Obstructive sleep apnea and major depressive disorder: Shared transcriptional signatures and candidate pathways identified via bioinformatics analysis

Background Obstructive sleep apnea (OSA) frequently co‐occurs with major depressive disorder (MDD). However, the underlying biological mechanisms remain unclear. This study aimed to identify OSA‐related transcriptional signatures associated with depressive status using integrated bioinformatics and machine learning. Methods Transcriptomic datasets GSE98793 and GSE135917 were obtained from the Gene Expression Omnibus. Shared differentially expressed genes (DEGs) were defined as OSA‐related DEGs (OSA‐DEGs). Functional enrichment analyses were conducted to explore the underlying biological pathways. Three machine learning algorithms LASSO, support vector machine‐recursive feature elimination, and random forest, were applied to identify key genes. A support vector machine (SVM) model was constructed to evaluate diagnostic performance. Drug–gene interaction analysis was performed to identify potential therapeutic targets. Results OSA‐DEGs were enriched in pathways related to ribosomal biogenesis, cytoplasmic translation, and immune responses. Six core genes were identified (KLRB1, SPINK2, PPP1R17, ILF3‐AS1, BLOC1S6, and TROVE2). The six‐gene SVM model achieved a sensitivity of 0.842 and an area under the curve (AUC) of 0.723 in internal validation. External validation using an independent MDD dataset yielded AUCs of 0.646 using equal weighting. Drug–gene interaction analysis identified potential agents targeting BLOC1S6. Conclusions This study identified an OSA‐related transcriptional signature associated with depressive status, providing preliminary transcriptomic evidence for OSA‐MDD comorbidity. All findings are hypothesis‐generating and require independent validation.