DiffInt: A Pharmacophore-Aware Diffusion Model for Structure-Based Drug Design with Explicit Hydrogen Bond Interaction Guidance

The design of drug molecules is a critical stage in the drug discovery process. The use of pharmacophore models in structure-based drug discovery has long played an important role in efficient development. Significant progress has been made in recent years in the generation of 3D molecules via deep generation models. However, while many existing models have succeeded in incorporating structural information of target proteins, they have not been able to address important interactions between proteins and drug molecules, especially hydrogen bonds, explicitly. In this study, we propose DiffInt as a novel structure-based approach that explicitly addresses interactions. The model naturally incorporates hydrogen bonds between the protein and ligand by treating them as pseudoparticles. The experimental results show that DiffInt reproduces hydrogen bonds and that the hydrogen binding energies significantly outperform those of existing models. To facilitate the use of our tool for generating new drug molecules based on any protein three-dimensional structure, we have made the source code and trained model available on GitHub (https://github.com/sekijima-lab/DiffInt) under the MIT license, with the execution environment provided on Google Colab.