Identification and prognostic value of a glycolysis-related gene signature in patients with bladder cancer

Abstract

Bladder cancer (BC) is one of the most common malignancies worldwide. Several biomarkers related to the prognosis of patients with BC have previously been identified. However, these prognostic models use only one gene and are thus not reliable or accurate enough. The purpose of our study was to develop an innovative gene signature that has greater prognostic value in BC. So, in this study, we performed mRNA expression profiling of glycolysis-related genes in BC (n = 407) cohorts by mining data from The Cancer Genome Atlas (TCGA) database. The glycolysis-related gene sets were confirmed using the Gene Set Enrichment Analysis (GSEA). Using Cox regression analysis, a risk score staging model was built based on the genes that were determined to be significantly associated with BC outcome. Eventually, the system of risk score was structured to predict a patient's survival, and we identified four genes (CHPF, AK3, GALK1, and NUP188) that were associated with the outcomes of BC patients. According to the above-mentioned gene signature, patients were divided into two risk subgroups. The analysis showed that our constructed risk model was independent of clinical features and that the risk score was a highly powerful tool for predicting the overall survival (OS) of BC patients. Taking together, we identified a gene signature associated with glycolysis that could effectively predict the prognosis of BC patients. Our findings offer a new perspective for the clinical research and treatment of BC.

Figure 1

Enrichment plots of two glycolysis-related gene sets in BC from GSEA. The gene sets of HALLMARK_GLYCOLYSIS (A) and REACTOME_GLYCOLYSIS (B) differ significantly between normal samples and BC samples.

Figure 2

The four-gene risk signature related to glycolysis predicts the OS of BC patients. (A) Risk score curve of patients’ distribution. (B) The relationship between survival status and survival time (years). (C) The alteration of genes expression profile is associated with risk score in Heat map.

Figure 3

Univariable and multivariable independent prognostic analyses for clinical features in BC. (A) The age, TNM stage, T stage, N stage, and risk score had significant differences (P < .05) in the univariate analysis, which indicate those factors were related to patients OS. (B) In the multivariate analysis, the age and risk score could be selected as the independent prognostic factors with P values <.05.

Figure 4

Genetic alteration and the identification of genes signature associated with patient's prognosis. (A) The mutations frequency and type of four glycolysis-related genes in BC clinical samples. (B) The amount, height and location of the annotation represent different mutations of each gene. (C) The expression of selected genes was different in normal and tumor groups (^∗P < .05, ^∗∗P < .01, ^∗∗∗P < .001).

Figure 5

Kaplan–Meier analysis for BC patients. According to risk score, individuals with BC divided into the high-risk and low-risk groups, and Kaplan–Meier OS curve showed significantly statistical difference in two groups (A). Clinical features that include age (B), TNM stage (C), T stage (D), M stage (E), and N stage (F) were also significantly associated with patients OS.

Figure 6

Survival analysis of Kaplan–Meier curves with clinical subgroups for the prognostic value of risk signature. (A) K–M curves for the patient group with age ≤65 (n = 160) and patient group with age >65 (n = 247). (B) K–M curves for the male group (n = 300) and female group (n = 107). (C) K–M curves for the stage I to II group (n = 132) and stage III to IV group (n = 273). (D) K–M curves for the T0–2 group (n = 123) and the T3–4 group (n = 251). (E) K–M curves for the N0 group (n = 237) and the N1–3 group (n = 128). K–M curves for the M0 group (n = 196) (F) and the high-grade group (n = 383) (G).