cc-mapping 0.2.3__tar.gz → 0.2.5__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (23) hide show
  1. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/PKG-INFO +1 -1
  2. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/pyproject.toml +1 -1
  3. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/thresholding/sequential.py +25 -15
  4. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/LICENSE +0 -0
  5. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/README.md +0 -0
  6. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/__init__.py +0 -0
  7. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/core.py +0 -0
  8. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/feature_selection/__init__.py +0 -0
  9. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/feature_selection/_base.py +0 -0
  10. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/feature_selection/_persistence.py +0 -0
  11. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/feature_selection/_plotting.py +0 -0
  12. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/feature_selection/_preprocessing.py +0 -0
  13. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/feature_selection/_random_forest.py +0 -0
  14. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/feature_selection/_training.py +0 -0
  15. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/manifold.py +0 -0
  16. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/plot.py +0 -0
  17. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/preprocess.py +0 -0
  18. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/pseudotime.py +0 -0
  19. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/thresholding/__init__.py +0 -0
  20. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/thresholding/base.py +0 -0
  21. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/thresholding/single.py +0 -0
  22. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/utils.py +0 -0
  23. {cc_mapping-0.2.3 → cc_mapping-0.2.5}/src/cc_mapping/utils_v0.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: cc-mapping
3
- Version: 0.2.3
3
+ Version: 0.2.5
4
4
  Summary: Gaussian Mixture Model-based thresholding for single-cell gene expression analysis
5
5
  Home-page: https://github.com/StallaertLab/cc_mapping
6
6
  License: BSD-3-Clause
@@ -1,6 +1,6 @@
1
1
  [tool.poetry]
2
2
  name = "cc-mapping"
3
- version = "0.2.3"
3
+ version = "0.2.5"
4
4
  description = "Gaussian Mixture Model-based thresholding for single-cell gene expression analysis"
5
5
  authors = ["ddpoe <dap182@pitt.edu>"]
6
6
  readme = "README.md"
@@ -418,15 +418,26 @@ class SequentialGMM(GaussianMixtureModelBase):
418
418
  **gmm_kwargs
419
419
  )
420
420
  gmm.fit(subset_data.reshape(-1, 1))
421
-
421
+
422
+ # Sort GMM components by mean (low -> high) so column index matches the
423
+ # caller's ordered_labels convention (e.g. ['G1','S','G2'] = ascending
424
+ # DNA content). sklearn does NOT order components by mean, so without
425
+ # this sort, argmax(predict_proba) returns raw component indices that
426
+ # don't line up with the user-provided label order.
427
+ sort_order = np.argsort(gmm.means_.flatten())
428
+ sorted_means = gmm.means_.flatten()[sort_order]
429
+ sorted_covs = gmm.covariances_.flatten()[sort_order]
430
+ sorted_weights = gmm.weights_[sort_order]
431
+ sorted_data_probs = gmm.predict_proba(subset_data.reshape(-1, 1))[:, sort_order]
432
+
422
433
  # Extract GMM info
423
434
  gmm_info = _GaussianMixtureModelInfo(
424
435
  gmm_kwargs=gmm_kwargs,
425
- means=gmm.means_.flatten(),
426
- covs=gmm.covariances_.flatten(),
427
- weights=gmm.weights_,
436
+ means=sorted_means,
437
+ covs=sorted_covs,
438
+ weights=sorted_weights,
428
439
  n_components=n_components,
429
- data_probs=gmm.predict_proba(subset_data.reshape(-1, 1)),
440
+ data_probs=sorted_data_probs,
430
441
  )
431
442
 
432
443
  # Handle duplicate labels if needed.
@@ -1244,18 +1255,17 @@ class SequentialGMM(GaussianMixtureModelBase):
1244
1255
  )
1245
1256
 
1246
1257
  # Filter adata to only include cells with labels from this operation
1247
- # For refinement operations, we need to include all descendant labels
1248
- # since subsequent operations may have further refined the labels
1249
- if 'refined_from_labels' in op_data and op_data['refined_from_labels']:
1250
- # This was a refinement operation - find all labels that descended from it
1251
- labels_to_plot = self._get_descendant_labels(operation_name, ordered_labels)
1252
- else:
1253
- # This was an initial threshold operation - use ordered_labels directly
1254
- labels_to_plot = ordered_labels
1255
-
1258
+ # (or any of its descendants). Initial-threshold operations also need
1259
+ # the descendant lookup: by the time we plot, subsequent refinement
1260
+ # stages may have replaced this op's labels with finer-grained ones,
1261
+ # leaving zero cells under the original label strings.
1262
+ # _get_descendant_labels gracefully handles the no-descendants case
1263
+ # by returning the input labels unchanged.
1264
+ labels_to_plot = self._get_descendant_labels(operation_name, ordered_labels)
1265
+
1256
1266
  mask = self.adata.obs[obs_label].isin(labels_to_plot)
1257
1267
  adata_subset = self.adata[mask, :]
1258
-
1268
+
1259
1269
  # Call base class plotting method with explicit parameters
1260
1270
  ax = super()._plot_hist_base(
1261
1271
  adata=adata_subset,
File without changes
File without changes