Meta-analysis of gene expression signatures defining the epithelial to mesenchymal transition during cancer progression

Abstract

The epithelial to mesenchymal transition (EMT) represents a crucial event during cancer progression and dissemination. EMT is the conversion of carcinoma cells from an epithelial to a mesenchymal phenotype that associates with a higher cell motility as well as enhanced chemoresistance and cancer stemness. Notably, EMT has been increasingly recognized as an early event of metastasis. Numerous gene expression studies (GES) have been conducted to obtain transcriptome signatures and marker genes to understand the regulatory mechanisms underlying EMT. Yet, no meta-analysis considering the multitude of GES of EMT has been performed to comprehensively elaborate the core genes in this process. Here we report the meta-analysis of 18 independent and published GES of EMT which focused on different cell types and treatment modalities. Computational analysis revealed clustering of GES according to the type of treatment rather than to cell type. GES of EMT induced via transforming growth factor-β and tumor necrosis factor-α treatment yielded uniformly defined clusters while GES of models with alternative EMT induction clustered in a more complex fashion. In addition, we identified those up- and downregulated genes which were shared between the multitude of GES. This core gene list includes well known EMT markers as well as novel genes so far not described in this process. Furthermore, several genes of the EMT-core gene list significantly correlated with impaired pathological complete response in breast cancer patients. In conclusion, this meta-analysis provides a comprehensive survey of available EMT expression signatures and shows fundamental insights into the mechanisms that are governing carcinoma progression.

Figure 1. Cluster analysis of genes shared between at least 10 GES datasets shows distinguishable and significant clusters.

Genes shared between at least 10 out of 24 datasets were used for Manhattan hierarchical clustering. The type of regulation within a particular study was visualized via heatmap. Columns: genes shared between at least 10 datasets (n = 365); rows: analyzed GES (24 datasets in total); green: downregulated genes; red: upregulated genes; black: genes not regulated. GSE: Gene expression omnibus (GEO) series record; E.TABM: ArrayExpress (AE) series record; TGF, transforming growth factor; TNF, tumor necrosis factor.

Figure 2. Gene expression studies cluster according to the mode of EMT initiation rather than to cell type.

The cell type and treatment modality of EMT was annotated and revealed clustering according to the mode of EMT induction. The clustering persisted when genes shared between at least 14 GES datasets were used for the analysis. (A) Hierarchical clustering of 365 genes shared between at least 10 datasets. (B) Hierarchical clustering of 41 genes shared between at least 14 datasets. The legend indicates cell type and treatment modality (right panel). *, Transcription factor vectors: Runx2, Six1, Snail, Twist and Goosecoid. GSE: Gene expression omnibus (GEO) series record; E.TABM: ArrayExpress (AE) series record; TGF, transforming growth factor; TNF, tumor necrosis factor.

Figure 3. The 130 genes EMT-core list and the 365 genes list exhibit comparable enrichment ratios of GO biological processes and KEGG pathways.

The enrichment ratio is the number of observed genes divided by the number of expected genes for a given term or pathway. Enrichment ratios were obtained from WebGestalt or calculated with data from FatiGO. GO, gene ontology; BP, biological process; KEGG, Kyoto encyclopedia of genes and genomes.