Construction and verification of an endoplasmic reticulum stress-related prognostic model for endometrial cancer based on WGCNA and machine learning algorithms.

Background: Endoplasmic reticulum (ER) stress arises from the accumulation of misfolded or unfolded proteins within the cell and is intricately linked to the initiation and progression of various tumors and their therapeutic strategies. However, the precise role of ER stress in uterine corpus endometrial cancer (UCEC) remains unclear. Methods: Data on patients with UCEC and control subjects were obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. Using differential expression analysis and Weighted Gene Co-expression Network Analysis (WGCNA), we identified pivotal differentially expressed ER stress-related genes (DEERGs). Further validation of the significance of these genes in UCEC was achieved through consensus clustering and bioinformatic analyses. Using Cox regression analysis and several machine learning algorithms (least absolute shrinkage and selection operator [LASSO], eXtreme Gradient Boosting [XGBoost], support vector machine recursive feature elimination [SVM-RFE], and Random Forest), hub DEERGs associated with patient prognosis were effectively identified. Based on the four identified hub genes, a prognostic model and nomogram were constructed. Additionally, a drug sensitivity analysis and Results: A total of 94 DEERGs were identified in patients with UCEC and healthy controls. Consensus clustering analysis revealed significant differences in prognosis, typical immune checkpoints, and tumor microenvironments between the subtypes. Using Cox regression analysis and machine learning, four hub DEERGs, MYBL2, RADX, RUSC2, and CYP46A1, were identified to construct a prognostic model. The reliability of the model was validated using receiver operating characteristic (ROC) curves. Decision curve analysis (DCA) demonstrated the superior predictive ability of the nomogram in terms of 3- and 5-year survival, compared with that of other clinical indicators. Drug sensitivity analysis revealed increased sensitivity to dactinomycin, docetaxel, selumetinib, and trametinib in the low-risk group. The expressions of RADX, RUSC2, and CYP46A1 were downregulated, whereas that of MYBL2 was upregulated in UCEC tissues, as demonstrated by reverse transcription-quantitative polymerase chain reaction (RT-qPCR) and immunofluorescence assays. Conclusion: This study developed a stable and accurate prognostic model based on multiple bioinformatics analyses, which can be used to assess the prognosis of UCEC. This model may contribute to future research on the risk stratification of patients with UCEC and the formulation of novel treatment strategies.