Skip to content

Add SenKin CITE-seq method (LightGBM + GRU ensemble) - #18

Open
benjaminfreyuu wants to merge 2 commits into
openproblems-bio:mainfrom
benjaminfreyuu:add-senkin-clean
Open

Add SenKin CITE-seq method (LightGBM + GRU ensemble)#18
benjaminfreyuu wants to merge 2 commits into
openproblems-bio:mainfrom
benjaminfreyuu:add-senkin-clean

Conversation

@benjaminfreyuu

Copy link
Copy Markdown

Describe your changes

Checklist before requesting a review

  • [x ] I have performed a self-review of my code

  • Check the correct box. Does this PR contain:

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

  • [ x] CI Tests succeed and look good!

@VladimirShitov
VladimirShitov self-requested a review July 1, 2026 13:22

@VladimirShitov VladimirShitov left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Thanks! Looks very good overall, but some functionality should be moved to https://github.com/lueckenlab/senkin-tmp-cite-pred and imported from there for better reusability

@@ -0,0 +1,27 @@
__merge__: ../../../api/comp_method.yaml
name: senkin

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Can we call it senkin_tmp? There were 2 team members, would be nice to mention both

45% MSE) of per-fold averaged outputs.
references:
doi:
- 10.1101/2022.04.11.487796

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Suggested change
- 10.1101/2022.04.11.487796
- 10.64898/2026.02.24.707614v1

Comment thread src/methods/senkin/senkin_train/script.py
@VladimirShitov

Copy link
Copy Markdown

Could you update this one with the updated code from senkin-tmp repo and then merge (or tell me to merge)?

Replace the inline _lognorm and _clr_tsvd_fitted duplicates in senkin_train
with the now-published library functions log_normalize() and clr_tsvd() from
senkin_tmp_cite_pred.preprocess. Behaviour is unchanged: log_normalize uses
target_sum=1e4 (CP10K + log1p) matching the old _lognorm, and clr_tsvd uses
random_state=42 for reproducible components. The previously-kept fitted TSVD
object was unused and is dropped.
@benjaminfreyuu

Copy link
Copy Markdown
Author

Replaced the inline _lognorm and _clr_tsvd_fitted duplicates in senkin_train
with the added library functions log_normalize() and clr_tsvd() from
senkin_tmp_cite_pred.preprocess.

Ready to merge @VladimirShitov

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