Identification of crucial genes for polycystic ovary syndrome and atherosclerosis through comprehensive bioinformatics analysis and machine learning.

Objective: To identify potential biomarkers in patients with polycystic ovary syndrome (PCOS) and atherosclerosis, and to explore the common pathologic mechanisms between these two diseases in response to the increased risk of cardiovascular diseases in patients with PCOS.

Methods: PCOS and atherosclerosis data sets were downloaded from the GEO database, and their differentially expressed genes were identified. Weighted gene co-expression network analysis was used to obtain intersection genes, and then protein-protein interaction and functional enrichment analysis were performed. Machine learning algorithms were used to select the key genes, which were then validated through external data sets. We constructed a nomogram to predict the risk of atherosclerosis in women with PCOS. Finally, the CIBERSORT algorithm was used to analyze the infiltration of immune cells in the atherosclerosis group.

Results: We identified six hub genes (CD163, LAPTM5, TNFSF13B, MS4A4A, FGR, and IRF1) that exhibited excellent diagnostic value in validation data sets. Gene ontology terms and KEGG signaling pathway analysis revealed that key genes were associated with immune responses and inflammatory reactions. Abnormal immune cell infiltration was also found in the atherosclerosis group and was correlated with the six hub genes.

Conclusion: Common therapeutic targets of PCOS and atherosclerosis were preliminarily identified through bioinformatics analysis and machine learning techniques. These findings provide new treatment ideas for reducing the risk that PCOS will develop into atherosclerosis.