Fig. 1. Protein design using RFdiffusion.

a, Diffusion models for proteins are trained to recover corrupted (noised) protein structures and to generate new structures by reversing the corruption process through iterative denoising of initially random noise X_T into a realistic structure X₀ (top panel). The RF structure prediction network (middle panel, left side) is fine-tuned with minimal architectural changes into RFdiffusion (middle panel, right side); the denoising network of a DDPM is also shown. In RF, the primary input to the model is the sequence. In RFdiffusion, the primary input is diffused residue frames (coordinates and orientations). In both cases, the model predicts final 3D coordinates (denoted ${\widehat{X}}_0$ in RFdiffusion). The bottom panel shows that in RFdiffusion, the model receives its previous prediction as a template input (‘self-conditioning’, Supplementary Methods). At each timestep t of a trajectory (typically 200 steps), RFdiffusion takes ${\widehat{X}}_0^{t+1}$ from the previous step and X_t and then predicts an updated X₀ structure (${\widehat{X}}_0^t$). The next coordinate input to the model ($X_{t-1}$) is generated by a noisy interpolation (interp) towards ${\widehat{X}}_0^t$. b, RFdiffusion is broadly applicable for protein design. RFdiffusion generates protein structures either without further input (top row) or by conditioning on (top to bottom): symmetry specifications; binding targets; protein functional motifs or symmetric functional motifs. In each case random noise, along with conditioning information, is input to RFdiffusion, which iteratively refines that noise until a final protein structure is designed. c, An example of an unconditional design trajectory for a 300-residue chain, depicting the input to the model (X_t) and the corresponding ${\widehat{X}}_0$ prediction. At early timesteps (high t), ${\widehat{X}}_0$ bears little resemblance to a protein but is gradually refined into a realistic protein structure.