Preeclampsia (PE) remains a leading cause of maternal and perinatal mortality worldwide, and the combined use of Shuangjiang Decoction with Labetalol hydrochloride (SJD-Labetalol) has shown promising therapeutic efficacy in clinical settings. However, the underlying molecular mechanisms remain insufficiently understood. This study integrated GEO dataset analysis with network pharmacology and machine learning approaches to elucidate the therapeutic mechanism of SJD-Labetalol. 83 overlapping drug targets were identified, and ten hub genes were highlighted (IL1A, IFNG, BCL2, REN, XDH, NOS3, NOS2, EGFR, MMP3, and CCK). These hub genes were extensively involved in the HIF-1 signaling pathway, fluid shear stress and atherosclerosis, estrogen signaling pathway and calcium signaling pathway. Molecular docking confirmed strong binding affinities between active ingredients (e.g. Rhein, Baicalein, Tanshinone IIA) and these hub proteins. Machine learning-based diagnostic modeling further identified five hub genes (IFNG, MMP3, NOS2, NOS3, REN) as potential biomarkers for PE, achieving an average ROC-AUC of 0.82 in validation cohorts. In summary, this integrative analysis provides a comprehensive molecular basis for the synergistic antihypertensive, anti-inflammatory, and placental protective effects of SJD-Labetalol, offering novel insights for targeted therapeutic strategies in PE management.
Chen et al. (Mon,) studied this question.