We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Investigation of the molecular network underlying PET-MPs-induced inflammatory bowel disease via integrated machine learning and molecular docking approaches
Summary
Scientists used computer models to explore whether PET microplastics—tiny plastic particles from common plastic bottles and packaging—could play a role in inflammatory bowel disease (IBD), a painful digestive condition. Using data analysis and computer simulations (not tests in humans or animals), they found that a PET-related compound may bind to 14 specific genes linked to Crohn's disease and ulcerative colitis, suggesting a possible way microplastics could contribute to gut inflammation. This is early, computer-based research meant to guide future lab studies—it doesn't prove microplastics cause IBD in people, but it str
Polyethylene terephthalate microplastics (PET-MPs), as environmental contaminants, have raised significant concerns due to their potential toxicity, leading to serious environmental pollution and health issues. However, their impact on inflammatory bowel disease (IBD) remains poorly elucidated. This study aims to investigate the potential molecular mechanisms linking PET-MPs to IBD pathogenesis. Multiple datasets were employed to identify Crohn's disease (CD)- and ulcerative colitis (UC)-associated targets. Multi-machine learning approaches were combined with molecular docking of a PET-related compound to evaluate potential binding interactions with the identified hub targets. This study delineated 9 putative targets associated with PET-MPs-related CD pathogenesis and 17 potential targets associated with UC pathogenesis. For CD, GBM showed the best performance among all models, with a mean ROC-AUC of 0.862; for UC, RF performed best, with a mean ROC-AUC of 0.806, based on both training and validation sets. Multi-machine learning analysis identified 14 hub genes as candidate key regulatory factors. SHAP analysis highlighted their significant contributions to the model predictions. Molecular docking simulations suggested favorable binding affinities between a PET-related compound and the hub targets. This study suggests that PET-MPs may contribute to IBD pathogenesis by potentially interacting with 14 machine learning-prioritized hub genes. Molecular docking analyses indicated predicted high-affinity binding between a PET-related compound and these targets. Collectively, these findings provide a hypothesis-generating framework for investigating the potential role of PET-MPs in IBD progression.