Discovery of a novel three-long non-coding RNA signature for predicting the prognosis of patients with gastric cancer

Baokground: Accumulating evidence demonstrates that long non-coding RNAs (lncRNAs) play a predictive role in the prognosis of gastric cancer (GC). The present study aims to construct a lncRNA-based model via mining data of The Cancer Genome Atlas (TCGA). Methods: Differentially expressed lncRNAs were first identified, followed by univariate Cox analysis, Robust likelihood-based survival model and multivariate Cox analysis to construct a signature composed of lncRNAs. Results: A three-lncRNA based predictive signature (OVAAL, FLJ16779, FAM230D) was established to stratify GC patients into high- and low-risk groups. Patients in the high-risk group had markedly shorter overall survival (OS) than those in the low-risk group, which was verified by the ROC curve. Then, we validated the predictive power of the scoring system in other two cohorts. Multivariate Cox analysis also indicated that the 3-lncRNA signature was an independent prognostic factor for survival prediction in GC patients. Moreover, Gene Set Enrichment Analysis (GSEA) revealed that diverse metabolic pathways significantly clustered in the low-risk group, which might explain how the 3-lncRNA signature promoted gastric carcinogenesis. Conclusions: We established a robust three-lncRNA model to predict the OS of GC patients, which might benefit the clinical decision making for personalized treatment and prognostic prediction for GC patients.