Long noncoding RNAs to predict postoperative recurrence in bladder cancer and to develop a new molecular classification system

Abstract

Background: Reliable molecular markers are much needed for early prediction of recurrence in muscle-invasive bladder cancer (MIBC) patients. We aimed to build a long-noncoding RNA (lncRNA) signature to improve recurrence prediction and lncRNA-based molecular classification of MIBC.

Methods: LncRNAs of 320 MIBC patients from the Cancer Genome Atlas (TCGA) database were analyzed, and a nomogram was established. A molecular classification system was created, and immunotherapy and chemotherapy response predictions, immune score analysis, immune infiltration analysis, and mutational data analysis were conducted. Survival analysis validation was also performed.

Results: An eight-lncRNA signature classifed the patients into high- and low-risk subgroups, and these groups had significantly different (disease-free survival) DFS. The ability of the eight-lncRNA signature to make an accurate prognosis was tested using a validation dataset from our samples. The nomogram achieved a C-index of 0.719 (95% CI, 0.674-0.764). Time-dependent receiver operating characteristic curve (ROC) analysis indicated the superior prognostic accuracy of nomograms for DFS prediction (0.76, 95% CI, 0.697-0.807). Further, the four clusters (median DFS = 11.8, 15.3, 17.9, and 18.9 months, respectively) showed a high frequency of TTN (cluster 1), fibroblast growth factor receptor-3 (cluster 2), TP53 (cluster 3), and TP53 mutations (cluster 4), respectively. They were enriched with M2 macrophages (cluster 1), CD8⁺ T cells (cluster 2), M0 macrophages (cluster 3), and M0 macrophages (cluster 4), respectively. Clusters 2 and 3 demonstrated potential sensitivity to immunotherapy and insensitivity to chemotherapy, whereas cluster 4 showed potential insensitivity to immunotherapy and sensitivity to chemotherapy.

Conclusions: The eight-lncRNA signature risk model may be a reliable prognostic signature for MIBC, which provides new insights into prediction of recurrence of MIBC. The model may help clinical decision and eventually benefit patients.

Keywords: biomarker; bladder cancer; lncRNA; molecular subtypes; recurrence.

FIGURE 1

(A) Flowchart of study. (B) Kaplan–Meier curves of DFS based on the lncScore in MIBC patients. (C) Construction of a Cox model for DFS. (D) Nomogram to predict the DFS of MIBC patients. (E) Calibration curves of the nomogram to predict the 3‐year DFS. (F) Calibration curves of the nomogram to predict the 5‐year DFS. (G) Prediction of DFS by time‐dependent ROC analysis

FIGURE 2

(A) Optimal k‐value selection graph for consistent clustering. (B) Consistent clustering CDF graph. (C) Sample clustering heatmap for k = 4. (D) Kaplan–Meier curves among the four subtypes of bladder cancer

FIGURE 3

(A) Prediction of ICI therapy for four subtypes of bladder cancer. (B) Prediction of cisplatin for four subtypes of bladder cancer. (C) Prediction of gemcitabine for four subtypes of bladder cancer

FIGURE 4

(A) Stromal scores of the four subtypes of bladder cancer. (B) Immune Scores of the four subtypes of bladder cancer. (C) Stromal scores of the different stages of bladder cancer. (D) Immune Scores of the different stages of bladder cancer. (E) Kaplan–Meier curves among high and low Stromal score groups. (F) Kaplan–Meier curves among high and low Immune score groups. (G) Heatmap of grade, gender, age, stromal score, and immune Score. (H) Proportions of tumor‐infiltrating immune cells among the four subtypes of bladder cancer

FIGURE 5

(A) Bladder cancer mutational profile. (B) Distribution of common gene mutations in bladder cancer cluster 1. (C) Distribution of common gene mutations in bladder cancer cluster 2. (D) Distribution of common gene mutations in bladder cancer cluster 3. (E) Distribution of common gene mutations in bladder cancer cluster 4

FIGURE 6

(A) Similarity between mutation characteristics of bladder cancer cluster 1 and cosmic mutation signature. (B) Similarity between mutation characteristics of bladder cancer cluster 2 and cosmic mutation signature. (C) Similarity between mutation characteristics of bladder cancer cluster 3 and cosmic mutation signature. (D) Similarity between mutation characteristics of bladder cancer cluster 4 and cosmic mutation signature. (E) Frequency distribution of 96 mutation types in bladder cancer cluster 1. (F) Frequency distribution of 96 mutation types in bladder cancer cluster 2. (G) Frequency distribution of 96 mutation types in bladder cancer cluster 3. (H) Frequency distribution of 96 mutation types in bladder cancer cluster 4