Fix ms2 transferlearning ms2 bug #407
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
GeorgWa
added
the
test:e2e
|
Hi Mo, we got rid of development branch. Can you reopen the PR based of main? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
A fix for #406
This might be a good place to explain what was going on:
From my experiences, in peptdeep when using the prediction functionality directly from the model class (instead of using predict_all in the model manager), it expects the precursors to be sorted by nAA. If they aren’t sorted, you end up with an all-zero fragments dataframe. That’s why I added the df_refinement step in this PR to handle this issue.
When the precursors are sorted by nAA, PeptDeep drops the old fragment indices and reinitializes them (in-place) based on the refined precursors. This caused problems when trying to compare predictions with a ground truth. This part of the issue was already handled but I wanted to explain why we are doing multiple preprocessing steps before prediction, and this commit specifically fixes the nAA sorting-related problem.
This should address both issues and ensure things work as expected.