Idiopathic pulmonary fibrosis (IPF), the most common idiopathic interstitial pneumonia, is a chronic and fatal fibrotic lung disease with unknown etiology, with higher incidence in older adults whose median age at diagnosis is about 65 years and the median survival time ranging 3–5 years after diagnosis [1], [2]. Patients often appear respiratory failure at the end stage. In recent years, the incidence and mortality of IPF have risen rapidly worldwide [2], [3]. Several comorbidities can occur [4], [5], [6], [7], among which patients with IPF have a risk nearly five times as high as that of the general population to develop lung cancer (LC) [8], [9] primarily developing in periphery adjacent to fibrotic areas of patients with IPF. Additionally, epidemiological evidence suggests that the incidence of lung cancer developed in patients with IPF ranges from 3 % to 22 % [10], [11], indicating there is no doubt about the association of IPF and LC.

The occurrence of LC is associated with the poor prognosis of IPF with a reduced median survival time (1.6–1.7 years) compared with IPF patients without LC [12]. There is no consensus statement raising the management and treatment for patients with this disease combination, thus early diagnosis through appropriate screening algorithms and detective methods is vital. High-resolution CT (HRCT) suggested by the comment to monitor the progression of IPF is difficult to detect precancerous lesion [10], [11]. The awareness of the pathogenic mechanisms of the coexistence of IPF and LC is essential to raise for excavating effective management and therapy of patients with both disorders. While recent studies have illustrated that multiple-overlapping mechanisms, including common genetic mutants, epigenetic alterations and activation of signal transduction pathways, involve the occurrence of IPF and LC [11], [13], [14], [15], how abnormal interstitial lung tissues produce cancerous lesion remains enigmatic. More identifications of molecular mechanisms promoting carcinogenesis within fibrotic lung are needed to further elucidate the coexistence of two lethal lung diseases.

In this context, we investigated links between IPF and NSCLC, comprising biological mechanisms involved by differentially expressed genes in two lung disorders’ tissue compared with normal tissues, which was based on comprehensive bioinformatics analysis and machine learning of gene expression profile from lung disorders’ tissue sample.