DeltaDiff: Training-Free, Physics-Guided Machine Learning for Predicting Mutant Protein Structures

Abstract: Determining mutant protein structures is critical for understanding the mechanistic roles of mutations in biochemical processes. However, experimental characterization and conventional theoretical modeling are often expensive and time-consuming. Recent advances in machine learning provide new opportunities to efficiently predict protein structures from primary sequences. Nevertheless, applying these models to proteins with single-site or few-site mutations remains challenging because mutant sequences are often highly similar to their wild-type counterparts. Here, we introduce DeltaDiff, a physics-guided inference framework for mutant-structure generation that incorporates mutation-aware physical guidance into a baseline diffusion model. We evaluate DeltaDiff on three representative systems: Chignolin T8P, Novispirin G-10, and BBL D162N. All three examples involve nonlocal structural changes, making accurate mutant-structure prediction challenging. DeltaDiff captures key mutation-induced conformational changes without requiring retraining or fine-tuning of the baseline model. These results establish a foundation for efficient mutant-structure prediction at a fraction of the cost of conventional methods, facilitating rational mutant design.