Machine learning-based integration develops a disulfidptosis-related lncRNA signature for improving outcomes in gastric cancer

Abstract

Gastric cancer remains one of the deadliest cancers globally due to delayed detection and limited treatment options, underscoring the critical need for innovative prognostic methods. Disulfidptosis, a recently discovered programmed cell death triggered by disulphide stress, presents a fresh avenue for therapeutic exploration. This research examines disulfidptosis-related long noncoding RNAs (DRLs) in gastric cancer, with the goal of leveraging these lncRNAs as potential markers to enhance patient outcomes and treatment approaches. Comprehensive genomic and clinical data from stomach adenocarcinoma (STAD) were obtained from The Cancer Genome Atlas (TCGA). Employing least absolute shrinkage and selection operator (LASSO) regression analysis, a prognostic model was devised incorporating five key DRLs to forecast survival rates. The effectiveness of this model was validated using Kaplan-Meier survival plots, receiver operating characteristic (ROC) curves, and extensive functional enrichment studies. The importance of select lncRNAs and the expression variability of genes tied to disulfidptosis were validated via quantitative real-time PCR (qRT-PCR) and Western blot tests, establishing a solid foundation for their prognostic utility. Analyses of functional enrichment and tumour mutation burden highlighted the biological importance of these DRLs, connecting them to critical cancer pathways and immune responses. These discoveries broaden our comprehension of the molecular framework of gastric cancer and bolster the development of tailored treatment plans, highlighting the substantial role of DRLs in clinical prognosis and therapeutic intervention.

Keywords: Disulfidptosis; LASSO regression analysis; gastric cancer; lncRNA; machine learning.