Integrating multi-omics data and machine learning to identify endocrine disrupting chemicals targeting key ccRCC-related genes.

Clear cell renal cell carcinoma (ccRCC) is a highly aggressive and metastatic malignancy that poses a serious threat to patient health. While its development involves both genetic and environmental influences, the interactions between genetic susceptibility and endocrine-disrupting chemicals (EDCs) remain poorly understood. In this study, we integrated multi-omics datasets and applied machine learning approaches to identify EDCs and their associated target genes implicated in ccRCC pathogenesis. We analyzed bulk and single-cell RNA sequencing data and evaluated 101 machine learning algorithms to construct a robust prognostic model. This analysis identified 8 EDCs potentially involved in ccRCC: Diethylnitrosamine, Diethylstilbestrol, Resveratrol, 4,4'-diaminodiphenylmethane, Trichloroethylene, Arsenic, Lead, and 2,3,5-(triglutathion-S-yl)hydroquinone. 5 EDC-associated prognostic genes-BIRC5, CCND1, RRM2, CDH1, and TRIB3-were also identified. Pathway enrichment and immune infiltration analyses revealed intricate interactions between these genes and the tumor microenvironment. Furthermore, cell-cell communication analysis revealed distinct signaling patterns among EDC-associated subpopulations, offering new insights into how EDCs may modulate gene expression and contribute to ccRCC progression. This study provides a foundation for future investigations into EDC-driven tumor biology and may guide the development of targeted therapies and preventative strategies against ccRCC.