Rocco Moretti

The numbers which come out of Rosetta protocols (including Rosetta ddG calculations) are typically in arbitrary units. It's been observed that these number correlate reasonably well with experimental measurements, but...

> |pdb|dG_pred|total_score| > |design_ppi_817_dldesign_0_cycle1|-432.69906862683206|113733.31551370105| > > Is such a ΔG[bind] value still credible? Or does total_score reflect a more reasonable value? When you get ludicrously extreme ddG score values, it...

The main documentation are the examples in the [README](https://github.com/RosettaCommons/RFdiffusion?tab=readme-ov-file#rfdiffusion), and the example scripts in the `examples/` directory.

Yes. RFdiffusion only generates backbone structures. As such, the output at positions which were generated by RFdiffusion will by Gly (i.e. only a backbone). If you do want to determine...

I'm unsure how well RFdiffusion works with insertion codes. You can try explicitly including things in the contig (something like `[B1-52/B52A-52A/B53-94/14-20/B103-111]`), but I haven't tried that at all. You may...

Where are you changing the value? If I pass `diffuser.T=XYZ` on the run_inference.py command line, I get a "WARNING: You are changing diffuser.T from the value this model was trained...

I don't have extensive experience with changing the number of iteration steps, but I will note that RFdiffusion was originally trained with a diffuser.T of 200. It could very well...

The way `contigmap.length` works is that the standard random length generation is applied, and the resultant length is checked against the allowed length range. If the generated length is outside...

The `conda env create -f env/SE3nv.yml` should create the `SE3nv` environment and populate it with packages. If you're not seeing anything with a `conda list`, then something likely went wrong...

It looks specifically like the issue might be the torchvision and torchaudio dependencies, and that they're looking for a higher level of cuda for some reason. See if editing the...