Combining machine learning and molecular docking to unravel the molecular network of bladder cancer induced by 2-naphthylamine.

OBJECTIVE: Bladder cancer (BLCA) is among the most common malignant tumors found in the urinary tract. However, the carcinogenic mechanism of 2-Naphthylamine (2-NA), a class I carcinogen with a well-established association with BLCA, remains inadequately elucidated. The objective of research is to elucidate the molecular mechanisms underlying 2-NA-induced BLCA. METHODS: Analysis of differential expression was performed on various datasets to pinpoint target genes linked to BLCA. We used a comprehensive process integrating machine learning, network toxicology, molecular docking and molecular dynamics simulations to study the binding interactions between 2-NA and target proteins. RESULTS: Our research identified 29 potential targets implicated in 2-NA-induced BLCA. Subsequent analyses utilizing machine learning techniques prioritized 14 core genes (SKP2, SCN11A, DHCR7, AURKB, PFKFB4, EBP, CA2, NUDT1, DUSP2, KIF20A, BLM, IGFBP2, EZH2, TPX2) as pivotal regulators. SKP2 and EBP were identified as the most impactful predictors, showing notable effects in advancing bladder cancer. Furthermore, molecular docking simulations and molecular dynamics simulations indicated strong binding specificity between 2-NA and the target proteins SKP2 and EBP. CONCLUSION: The findings of our study indicate 2-NA potentially facilitates BLCA pathogenesis by influencing specific genes and signaling pathways. Utilizing machine learning techniques, 14 key genes were identified. Subsequent molecular docking analyses and molecular dynamics simulations verified the strong binding affinity of 2-NA to the critical targets SKP2 and EBP. These results provide valuable insights for further mechanistic investigations into 2-NA-induced bladder carcinogenesis.