Contigs in google colab vs Contigs in github during binder design

[Karis-Kungsamutr]

I've been having some difficulties with the format in which the pdb files are output from rfdiffusion, where the designed binder is output as chain A rather than chain B which seems to cause some issues for proteinMPNN later on. I noticed that the google colab version seems to fix this by omitting the /0 when specifying the config options, and then running fix_pdb() on the outputs to fix the chains, is this correct?

If so, I wanted to confirm whether this is also a better way to run the code locally or if some further setup is required such that config doesn't need /0 specified to design binders properly?