Clinical and molecular assessment of an onco-immune signature with prognostic significance in patients with colorectal cancer

Abstract

Understanding the complex tumor microenvironment is key to the development of personalized therapies for the treatment of cancer including colorectal cancer (CRC). In the past decade, significant advances in the field of immunotherapy have changed the paradigm of cancer treatment. Despite significant improvements, tumor heterogeneity and lack of appropriate classification tools for CRC have prevented accurate risk stratification and identification of a wider patient population that may potentially benefit from targeted therapies. To identify novel signatures for accurate prognostication of CRC, we quantified gene expression of 12 immune-related genes using a medium-throughput NanoString quantification platform in 93 CRC patients. Multivariate prognostic analysis identified a combined four-gene prognostic signature (TGFB1, PTK2, RORC, and SOCS1) (HR: 1.76, 95% CI: 1.05-2.95, *p < 0.02). The survival trend was captured in an independent gene expression data set: GSE17536 (177 patients; HR: 3.31, 95% CI: 1.99-5.55, *p < 0.01) and GSE14333 (226 patients; HR: 2.47, 95% CI: 1.35-4.53, *p < 0.01). Further, gene set enrichment analysis of the TCGA data set associated higher prognostic scores with epithelial-mesenchymal transition (EMT) and inflammatory pathways. Comparatively, a lower prognostic score was correlated with oxidative phosphorylation and MYC and E2F targets. Analysis of immune parameters identified infiltration of T-reg cells, CD8⁺ T cells, M2 macrophages, and B cells in high-risk patient groups along with upregulation of immune exhaustion genes. This molecular study has identified a novel prognostic gene signature with clinical utility in CRC. Therefore, along with prognostic features, characterization of immune cell infiltrates and immunosuppression provides actionable information that should be considered while employing personalized medicine.

Keywords: colon; colorectal cancer; gene signature; immune; personalized medicine; preventive; prognostic genes.

FIGURE 1

Mutation profiling of immune gene panel in TCGA‐COAD. (A) Waterfall plot showing the landscape of mutations in COAD samples. The tumor mutation burden is depicted as a bar plot above the legend. Different colors depict specific mutation types. (B) SNV (single nucleotide variation) percentage heatmap depicting higher frequency in COAD data set, (C) comparative pie‐plot summary of CNV percentage in major cancer, (D) network analysis of immune genes (E) PCA analysis of 12 genes in normal versus tumor tissue of TCGA‐COAD CRC samples

FIGURE 2

Survival analysis. (A) The combined prognostic score of TGFB1 and PTK2 in the internal data set and (B) TCGA data set. (C) The combined prognostic score of RORC and SOCS1 in the internal data set and (D) TCGA data set

FIGURE 3

Combined four‐gene prognostic assessment in internal and external data sets. (A) k‐mean clustering of gene expression and overall survival in internal data sets; (B) survival difference between higher and lower gene expression clusters (C) KM estimate based on the four‐gene prognostic score in the internal data set (D) external GEO data set GSE14333, and (E) external GEO data set GSE17536

FIGURE 4

(A) Volcano plot depicting differential expression of genes in high‐risk and low‐risk CRC patients in TCGA data set. (B) GO term enrichment in the low‐risk group. (C) GO term enrichment in the high‐risk group and (D) differential enrichment of hallmarks in cancer in two risk groups

FIGURE 5

Gene set enrichment analysis based on risk stratification in TCGA data set. In the high‐risk group, enriched pathways included (a) allograft rejection, (B) epithelial–mesenchymal transition, and (C) inflammatory response. In the low‐risk group, (D) MYC targets, (E) E2F targets, and (F) oxidative phosphorylation were enriched. (G) Comparative analysis of the high‐ and low‐risk groups, depicting differential expression of genes in key pathways

FIGURE 6

(A) Differential infiltration of immune cells in high‐risk and low‐risk groups of TCGA data set. (B) Infiltration of macrophages. (C) Pathway clustering of exhaustion genes. (D) z‐score of exhaustion genes in the two risk groups