feat: add mixscale continuous perturbation scoring#945
feat: add mixscale continuous perturbation scoring#945stefanm808 wants to merge 2 commits intoscverse:mainfrom
Conversation
Implements the Mixscale scoring method (Jiang et al., Nat Cell Biol 2025) as a new method on the Mixscape class. Unlike the binary KO/NP classification in mixscape(), mixscale() computes a continuous perturbation efficiency score per cell likescalar projection onto the estimated perturbation direction vector. Reuses existing _get_perturbation_markers() pipeline for DE gene detection and follows the same code patterns as mixscape() for split handling, layer access & scaling. Closes scverse#921 (partial - continuous scoring component)
for more information, see https://pre-commit.ci
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #945 +/- ##
==========================================
- Coverage 73.54% 72.08% -1.46%
==========================================
Files 48 48
Lines 5613 5804 +191
==========================================
+ Hits 4128 4184 +56
- Misses 1485 1620 +135
🚀 New features to boost your workflow:
|
Zethson
left a comment
Zethson
left a comment
There was a problem hiding this comment.
Hi,
thanks for the contribution! I'd very happy to get this feature merged eventually.
This looks a bit AI generated. Could you please disclose that? There's a few things that the contributing guide outlines that was missed. It would be awesome if you could have another look, please.
Some initial feedback:
- Should this be in the mixscape code base or should this be its own Tool? Even from a user perspective.
- This also needs to show up in the tutorials. Maybe a general version of mixscape & mixscale? We might need a new term then.
- We should likely also point this out clearer in our documentation which pretty much just mentions mixscale for now.
- The ground truth is the R implementation. Could you please compare your version against the R version? We did the same for mixscape. They should be as close as possible.
| ): | ||
| """Calculate continuous perturbation scores using the Mixscale method. | ||
|
|
||
| Unlike :meth:`mixscape` which performs binary KO/NP classification via |
There was a problem hiding this comment.
This sphinx ref doesn't work. Please fix it.
| """Calculate continuous perturbation scores using the Mixscale method. | ||
|
|
||
| Unlike :meth:`mixscape` which performs binary KO/NP classification via | ||
| Gaussian Mixture Models, this method assigns a continuous perturbation |
There was a problem hiding this comment.
Please format these docstrings like the others are formatted. This is LLM generated.
| test_method=test_method, | ||
| ) | ||
|
|
||
| # Get perturbation signature matrix |
| categories = split_obs.unique() | ||
| split_masks = [split_obs == category for category in categories] | ||
|
|
||
| # Reuse the existing DE gene detection pipeline |
There was a problem hiding this comment.
I guess this is LLM noise. Please remove it
| continue | ||
|
|
||
| de_genes = perturbation_markers[(category, gene)] | ||
| # Limit to max_de_genes |
| pvec = dat.dot(vec) / vec_norm_sq if isinstance(dat, spmatrix) else np.dot(dat, vec) / vec_norm_sq | ||
| pvec = np.asarray(pvec).flatten() | ||
|
|
||
| # Extract scores for guide and NT cells |
|
|
||
|
|
||
| @pytest.fixture | ||
| def synthetic_perturbation_adata(): |
There was a problem hiding this comment.
Can you reuse the fixture that we're using to test mixscape?
| return adata | ||
|
|
||
|
|
||
| class TestMixscale: |
There was a problem hiding this comment.
We're not really using test classes in pertpy
| assert gene_a_scores.abs().mean() > 0 | ||
| assert gene_b_scores.abs().mean() > 0 | ||
|
|
||
| def test_sparse_input(self, synthetic_perturbation_adata): |
There was a problem hiding this comment.
A bit of a useless test. But ideally this were parametrized for the different array types instead of being its own test.
3 participants
Implements the Mixscale scoring method (Jiang et al., Nat Cell Biol 2025) as a new method on the Mixscape class. Unlike the binary KO/NP classification in mixscape(), mixscale() computes a continuous perturbation efficiency score per cell likescalar projection onto the estimated perturbation direction vector.
Reuses existing _get_perturbation_markers() pipeline for DE gene detection and follows the same code patterns as mixscape() for split handling, layer access & scaling.
Closes #921 (partial - continuous scoring component)
PR Checklist
Description of changes
Added
Mixscape.mixscale()for continuous perturbation efficiency scoring, implementing the method from Jiang, Dalgarno et al., Nature Cell Biology (2025). Unlike the binary KO/NP classification inmixscape(),mixscale()computes a continuous perturbation efficiency score per cell via scalar projection onto the estimated perturbation direction vector. This is particularly useful for CRISPRi/CRISPRa screens where cells exhibit a gradient of perturbation responses.Usage:
Technical details
Algorithm:
_get_perturbation_markers()pipeline for DE gene detectionFollows the same code patterns as
mixscape()for split handling, layer access, and scaling. No new dependencies added. 9 new tests added, all 5 existing Mixscape tests still pass.Additional context
This addresses item 1 (continuous perturbation scoring) from #921. Items 2-4 (weighted DE, decomposition, program signatures) are planned for follow-up PRs.