Integrating single-cell analysis and machine learning algorithms to explore lactylation-related molecular mechanisms and therapeutic responses in clear cell renal cell carcinoma and identifying CDT1 as a potential biomarker.

Background and aim: Lactylation is a novel histone modification driven by lactate accumulation, which has been implicated in clear cell renal cell carcinoma (ccRCC) progression. However, its comprehensive molecular mechanism and clinical relevance remain poorly understood. This study aimed to investigate lactylation-related molecular mechanisms and therapeutic responses in ccRCC using integrated single-cell analysis and machine learning algorithms. Methods: We integrated single-cell RNA sequencing and bulk transcriptomic data from patients with ccRCC. Transcriptional signatures of lactylation-related genes were evaluated using four gene set scoring algorithms. Key lactylation-related genes were identified through weighted gene co-expression network analysis and differential expression analysis. A prognostic model was constructed using 10 machine learning algorithms and subsequently validated in independent cohorts. The functional role of the core gene, Results: We established a prognostic model comprising 13 lactylation-related genes. The model robustly stratified patients into high- and low-risk groups with distinct survival outcomes, immune microenvironment features, and immunotherapy responses. Functional assays revealed that Conclusions: This study delineates the molecular heterogeneity associated with lactylation-related gene expression in ccRCC and presents a validated prognostic model. It identifies