AI-Powered Marine Drug Discovery: A Putative Dual c-Met/VEGFR2 Lead Candidate for Hepatocellular Carcinoma via Deep Learning and Multiscale Simulation

Background: Hepatocellular carcinoma (HCC) remains a leading cause of cancer mortality. The c-Met and VEGFR2 pathways synergistically drive HCC progression. Marine natural products offer chemically diverse drug reservoirs; however, conventional activity-guided isolation faces labor intensity, low throughput, and frequent compound rediscovery, limiting marine drug development. Objective: To pioneer an artificial intelligence-driven marine drug discovery workflow integrating deep learning virtual screening for identifying dual c-Met/VEGFR2 promising in silico candidate from marine natural product repositories. Methods: UniSite predicted binding pockets in c-Met (PDB: 4R1V) and VEGFR2 (PDB: 2XIR). Drug-likeness filtering of 695,000 compounds from COCONUT and CMNPD databases yielded 84,730 candidates. DiffDock-based screening identified dual-target binders, validated through 200 ns molecular dynamics simulations, MM-GBSA calculations, and DFT analyses. Results: The marine phthalide CMNPD30506 [(S)-3-ethyl-5,6-dihydroxyphthalide] emerged as the lead candidate, engaging VEGFR2 via four hydrophobic contacts and one π-cation interaction with LYS868, while binding c-Met through four hydrophobic interactions, two hydrogen bonds, and π-π stacking. Molecular dynamics demonstrated stable RMSD profiles and dynamic hydrogen bond enrichment. MM-GBSA revealed binding free energies of −14.79 and −13.28 kcal/mol for VEGFR2 and c-Met, respectively, driven by van der Waals forces. DFT calculations indicated a HOMO-LUMO gap of 2.410 eV. Conclusions: This AI-augmented workflow successfully identified CMNPD30506 as a promising dual c-Met/VEGFR2 HCC therapeutic from marine libraries, overcoming traditional discovery bottlenecks through integrated deep learning and physics-based simulations, exemplifying AI’s potential in marine pharmacological research.