A novel prognostic signature based on cuproptosis-related lncRNA mining in colorectal cancer

Background: Colorectal cancer (CRC) is a common malignant tumor that affects the large bowel or the rectum. Cuproptosis, recently discovered programmed cell death process, may play an important role in CRC tumorigenesis. Long non-coding RNAs (lncRNAs) can alter the proliferation of colorectal cancer cells through the control and activation of gene expression. To date, cuproptosis-related lncRNAs, have not been investigated as potential predictive biomarkers in colorectal cancer. Methods: The mRNA and lncRNA expression data of colorectal cancer were gathered from The Tumor Genome Atlas (TCGA) database, and Pearson correlation analysis and univariate Cox regression analysis were used to identify the lncRNAs with differential prognosis. Colorectal cancer was classified using consistent clustering, and the clinical significance of different types, tumor heterogeneity, and immune microenvironment differences was investigated. The differential lncRNAs were further screened using LASSO regression to develop a risk scoring model, which was then paired with clinicopathological variables to create a nomogram. Finally, the copy number changes in the high-risk and low-risk groups were compared. Results: Two clusters were formed based on the 28 prognostic cuproptosis-related lncRNAs, and the prognosis of cluster 2 was found to be significantly lower than that of cluster 1. Cluster 1 showed increased immune cell infiltration and immunological score, as well as strong enrichment of immune checkpoint genes. Next, LASSO regression was used to select 11 distinctive lncRNAs, and a risk score model was constructed using the training set to distinguish between high and low-risk groups. Patients in the high-risk group had a lower survival rate than those in the low-risk group, and both the test set and the total set produced consistent results. The AUC value of the ROC curve revealed the scoring model's efficacy in predicting long-term OS in patients. Moreover, the model could be used as an independent predictor when combined with a multivariate analysis of clinicopathological features, and our nomogram could be used intuitively to predict prognosis. Conclusion: Collectively, we developed a risk model using 11 differential lncRNAs and demonstrated that the model has predictive value as well as clinical and therapeutic implications for predicting prognosis in CRC patients.