Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Chai prediction with ligands

Open
#29 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
35/100
Issue type
Bug
Clarity
Mostly clear
Activity status
Stale
Tech stack
python

Research direction

Trace the Chai1 pipeline that generates input FASTA files and the RFdiffusion2 output backbone residue numbering. Reproduce a run with two ligands sharing a name, then verify that ligands are not written as protein entries and that both ligand copies remain in the Chai1 input and metrics results.

Written by the indexing model from the issue text.

Description

Hi!

I've noticed two bugs relating to Chai1 prediction of ligands when running the pipeline.

  1. Ligands are incorrectly added as 'protein' entries into the Chai1 input fasta files.
  2. If backbones are generated around two ligands of the same name, then they will both be incorrectly given the same residue number in the RFdiffusion2 output backbone. This doesn't affect the LigandMPNN step, but it means that only one copy of the ligand is added to the Chai1 input fasta file. This means the predicted structures only have one of two ligands, throwing off the metrics step.

Happy to share more info if needed. Thanks!

Dominant language
Python
Stars
443
Forks
70
PR merge metrics
No merged PRs in 30d

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 RosettaCommons/RFdiffusion2

All issues in RosettaCommons/RFdiffusion2

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.