A Molecular-Protein Fusion Framework for Rapid Virtual Screening: Accelerating Lead Discovery for "Undruggable'' Oncogenic Targets.

Background/Objectives: KRAS G12D is one of the most frequent oncogenic mutations in pancreatic ductal adenocarcinoma (PDAC) and remains challenging to target because of its limited druggable binding pockets. This study aimed to develop a machine learning-based framework for rapid virtual screening of potential KRAS G12D inhibitors. Methods: A molecular-protein fusion prediction framework, MPFF-IS, was constructed by integrating the ESM2 protein language model with an MPNN-GNN molecular graph network to enable joint representation learning of protein and compound features. The model was trained using a KRAS G12D inhibitor dataset and applied to screen compounds from multiple chemical libraries. AutoDock Vina docking and 300 ns GROMACS molecular dynamics simulations were subsequently performed for structural validation. Results: MPFF-IS achieved favorable predictive performance on the test dataset and identified 2663 candidate compounds from more than 134,000 screened molecules. Several candidate ligands exhibited favorable binding affinity, stable proteinligand interactions, and enhanced structural stability compared with reference inhibitors, including MRTX1133 and BI-2852. Molecular dynamics analyses further supported the stability of the predicted complexes and the involvement of key binding residues within the KRAS G12D pocket. Conclusions: These findings demonstrate that MPFF-IS can efficiently identify potential KRAS G12D inhibitors and may provide a useful computational framework for precision drug discovery targeting difficult oncogenic proteins.