Stitching Molecular Worlds Together with Physics-Coupled Diffusion Models
Complex chemical systems often contain multiple components or large molecules, giving rise to substantial chemical and conformational complexity. Modeling the structures of these systems is crucial for mechanistic understanding of chemical processes and rational design, but remains highly challenging for both conventional theoretical approaches and machine learning. Here, we introduce physical-interaction-coupled diffusion models (PICDiff), a framework that couples independently trained diffusion models for subsystems of a complex system through explicit bonded and nonbonded interactions during inference. PICDiff reduces the difficulty of applying generative models to chemically and conformationally complex systems by decomposing them into smaller subsystems that are less complex and more amenable to machine-learning-based modeling. Using peptide-polymer binding and polymer conformation sampling as examples, we demonstrate that PICDiff can quantitatively sample conformations and model the thermodynamics of complex chemical systems. These results show that PICDiff provides a general and practical approach for modeling complex chemical systems by combining learned models of simpler molecular subsystems through physical interactions.