Biological convergence of cancer signatures

Abstract

Gene expression profiling has identified cancer prognostic and predictive signatures with superior performance to conventional histopathological or clinical parameters. Consequently, signatures are being incorporated into clinical practice and will soon influence everyday decisions in oncology. However, the slight overlap in the gene identity between signatures for the same cancer type or condition raises questions about their biological and clinical implications. To clarify these issues, better understanding of the molecular properties and possible interactions underlying apparently dissimilar signatures is needed. Here, we evaluated whether the signatures of 24 independent studies are related at the genome, transcriptome or proteome levels. Significant associations were consistently observed across these molecular layers, which suggest the existence of a common cancer cell phenotype. Convergence on cell proliferation and death supports the pivotal involvement of these processes in prognosis, metastasis and treatment response. In addition, functional and molecular associations were identified with the immune response in different cancer types and conditions that complement the contribution of cell proliferation and death. Examination of additional, independent, cancer datasets corroborated our observations. This study proposes a comprehensive strategy for interpreting cancer signatures that reveals common design principles and systems-level properties.

Figure 1. Integrative analysis of cancer signatures.

Strategy for defining the common properties and interactions between signatures at the genome, transcriptome and proteome levels, and validation in independent datasets.

Figure 2. Genomic and transcriptomic properties of cancer signatures associated with the potential for cell proliferation and repressed cell death.

A, representation of E2F motifs based on JASPAR and TRANSFAC matrices and the Poisson distribution, with P values adjusted using the FDR approach for analyses-columns. Values are shown as detailed in the inset: red/orange indicates significant over-representation and blue indicates significant under-representation. The E2F1_Q6 motif represents the putative action of E2F1 and MYC. B, representation of E2F1-AP2 and E2F4 binding sites from chromatin immunoprecipitation (chip) assays using the same statistical methodology as described above. The E2F4 data correspond to the joint analysis of cell cycle phases . C, representation of genes with periodic expression through the cell cycle. D, representation of ER transcriptional regulation from chromatin immunoprecipitation assays or transcriptional changes in MCF7 cells. E, representation of additional promoter motifs using TRANSFAC matrices. The wound response signature without cell cycle-associated genes is indicated by the suffix “(-cc)”, and the “total set” signature of ER-negative breast cancer contains the immune response plus other biological processes such as the cell cycle. The dasatinib predictive signature is divided into two sets for the effect in prostate and breast cancer respectively. The colorectal prognostic signatures are as defined in Table S1.

Figure 3. Expression correlations with defined transcription factors.

A, expression correlations between seven transcription factors―gene names shown at the top of each graph―and genes differentially expressed for breast cancer prognosis measured by metastasis events up to 5 years (pink curves) relative to non-differentially expressed genes in this condition (brown curves). The graphs show absolute PCC values. B, same analysis for differentially expressed genes after docetaxel treatment of breast cancer patients relative to non-differentially expressed genes in this condition. Results for E2F1, E2F4, MYB and MYC are for average values of all microarray probes representing each factor, whereas the insets show the results for individual probes with significant differences.

Figure 4. Transcriptomic correlations between signatures and with defined biological processes.

A, heat map of average PCCs between cancer signatures in a breast cancer gene expression dataset . Significant co-expression (empirical P values<0.05) is indicated by dots. Note that the matrix is not symmetrical because the results were dependent on the size of each gene set; therefore, the larger gene sets (e.g. wound response or invasiveness) showed significant co-expression with many other signatures, perhaps partly due to the fact that they had greater statistical power with which to detect them. Each dot corresponds to the comparison between a signature on the left (simulated set) and a signature at the bottom. The Cell Death and Mitosis sets are highlighted in pink. B, left panel, list of signatures that showed significant correlation with the Cell Death or Mitosis complete GO sets. Right panel, list of signatures that showed significant correlation with the Cell Death or Mitosis sets, but only using their principal components. C, observed (discontinuous red line) versus expected (black curve for 10,000 randomly selected sets) average PCCs between the Mitosis set and the 70-gene set, the Cell Death set, or genes with periodic expression through the cell cycle.

Figure 5. Proximity between gene products of signatures in the interactome network.

A, heat map of average shortest paths between proteins encoded by signatures. This analysis was performed using only the giant network component. An example of shortest path differences with respect to the giant component is shown in the right panel for the comparison between the complete Cell Death and Mitosis GO sets. B, heat map of comparisons of 1,000 randomly selected 50-protein sets in the giant component. Right panel, density plot of average shortest path in randomly selected sets: the 5% lower values are highlighted, which correspond to an average shortest path <4.09. Comparisons between signatures below this empirical cut-off are shown by dots in A. C, left panel, network representation of average shortest paths between Cell Death and Mitosis and cancer signatures as shown in the inset. Edges lengths are proportional to the average shortest path values. Right panel, network representation of average shortest paths between Cell Death and Mitosis and cancer signatures or randomly selected protein sets with equivalent degree centrality.

Figure 6. Asymmetric distribution of gene annotations in the response to cetuximab treatment.

A, left panel, GSEA results for the strongest associated phenotype with high-expression genes predicting treatment response (log₂ HR>0). Central panel, expression analysis plot of the extreme gene expression (EREG), which was also noted in the original publication . Right panel, additional phenotypic and GO term sets with high-expression genes associated to treatment response at FDR Q values<1%. B, left panel, GSEA results for the strongest associated phenotype with low-expression genes predicting treatment response (log₂ HR<0). Central panel, expression analysis plot of the extreme gene expression (IL15). Right panel, additional phenotypic and GO term sets with low-expression genes associated to treatment response at FDR Q values<1%. C, Histogram plot of average expression values of genes annotated with the Immune Response or Mitosis across samples in the cetuximab dataset. Average GO set expression values show a negative correlation with ordered metastatic samples.