spatial-aim 1.2.0__tar.gz → 1.3.0__tar.gz

{spatial_aim-1.2.0 → spatial_aim-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spatial-aim
-Version: 1.2.0
+Version: 1.3.0
 Summary: SpatialAIM — annotation-independent mapping of scRNA-seq references onto high-resolution spatial transcriptomics
 Author-email: Dominik Pysch <dominik.pysch@fau.de>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -702,6 +702,9 @@ Requires-Dist: squidpy>=1.4
 Requires-Dist: igraph>=0.11
 Requires-Dist: leidenalg>=0.10
 Requires-Dist: umap-learn>=0.5
+Requires-Dist: tifffile>=2024.8
+Requires-Dist: zarr>=2.16
+Requires-Dist: scikit-image>=0.22
 Requires-Dist: streamlit>=1.40
 Requires-Dist: plotly>=5.20
 Requires-Dist: kaleido>=0.2
@@ -709,6 +712,7 @@ Provides-Extra: data
 Requires-Dist: matplotlib>=3.9; extra == "data"
 Requires-Dist: scikit-learn>=1.4; extra == "data"
 Requires-Dist: rdata>=1.1; extra == "data"
+Requires-Dist: h5py>=3.10; extra == "data"
 Provides-Extra: dev
 Requires-Dist: pytest>=8; extra == "dev"
 Requires-Dist: black>=24; extra == "dev"
@@ -785,7 +789,8 @@ DATA/
 │   └── <scName>.h5ad
 ├── ST/
 │   ├── index.csv          # one row per ST dataset
-│   └── <stName>.h5ad
+│   ├── <stName>.h5ad
+│   └── Segmentation/      # optional cell segmentation masks (index.csv column `Segmentation`)
 └── pairs.csv              # links scRNA ↔ ST: PairID, scName, stName, …
 ```
 
@@ -822,7 +827,7 @@ Please install the corresponding conda environments on your computer.
 Check whether your data meets the main requirements.
 
 ```bash
-spatialaim validate --scdata path/to/sc.h5ad --stdata path/to/st.h5ad
+spatialaim validate --scdata path/to/sc.h5ad --stdata path/to/st.h5ad [--segmentation path/to/mask.tif]
 ```
 
 or for every pair of a `pairs.csv` laid out as in [Batch Processing](#batch-processing):
@@ -840,6 +845,10 @@ Validations per dataset:
   - raw count matrices (no NaN values, np negative values, integer-looking, not library-size normalized or log1p'd)
   - unique uppercase gene names
   - `obsm["spatial"]` of shape `(n_spots, 2)`.
+- Optional cell segmentation mask of an ST slice
+  - a 2D `.tif`/`.tiff` of dtype `uint32`: `0` = background, cells labelled `1..max` without gaps (labels without a cell in the h5ad are fine)
+  - the ST h5ad carries the integer `obs["segmentation_id"]` (each cell's mask label, `0` = no segmentation): non-negative, non-zero ids unique and present in the mask
+  - `uns["segmentation_pixel_size_um"]` (µm per pixel) is optional - a warning if missing
 - Per pair
   - the size of the shared-gene intersection
   - whether any ST spot is left all-zero by it.
@@ -856,6 +865,7 @@ spatialaim gui [--server_port 8501]
 Open the printed URL (default http://localhost:8501), set the inputs, pick one or multiple mapper(s), and click **Run**.
 As soon as both `.h5ad` paths are set, the GUI runs the same checks as [`spatialaim validate`](#validate-a-dataset-pair-spatialaim-validate) on that pair: a clean pair is confirmed with a tick in the sidebar, any error or warning is shown in a dialog you can close to continue anyway.
 The GUI writes each mapper's sweep to  `<output_dir>/<mapper>/`. The results using each mapper are visualized in different tabs. When having run multiple mappers, also a "Compare" tab appears.
+An optional **Segmentation path** (the ST slice's cell segmentation mask, see the sidebar's *Info*) is validated with the pair and passed to the runs; their mapper tabs then get a "Shape features" card (shape consistency and the cells' area / eccentricity / solidity per cell type), and the cell-type modal a "Shape features" view. Without it the GUI is unchanged.
 
 ### Run via CLI (`spatialaim run`)
 
@@ -882,6 +892,7 @@ Give such runs their own `--output_dir`: a run root is named after the mapper al
 spatialaim run --scdata path/to/sc.h5ad \
 		--stdata path/to/st.h5ad \
 		--output_dir path/to/out_dir \
+		[--segmentation path/to/mask.tif] \
 		[--mapping nearest_centroid|wann|tangram|tacco|dot] \
 		[--linkage_method average|ward] \
 		[--start_from_annotation <obs_column>] \
@@ -890,7 +901,9 @@ spatialaim run --scdata path/to/sc.h5ad \
 		[--logging verbose]
 ```
 
-**Batch mode (all pairs in `pairs.csv`):**
+`--segmentation` is the ST slice's optional cell segmentation mask; with it the analysis also scores **shape consistency** (column `shape` of `k_comparison.csv`), without it that score is NaN.
+
+**Batch mode (all pairs in `pairs.csv`):** each slice's mask is taken from the `Segmentation` column of `ST/index.csv` (file in `ST/Segmentation/`), if set.
 
 ```bash
 spatialaim run --pairs_csv path/to/pairs.csv \
@@ -909,19 +922,20 @@ Each pair is written to `<out_dir>/<PairID>_<scName>__<stName>/`.
 
 **Output layout** (per pair):
 
-- `<mapping>/config.yaml` — the run configuration.
-- `start_clustering.h5ad` — per-cell start cluster (`start_cluster` id + `start_cluster_name`); computed once, reused for every `K`.
-- `k_<kkk>/` — one folder per `K`:
-	- `spot_to_state_mapping_soft.h5ad` — the spot→state matrix `P` (spots × `K`);
-	    carries `obs["mapping_confidence"]` when the mapper defines one.
-	- `spot_to_state_mapping.csv` — `P` as CSV (for eyeballing).
-	- `start_cluster_to_state.csv` — the start-cluster→state tree cut.
-	- `analysis/data/` — machine-readable metrics for that `K` (no figures; the GUI renders them).
-- `k_comparison.csv` — one row per `K`: the measured metrics, plus each criterion's combined
-    score (harmonic mean of its two curves), the overall score across criteria, and a
-    `pareto` flag.
-- `k_selection.json` — the proposal: the Pareto-optimal `K`, and the best `K` per criterion
-    and overall, each with its score. Same computation the GUI's "Choose K" card shows.
+```
+<out_dir>/
+├── reference_scaffold.h5ad        # cached reference preparation, shared by all mappers
+└── <mapping>/                     # one folder per mapper, e.g. nearest_centroid/
+    ├── config.yaml                # the run's settings
+    ├── start_clustering.h5ad      # each reference cell's start cluster
+    ├── cell_shape_features.csv    # only with a segmentation mask: area, eccentricity, solidity per cell
+    ├── k_<kkk>/                   # one folder per K
+    │   ├── spot_to_state_mapping_soft.h5ad   # the mapping P (spots × K), plus confidence if the mapper has one
+    │   ├── start_cluster_to_state.csv        # which state each start cluster belongs to
+    │   └── analysis/data/                    # the metrics for this K (the GUI plots them)
+    ├── k_comparison.csv           # one row per K: all metrics and the K-selection scores
+    └── k_selection.json           # the suggested K, overall and per criterion
+```
 
 **Sample-dataset example:**
 

{spatial_aim-1.2.0 → spatial_aim-1.3.0}/README.md

@@ -64,7 +64,8 @@ DATA/
 │   └── <scName>.h5ad
 ├── ST/
 │   ├── index.csv          # one row per ST dataset
-│   └── <stName>.h5ad
+│   ├── <stName>.h5ad
+│   └── Segmentation/      # optional cell segmentation masks (index.csv column `Segmentation`)
 └── pairs.csv              # links scRNA ↔ ST: PairID, scName, stName, …
 ```
 
@@ -101,7 +102,7 @@ Please install the corresponding conda environments on your computer.
 Check whether your data meets the main requirements.
 
 ```bash
-spatialaim validate --scdata path/to/sc.h5ad --stdata path/to/st.h5ad
+spatialaim validate --scdata path/to/sc.h5ad --stdata path/to/st.h5ad [--segmentation path/to/mask.tif]
 ```
 
 or for every pair of a `pairs.csv` laid out as in [Batch Processing](#batch-processing):
@@ -119,6 +120,10 @@ Validations per dataset:
   - raw count matrices (no NaN values, np negative values, integer-looking, not library-size normalized or log1p'd)
   - unique uppercase gene names
   - `obsm["spatial"]` of shape `(n_spots, 2)`.
+- Optional cell segmentation mask of an ST slice
+  - a 2D `.tif`/`.tiff` of dtype `uint32`: `0` = background, cells labelled `1..max` without gaps (labels without a cell in the h5ad are fine)
+  - the ST h5ad carries the integer `obs["segmentation_id"]` (each cell's mask label, `0` = no segmentation): non-negative, non-zero ids unique and present in the mask
+  - `uns["segmentation_pixel_size_um"]` (µm per pixel) is optional - a warning if missing
 - Per pair
   - the size of the shared-gene intersection
   - whether any ST spot is left all-zero by it.
@@ -135,6 +140,7 @@ spatialaim gui [--server_port 8501]
 Open the printed URL (default http://localhost:8501), set the inputs, pick one or multiple mapper(s), and click **Run**.
 As soon as both `.h5ad` paths are set, the GUI runs the same checks as [`spatialaim validate`](#validate-a-dataset-pair-spatialaim-validate) on that pair: a clean pair is confirmed with a tick in the sidebar, any error or warning is shown in a dialog you can close to continue anyway.
 The GUI writes each mapper's sweep to  `<output_dir>/<mapper>/`. The results using each mapper are visualized in different tabs. When having run multiple mappers, also a "Compare" tab appears.
+An optional **Segmentation path** (the ST slice's cell segmentation mask, see the sidebar's *Info*) is validated with the pair and passed to the runs; their mapper tabs then get a "Shape features" card (shape consistency and the cells' area / eccentricity / solidity per cell type), and the cell-type modal a "Shape features" view. Without it the GUI is unchanged.
 
 ### Run via CLI (`spatialaim run`)
 
@@ -161,6 +167,7 @@ Give such runs their own `--output_dir`: a run root is named after the mapper al
 spatialaim run --scdata path/to/sc.h5ad \
 		--stdata path/to/st.h5ad \
 		--output_dir path/to/out_dir \
+		[--segmentation path/to/mask.tif] \
 		[--mapping nearest_centroid|wann|tangram|tacco|dot] \
 		[--linkage_method average|ward] \
 		[--start_from_annotation <obs_column>] \
@@ -169,7 +176,9 @@ spatialaim run --scdata path/to/sc.h5ad \
 		[--logging verbose]
 ```
 
-**Batch mode (all pairs in `pairs.csv`):**
+`--segmentation` is the ST slice's optional cell segmentation mask; with it the analysis also scores **shape consistency** (column `shape` of `k_comparison.csv`), without it that score is NaN.
+
+**Batch mode (all pairs in `pairs.csv`):** each slice's mask is taken from the `Segmentation` column of `ST/index.csv` (file in `ST/Segmentation/`), if set.
 
 ```bash
 spatialaim run --pairs_csv path/to/pairs.csv \
@@ -188,19 +197,20 @@ Each pair is written to `<out_dir>/<PairID>_<scName>__<stName>/`.
 
 **Output layout** (per pair):
 
-- `<mapping>/config.yaml` — the run configuration.
-- `start_clustering.h5ad` — per-cell start cluster (`start_cluster` id + `start_cluster_name`); computed once, reused for every `K`.
-- `k_<kkk>/` — one folder per `K`:
-	- `spot_to_state_mapping_soft.h5ad` — the spot→state matrix `P` (spots × `K`);
-	    carries `obs["mapping_confidence"]` when the mapper defines one.
-	- `spot_to_state_mapping.csv` — `P` as CSV (for eyeballing).
-	- `start_cluster_to_state.csv` — the start-cluster→state tree cut.
-	- `analysis/data/` — machine-readable metrics for that `K` (no figures; the GUI renders them).
-- `k_comparison.csv` — one row per `K`: the measured metrics, plus each criterion's combined
-    score (harmonic mean of its two curves), the overall score across criteria, and a
-    `pareto` flag.
-- `k_selection.json` — the proposal: the Pareto-optimal `K`, and the best `K` per criterion
-    and overall, each with its score. Same computation the GUI's "Choose K" card shows.
+```
+<out_dir>/
+├── reference_scaffold.h5ad        # cached reference preparation, shared by all mappers
+└── <mapping>/                     # one folder per mapper, e.g. nearest_centroid/
+    ├── config.yaml                # the run's settings
+    ├── start_clustering.h5ad      # each reference cell's start cluster
+    ├── cell_shape_features.csv    # only with a segmentation mask: area, eccentricity, solidity per cell
+    ├── k_<kkk>/                   # one folder per K
+    │   ├── spot_to_state_mapping_soft.h5ad   # the mapping P (spots × K), plus confidence if the mapper has one
+    │   ├── start_cluster_to_state.csv        # which state each start cluster belongs to
+    │   └── analysis/data/                    # the metrics for this K (the GUI plots them)
+    ├── k_comparison.csv           # one row per K: all metrics and the K-selection scores
+    └── k_selection.json           # the suggested K, overall and per criterion
+```
 
 **Sample-dataset example:**
 

{spatial_aim-1.2.0 → spatial_aim-1.3.0}/environment.yml

@@ -15,15 +15,19 @@ dependencies:
   - scipy==1.18.0
   - pyyaml==6.0.3
   - anndata==0.12.7
-  - scanpy==1.11.5          # Leiden over-clustering, UMAP, analysis.biology
+  - scanpy==1.11.5          # Leiden over-clustering, UMAP, analysis.coherence
+  - tifffile                # cell segmentation masks
+  - zarr                    # reading large masks in bands
+  - scikit-image            # shape-consistency metric (regionprops); rasterising masks at curation
   # --- data preparation only ---
   - matplotlib==3.9.2
   - rdata                   # read R .Rds sources (curate_datasets/curate_05_mouse_embryo)
+  - h5py                    # read HDF5 sources (curate_datasets 01, 02, 09)
   - pip:
     # --- core (pip-only) ---
-    - igraph                # modularity (metrics.biology)
+    - igraph                # modularity (metrics.modularity)
     - leidenalg             # Leiden over-clustering
-    - squidpy               # spatial metrics (analysis.topology)
+    - squidpy               # spatial metrics (analysis.spatial_organization)
     # --- GUI only ---
     - streamlit
     - plotly

{spatial_aim-1.2.0 → spatial_aim-1.3.0}/pyproject.toml

@@ -44,6 +44,9 @@ dependencies = [
     "igraph>=0.11",
     "leidenalg>=0.10",
     "umap-learn>=0.5",
+    "tifffile>=2024.8",  # cell segmentation masks
+    "zarr>=2.16",  # reading large masks in bands
+    "scikit-image>=0.22",  # shape-consistency metric (regionprops), rasterising masks
     # GUI
     "streamlit>=1.40",
     "plotly>=5.20",
@@ -51,7 +54,7 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-data = ["matplotlib>=3.9", "scikit-learn>=1.4", "rdata>=1.1"]
+data = ["matplotlib>=3.9", "scikit-learn>=1.4", "rdata>=1.1", "h5py>=3.10"]
 dev = [
     "pytest>=8",
     "black>=24",
@@ -78,7 +81,6 @@ where = ["src"]
 # curate_06_mouse_retina reads an R .qs object, so it ships an R script and the
 # env spec for the small R environment that runs it.
 "spatialaim.data.curate_datasets" = ["*.yml", "*.R"]
-
 [tool.setuptools_scm]
 # Version is derived from git tags (e.g. v0.1.0). Falls back to 0.0.0.dev* in a
 # source tree without tags.

{spatial_aim-1.2.0 → spatial_aim-1.3.0}/src/spatial_aim.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spatial-aim
-Version: 1.2.0
+Version: 1.3.0
 Summary: SpatialAIM — annotation-independent mapping of scRNA-seq references onto high-resolution spatial transcriptomics
 Author-email: Dominik Pysch <dominik.pysch@fau.de>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -702,6 +702,9 @@ Requires-Dist: squidpy>=1.4
 Requires-Dist: igraph>=0.11
 Requires-Dist: leidenalg>=0.10
 Requires-Dist: umap-learn>=0.5
+Requires-Dist: tifffile>=2024.8
+Requires-Dist: zarr>=2.16
+Requires-Dist: scikit-image>=0.22
 Requires-Dist: streamlit>=1.40
 Requires-Dist: plotly>=5.20
 Requires-Dist: kaleido>=0.2
@@ -709,6 +712,7 @@ Provides-Extra: data
 Requires-Dist: matplotlib>=3.9; extra == "data"
 Requires-Dist: scikit-learn>=1.4; extra == "data"
 Requires-Dist: rdata>=1.1; extra == "data"
+Requires-Dist: h5py>=3.10; extra == "data"
 Provides-Extra: dev
 Requires-Dist: pytest>=8; extra == "dev"
 Requires-Dist: black>=24; extra == "dev"
@@ -785,7 +789,8 @@ DATA/
 │   └── <scName>.h5ad
 ├── ST/
 │   ├── index.csv          # one row per ST dataset
-│   └── <stName>.h5ad
+│   ├── <stName>.h5ad
+│   └── Segmentation/      # optional cell segmentation masks (index.csv column `Segmentation`)
 └── pairs.csv              # links scRNA ↔ ST: PairID, scName, stName, …
 ```
 
@@ -822,7 +827,7 @@ Please install the corresponding conda environments on your computer.
 Check whether your data meets the main requirements.
 
 ```bash
-spatialaim validate --scdata path/to/sc.h5ad --stdata path/to/st.h5ad
+spatialaim validate --scdata path/to/sc.h5ad --stdata path/to/st.h5ad [--segmentation path/to/mask.tif]
 ```
 
 or for every pair of a `pairs.csv` laid out as in [Batch Processing](#batch-processing):
@@ -840,6 +845,10 @@ Validations per dataset:
   - raw count matrices (no NaN values, np negative values, integer-looking, not library-size normalized or log1p'd)
   - unique uppercase gene names
   - `obsm["spatial"]` of shape `(n_spots, 2)`.
+- Optional cell segmentation mask of an ST slice
+  - a 2D `.tif`/`.tiff` of dtype `uint32`: `0` = background, cells labelled `1..max` without gaps (labels without a cell in the h5ad are fine)
+  - the ST h5ad carries the integer `obs["segmentation_id"]` (each cell's mask label, `0` = no segmentation): non-negative, non-zero ids unique and present in the mask
+  - `uns["segmentation_pixel_size_um"]` (µm per pixel) is optional - a warning if missing
 - Per pair
   - the size of the shared-gene intersection
   - whether any ST spot is left all-zero by it.
@@ -856,6 +865,7 @@ spatialaim gui [--server_port 8501]
 Open the printed URL (default http://localhost:8501), set the inputs, pick one or multiple mapper(s), and click **Run**.
 As soon as both `.h5ad` paths are set, the GUI runs the same checks as [`spatialaim validate`](#validate-a-dataset-pair-spatialaim-validate) on that pair: a clean pair is confirmed with a tick in the sidebar, any error or warning is shown in a dialog you can close to continue anyway.
 The GUI writes each mapper's sweep to  `<output_dir>/<mapper>/`. The results using each mapper are visualized in different tabs. When having run multiple mappers, also a "Compare" tab appears.
+An optional **Segmentation path** (the ST slice's cell segmentation mask, see the sidebar's *Info*) is validated with the pair and passed to the runs; their mapper tabs then get a "Shape features" card (shape consistency and the cells' area / eccentricity / solidity per cell type), and the cell-type modal a "Shape features" view. Without it the GUI is unchanged.
 
 ### Run via CLI (`spatialaim run`)
 
@@ -882,6 +892,7 @@ Give such runs their own `--output_dir`: a run root is named after the mapper al
 spatialaim run --scdata path/to/sc.h5ad \
 		--stdata path/to/st.h5ad \
 		--output_dir path/to/out_dir \
+		[--segmentation path/to/mask.tif] \
 		[--mapping nearest_centroid|wann|tangram|tacco|dot] \
 		[--linkage_method average|ward] \
 		[--start_from_annotation <obs_column>] \
@@ -890,7 +901,9 @@ spatialaim run --scdata path/to/sc.h5ad \
 		[--logging verbose]
 ```
 
-**Batch mode (all pairs in `pairs.csv`):**
+`--segmentation` is the ST slice's optional cell segmentation mask; with it the analysis also scores **shape consistency** (column `shape` of `k_comparison.csv`), without it that score is NaN.
+
+**Batch mode (all pairs in `pairs.csv`):** each slice's mask is taken from the `Segmentation` column of `ST/index.csv` (file in `ST/Segmentation/`), if set.
 
 ```bash
 spatialaim run --pairs_csv path/to/pairs.csv \
@@ -909,19 +922,20 @@ Each pair is written to `<out_dir>/<PairID>_<scName>__<stName>/`.
 
 **Output layout** (per pair):
 
-- `<mapping>/config.yaml` — the run configuration.
-- `start_clustering.h5ad` — per-cell start cluster (`start_cluster` id + `start_cluster_name`); computed once, reused for every `K`.
-- `k_<kkk>/` — one folder per `K`:
-	- `spot_to_state_mapping_soft.h5ad` — the spot→state matrix `P` (spots × `K`);
-	    carries `obs["mapping_confidence"]` when the mapper defines one.
-	- `spot_to_state_mapping.csv` — `P` as CSV (for eyeballing).
-	- `start_cluster_to_state.csv` — the start-cluster→state tree cut.
-	- `analysis/data/` — machine-readable metrics for that `K` (no figures; the GUI renders them).
-- `k_comparison.csv` — one row per `K`: the measured metrics, plus each criterion's combined
-    score (harmonic mean of its two curves), the overall score across criteria, and a
-    `pareto` flag.
-- `k_selection.json` — the proposal: the Pareto-optimal `K`, and the best `K` per criterion
-    and overall, each with its score. Same computation the GUI's "Choose K" card shows.
+```
+<out_dir>/
+├── reference_scaffold.h5ad        # cached reference preparation, shared by all mappers
+└── <mapping>/                     # one folder per mapper, e.g. nearest_centroid/
+    ├── config.yaml                # the run's settings
+    ├── start_clustering.h5ad      # each reference cell's start cluster
+    ├── cell_shape_features.csv    # only with a segmentation mask: area, eccentricity, solidity per cell
+    ├── k_<kkk>/                   # one folder per K
+    │   ├── spot_to_state_mapping_soft.h5ad   # the mapping P (spots × K), plus confidence if the mapper has one
+    │   ├── start_cluster_to_state.csv        # which state each start cluster belongs to
+    │   └── analysis/data/                    # the metrics for this K (the GUI plots them)
+    ├── k_comparison.csv           # one row per K: all metrics and the K-selection scores
+    └── k_selection.json           # the suggested K, overall and per criterion
+```
 
 **Sample-dataset example:**
 

{spatial_aim-1.2.0 → spatial_aim-1.3.0}/src/spatial_aim.egg-info/SOURCES.txt

@@ -32,20 +32,25 @@ src/spatialaim/config.py
 src/spatialaim/io.py
 src/spatialaim/sweep.py
 src/spatialaim/tree.py
+src/spatialaim/utils.py
 src/spatialaim/analysis/__init__.py
-src/spatialaim/analysis/analysis.py
-src/spatialaim/analysis/biology.py
-src/spatialaim/analysis/confidence.py
-src/spatialaim/analysis/ksweep.py
+src/spatialaim/analysis/coherence.py
 src/spatialaim/analysis/loading.py
-src/spatialaim/analysis/onehot.py
 src/spatialaim/analysis/reconstruction.py
-src/spatialaim/analysis/topology.py
-src/spatialaim/analysis/utils.py
+src/spatialaim/analysis/run.py
+src/spatialaim/analysis/shape_consistency.py
+src/spatialaim/analysis/spatial_organization.py
+src/spatialaim/analysis/compare_ks/__init__.py
+src/spatialaim/analysis/compare_ks/collect.py
+src/spatialaim/analysis/compare_ks/criteria.py
+src/spatialaim/analysis/compare_ks/run.py
+src/spatialaim/analysis/compare_ks/scoring.py
+src/spatialaim/analysis/compare_ks/selection.py
 src/spatialaim/data/__init__.py
 src/spatialaim/data/curate_datasets/README.md
 src/spatialaim/data/curate_datasets/__init__.py
 src/spatialaim/data/curate_datasets/_common.py
+src/spatialaim/data/curate_datasets/_segmentation.py
 src/spatialaim/data/curate_datasets/curate_01_mouse_ssp.py
 src/spatialaim/data/curate_datasets/curate_02_colorectal_cancer.py
 src/spatialaim/data/curate_datasets/curate_03_mouse_liver.py
@@ -63,16 +68,42 @@ src/spatialaim/data/validate/common.py
 src/spatialaim/data/validate/runner.py
 src/spatialaim/data/validate/validate_pair.py
 src/spatialaim/data/validate/validate_sc.py
+src/spatialaim/data/validate/validate_segmentation.py
 src/spatialaim/data/validate/validate_st.py
 src/spatialaim/gui/__init__.py
 src/spatialaim/gui/__main__.py
 src/spatialaim/gui/app.py
 src/spatialaim/gui/compute.py
 src/spatialaim/gui/data_access.py
-src/spatialaim/gui/render.py
+src/spatialaim/gui/loaders.py
 src/spatialaim/gui/scaffold.py
+src/spatialaim/gui/sidebar.py
 src/spatialaim/gui/state_names.py
-src/spatialaim/gui/widgets.py
+src/spatialaim/gui/texts.py
+src/spatialaim/gui/validation.py
+src/spatialaim/gui/render/__init__.py
+src/spatialaim/gui/render/cell_type.py
+src/spatialaim/gui/render/common.py
+src/spatialaim/gui/render/headline.py
+src/spatialaim/gui/render/ksweep.py
+src/spatialaim/gui/render/markers.py
+src/spatialaim/gui/render/report.py
+src/spatialaim/gui/render/scatter.py
+src/spatialaim/gui/render/shape.py
+src/spatialaim/gui/views/__init__.py
+src/spatialaim/gui/views/cards.py
+src/spatialaim/gui/views/cell_type_modal.py
+src/spatialaim/gui/views/choose_k.py
+src/spatialaim/gui/views/compare_tab.py
+src/spatialaim/gui/views/controls.py
+src/spatialaim/gui/views/mapper_tab.py
+src/spatialaim/gui/views/reference_tab.py
+src/spatialaim/gui/views/report.py
+src/spatialaim/gui/widgets/__init__.py
+src/spatialaim/gui/widgets/headline_plot.py
+src/spatialaim/gui/widgets/linked_plot.py
+src/spatialaim/gui/widgets/plotly_fit.py
+src/spatialaim/gui/widgets/slider.py
 src/spatialaim/mapping/__init__.py
 src/spatialaim/mapping/base.py
 src/spatialaim/mapping/confidence.py
@@ -80,11 +111,9 @@ src/spatialaim/mapping/nearest_centroid.py
 src/spatialaim/mapping/reference.py
 src/spatialaim/mapping/wann.py
 src/spatialaim/metrics/__init__.py
-src/spatialaim/metrics/biology.py
 src/spatialaim/metrics/cossim.py
-src/spatialaim/metrics/kselection.py
-src/spatialaim/metrics/onehot.py
-src/spatialaim/metrics/reconstruction.py
+src/spatialaim/metrics/modularity.py
+src/spatialaim/metrics/shape_consistency.py
 src/spatialaim/metrics/topology.py
 src/spatialaim/reference_aligners/__init__.py
 src/spatialaim/reference_aligners/environment_dot.yml

{spatial_aim-1.2.0 → spatial_aim-1.3.0}/src/spatial_aim.egg-info/requires.txt

@@ -8,6 +8,9 @@ squidpy>=1.4
 igraph>=0.11
 leidenalg>=0.10
 umap-learn>=0.5
+tifffile>=2024.8
+zarr>=2.16
+scikit-image>=0.22
 streamlit>=1.40
 plotly>=5.20
 kaleido>=0.2
@@ -16,6 +19,7 @@ kaleido>=0.2
 matplotlib>=3.9
 scikit-learn>=1.4
 rdata>=1.1
+h5py>=3.10
 
 [dev]
 pytest>=8

{spatial_aim-1.2.0 → spatial_aim-1.3.0}/src/spatial_aim.egg-info/scm_file_list.json

@@ -21,15 +21,18 @@
     "src/spatialaim/adata_schema.py",
     "src/spatialaim/aggregation.py",
     "src/spatialaim/analysis/__init__.py",
-    "src/spatialaim/analysis/analysis.py",
-    "src/spatialaim/analysis/biology.py",
-    "src/spatialaim/analysis/confidence.py",
-    "src/spatialaim/analysis/ksweep.py",
+    "src/spatialaim/analysis/coherence.py",
+    "src/spatialaim/analysis/compare_ks/__init__.py",
+    "src/spatialaim/analysis/compare_ks/collect.py",
+    "src/spatialaim/analysis/compare_ks/criteria.py",
+    "src/spatialaim/analysis/compare_ks/run.py",
+    "src/spatialaim/analysis/compare_ks/scoring.py",
+    "src/spatialaim/analysis/compare_ks/selection.py",
     "src/spatialaim/analysis/loading.py",
-    "src/spatialaim/analysis/onehot.py",
     "src/spatialaim/analysis/reconstruction.py",
-    "src/spatialaim/analysis/topology.py",
-    "src/spatialaim/analysis/utils.py",
+    "src/spatialaim/analysis/run.py",
+    "src/spatialaim/analysis/shape_consistency.py",
+    "src/spatialaim/analysis/spatial_organization.py",
     "src/spatialaim/cli.py",
     "src/spatialaim/clustering.py",
     "src/spatialaim/config.py",
@@ -37,6 +40,7 @@
     "src/spatialaim/data/curate_datasets/README.md",
     "src/spatialaim/data/curate_datasets/__init__.py",
     "src/spatialaim/data/curate_datasets/_common.py",
+    "src/spatialaim/data/curate_datasets/_segmentation.py",
     "src/spatialaim/data/curate_datasets/curate_01_mouse_ssp.py",
     "src/spatialaim/data/curate_datasets/curate_02_colorectal_cancer.py",
     "src/spatialaim/data/curate_datasets/curate_03_mouse_liver.py",
@@ -54,16 +58,42 @@
     "src/spatialaim/data/validate/runner.py",
     "src/spatialaim/data/validate/validate_pair.py",
     "src/spatialaim/data/validate/validate_sc.py",
+    "src/spatialaim/data/validate/validate_segmentation.py",
     "src/spatialaim/data/validate/validate_st.py",
     "src/spatialaim/gui/__init__.py",
     "src/spatialaim/gui/__main__.py",
     "src/spatialaim/gui/app.py",
     "src/spatialaim/gui/compute.py",
     "src/spatialaim/gui/data_access.py",
-    "src/spatialaim/gui/render.py",
+    "src/spatialaim/gui/loaders.py",
+    "src/spatialaim/gui/render/__init__.py",
+    "src/spatialaim/gui/render/cell_type.py",
+    "src/spatialaim/gui/render/common.py",
+    "src/spatialaim/gui/render/headline.py",
+    "src/spatialaim/gui/render/ksweep.py",
+    "src/spatialaim/gui/render/markers.py",
+    "src/spatialaim/gui/render/report.py",
+    "src/spatialaim/gui/render/scatter.py",
+    "src/spatialaim/gui/render/shape.py",
     "src/spatialaim/gui/scaffold.py",
+    "src/spatialaim/gui/sidebar.py",
     "src/spatialaim/gui/state_names.py",
-    "src/spatialaim/gui/widgets.py",
+    "src/spatialaim/gui/texts.py",
+    "src/spatialaim/gui/validation.py",
+    "src/spatialaim/gui/views/__init__.py",
+    "src/spatialaim/gui/views/cards.py",
+    "src/spatialaim/gui/views/cell_type_modal.py",
+    "src/spatialaim/gui/views/choose_k.py",
+    "src/spatialaim/gui/views/compare_tab.py",
+    "src/spatialaim/gui/views/controls.py",
+    "src/spatialaim/gui/views/mapper_tab.py",
+    "src/spatialaim/gui/views/reference_tab.py",
+    "src/spatialaim/gui/views/report.py",
+    "src/spatialaim/gui/widgets/__init__.py",
+    "src/spatialaim/gui/widgets/headline_plot.py",
+    "src/spatialaim/gui/widgets/linked_plot.py",
+    "src/spatialaim/gui/widgets/plotly_fit.py",
+    "src/spatialaim/gui/widgets/slider.py",
     "src/spatialaim/io.py",
     "src/spatialaim/mapping/__init__.py",
     "src/spatialaim/mapping/base.py",
@@ -72,11 +102,9 @@
     "src/spatialaim/mapping/reference.py",
     "src/spatialaim/mapping/wann.py",
     "src/spatialaim/metrics/__init__.py",
-    "src/spatialaim/metrics/biology.py",
     "src/spatialaim/metrics/cossim.py",
-    "src/spatialaim/metrics/kselection.py",
-    "src/spatialaim/metrics/onehot.py",
-    "src/spatialaim/metrics/reconstruction.py",
+    "src/spatialaim/metrics/modularity.py",
+    "src/spatialaim/metrics/shape_consistency.py",
     "src/spatialaim/metrics/topology.py",
     "src/spatialaim/reference_aligners/__init__.py",
     "src/spatialaim/reference_aligners/environment_dot.yml",
@@ -89,6 +117,7 @@
     "src/spatialaim/reference_aligners/run_tangram.py",
     "src/spatialaim/sweep.py",
     "src/spatialaim/tree.py",
+    "src/spatialaim/utils.py",
     "tests/test_cli.py",
     "tests/test_gui_imports.py",
     "tests/test_registry.py",

spatial_aim-1.3.0/src/spatial_aim.egg-info/scm_version.json

@@ -0,0 +1,8 @@
+{
+  "tag": "1.3.0",
+  "distance": 0,
+  "node": "g3ff1552b03833c77cdbaada6b0efd4e446c91b6a",
+  "dirty": false,
+  "branch": "HEAD",
+  "node_date": "2026-10-14"
+}

{spatial_aim-1.2.0 → spatial_aim-1.3.0}/src/spatialaim/__init__.py

@@ -1,5 +1,7 @@
-"""SpatialAIM (Annotation Independent Mapping): over-cluster an scRNA reference, agglomerate
-the subclusters into K states, and map ST spots onto those states across a K sweep.
+"""
+SpatialAIM (Annotation Independent Mapping): split an scRNA reference into start
+clusters, agglomerate them into K states, and map ST spots onto those states across a
+K sweep.
 Public surface: ``SpatialAIMConfig``, ``MAPPING_CHOICES``, ``run``, ``SpotStateMapper``.
 
 These names are exposed lazily (PEP 562) so that importing ``spatialaim``, or a

spatial_aim-1.3.0/src/spatialaim/__main__.py

@@ -0,0 +1,8 @@
+"""
+Enable ``python -m spatialaim ...`` as an alias for the ``spatialaim`` console script.
+"""
+
+from spatialaim.cli import main
+
+if __name__ == "__main__":
+    raise SystemExit(main())