RosettaCommons / RosettaCommons/foundry

input.json creation for antibody design problem (Please help me)

Open
#190 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question RFdiffusion3
Dominant language
Python
Stars
966
Forks
181
Avg merge
4d 4h
Merged PRs (30d)
2

Description

Hello,

Hi RFD3 team,

I'm trying to design nanobody CDRs while keeping the framework regions and target protein fixed. I want to clarify the correct input specification approach.

My goal:

  • Keep Framework regions (FR1: F1-26, FR2: F33-52, FR3: F60-101, FR4: F108-116) from input PDB with fixed sequence and coordinates
  • Design only CDR1 (length 6-8), CDR2 (length 6-8), and CDR3 (length 9-15) with new sequences and structures
  • Keep target protein (chain A, residues 100-550) fixed
  • Use hotspot-driven design with specific residues
    here is my current input.json file:

{
"nanobody_cdr_design": {
"input": "nanobody_target.pdb",
"dialect": 2,
"contig": "F1-26,6-8,F33-52,6-8,F60-101,9-15,F108-116,/0,A100-550",
"select_hotspots": "A148,A151,A152,A538,A539",
"infer_ori_strategy": "hotspots",
"plddt_enhanced": true,
"is_non_loopy": true
}
}

Questions:

  1. Is this the correct input file for my use case? Does it correctly preserve frameworks and design only CDRs?
  2. Should I add any additional parameters (like select_fixed_atoms or select_unfixed_sequence) for this design scenario, or are the defaults sufficient?

Contributor guide

Open the contributing guide

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

Start with the RFD3 input specification and examples, then compare the issue's input.json fields, contig ranges, hotspot selection, and fixed-region requirements against them. Done means providing or recording an authoritative answer about the required parameters for this antibody-design scenario.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
bioinformatics, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 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.