GenUnfold: Rapidly Predict Protein Mechanical Unfolding Trajectory via a Physics-Guided Diffusion Model

Many fundamental biological processes are governed by mechanical forces, with proteins acting as the key molecular mediators. Elucidating how protein unfolding responds to force is critical for understanding the mechano-pathologies, such as cardiomyopathy and muscular dystrophy. While the unfolding trajectories measured by Single-Molecule Force Spectroscopy (SMFS) map the instantaneous force response against molecular extension, its broader application is limited by time-consuming data collection and high operational costs. Here, we present the first scalable generative diffusion framework for full unfolding trajectory prediction, which integrates protein encoders for multi-scale conditioning. Beyond establishing the field's first systematic benchmark using existing models, we propose GenUnfold, a novel physics-guided diffusion model that combines global coevolutionary context with a local mechanical representation of the protein. The representation is derived from a novel physics-biased attention mechanism, which steers the generative diffusion process by modeling dynamic residue dependencies as a function of both structural topology and interaction stiffness. The benchmark for this task is built upon the biomolecule stretching database and several representative baseline models. Empirical results demonstrate that GenUnfold achieves state-of-the-art performance, reducing distributional error (FID) by 30\% and 54\% compared to pretrained Evolutionary Scale Model (ESM)-2 and standard transformer, respectively. Beyond statistical curve similarity, GenUnfold demonstrates superior physical consistency; in downstream mechanical property prediction, it reduces prediction errors for unfolding force and energy distributions by 6\% and 36\% over the ESM-2 baseline. These results indicate that while existing generative AI approaches can alleviate the need for predicting representative force curves, GenUnfold further improves performance by leveraging the synergy between protein structure and evolutionary information. By enabling proteome-wide screening to identify mechanical candidates before costly physical validation, our approach is promising to accelerate the discovery of force-targeted therapeutics.

Many proteins act like tiny mechanical parts in cells: they stretch, absorb force, and sometimes unfold to protect tissues from damage. Understanding these responses is important for diseases linked to mechanical failure, such as heart disease and muscular dystrophy, but measuring them one molecule at a time is slow, expensive, and often requires many repeated experiments. Existing computer simulations can provide detailed information, but they are also too costly to use at the scale of thousands of proteins. We developed GenUnfold, an AI model that predicts how a protein will unfold when it is pulled, using only its amino-acid sequence and three-dimensional structure. The model combines information learned from protein sequences with simple physical clues about how force travels through a protein’s structure, allowing it to generate full force–extension curves rather than a single score. On a large benchmark of simulated stretching data, GenUnfold produced more realistic unfolding trajectories and better estimates of key mechanical properties than strong machine-learning baselines. By making protein mechanical testing faster and more scalable, GenUnfold could help researchers screen many proteins before running costly experiments. This may accelerate the search for mechanically resilient proteins and support future studies of force-related diseases and therapies.