Summary
Protein structure diffusion works best on small protein sizes. (1) tried to refold proteins generated using RF-diffusion and ProteinMPNN and using AlphaFold2 (single sequence) and found that they generally disagreed if they were too big. Likewise, (2) could not reliably refold proteins in silico if they were greater than ~200-300 residues.
Figures
Figures 2B and 2C from (1)
Figure S14 from (2)
1.
Watson JL, Juergens D, Bennett NR, Trippe BL, Yim J, Eisenach HE, et al. De novo design of protein structure and function with RFdiffusion. Nature. 2023;620(7976):1089–100. Available from: https://doi.org/10.1038/s41586-023-06415-8
2.
Ingraham JB, Baranov M, Costello Z, Barber KW, Wang W, Ismail A, et al. Illuminating protein space with a programmable generative model. Nature. 2023;623(7989):1070–8. Available from: https://doi.org/10.1038/s41586-023-06728-8