Idiopathic pulmonary fibrosis (IPF), a progressive and fatal lung disease, significantly increases the risk of lung cancer, particularly lung adenocarcinoma (LUAD). However, the shared genetic mechanisms driving IPF and LUAD comorbidities remain poorly understood, necessitating integrated multi-omics investigations. Through bulk and single-cell transcriptomic analyses, we identified 308 shared differentially expressed genes enriched in lipid metabolism and immune-inflammatory processes. Additionally, single-cell profiling revealed significant alterations in epithelial cells and macrophage populations between LUAD and IPF tissues, underscoring their role in disease progression. Furthermore, the copy number variation profiling identified a premalignant epithelial subpopulation in IPF exhibiting transcriptional signatures resembling LUAD malignant epithelial cells, and trajectory analysis illustrated a potential temporal progression toward malignancy. To identify co-causal genes, we performed weighted gene coexpression network analysis, defining modules associated with key cell types involved in comorbidities. Moreover, leveraging 101 algorithm combinations across ten machine learning approaches, we constructed a robust prognostic model, pinpointing CHST6 as a top prognostic gene consistently upregulated in both LUAD and IPF. Functional validation confirmed that CHST6 promotes lung cancer cell proliferation, migration, and invasion. In conclusion, our findings elucidate the shared molecular landscape of LUAD and IPF and propose that CHST6 is a promising co-disease therapeutic target.