Identification of Key Genes Associated with Overall Survival in Glioblastoma Multiforme Using TCGA RNA-Seq Expression Data

Abstract

Background/Objectives: Glioblastoma multiforme (GBM) is an aggressive and heterogeneous brain tumor with poor prognosis, emphasizing the need for reliable molecular biomarkers to improve patient stratification and treatment planning. This study aimed to identify key genes associated with overall survival in GBM by employing and comparing machine learning (ML) and deep learning (DL) approaches using RNA-Seq gene expression data. Methods: RNA-Seq expression and clinical data for primary GBM tumors were obtained from The Cancer Genome Atlas (TCGA). A univariate Cox proportional hazards regression was used to identify survival-associated genes. For survival prediction, ML-based feature selection techniques-RF, GB, SVM-RFE, RF-RFE, and PCA-were used to construct multivariate Cox models. Separately, DeepSurv, a DL-based survival model, was trained using the significant genes from the univariate analysis. Gradient-based importance scoring was applied to determine key genes from the DeepSurv model. Results: Univariate analysis yielded 694 survival-associated genes. The best ML-based Cox model (RF-RFE with 90% training data) achieved a c-index of 0.725. In comparison, DeepSurv demonstrated superior performance with a c-index of 0.822. The top 10 genes were identified from the DeepSurv analysis, including CMTR1, GMPR, and PPY. Kaplan-Meier survival curves confirmed their prognostic significance, and network analysis highlighted their roles in processes such as purine metabolism, RNA processing, and neuroendocrine signaling. Conclusions: This study demonstrates the effectiveness of combining ML and DL models to identify prognostic gene expression biomarkers in GBM, with DeepSurv providing higher predictive accuracy. The findings offer valuable insights into GBM biology and highlight candidate biomarkers for further validation and therapeutic development.

Keywords: Cox regression; RNA-Seq; biomarkers; deep learning; gene network analysis; glioblastoma multiforme; machine learning; survival analysis.

Figure 1

Mean variance trend plot of voom-transformed data.

Figure 2

Principal component analysis of tumor and normal tissue samples.

Figure 3

Kaplan–Meier survival curves comparing overall survival between patient groups stratified by gene expression level (UP = high expression, DOWN = low expression) for the top prognostic genes: (a) CMTR1, (b) RPL23AP42, (c) TSPYL1, (d) AC011287.1, (e) RPL7L1P8, (f) CCDC107, (g) AL354743.2, (h) GMPR, (i) PPY, (j) MT-TL1.

Figure 4

Protein–protein interaction (PPI) network highlighting hub genes among the top-ranked prognostic candidates and their interacting partners.