Rocco Moretti

The `inpaint_str_helix` is a somewhat recent addition. A potential work-around until this gets examined and addressed is to revert to an older version with something like `git checkout v1.1.0`

Including which file or directory is not found (should be the line after the message you quote) may help track down which particular part of the process is at issue,...

> No such file or directory: '&WVS.pdb1' I'm concerned about the `&` and `1` there. My guess is that however you're specifying your input PDB names, you're getting extra spurious...

> the bonding seems unusual, as shown in the figure. Keep in mind that the PDB format doesn't really encode bonds. What's happening here is that PyMol (and other such...

My understanding is that hotspots are used primarily to direct generation, not to improve it. That is, when you do free design, RFdiffusion is permitted to create designs wherever it...

I'm not aware of papers which have specifically looked at the correlation between generated protein length and binder design success, but that doesn't mean there aren't any out there. That...

Yes, this is expected. RFdiffusion is used for backbone generation. It does not predict residue identities. The classic workflow (as exemplified by the experimental examples in the original RFdiffusion paper,...

Ah yes, sorry. I believe that is the intended behavior as well. The internals of RFdiffusion only work on backbone coordinates, so only the backbones (and amino acid identity) of...

You'd generally take the sequences, put them through a structure prediction program (Alphafold/Boltz/Chai)(*) and then run the analysis on the predicted results. Ideally that would work. You may get issues...

There's not currently a way to use a SMILES designation to specify a ligand. However, there is a way to specify an SDF, and allow the internal parameterization of Rosetta...