Joseph Watson/Watchwell
Joseph Watson/Watchwell
Training is described in some detail in the RFdiffusion supplement. That would be a good place to start :) In terms of evaluation, we evaluated on all of the benchmarks...
Great idea - we'll set this up ASAP!
Yes! So the trb file contains the mappings of where residues were in the input, and where they ended up in the output. These are "con_ref_idx0" and "con_hal_idx0" (named such...
I think this is probably because there is a residue in the pdb file that has sequence, but isn't resolved in the structure (our parsers typically assume everything is present...
@sokrypton would be the best person to ask about doing this in colab!
you could totally set the secondary structure to be a loop in a secondary structure input. You'd just need to make a secondary structure input (loops are value 2), and...
There are a few ways to do this. One way would be to used the scaffoldguided.sampled_insertion/sampled_N/sampled_C flags, which basically randomly sample length up to what you provide, and insert this...
I think you can probably truncate the input, by e.g. reducing the length of secondary structure elements in the binder. For sure you risk making something implausible, but it should...
I think this has been raised previously - I think it's a Windows problem. It looks like a datatype issue where seq_orig is int32 and seq_init is int64, which only...
I think if you can make a pdb file of the rigen output (you would need backbones on the amino acid residues) you can then use normal contig logic