Improve MSA extraction from RoseTTAFold-All-Atom internal chain directories
Nobody has claimed this yet.
- Dominant language
- HTML
- Stars
- 115
- Forks
- 75
- PR merge metrics
- No merged PRs in 30d
Description
Description of feature
The current RFAA MSA extraction reaches into RFAA's internal working directories to grab per-chain A3M files.
These are raw search results, not the final paired MSA that RFAA actually uses for prediction. As a result, read_a3m() in extract_metrics.py treats all chains as unpaired and stacks them with gap padding, missing the co-evolutionary pairing information.
Original TODO here.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Read modules/local/run_rosettafold_all_atom/main.nf at the referenced TODO and inspect read_a3m() in extract_metrics.py. Determine where the final paired MSA used by RoseTTAFold-All-Atom is available instead of the per-chain raw A3M files. Done means extraction preserves the co-evolutionary pairing information rather than treating every chain as unpaired.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- bioinformatics, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100