RosettaCommons / RosettaCommons/RFdiffusion

Contigs in google colab vs Contigs in github during binder design

Open
#304 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.1k
Forks
644
PR merge metrics
No merged PRs in 30d

Description

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?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Compare the Google Colab and local binder-design configuration, focusing on omitting /0 and applying fix_pdb() to the outputs. Reproduce the chain-A versus chain-B result, then verify whether the resulting PDB is accepted by ProteinMPNN and document whether local setup needs additional configuration.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.