Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule
This work addresses a bottleneck in deep generative models for drug design, offering a novel scheduling method that enhances molecular geometry and interaction modeling, with potential impact on pharmaceutical research.
The paper tackled the challenge of modeling geometric structures in Structure-Based Drug Design (SBDD) by addressing the twisted probability path of multi-modalities, proposing a VLB-Optimal Scheduling (VOS) strategy that optimizes the Variational Lower Bound as a path integral. This approach achieved a state-of-the-art PoseBusters passing rate of 95.9% on CrossDock, representing a more than 10% improvement over strong baselines while maintaining high affinities and intramolecular validity.
Structure-Based Drug Design (SBDD) is crucial for identifying bioactive molecules. Recent deep generative models are faced with challenges in geometric structure modeling. A major bottleneck lies in the twisted probability path of multi-modalities -- continuous 3D positions and discrete 2D topologies -- which jointly determine molecular geometries. By establishing the fact that noise schedules decide the Variational Lower Bound (VLB) for the twisted probability path, we propose VLB-Optimal Scheduling (VOS) strategy in this under-explored area, which optimizes VLB as a path integral for SBDD. Our model effectively enhances molecular geometries and interaction modeling, achieving state-of-the-art PoseBusters passing rate of 95.9% on CrossDock, more than 10% improvement upon strong baselines, while maintaining high affinities and robust intramolecular validity evaluated on held-out test set. Code is available at https://github.com/AlgoMole/MolCRAFT.