Skip to content

Implement vertical emd and split perfect integration #63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 10 commits into from
May 23, 2025

Conversation

ghar1821
Copy link
Contributor

@ghar1821 ghar1821 commented May 22, 2025

Describe your changes

Introduced new vertical emd metric and split the perfect integration into both vertical and horizontal.

Checklist before requesting a review

  • I have performed a self-review of my code

  • Check the correct box. Does this PR contain:

    • Breaking changes
    • New functionality
    • Major changes
    • Minor changes
    • Bug fixes
  • Proposed changes are described in the CHANGELOG.md

  • CI Tests succeed and look good!

@ghar1821 ghar1821 requested a review from LuLeom May 22, 2025 13:53
use nan mean and nan max so NaN elements are not counted
@ghar1821 ghar1821 marked this pull request as ready for review May 22, 2025 14:10
Copy link
Contributor

@LuLeom LuLeom left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for your effort @ghar1821 !
The PR looks good to me.
The only thing that I would add would be the flag _horizontal for the rest of the emd metrics in emd/config.vsh.yaml and emd/script.py (e.g. emd_mean_ct -> emd_mean_ct_horiz) so that the final heatmap would be easier to understand.

label: Perfect Integration Vertical
# A one sentence summary of how this method works (required). Used when
# rendering summary tables.
summary: "Positive control method which imitates what perfect batch integration."
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would say 'Positive control method for vertical metrics reflecting a scenario in which all samples belong to the same batch'

description: |
This control method return all samples from batch 1.
Because the samples all came from one batch, there should be no batch effect when
measuring vertical metrics.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would specify that yes, we do not expect batch effect, but we still expect a sample-level effect due to the underlying different biology of the samples included in the same batch

@ghar1821 ghar1821 merged commit 9339efd into main May 23, 2025
8 checks passed
@rcannood rcannood deleted the implement_vertical_emd branch June 19, 2025 07:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants