Machine learning-based prognostic modeling of seven signatures associated with lysosomes for predicting prognosis and immune status in clear cell renal cell carcinoma.

BACKGROUND

Clear cell renal cell carcinoma (ccRCC) is the most common subtype of kidney cancer and is associated with poor prognosis in advanced stages. This study aims to develop a prognostic model for patients with ccRCC based on a lysosome-related gene signature.

METHODS

The clinical and transcriptomic data of Kidney Renal Clear Cell Carcinoma (KIRC) patients were downloaded from TCGA, cBioportal and GEO databases, and lysosome-related gene sets were acquired in the previous study. TCGA data was used as a training set to investigate the prognostic role of lysosomal-related genes in ccRCC, and cBioportal and GEO databases were used for validation. After the lysosome-related differentially expressed genes were found, machine learning method was used to construct a risk model, and Kaplan-Meier (K-M) and receiver operating characteristic curves (ROC) were used to evaluate the performance of the model.

RESULTS

Machine learning methods were utilized to identify seven gene signatures related to lysosome, which accurately predict the prognosis of ccRCC. Patients with higher risk scores demonstrate poorer overall survival (HR: 2.467, 95%CI: 1.642-3.706, P<0.001), and significant disparities in immune infiltration, immune score, and response to anticancer drugs are observed between the high-risk group and the low-risk group (P<0.001).

CONCLUSIONS

The prognostic model developed in this study demonstrates a high efficacy in accurately predicting the overall survival (OS) of ccRCC patients, thereby offering a novel perspective for the advancement of ccRCC treatment.