Affiliation:
1. Fujian Maternity and Child Health Hospital, Fujian Medical University
Abstract
Abstract
Preeclampsia (PE) is a serious condition that affects pregnant women worldwide. This study aimed to identify diagnostic candidate genes for PE. Gene expression from a PE cohort and controls was analyzed using Limma and weighted gene coexpression network analysis (WGCNA) to identify differentially expressed genes (DEGs) and module genes. Machine learning techniques were then used to identify immune-associated hub genes for PE diagnosis, resulting in the selection of two significant genes (F13A1 and SCCPDH). A nomogram and receiver operating characteristic (ROC) curve were developed to evaluate the diagnostic value, which was high for both hub genes (AUC: 0.9 and 0.88, respectively). A deconvolution study also identified dysregulated immune cells in PE. Overall, this study provides potential diagnostic candidate genes for PE patients and highlights the importance of early diagnosis and treatment for this condition.
Publisher
Research Square Platform LLC
Reference42 articles.
1. Identification of Immune-Associated Genes in Diagnosing Aortic Valve Calcification With Metabolic Syndrome by Integrated Bioinformatics Analysis and Machine Learning;Zhou Y;Front Immunol,2022
2. An integrative bioinformatics analysis of microarray data for identifying hub genes as diagnostic biomarkers of preeclampsia;Liu K;Bioscience reports,2019
3. A cost-effective machine learning-based method for preeclampsia risk assessment and driver genes discovery;Wang H;Cell & bioscience,2023
4. The etiology of preeclampsia;Jung E;American journal of obstetrics and gynecology,2022
5. Chappell, L. C., Cluver, C. A., Kingdom, J. & Tong, S. Preeclampsia. Lancet (London, England) 398, 341–354, doi:10.1016/s0140-6736(20)32335-7 (2021).