Co-expression network analysis of gene expression profiles of HER2+ breast cancer-associated brain metastasis

Abstract

Brain metastasis occurs in ~30% of patients with breast cancer, and patients with human epidermal growth factor receptor 2 (HER2)⁺ breast cancer have a particularly high frequency of brain metastasis. Weighted gene co-expression network analysis was conducted to identify the hub differentially expressed genes from patients with HER2⁺ breast cancer between brain metastases and primary tumors. The potential candidate genes were investigated in another set of patient samples to confirm their relevance. The results indicated that a number of pathways altered significantly when breast cancer metastasized to the brain. Cyclophilin A (CypA) and ribosomal protein L17 (RPL17) were overexpressed in breast cancer-associated brain metastases, whereas tumor protein 63 (TP63) and von Willebrand factor A domain-containing 8 (VWA8) were significantly downregulated in breast cancer brain metastases. Furthermore, the expression of CypA and RPL17 in brain metastases were significantly increased compared with that in primary breast tumors, and the expression of TP63 and VWA8 in brain metastases were significantly decreased. This result indicated that the significant differences in expression observed between primary breast tumors and brain metastases were derived from significantly altered systems, including gene modules rather than single genes.

Keywords: brain metastasis; breast cancer; expression profile; human epidermal growth factor receptor 2+; weighted gene co-expression network analysis.

Figure 1.

Heatmap of the overall dataset. Each column represents the corresponding sample of the dataset. Each row represents a gene. The tag title represents the respective tag applied to detect the expression of each gene. As depicted by the color bar, blue represents decreased expression and red represents increased expression.

Figure 2.

Sample dendrogram and trait heatmap. Samples were clustered according to the expression microarray, and there was no notable outlier; therefore, all the patients were included in the present analysis. White represents 0 (primary tumor) and red represents 1 (brain metastasis).

Figure 3.

Analysis of network topology for various soft-thresholding powers. Power 18 was selected as the lowest power for the scale-free topology, for which the fitting index reached 0.90.

Figure 4.

Different genes are grouped into modules according to the association of expression among them. Different colors represent different modules. In the cluster dendrogram, each leaf, represented by a short vertical line, corresponds to a gene. Branches of the dendrogram group together to form densely interconnected highly co-expressed genes. Module identification amounted to the identification of individual branches. Owing to the marked association among the genes inside each module, the modules with similar expression profiles were merged. The modules were associated with brain metastasis according to the overall gene significance inside each module. As depicted by the color bar, the further the value was from 0, the more significant the association was between brain metastasis and the module. Red depicts the positive associations and green depicts the negative associations.

Figure 5.

Heatmaps of the expression profile of the yellow module. Each column represents the corresponding sample of the dataset. Each row represents a gene. The tag title represents the respective tag applied to detect the expression of each gene. As depicted by the color bar, blue represents decreased expression and red represents increased expression.

Figure 6.

Heatmaps of the expression profile of the grey module. Each column represents the corresponding sample of the dataset. Each row represents a gene. The tag title represents the respective tag applied to detect the expression of each gene. As depicted by the color bar, blue represents decreased expression and red represents increased expression.

Figure 7.

Visualization of the network from the yellow module. Every block represents a gene, and the line between blocks represents the association. The wider the line, the more significant the association.

Figure 8.

Visualization of the network from the grey module. Every block represents a gene, and the line between blocks represents the association. The wider the line, the more significant the association.

Figure 9.

Original expression data of CypA, RPL17, TP63 and VWA8 in the training dataset. *P<0.05. CypA, cyclophilin A; RPL17, ribosomal protein L17; TP63, tumor protein p63; VWA8, von Willebrand factor A domain-containing 8.

Figure 10.

Corresponding results of GO analysis and KEGG pathway analysis for the yellow module and grey module. GO, Gene Ontology; KEGG, Kyoto Encyclopedia of Genes and Genomes; BP, biological process; CC, cell component; MF, molecular function.

Figure 11.

The expression level of CypA, RPL17, TP63 and VWA8 in patients with primary breast tumors compared with brain metastases. *P<0.05. CypA, cyclophilin A; RPL17, ribosomal protein L17; TP63, tumor protein p63; VWA8, von Willebrand factor A domain-containing 8.

Figure 12.

The expression level of CypA, RPL17, TP63 and VWA8 associated with the progression to brain metastasis following surgery for primary breast cancer. P>0.05. CypA, cyclophilin A; RPL17, ribosomal protein L17; TP63, tumor protein p63; VWA8, von Willebrand factor A domain-containing 8.