Comprehensive Analysis of Cuproptosis-Related Genes According to Cancer Stage and Their Prognostic Value in Cervical Cancer.

Cuproptosis is a novel form of metabolism-associated cell death. Cervical cancer (CC) exhibits elevated serum copper levels and mitochondrial metabolic reprogramming, making cuproptosis-related genes (CRGs) potentially critical for prognosis prediction and therapeutic targeting. However, studies on CRGs in CC remain limited. This study aimed to construct prognostic and cancer staging models for CC using machine learning (ML) algorithms. Gene expression profiles of patients with CC were obtained from the TCGA and GEO databases. Five ML algorithms were employed to identify significant factors, including random forest (RF), support vector machine (SVM), Gaussian mixture model (GMM), Bayesian, and StepCox. A prognostic model was subsequently constructed using LASSO-Cox regression based on the selected genes. Concurrently, a cancer staging model was built using ML algorithms incorporating three distinct gene categories. Finally, qRT-PCR and Western blotting were conducted to validate the expression of signature genes at both the tissue and cellular levels. Additionally, CTD-based screening and in vitro functional assays were performed to evaluate the effects of DDP on CC cells. Through integrated bioinformatics and ML approaches, a prognostic model comprising nine CRGs was successfully established (GMM = 0.72). The derived risk score served as an independent prognostic indicator for CC (