Machine learning and network pharmacology-assisted discovery of natural product inhibitors targeting Plasmodium falciparum lysyl-tRNA synthetase.

The emergence of drug-resistant Plasmodium falciparum necessitates novel antimalarial strategies. Lysyl-tRNA synthetase from Plasmodium falciparum (PfLysRS), an essential enzyme involved in protein biosynthesis, represents a promising molecular target for structure-based drug discovery and development of effective antimalarial agents. In this study, an integrated computational workflow identified three natural product-derived lead compounds, MolPort-001-742-110, MolPort-000-778-336, and MolPort-001-740-194, through structure-based virtual screening with favourable binding affinity and interaction profiles within the catalytic pocket. Density functional theory (DFT) optimized ligand geometries and characterized their electronic properties, while five independent 200 ns molecular dynamics (MD) simulations confirmed stable protein-ligand interactions. Molecular mechanics/generalized Born surface area (MM/GBSA) binding free energy calculations, principal component analysis (PCA), free energy landscape (FEL) mapping, and quantum mechanics/molecular mechanics (QM/MM) analyses further demonstrated energetically favourable binding and provided mechanistic insights into ligand stabilization. Machine learning predicted promising pIC50 values, supporting potential inhibitory activity against PfLysRS, whereas network pharmacology suggested modulation of multiple malaria-related targets and pathways associated with parasite survival, host responses, and disease progression. Overall, three promising natural product scaffolds were identified as potential PfLysRS inhibitors, providing a strong computational basis for biochemical, cellular, in vivo, and preclinical validation towards next-generation antimalarial development.