Integrating AI-driven single-cell analysis to decode epithelial heterogeneity: A prognostic signature and translational immunotherapy strategy targeting KRT18-induced PD-L1 in lung adenocarcinoma

Objective: The heterogeneity of epithelial cells and their interaction with the immune microenvironment play crucial roles in tumor progression, but the underlying mechanisms remain unclear. Methods: We analyzed single-cell transcriptomic data from normal and tumor tissues to characterize epithelial cells and their microenvironment. Key genes were identified and used, via survival analysis and multiple machine learning methods, to construct a prognostic model termed the Epithelial Signature (EpiSig). We further validated, through a series of experiments, the critical immunological roles of the key genes incorporated into the EpiSig model. Results: activated NF-kB/p65 to upregulate PD-L1, promoting immune exclusion and impairing T-cell effector function. Conclusions: may serve as a promising therapeutic target in LUAD.