Expression signature of IFN/STAT1 signaling genes predicts poor survival outcome in glioblastoma multiforme in a subtype-specific manner

Abstract

Previous reports have implicated an induction of genes in IFN/STAT1 (Interferon/STAT1) signaling in radiation resistant and prosurvival tumor phenotypes in a number of cancer cell lines, and we have hypothesized that upregulation of these genes may be predictive of poor survival outcome and/or treatment response in Glioblastoma Multiforme (GBM) patients. We have developed a list of 8 genes related to IFN/STAT1 that we hypothesize to be predictive of poor survival in GBM patients. Our working hypothesis that over-expression of this gene signature predicts poor survival outcome in GBM patients was confirmed, and in addition, it was demonstrated that the survival model was highly subtype-dependent, with strong dependence in the Proneural subtype and no detected dependence in the Classical and Mesenchymal subtypes. We developed a specific multi-gene survival model for the Proneural subtype in the TCGA (the Cancer Genome Atlas) discovery set which we have validated in the TCGA validation set. In addition, we have performed network analysis in the form of Bayesian Network discovery and Ingenuity Pathway Analysis to further dissect the underlying biology of this gene signature in the etiology of GBM. We theorize that the strong predictive value of the IFN/STAT1 gene signature in the Proneural subtype may be due to chemotherapy and/or radiation resistance induced through prolonged constitutive signaling of these genes during the course of the illness. The results of this study have implications both for better prediction models for survival outcome in GBM and for improved understanding of the underlying subtype-specific molecular mechanisms for GBM tumor progression and treatment response.

Figure 1. Survival Curves for age-adjusted Cox Proportional Hazard models for 1^st quartile (red) and 3^rd quartile (blue) gene expression values for each gene in the Proneural subtype.

Figure 2. Bar plot of total explained variance (R²) for survival models discovered using stepwise selection with genes only (“No Age”) or with genes and age (“Age”) for all GBM patients and by subtype.

Figure 3. Graph of predicted and actual survival times in Proneural subtype for the discovery data set (left) and the validation data set (right) using the age-adjusted stepwise selection model (up to IFI44).

The correlation between predicted and actual survival values is 0.64 (0.45, 0.77) in the discovery set and 0.39 (0.16, 0.57) in validation set.

Figure 4. Functional Annotation networks from IPA (Ingenuity Pathway Analysis) that show documented gene relationships among the genes in the hypothesized eight gene STAT1/IFN gene set (A) and that show the functional relationships among these genes as they relate to Interferon signaling (B) (genes in eight gene signature are shaded).

Figure 5. Discovered Bayesian Network for the full set of GBM (A) and the Proneural subtype (B).

Growth-shrink algorithm was used and 80% bootstrap support for presence of edges and 50% bootstrap support for edge direction were required for the full sample (A), and 50% each were required for the Proneural subtype (B). With the more stringent criteria for the Proneural subtype (80% bootstrap support for edge presence) the OAS1->MX1 and ISG15->IFIT1 edges were discovered.