[Proteina-Complexa] `target_schema.md` field documentation is inaccurate

Open Beginner friendly
#46 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
84/100
Issue type
Documentation
Clarity
Clearly specified
Activity status
Quiet
Tech stack
python
Domain
documentation

Research direction

Open target_schema.md and inspect the cited behavior in binder_eval_utils.py:272 and gen_dataset.py:620,640,669. Correct the target_input, ligand, and ligand_only descriptions, then verify that the documented examples match the parser and generation behavior described in the issue.

Written by the indexing model from the issue text.

Description

Several target_schema.md field descriptions have drifted from the code:

  • target_input format — doc lists A1-115/0 50-100 ("RFdiffusion contigs"), but the parser only splits on commas (binder_eval_utils.py:272); only A1-115 and "A96-174,A306-446" work.
  • ligand list vs SMILES — a ligand list is valid for generation (gen_dataset.py:640,669) but requires use_bonds_from_file:True and no SMILES; the add CLI is single-only. The doc doesn't state this exclusivity.
  • ligand_only — doc says "no protein interface"; really True = the whole file is the ligand, False = extract named residue(s) (gen_dataset.py:620). Shipped *_ligand_centered.pdb are ligand-only.

Severity: Medium · Status: doc open (notebooks corrected)

Steps to reproduce
  1. Follow target_schema.md for any field above.
  2. → the slash target_input is silently ignored; a ligand list + SMILES errors; ligand_only behaves opposite to the description.
Fix

Correct the three field descriptions (drop the slash row; document list ⇒ use_bonds_from_file + no SMILES; rewrite ligand_only).

Environment

NVIDIA A100 80GB PCIe · driver 565.57.01 · CUDA 12.7 · repo branch dev @ 916eaae · UV runtime.

Dominant language
Python
Stars
432
Forks
78
Avg merge
10d 46m
Merged PRs (30d)
1

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.

More from NVIDIA-BioNeMo/Proteina-Complexa

All issues in NVIDIA-BioNeMo/Proteina-Complexa

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.