Written By: IJCP Editorial Team

Published On: 04 Mar, 2025 1:33 PM | Updated On: 04 Mar, 2025 1:45 PM

Recognition of Crucial Genes for PCOS and Atherosclerosis via Comprehensive Bioinformatics Analysis and Machine Learning

This study aimed to recognise potential biomarkers in patients with polycystic ovary syndrome (PCOS) and atherosclerosis, as well as to investigate the shared pathological mechanisms linking these two conditions, particularly regarding the heightened risk of cardiovascular diseases in PCOS patients.

Data sets related to PCOS and atherosclerosis were obtained from the GEO database to identify differentially expressed genes. A weighted gene co-expression network analysis was conducted to find common genes, followed by protein-protein interaction and functional enrichment analyses. Machine learning algorithms were employed to pinpoint key genes, which were then validated using external data sets. A nomogram was created to predict the risk of atherosclerosis in women with PCOS. Additionally, the CIBERSORT algorithm was utilized to assess immune cell infiltration in the atherosclerosis group.

The results showed that:

• The researchers 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.

• Atherosclerosis group showed abnormal immune cell infiltration and was correlated with the six hub genes.

To summarize, common therapeutic targets of PCOS and atherosclerosis were can be chiefly identified through bioinformatics analysis and machine learning techniques. These findings provide new treatment approaches for reducing the risk that PCOS will develop into atherosclerosis.

Source: Wang L, Zhang Y, Ji F, Si Z, Liu C, Wu X, Wang C, Chang H. Identification of crucial genes for polycystic ovary syndrome and atherosclerosis through comprehensive bioinformatics analysis and machine learning. Int J Gynaecol Obstet. 2025 Feb 21. doi: 10.1002/ijgo.70014. Epub ahead of print. PMID: 39981695.