Integrating bioinformatics and machine learning to unravel shared mechanisms and biomarkers in chronic obstructive pulmonary disease and type 2 diabetes

Abstract

Background Chronic obstructive pulmonary disease (COPD) and type 2 diabetes mellitus (T2DM) are on the rise. While there is evidence of a link between the two diseases, the pathophysiological mechanisms they share are not fully understood. Methods In this study, the co-expressed genes of COPD and T2DM in Gene Expression Omnibus database were identified by bioinformatics method, and the functional enrichment analysis was performed. Machine learning algorithms were used to identify biomarkers. The diagnostic value of these biomarkers was assessed by receiver operating characteristic analysis, and their relationship to immune cells was investigated by immunoinfiltration analysis. Finally, real-time quantitative polymerase chain reaction was performed. Results A total of five overlapping genes were obtained, focusing on pathways associated with insulin resistance and inflammatory mediators. The machine learning method identified three biomarkers: matrix metalloproteinase 9, laminin α4, and differentially expressed in normal cells and neoplasia domain containing 4 C, all of which were shown to have high diagnostic values by receiver operating characteristic analysis. Immunoinfiltration analysis showed that it was associated with a variety of immune cells. In addition, the real-time quantitative polymerase chain reaction results confirmed agreement with our bioinformatics analysis. Conclusions Our study sheds light on the common pathogenesis and biomarkers of both diseases, and these findings have potential implications for the development of new diagnostic and treatment strategies for COPD and T2DM. Key message What is already known on this topic? Chronic obstructive pulmonary disease (COPD) and type 2 diabetes mellitus (T2DM) often coexist as comorbidities. However, the exact mechanistic link between the two diseases remains complex, multifactorial, and not fully understood. What this study adds? Three biomarkers, including matrix metalloproteinase, laminin α4, and differentially expressed in normal cells and neoplasia domain containing 4 C, were identified as key co-expression hub genes in COPD and T2DM. How this study might affect research, practice or policy? Future studies may benefit from incorporating a larger sample set to further explore and validate the diagnostic and therapeutic effects of these core genes.