bytedance / bytedance/Protenix

Performance difference after updating to 0.5.0

Open
#145 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.1k
Forks
312
PR merge metrics
No merged PRs in 30d

Description

I have used v0.2.0 to predict the ligand-protein stcuture of one protein without known struture. It outputed a pTM = 0.67 & ipTM = 0.97. After updating to v0.5.0, using the same json input, it outputs a pTM = 0.16 & ipTM = 0.77.

By manually checking, the predictied strutures by V0.2.0 and V0.5.0 are very inconsistent. Under such condition, should I down-grade protenix to v0.2.0? What is the reason for such difference?

Thanks,

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 by reproducing the reported prediction with the same JSON input under v0.2.0 and v0.5.0, then compare the resulting pTM, ipTM, and predicted structures. Determine whether the difference is an intentional version change or a regression, and document the cause and expected behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
bioinformatics, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 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.