Identification of frequent cytogenetic aberrations in hepatocellular carcinoma using gene-expression microarray data

Abstract

Background: Hepatocellular carcinoma (HCC) is a leading cause of death worldwide. Frequent cytogenetic abnormalities that occur in HCC suggest that tumor-modifying genes (oncogenes or tumor suppressors) may be driving selection for amplification or deletion of these particular genetic regions. In many cases, however, the gene(s) that drive the selection are unknown. Although techniques such as comparative genomic hybridization (CGH) have traditionally been used to identify cytogenetic aberrations, it might also be possible to identify them indirectly from gene-expression studies. A technique we have called comparative genomic microarray analysis (CGMA) predicts regions of cytogenetic change by searching for regional gene-expression biases. CGMA was applied to HCC gene-expression profiles to identify regions of frequent cytogenetic change and to identify genes whose expression is misregulated within these regions.

Results: Using CGMA, 104 HCC gene-expression microarray profiles were analyzed. CGMA identified 13 regions of frequent cytogenetic change in the HCC samples. Ten of these regions have been detected in previous CGH studies (+lq, -4q, +6p, -8p, +8q, -13q, -16q, -17p, +17q, +20q). CGMA identified three additional regions that have not been previously identified by CGH (+5q, +12q, +19p). Genes located in regions of frequent cytogenetic change were examined for changed expression in the HCC samples.

Conclusions: Our results suggest that CGMA predictions using gene-expression microarray datasets are a practical alternative to CGH profiling. In addition, CGMA might be useful for identifying candidate genes within cytogenetically abnormal regions.

Figure 1

Comparative genomic microarray analysis of hepatocellular carcinoma gene expression profiles. (a) A bar graph of log-transformed expression ratios (tumor versus normal) for genes located on chromosome 8q for sample SF13. The gene-expression values are organized from the chromosome telomere (top) to the centromere (bottom). A scale is shown above the graph. (b) CGMA expression profiles for 104 HCC tissue samples. Before CGMA analysis, gene-expression ratios were transformed such that each tumor gene-expression value was compared to the expression value from the non-cancerous tissue sample retrieved from the same patient. If the normal tissue was not present, the global mean of the non-tumor tissues was used. Genomic regions that show a significant number of downregulated genes are shown in green whereas genomic regions that show a significant number of upregulated genes are shown in red. The color intensity indicates the significance of the expression bias. The lowest-intensity color indicates a z-statistic = 1.96 (α = 0.05) while the most intense color indicates a z-statistic <3.29 (α < 0.001). The mean z-statistic for each genomic region is displayed in the rightmost column. (c) Chromosomal regions that had a significant gene-expression bias in more than 35% of HCC samples are listed. Red represents chromosomal gains and green represents losses. The corresponding percentages of samples that displayed frequent chromosomal aberrations identified in two CGH studies. Values from Wong et al.[12] are represented as CGH₁ and values from Marchio et al. [11] are represented as CGH₂.

Figure 2

Thirteen hepatocellular carcinoma CGH studies compared to CGMA predictions. Frequent chromosomal aberrations detected by 13 CGH studies (see References) and by CGMA are displayed as a heat map. Green indicates regions of frequent chromosomal loss and red indicates regions of frequent chromosomal gain. At the right is a consensus profile of chromosomal regions that were altered in at least 35% of the CGH studies.

Figure 3

CGMA comparisons of multiple tumor nodules isolated from the same patient. The data were generated and presented as in Figure 1. Tumor sample names are presented as patient number with a tumor nodule suffix. CGMA profiles were arranged by hierarchical clustering (average linkage clustering) using the sign test z-statistic of each chromosomal region [38].