Gene expression profile identifies distinct molecular subtypes and potential therapeutic genes in Merkel cell carcinoma

Abstract

Merkel cell carcinoma (MCC) is a rare primary cutaneous neoplasm of neuroendocrine carcinoma of the skin. About 80% of the MCC occurs due to Merkel cell polyomavirus (MCPyV) and 20% of the tumors usually occur due to severe UV exposure which is a more aggressive type of MCC. It tends to have an increased incidence rate among elderly and immunosuppressed individuals. On therapeutic level, sub-classification of MCC through molecular subtyping has emerged as a promising technique for MCC prognosis. In current study, two consistent distinct molecular subtypes of MCCs were identified using gene expression profiling data. Subtypes I MCCs were associated with spliceosome, DNA replication and cellular pathways. On the other hand, genes overexpressed in subtype II were found active in TNF signalling pathway and MAPK signalling pathway. We proposed different therapeutic targets based on subtype specificity, such as PTCH1, CDKN2A, AURKA in case of subtype I and MCL1, FGFR2 for subtype II. Such findings may provide fruitful knowledge to understand the intrinsic subtypes of MCCs and the pathways involved in distinct subtype oncogenesis, and will further advance the knowledge in developing a specific therapeutic strategy for these MCC subtypes.

Keywords: Gene expression; Merkel cell carcinoma; Molecular subtype; Subtype specific treatment.

Fig. 1

Identification of two molecular subtypes of MCC in GSE39612. (A) Empirical cumulative distribution plot determines the optimal number of MCC molecular subtypes. (B) Relative increase in the area under the CDF curve along with increasing assumed number of molecular subtypes. (C) Consensus clustering matrix of MCC samples using two molecular subtypes. (D) Silhouette analysis of MCC samples based on the assignment from Consensus Clustering.

Fig. 2

Identification of two molecular subtypes of MCC in GSE22396. (A) Empirical cumulative distribution plot determines the optimal number of MCC molecular subtypes. (B) Relative increase in the area under the CDF curve along with increasing assumed number of molecular subtypes. (C) Consensus clustering matrix of MCC samples using two molecular subtypes. (D) Silhouette analysis of MCC samples based on the assignment from Consensus Clustering.

Fig. 3

Association in the SubMap matrix between the subtypes of two independent dataset GSE3916 and GSE22396 showing the significant correlation. The correlation significance was denoted by FDR-corrected p-value.

Fig. 4

Pathways enriched in each MCC subtypes. (A) KEGG pathways in subtype I. (B) KEGG pathways in subtype II.

Fig. 5

GSEA reveals different gene expression signature in distinct MCC molecular subtypes. (A) Representing different gene expression patterns in subtype I and subtype II. Red, overexpressed genes; blue, down expressed genes. (B) GSEA shows the activity of DNA replication and Spliceosome pathways in subtype I. (C) GSEA demonstrated the activity of Toll like receptor signalling and cytosolic DNA sensing pathways in subtype II. Whereas NES is denoting normalized enriched score and FDR is denoting false discovery rate.