Unified Sampling and Ranking for Protein Docking with DFMDock

Recent diffusion-based approaches to protein-protein docking typically decouple structure generation from decoy ranking. We introduce DFMDock (Denoising Force Matching for Docking), a unified diffusion model that integrates generative sampling and energy-based ranking through physically motivated supervision. DFMDock predicts both denoising forces and a scalar energy, trained using force matching and energy contrastive objectives. The predicted forces guide the reverse diffusion process, while the energy enables decoy ranking without relying on a separately trained confidence model. On the Docking Benchmark 5, DFMDock achieves a 4.9% Top-1 and 31.6% Oracle success rate, outperforming DiffDock-PP (4.3% and 16.2%, respectively). Unlike co-folding models, DFMDock does not require multiple sequence alignments (MSAs) and generalizes to unseen targets. In decoy ranking, its learned energy function outperforms Rosetta energy and model-derived confidence scores, producing funnel-shaped energy landscapes enriched for near-native structures. These results suggest DFMDock as an efficient and physically grounded approach to diffusion-based protein docking.