Integrating machine learning and molecular docking to decipher the molecular network of aflatoxin B1-induced hepatocellular carcinoma

Abstract

Objective: This study aims to investigate the molecular mechanisms underlying hepatocellular carcinoma (HCC) induced by Aflatoxin B1 (AFB1).

Methods: Differential expression analysis of multiple datasets was performed to identify HCC-related target genes. Machine learning algorithms, network toxicology, and molecular docking techniques were integrated to explore the binding interactions between AFB1 and target proteins.

Results: A total of 48 genes were identified as potential targets for AFB1-induced hepatocarcinogenesis. Subsequent machine learning analysis prioritized six core genes (RND3, PCK1, AURKA, BCAT2, UCK2, and CCNB1) as key regulators. Among these, RND3 and PCK1 exhibited significant downregulation, while AURKA, BCAT2, UCK2 and CCNB1 showed marked upregulation (P < 0.05). Molecular docking simulations revealed strong binding specificity between AFB1 and target proteins.

Conclusion: This study demonstrates that AFB1 may promote HCC pathogenesis by targeting specific genes and signaling pathways. Machine learning identified six core regulatory genes, and molecular docking confirmed AFB1's high binding affinity with key targets. These findings provide critical insights for further mechanistic exploration of AFB1-induced hepatocarcinogenesis.

Keywords: aflatoxin B1; bioinformatics; hepatocellular carcinoma; machine learning; molecular docking.