Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows

2025-03-06

AI Summary

Conventional structure-based drug design (SBDD) often assumes protein binding sites to be rigid, limiting its ability to address conformational dynamics. Method: We propose DynamicFlow—the first all-atom stochastic flow generative model explicitly designed for joint protein–ligand conformational transformation. It end-to-end generates multiple holo-like protein pocket conformations from an apo structure alongside geometrically and energetically compatible ligands. To enable training, we construct the first MD-based dataset of polymorphic apo–holo pocket pairs and integrate flow matching, stochastic differential equations, and 3D geometric modeling. Contribution/Results: DynamicFlow achieves superior structural accuracy, drug-likeness, and docking success rates versus baseline methods. In downstream SBDD tasks, it reduces binding affinity prediction error by 27.4%, effectively overcoming the rigid-pocket assumption bottleneck.

Technology Category

• Machine Learning: Structured Learning
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The dynamic nature of proteins, influenced by ligand interactions, is essential for comprehending protein function and progressing drug discovery. Traditional structure-based drug design (SBDD) approaches typically target binding sites with rigid structures, limiting their practical application in drug development. While molecular dynamics simulation can theoretically capture all the biologically relevant conformations, the transition rate is dictated by the intrinsic energy barrier between them, making the sampling process computationally expensive. To overcome the aforementioned challenges, we propose to use generative modeling for SBDD considering conformational changes of protein pockets. We curate a dataset of apo and multiple holo states of protein-ligand complexes, simulated by molecular dynamics, and propose a full-atom flow model (and a stochastic version), named DynamicFlow, that learns to transform apo pockets and noisy ligands into holo pockets and corresponding 3D ligand molecules. Our method uncovers promising ligand molecules and corresponding holo conformations of pockets. Additionally, the resultant holo-like states provide superior inputs for traditional SBDD approaches, playing a significant role in practical drug discovery.

Problem

• Incorporates protein dynamics into drug design to improve accuracy.
• Overcomes limitations of rigid structures in traditional SBDD methods.
• Uses generative modeling to predict protein-ligand conformational changes.

Innovation

• Generative modeling for drug design
• Full-atom stochastic flow model
• DynamicFlow transforms apo to holo states