Mutational landscape of MCPyV-positive and MCPyV-negative Merkel cell carcinomas with implications for immunotherapy

Abstract

Merkel cell carcinoma (MCC) is a rare but highly aggressive cutaneous neuroendocrine carcinoma, associated with the Merkel cell polyomavirus (MCPyV) in 80% of cases. To define the genetic basis of MCCs, we performed exome sequencing of 49 MCCs. We show that MCPyV-negative MCCs have a high mutation burden (median of 1121 somatic single nucleotide variants (SSNVs) per-exome with frequent mutations in RB1 and TP53 and additional damaging mutations in genes in the chromatin modification (ASXL1, MLL2, and MLL3), JNK (MAP3K1 and TRAF7), and DNA-damage pathways (ATM, MSH2, and BRCA1). In contrast, MCPyV-positive MCCs harbor few SSNVs (median of 12.5 SSNVs/tumor) with none in the genes listed above. In both subgroups, there are rare cancer-promoting mutations predicted to activate the PI3K pathway (HRAS, KRAS, PIK3CA, PTEN, and TSC1) and to inactivate the Notch pathway (Notch1 and Notch2). TP53 mutations appear to be clinically relevant in virus-negative MCCs as 37% of these tumors harbor potentially targetable gain-of-function mutations in TP53 at p.R248 and p.P278. Moreover, TP53 mutational status predicts death in early stage MCC (5-year survival in TP53 mutant vs wild-type stage I and II MCCs is 20% vs. 92%, respectively; P = 0.0036). Lastly, we identified the tumor neoantigens in MCPyV-negative and MCPyV-positive MCCs. We found that virus-negative MCCs harbor more tumor neoantigens than melanomas or non-small cell lung cancers (median of 173, 65, and 111 neoantigens/sample, respectively), two cancers for which immune checkpoint blockade can produce durable clinical responses. Collectively, these data support the use of immunotherapies for virus-negative MCCs.

Keywords: Merkel cell carcinoma; Merkel cell polyomavirus; TP53; cancer genetics; tumor neoantigens.

Figure 1. Landscape of somatic alterations in MCC

A. Number of non-synonymous and synonymous somatic single nucleotide variants (SSNVs) per sample. B. Relative frequency of the SSNVs with the relative frequency of an ultraviolet light or age-induced mutational signature. C. Clinical parameters associated with each tumor that relate to viral status. For viral copy number (CN), light blue reflects LT4-TPO DNA-PCR ratios < 0.1. Dark blue reflects ratios > 0.1. For T antigen antibody serology, dark green indicates antibody titers< 1:150 (seropositive) and light green indicates antibody titers > 1:75 (seronegative). For viral CN and for T antigen serologies, light gray boxes indicate test not done for the sample. For location, light gray boxes indicate other location or primary site not known. D. Select significant somatic mutations identified by exome sequencing are shown. Genes were identified by significant mutation burden (TP53), significant burden of damaging mutations (TP53 and RB1), presence of hotspot mutations in canonical oncogenes (HRAS, KRAS, AKT1, PIK3CA), and presence of damaging mutations in canonical tumor suppressors. Brown square indicates damaging mutations, i.e. nonsense mutations, frameshift mutations, and splice-site mutations. Green indicates missense mutations.

Figure 2. Somatic copy number variants in MCC

A. Number of alleles deleted or amplified at each genomic position across the MCC cohort. These numbers reflect the product of the number of alleles gained or lost per each sample and the number of samples harboring SCNVs at that position. B. Significant focal SCNVs identified by GISTIC. Q-value threshold (indicated by green line) = 0.25.

Figure 3. MCC-HI's are MCPyV-negative and harbor ultraviolet light-induced mutations

A. Histogram of SSNVs among tumors demonstrates a striking bimodal distribution of mutational burden in MCCs. B. Relative number of SSNVs in MCCs compared to all solid tumors sequenced by The Cancer Genome Atlas. The red line reflects the median number of SSNVs in each group. Samples are indicated by standard TCGA terminology. C. Relative viral load in MCC-HIs and MCC-LOs. Relative number of viral genomes were assessed by qRT-PCR. TPO was used as a control for relative amounts of host genomic DNA. D. The proportion of mutations whose genomic context suggest they were caused by ultraviolet light. For panels C and D, the colored lines indicates the median value for each subgroup. Statistical significance was determined with a two-sided unpaired t-test.

Figure 4. Statistically significant mutations in MCPyV-negative MCC

A. Schematic of SSNVs in RB1 and TP53. The domains were defined by Uniprot. Missense mutations are shown in Red. Damaging mutations are shown in black. B. Kaplan-Meier plot of overall survival as a function of TP53 mutational status in patients with Stage I MCC (left) or a combined cohort of Stage I and II MCCs (right). P-values were assessed by log-rank (Mantel-Cox) test.

Figure 5. MCPyV- MCCs have a high burden of predicted neoantigens

A. Plot of predicted neoantigens as a function of mutational burden. Mutant peptides that bind tightly to tumor cell's MHC class I molecules (Ka ≤ 500 nM) were identified for each tumor. These predicted neoantigens were plotted against the number of total somatic SNVs. Pearson linear regression analysis was performed. The gray shaded areas represent the 95% confidence interval. B. Plot of predicted neoantigens in MCPyV-negative (MCPyV-) MCCs vs. MCPyV-positive (MCPyV+) MCCs. Line indicates the median value for each subgroup. Statistical significance was determined using an unpaired t-test.