Predictive model in silicon and pathogenicity mechanism of metabolic syndrome: Impacts of heavy metal exposure

Although the association between heavy metals in human and the development of metabolic syndrome (MetS) have been extensively studied, the pathogenic mechanism of MetS affected by metals is not clear to date. In this study, a predictive model was developed with machine learning base on the large-scale dataset. These proposed models were evaluated via comparatively analysis of their accuracy and robustness. With the optimal model, two metals significantly correlated with MetS were screened and were employed to infer the pathogenicity mechanism of MetS via molecular docking. Significant associations between heavy metals and MetS were found. Molecular docking provided insights into the interactions between metal ions and key protein receptors involved in metabolic regulation, suggesting a mechanism by which heavy metals interfere with metabolic functions. Specifically, Ba and Cd affect the development of MetS thru their interactions with insulin and estrogen receptors. This study attempted to explore heavy metals' potential roles in MetS at the molecular level. These findings emphasize the importance of addressing environmental exposures in the prevention and treatment of MetS.