Machine learning-based identification of cuproptosis-related signatures and immune microenvironment in idiopathic pulmonary fibrosis

Idiopathic pulmonary fibrosis (IPF) is a fatal fibrotic lung disease. This study aimed to explore cuproptosis-related molecular clusters and build a predictive model for IPF. Using dataset GSE32537, we analyzed immune infiltration and cuproptosis regulators, followed by WGCNA and machine-learning modeling. Two cuproptosis-related clusters were identified, with C2 showing stronger immune activation. Among four algorithms, the GLM model showed the best performance (AUC = 0.992) and yielded a five-gene signature. The nomogram and calibration analyses confirmed its accuracy. This study provides a reliable IPF prediction model and insight into cuproptosis-related mechanisms.