Identification of Key Genes and Exploration of Therapeutic Targets for Chronic Tendon Injury Based on Bioinformatics and Machine Learning.

Background: Chronic tendon injury (CTI) is a common musculoskeletal disorder with complex molecular mechanisms, and currently lacks effective targeted therapeutic strategies. A comprehensive analysis of its key pathogenic genes and regulatory networks is crucial for the precise diagnosis and treatment of CTI. Methods: Differentially expressed genes (DEGs) in CTI and normal tendon tissue were identified using the GEO database, and intersected with genes derived from WGCNA to identify candidate genes. Subsequently, functional enrichment analysis was performed, and four machine learning algorithms were employed to further determine key genes. Finally, a systematic functional analysis of the key genes was performed, including assessments of diagnostic value, regulatory network construction, computational drug prediction and molecular docking. Results: A total of 271 candidate genes were identified, which were significantly enriched in focal adhesion, ECM-receptor interaction, and p53 signaling pathway. Subsequently, three key genes ( Conclusion: This study systematically revealed three key genes in CTI through comprehensive bioinformatics analysis. The diagnostic model, regulatory network, and predicted targeted drugs constructed based on these findings laid a solid theoretical foundation for subsequent translational medical research.