DNA methylation characteristics of primary melanomas with distinct biological behaviour

Abstract

In melanoma, the presence of promoter related hypermethylation has previously been reported, however, no methylation-based distinction has been drawn among the diverse melanoma subtypes. Here, we investigated DNA methylation changes associated with melanoma progression and links between methylation patterns and other types of somatic alterations, including the most frequent mutations and DNA copy number changes. Our results revealed that the methylome, presenting in early stage samples and associated with the BRAF(V600E) mutation, gradually decreased in the medium and late stages of the disease. An inverse relationship among the other predefined groups and promoter methylation was also revealed except for histologic subtype, whereas the more aggressive, nodular subtype melanomas exhibited hypermethylation as well. The Breslow thickness, which is a continuous variable, allowed for the most precise insight into how promoter methylation decreases from stage to stage. Integrating our methylation results with a high-throughput copy number alteration dataset, local correlations were detected in the MYB and EYA4 genes. With regard to the effects of DNA hypermethylation on melanoma patients' survival, correcting for clinical cofounders, only the KIT gene was associated with a lower overall survival rate. In this study, we demonstrate the strong influence of promoter localized DNA methylation changes on melanoma initiation and show how hypermethylation decreases in melanomas associated with less favourable clinical outcomes. Furthermore, we establish the methylation pattern as part of an integrated apparatus of somatic DNA alterations.

Figure 1. Methylation patterns of primary melanomas associated with known clinical predictors.

(A) Volcano plots of differentially methylated genes associated with known predictors. Blue dots indicates decreased and red indicates increased methylation as follows: Breslow thickness: 51 hypomethylated probes (43 individual genes) and 5 hypermethylated probes (5 individual genes); metastatic capacity: 23 hypomethylated probes (21 individual genes) and 5 hypermethylated probes (4 individual genes), ulceration: 48 hypomethylated probes (43 individual genes) and 8 hypomethylated probes (8 individual genes), histologic subtype: 28 hypomethylated probes (26 individual genes) 23 hypermethylated probes (20 individual genes) (B) A Venn diagrams indicate the overlap of differentially methylated genes (in left: number of hypomethylated genes; in right: number of hypermethylated genes) for each clinical predictor class.

Figure 2. Hypermethylation is an early event in melanomas and decreases with tumour thickness.

(A) The heatmap demonstrates the hypermethylation patterns (indicated in brown colour) of 45 CpGs, which can be detected in the early stages of melanomas (horizontal purple colour) but decrease from the medium stage (horizontal green colour) to the late stage (horizontal blue colour). (B) The principal component analysis for the distinction of the Breslow thickness the sample groups (large: blue dots; medium: green dots; and small melanoma samples: purple dots) based on the 45 differentially methylated CpGs. The analysis revealed that, according to the first three components, which covered the 56% of the total variance, the three groups were significantly different (p<0.05)

Figure 3. Differentially methylated gene sets between the BRAF^V600E mutant and wild-type classes.

(A) Differentially methylated gene sets between BRAF^V600E mutant and wild-type, metastatic and non-metastatic, ulcerated and non-ulcerated classes according to the Kyoto Encyclopaedia of Genes and Genomes. (B) Average log-ratios of methylation intensities in BRAF^V600E mutant and wild-type melanomas. Red indicates significant genes associated with ECM-receptor interaction and blue depicts significant genes on Cell communication pathway. (Eleven genes overlap between the ECM-receptor interaction and Cell communication.) (C) Venn diagram shows lack of overlap between differentially methylated genes associated with BRAF^V600E mutation and the known clinical predictors as Breslow thickness, metastatic capacity, ulceration and histologic subtype.

Figure 4. Hypermethylated genes associated with decreased survival rate in melanoma patients.

The Kaplan-Meier curves for genes (DSP, EPHB6, HCK, IL18, IRAK3 and KIT) whose hypermethylation was associated with a lower overall survival rate (OS); the Cox proportional univariate approach was performed on each gene to test whether a methylation status of a particular gene significantly influences the survival at the p<0.05 level.

Figure 5. Relationship between gene expression and DNA methylation.

The gene expressions of MCAM, FGFR3 and IL8 were measured by qRT-PCR and are presented as bars (fold change in left Y axis), and Avg-Beta methylation values are demonstrated as lines (shown in right Y axis). Methylation data was extracted from Illumina bead assay, with distinct probes represented as different lines. Gene expression differences among the groups were analysed using the Mann-Whitney test, which revealed significant differences for the MCAM and IL8 genes.

Figure 6. Coincidence of DNA copy number (CN) alterations and hypermethylation.

(A) The distribution of CN aberrations (red indicates CN losses and blue indicates CN gains on the frequency plot) specific for the BRAF^V600E mutant (purple line on the left) and BRAF^V600E wild-type (green line on the left) primary melanomas. The methylated genes are shown as blue lines in the lower part of the figure, and the red dotted circle highlights 6q23 as the only region where a coincidence was revealed. The significant CN alterations are highlighted in grey in the upper part of the figure. Frequent CN losses (B) and CN gains (C) are given based on the G-score of GISTIC algorithm, which is a measure of the frequency of occurrence of the aberration and the magnitude of the CN alteration at each location in the aggregate of all samples in the dataset. The locations of the alterations in each sample are permuted, simulating data with random aberrations, and the significance is represented as Q-Bounds. Grey lines indicate the peak, whereas the grey shaded area is an extended peak based on leave-one-out algorithm to allow for errors in the boundaries in a single sample. (C) Correlation plot for CN alterations and DNA methylation regarding the MYB gene and (D) the EYA4 gene.

Figure 7. FISH analysis to confirm array CGH results.

CN alteration at specific regions of a representative BRAF^V600E mutant primary melanoma: (A) CN gains were revealed at chromosome 6p while CN losses occurred at chromosome 6q in BRAF^V600E samples. (B) High level CN gain was seen at the region of 11q13–q14. (C) Four colour FISH was performed to verify the CN altered genomic regions: green fluorescence (gain of CCND1 gene on 11q13), yellow fluorescence (loss of MYB gene on 6q23), red fluorescence (gain of RREB1 gene on 6p25), whereas blue fluorescence indicates centromere 6.