Machine Learning-Driven Prognostic Analysis of Cuproptosis and Disulfidptosis-related lncRNAs in Clear Cell Renal Cell Carcinoma: A Step Towards Precision Oncology

Abstract

Abstract Background Clear cell renal cell carcinoma (ccRCC), the most prevalent type of kidney malignancy, is noted for its high fatality rate, underscoring the imperative for reliable diagnostic and prognostic indicators. The mechanisms of cell death, cuproptosis and disulfidptosis, recently identified, along with the variable expression of associated genes and long non-coding RNAs (lncRNAs), have been linked to the progression of cancer and resistance to treatment. The objective of this research is to delineate the functions of lncRNAs associated with cuproptosis and disulfidptosis (CDRLRs) in ccRCC, thereby enhancing the precision of prognostic evaluations and contributing to the development of targeted therapeutic approaches. Methods We applied the least absolute shrinkage and selection operator (LASSO) regression analysis to construct a prognostic signature from a set of CDRLRs. The data from The Cancer Genome Atlas (TCGA) was segmented into high and low-risk groups based on median risk scores from the signature, to investigate their prognostic disparities. Results The derived signature, which includes four CDRLRs—ACVR2B-AS1, AC095055.1, AL161782.1, and MANEA-DT—was confirmed to be predictive for ccRCC patient outcomes, as evidenced by receiver operating characteristic (ROC) curves and Kaplan-Meier (K-M) survival analysis. The prognostic model enabled the graphical prediction of 1-, 3-, and 5-year survival rates for ccRCC patients, with calibration plots affirming the concordance between anticipated and observed survival rates. Additionally, the study assessed tumor mutation burden (TMB) and the immune microenvironment (TME) using oncoPredict and Immunophenoscore (IPS) algorithms, uncovering that patients in the high-risk group presented with increased TMB and distinctive TME profiles, which may influence their response to targeted and immune therapies. Notably, marked differences in the sensitivity to anticancer drugs were observed between the risk groups. Conclusion This investigation introduces a prognostic signature comprising cuproptosis and disulfidptosis-associated lncRNAs as a viable biomarker for ccRCC. Beyond enhancing prognostic accuracy, this signature holds the promise for steering personalized treatments, thereby advancing precision oncology for ccRCC. However, it is imperative to pursue further clinical validation to adopt these insights into clinical practice.