sokrypton / sokrypton/ColabFold

How is ESMFold PAE output?

Open
#333 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
2.9k
Forks
747
PR merge metrics
No merged PRs in 30d

Description

Hi,

I am working with ESMFold and do not understand something. In the dictionary of the output, before parse_output function, there is a predicted_aligned_error key, which I thought would the PAE. HOwever, I see in the notebook, that PAE is ectracted from an other element:
pae = (output["aligned_confidence_probs"][0] * np.arange(64)).mean(-1) * 31
Why is this done this way?

Thank you for the clarification!

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 notebook code around parse_output, predicted_aligned_error, and aligned_confidence_probs. Trace how each output is produced and document why the PAE is calculated from the confidence probabilities; the work is done when the relationship between the two keys and the formula is clear.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, numpy
Domain
bioinformatics
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.