Identification of macrophage-associated diagnostic biomarkers and molecular subtypes in gestational diabetes mellitus based on machine learning.

Gestational diabetes mellitus (GDM) is a common metabolic disorder during pregnancy, involving multiple immune and inflammatory factors. Macrophages play a crucial role in its development. This study integrated scRNA-seq and RNA-seq data to explore macrophage-related diagnostic genes and GDM subtypes. For scRNA-seq data, cell clusters were annotated using the SingleR package and validated with marker gene expression profiles, while hdWGCNA analysis identified three gene modules related to macrophages. A diagnostic model for GDM derived from endothelial cell transcriptomes was constructed by employing a variety of machine learning ensemble algorithms, achieving an AUC of 0.887. The model identified five differentially expressed genes (ZEB2, MALAT1, HEBP1, AHSA1, and TTC3) as potential diagnostic biomarkers. The CB-DSNMF algorithm was proposed to identify two distinct GDM subtypes from RNA-seq data, revealing significant differences in biological behaviours. This algorithm outperformed other baselines in multiple clustering metrics. Mendelian randomisation analysis identified ZEB2 as a gene causally related to GDM risk. A transcription factor (TF)-gene regulatory network was constructed for these genes using the ENCODE database. The study highlights the importance of macrophages in GDM, provides a high-precision diagnostic model, and offers new insights into personalised treatment strategies, contributing to a better understanding of GDM pathophysiology.