Toxicological Effects of Polyethylene Terephthalate Microplastics on Chronic Kidney Disease: An Integrative Bioinformatics, Network Toxicology, and Machine Learning Study.

Microplastics and nanoplastics (MNPs) are widely distributed in human organs, including the kidney, brain, and liver, where they induce oxidative stress and inflammatory responses. However, the toxicological effects of MNPs on chronic kidney disease (CKD) remain largely unexplored. In this study, we employed an integrated approach combining bioinformatics, network toxicology, machine learning, and molecular docking to investigate the potential impacts of polyethylene terephthalate microplastics (PET-MPs) on CKD. A total of 191 CKD-related targets were obtained from the GEO database, while 875 potential targets of PET-MPs were identified using PubChem, ChEMBL, SwissTargetPrediction, and the SEA Search platform. Through weighted gene co-expression network analysis (WGCNA) and machine learning, seven core targets were ultimately identified. KEGG pathway enrichment and Gene Ontology (GO) analyses indicated that PET-MPs may exert effects by modulating immune- and inflammation-related pathways as well as energy metabolism. Molecular docking revealed high-affinity interactions between the PET-MP-derived small molecules and the core targets, suggesting direct interference with cellular activities that could influence CKD progression. This computational framework not only elucidates potential molecular mechanisms of MNP-induced nephrotoxicity but also identifies candidate targets for therapeutic intervention, aligning with the scope of machine-learning-driven drug molecule design.