IPF-related new macrophage subpopulations and diagnostic biomarker identification - combine machine learning with single-cell analysis

Idiopathic Pulmonary Fibrosis (IPF) is a chronic disease with an unknown etiology and lacks specific treatment. Macrophages, as a major component of the lung immune system, play a crucial regulatory role in IPF, especially during the processes of inflammation and fibrosis. However, our understanding of the cellular heterogeneity, molecular characteristics, and clinical relevance of macrophages in IPF remains relatively limited. Through in-depth analysis of single-cell transcriptomic data from 8 IPF patients, we revealed distinct macrophage subtypes in IPF lung tissue. In this study, we identified a macrophage subset unique to IPF lung tissue, named ATP5-MΦ, whose expression of the ATP5 gene family is closely associated with oxidative phosphorylation and proton transmembrane transport, suggesting that ATP5-MΦ may have higher ATP synthesis capacity in IPF lung tissue. Furthermore, using hdWGCNA, we identified a co-expressed gene module associated with another macrophage subset in IPF (IPF-MΦ). Through machine learning methods, we identified IPF-MΦ feature genes (IRMG) with the potential to serve as prognostic markers for IPF and established a predictive model to assess the prognosis of IPF patients. Based on differential expression of IRMG, we successfully stratified IPF patients into two subtypes exhibiting distinct clinical outcomes and immune microenvironments. This study provides important molecular and clinical foundations for a deeper understanding of the pathogenesis of IPF and the development of relevant therapeutic strategies.