Interaction-constrained 3D molecular generation using a diffusion model enables structure-based pharmacophore modeling for drug design

A key challenge in structure-based drug design is generating three-dimensional molecules while preserving essential protein–ligand interactions. We propose a structure-based pharmacophore modeling framework based on a conditional diffusion model to generate molecules that satisfy specified interaction constraints. The proposed method incorporates a semantic fusion architecture that integrates multiple interaction-specific neural networks, each designed to capture distinct molecular interactions such as hydrogen bonds and hydrophobic interactions. The effectiveness of the method is demonstrated through a practical case study targeting the SARS-CoV-2 main protease, a critical antiviral target. Molecular dynamics simulations reveal that the generated molecules maintain both structural stability and key interactions comparable to those of a bioactive reference ligand. Binding free energy calculations using the molecular mechanics generalized Born surface area (MM/GBSA) method further demonstrate that several generated molecules exhibit more favorable binding affinities than that of the reference. ADMET profiling indicates that the generated molecules possess desirable drug-likeness and pharmacokinetic properties. The method also demonstrates generalizability to other protein targets and generates synthetically accessible molecules.