Deciphering the Anti-LUAD Mechanism of 4′-Demethyl-epipodophyllotoxin (4′-DMEP) via Machine Learning-Driven Target Identification and In Vitro Validation

4'-Demethyl-epipodophyllotoxin (4'-DMEP) is a precursor of etoposide and has attracted much attention due to its significant antitumor activity. In order to elucidate the molecular mechanism of its inhibition of lung adenocarcinoma (LUAD), this study comprehensively used network pharmacology, machine learning, and molecular simulation technology, and verified it through cell experiments. A total of 171 drug targets and 11,439 disease targets were collected from the public database, and 131 intersection targets were obtained using the Venny tool. Then the 131 targets were visualized by PPI network. Subsequently, 38 significantly differentially expressed targets were screened and identified in the GEPIA database, from which 18 survival-related genes were further screened. GO functions related to mitotic cell cycle regulation and ERK1/ERK2 signaling, as well as KEGG pathways including gap junction and infection-related pathways, were also enriched. Four machine learning models screened five characteristic genes (SLC2A1, TOP2A, MIF, TLR4, and PLA2G1B). Molecular docking confirmed high-affinity interactions (binding energies ≤ -6.1 kcal/mol), a finding that was further validated by molecular dynamics simulation. In vitro experiments revealed that 4'-DMEP inhibited A549 cell proliferation by inducing cell cycle arrest and apoptosis, with significant changes in the expression of SLC2A1, TOP2A, and MIF. These findings not only clarify its molecular mechanism but also provide new ideas for the precise treatment of lung adenocarcinoma.