Genomic copy number and expression patterns in testicular germ cell tumours

Abstract

Testicular germ cell tumours of adults and adolescents (TGCT) include seminomas (SE) and nonseminomas (NS), with spermatocytic seminomas (SSE) representing a distinct entity in older men. SE and NS have gain of 12p material in all cases, whereas SSE are associated with overrepresentation of chromosome 9. Here, we compare at the chromosomal level, copy number imbalances with global expression changes, identified by comparative expressed sequence hybridisation analyses, in seven SE, one combined tumour, seven NS and seven cell lines. Positive correlations were found consistent with copy number as a main driver of expression change, despite reported differences in methylation status in SE and NS. Analysis of chromosomal copy number and expression data could not distinguish between SE and NS, in-keeping with a similar genetic pathogenesis. However, increased expression from 4q22, 5q23.2 and 9p21 distinguished SSE from SE and NS and decreased copy number and expression from 2q36-q37 and 6q24 was a specific feature of NS-derived cell lines. Our analysis also highlights 19 regions with both copy number and expression imbalances in greater than 40% of cases. Mining available expression array data identified genes from these regions as candidates for involvement in TGCT development. Supplementary data is available at http://www.crukdmf.icr.ac.uk/array/array.html.

Figure 1

Frequency plots of copy number and expression imbalances in the different subtypes. The frequency of copy number and expression aberrations (X-axis) is plotted against the chromosomal location (Y axis) for each subtype. Graphs show the proportion of samples, which have copy number or expression aberrations where a positive frequency is equal to proportion of samples with increased copy number or expression and negative frequency equal to the proportion of samples with decreased copy number or expression at each chromosome cytoband. 26 SE, 24 NS, 6 CT and 7 cell lines were analysed by CGH. 7SE, 7NS, 10 cell lines and 5 SSE were analysed by CESH. (A), (B), (E) and (F) are the frequency plots for copy number aberrations determined by CGH for SE, NS, TGCT cell lines and combined tumours, respectively. (C), (D), (G) and (H) are the frequency plots for expression changes determined by CESH for SE, NS, TGCT cell lines and SSE, respectively.

Figure 2

Supervised learning of CESH data. (A) Loci that are differentially expressed between TGCT and SSE. (B) Loci that are differentially expressed between primary tumours and cell lines. Each box plot represents a chromosome locus identified as discriminatory between the groups, separated by dashed lines. Group 1 (left): primary SE and NS samples; Group 2 (middle): NS-derived cell lines; Group 3 (right): primary SSE samples. Each circle represents a sample within that group. The axis indicates the expression of each sample where 1 denotes increased expression; 0 normal and −1 decreased expression.