Integrating Mendelian Randomization and Machine Learning to Identify Hypoxia-Related Diagnostic Biomarkers and Causal Relationship in COPD
Year: 2025
Type: article
Abstract: Background: Chronic obstructive pulmonary disease (COPD) involves progressive lung function decline, with hypoxia playing a key pathogenic role. However, systematic investigations focusing on hypoxia-related genes (HRGs) in COPD remain limited. Methods: We applied machine learning to identify HRG-associated diagnostic biomarkers and evaluated their performance via Receiver Operating Characteristic (ROC) analysis. Mendelian randomization (MR) was conducted to assess causal relationships between candidate genes and COPD. A nomogram model was constructed to evaluate clinical utility, and a ceRNA network was developed using ENCORI database. Results: Six HRG-based diagnostic biomarkers were identified, including SLC2A1 , which demonstrated strong diagnostic value (AUC > 0.8). MR analysis revealed a significant causal effect of SLC2A1 expression on COPD risk (OR = 1.32, 95% CI: 1.02– 1.71, P < 0.05). Functional evidence suggests SLC2A1 promotes hypoxia-induced metabolic reprogramming in airway epithelial cells. The constructed nomogram showed good clinical applicability. ceRNA analysis highlighted MALAT1 , NEAT1 , and XIST as potential upstream regulators. Conclusion: Our findings identify SLC2A1 as a causal and diagnostically relevant gene in COPD, offering novel insight into hypoxia-driven disease mechanisms and supporting future personalized therapeutic strategies. Keywords: chronic obstructive pulmonary disease, hypoxia-related genes, Mendelian randomization, machine learning
Source: International Journal of COPD
DOI: 10.2147/copd.s524381
Authors: Wenhui Fu, Yangli Liu, Renjie Li, Haiying Jin
Language: English
Subfield: Pulmonary and Respiratory Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $2,836
OpenAlex ID: W4414126633