RosettaCommons / RosettaCommons/RFdiffusion

questions for pAE compute

Open
#307 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.1k
Forks
644
PR merge metrics
No merged PRs in 30d

Description

Hello! I have recently read your article "Atomically accurate de novo design of single-domain antibodies" and am very interested in it. In this article, there is a computational metric called pAE (predicted Aligned Error). In my studies, pAE refers to the alignment error between each pair of residues. If I calculate pAE for a segment of the sequence (for example, the CDR3 region), the result should be in the form of a matrix that stores the pAE between each pair of residues. How do you integrate the pAE of each pair of residues into a single value? And how is the criterion of pAE being less than 10 derived?

If you can clarify my doubts, I would be very grateful!

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.

Research direction

Start with the cited article and the issue's description of predicted Aligned Error (pAE), then trace how RFdiffusion reports or uses pAE for residue segments. Done means documenting how pairwise pAE values become a single segment value and explaining the origin of the less-than-10 criterion; no repository files or tests are identified in the issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
bioinformatics, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.