. The below bar represented ICI cluster, gene cluster and survival outcome.

Figure 5

The role of ICI scores in the evaluation of melanoma clinical characteristics and immune therapy benefit. (A) The forest plot of stratified survival analysis for clinical indicator based on ICI score. The length of the horizontal line represents the 95% CI for each group, the sample number, HR and 95%CI as well as P value of each group were listed. (B) Kaplan-Meier curves of overall survival for high and low ICI score cluster in GSE19423 cohort. Log rank test P =0.026. (C) The predictive value of the ICI score measured by ROC curves in GSE19423. (D) Kaplan-Meier curves of overall survival for high and low ICI score cluster in GSE78220. Log rank test P =0.014. (E) The predictive value of the ICI score measured by ROC curves in GSE78220. (F) Rate of clinical response to anti-PD1 treatment in high and low ICI score groups in GSE78220. (G) Kaplan-Meier curves of overall survival for high and low ICI score cluster in CA209038 cohort. Log rank test P =0.0449. (H) The predictive value of the ICI score measured by ROC curves in CA209038. (I) Rate of clinical response to anti-PD1 treatment in high and low ICI score groups in CA209038 cohort. (J) Mutation frequency between high and low ICI score group in CA209038 cohort.