Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces DeltaDiff, a training-free, physics-guided framework that enhances a baseline diffusion model for predicting mutant protein structures by incorporating mutation-aware physical guidance. The method addresses the challenge of accurately predicting conformational changes in proteins with single-site or few-site mutations, which are often structurally similar to their wild-type counterparts. Evaluated on three complex systems, DeltaDiff successfully captures critical mutation-induced changes without the need for retraining, significantly reducing the cost and time associated with conventional modeling techniques.
DeltaDiff achieves accurate mutant protein structure predictions without retraining, revolutionizing the efficiency of rational mutant design.
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.