spatialproteomics 0.8.6__tar.gz → 0.9.0__tar.gz

spatialproteomics-0.9.0/.gitignore

@@ -0,0 +1,15 @@
+__pycache__
+.pytest_cache
+format.sh
+tests/test_files/test2.zarr
+data
+Dev.ipynb
+Dev-checkpoint.ipynb
+.ipynb_checkpoints
+.DS_Store
+docs/notebooks/Interactivity.py
+docs/notebooks/.ipynb_checkpoints
+*.egg-info/
+*.egg
+dist/
+build/

{spatialproteomics-0.8.6/spatialproteomics.egg-info → spatialproteomics-0.9.0}/PKG-INFO

@@ -1,55 +1,60 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: spatialproteomics
-Version: 0.8.6
+Version: 0.9.0
 Summary: Spatialproteomics is an interoperable toolbox for analyzing highly multiplexed fluorescence image data
 Author: Matthias Meyer-Bender, Harald Vohringer
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Python: >=3.11
 Requires-Dist: cffi>=1.15.0
-Requires-Dist: xarray>=2024.0.0
-Requires-Dist: scikit-image>=0.25
 Requires-Dist: matplotlib>=3.8.0
-Requires-Dist: tqdm>=4.64.0
-Requires-Dist: scikit-learn>=1.4.2
-Requires-Dist: zarr
-Requires-Dist: numpy>=1.23
+Requires-Dist: numpy>=1.25
 Requires-Dist: opencv-python>=4.11.0
+Requires-Dist: pandas>=2.2.2
 Requires-Dist: pyyaml>=6.0
-Provides-Extra: docs
-Requires-Dist: Sphinx>=7.0.0; extra == "docs"
-Requires-Dist: sphinx-book-theme>=0.0.39; extra == "docs"
-Requires-Dist: sphinxcontrib-napoleon==0.7; extra == "docs"
-Requires-Dist: nbsphinx>=0.9; extra == "docs"
-Requires-Dist: sphinx-multiversion>=0.2.4; extra == "docs"
-Requires-Dist: IPython>=8.0.0; extra == "docs"
-Provides-Extra: spatialdata
-Requires-Dist: spatialdata>=0.4.0; extra == "spatialdata"
-Provides-Extra: cellpose
-Requires-Dist: cellpose>=3.1.0; extra == "cellpose"
-Provides-Extra: stardist
-Requires-Dist: stardist>=0.9.1; extra == "stardist"
+Requires-Dist: scikit-image>=0.25
+Requires-Dist: scikit-learn>=1.4.2
+Requires-Dist: tqdm>=4.64.0
+Requires-Dist: xarray>=2025.6.0
+Requires-Dist: zarr>=3.0.0
+Provides-Extra: all
+Requires-Dist: astir; extra == 'all'
+Requires-Dist: cellpose; extra == 'all'
+Requires-Dist: instanseg-torch>=0.1.0; extra == 'all'
+Requires-Dist: spatialdata; extra == 'all'
+Requires-Dist: spotiflow; extra == 'all'
+Requires-Dist: stardist; extra == 'all'
 Provides-Extra: anndata
-Requires-Dist: anndata; extra == "anndata"
+Requires-Dist: anndata>=0.10.0; extra == 'anndata'
 Provides-Extra: astir
-Requires-Dist: astir>=0.1.5; extra == "astir"
-Provides-Extra: spotiflow
-Requires-Dist: spotiflow; extra == "spotiflow"
+Requires-Dist: astir>=0.1.5; extra == 'astir'
+Provides-Extra: cellpose
+Requires-Dist: cellpose>=3.1.0; extra == 'cellpose'
 Provides-Extra: dev
-Requires-Dist: pytest>=7.1.2; extra == "dev"
-Requires-Dist: pytest-cov>=3.0.0; extra == "dev"
-Requires-Dist: black[jupyter]>=22.6.0; extra == "dev"
-Requires-Dist: isort>=5.10.1; extra == "dev"
-Requires-Dist: flake8>=5.0.4; extra == "dev"
-Requires-Dist: bandit>=1.7.4; extra == "dev"
-Requires-Dist: safety>=2.1.1; extra == "dev"
-Requires-Dist: typing_extensions>=4.16; extra == "dev"
-Provides-Extra: all
-Requires-Dist: spatialdata; extra == "all"
-Requires-Dist: cellpose; extra == "all"
-Requires-Dist: stardist; extra == "all"
-Requires-Dist: astir; extra == "all"
-Dynamic: license-file
+Requires-Dist: bandit>=1.7.4; extra == 'dev'
+Requires-Dist: black[jupyter]>=22.6.0; extra == 'dev'
+Requires-Dist: flake8>=5.0.4; extra == 'dev'
+Requires-Dist: isort>=5.10.1; extra == 'dev'
+Requires-Dist: pytest-cov>=3.0.0; extra == 'dev'
+Requires-Dist: pytest>=7.1.2; extra == 'dev'
+Requires-Dist: safety>=2.1.1; extra == 'dev'
+Requires-Dist: typing-extensions>=4.16; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: ipython>=8.0.0; extra == 'docs'
+Requires-Dist: nbsphinx>=0.9; extra == 'docs'
+Requires-Dist: sphinx-book-theme>=0.0.39; extra == 'docs'
+Requires-Dist: sphinx-multiversion>=0.2.4; extra == 'docs'
+Requires-Dist: sphinx>=7.0.0; extra == 'docs'
+Requires-Dist: sphinxcontrib-napoleon==0.7; extra == 'docs'
+Provides-Extra: instanseg
+Requires-Dist: instanseg-torch>=0.1.0; extra == 'instanseg'
+Provides-Extra: spatialdata
+Requires-Dist: spatialdata>=0.7.3; extra == 'spatialdata'
+Requires-Dist: zarr>=3.1.2; extra == 'spatialdata'
+Provides-Extra: spotiflow
+Requires-Dist: spotiflow; extra == 'spotiflow'
+Provides-Extra: stardist
+Requires-Dist: stardist>=0.9.1; extra == 'stardist'
+Description-Content-Type: text/markdown
 
 # spatialproteomics
 
@@ -73,6 +78,8 @@ Multiplexed imaging data comprises at least 3 dimensions (i.e. `channels`, `x`,
 
 Please refer to the [documentation](https://sagar87.github.io/spatialproteomics) for details on the API and tutorials.
 
+If you work with an AI coding assistant, point it to [llms.txt](https://sagar87.github.io/spatialproteomics/llms.txt) (an index of the documentation in Markdown) or [llms-full.txt](https://sagar87.github.io/spatialproteomics/llms-full.txt) (the complete documentation in a single file). Contributors using coding agents will find repository instructions in [AGENTS.md](AGENTS.md).
+
 ## Installation
 
 To install `spatialproteomics`, first create a python environment and install the package using 
@@ -93,6 +100,7 @@ The base version of `spatialproteomics` depends on the following packages:
 xarray
 zarr
 numpy
+pandas
 scikit-image
 scikit-learn
 opencv-python

{spatialproteomics-0.8.6 → spatialproteomics-0.9.0}/README.md

@@ -20,6 +20,8 @@ Multiplexed imaging data comprises at least 3 dimensions (i.e. `channels`, `x`,
 
 Please refer to the [documentation](https://sagar87.github.io/spatialproteomics) for details on the API and tutorials.
 
+If you work with an AI coding assistant, point it to [llms.txt](https://sagar87.github.io/spatialproteomics/llms.txt) (an index of the documentation in Markdown) or [llms-full.txt](https://sagar87.github.io/spatialproteomics/llms-full.txt) (the complete documentation in a single file). Contributors using coding agents will find repository instructions in [AGENTS.md](AGENTS.md).
+
 ## Installation
 
 To install `spatialproteomics`, first create a python environment and install the package using 
@@ -40,6 +42,7 @@ The base version of `spatialproteomics` depends on the following packages:
 xarray
 zarr
 numpy
+pandas
 scikit-image
 scikit-learn
 opencv-python

{spatialproteomics-0.8.6 → spatialproteomics-0.9.0}/pyproject.toml

@@ -1,31 +1,27 @@
 [project]
 name = "spatialproteomics"
-version = "0.8.6"
+version = "0.9.0"
 description = "Spatialproteomics is an interoperable toolbox for analyzing highly multiplexed fluorescence image data"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 authors = [
     {name="Matthias Meyer-Bender"},
     {name="Harald Vohringer"}
 ]
 dependencies = [
     "cffi>=1.15.0",
-    "xarray>=2024.0.0",
+    "xarray>=2025.6.0",
     "scikit-image>=0.25",
     "matplotlib>=3.8.0",
     "tqdm>=4.64.0",
     "scikit-learn>=1.4.2",
-    "zarr",  # note that if you use spatialdata, you should use zarr>=3.0.0
-    "numpy>=1.23",
+    "zarr>=3.0.0",  # zarr-python 3 reads and writes both zarr format v2 and v3
+    "numpy>=1.25",
     "opencv-python>=4.11.0",
+    "pandas>=2.2.2",
     "pyyaml>=6.0"
 ]
 
-[tool.setuptools.packages.find]
-where = ["."]
-include = ["spatialproteomics*"]
-
-
 [project.optional-dependencies]
 docs = [
     "Sphinx>=7.0.0",
@@ -35,12 +31,13 @@ docs = [
     "sphinx-multiversion>=0.2.4",
     "IPython>=8.0.0",
 ]
-spatialdata = ["spatialdata>=0.4.0"]
+spatialdata = ["spatialdata>=0.7.3", "zarr>=3.1.2"]  # spatialdata needs zarr>=3.1.2 but does not declare it
 cellpose = ["cellpose>=3.1.0"]
 stardist = ["stardist>=0.9.1"]
-anndata = ["anndata"]
+anndata = ["anndata>=0.10.0"]
 astir = ["astir>=0.1.5"]
 spotiflow = ["spotiflow"]
+instanseg = ["instanseg-torch>=0.1.0"]
 dev = [
     "pytest>=7.1.2",
     "pytest-cov>=3.0.0",
@@ -51,11 +48,18 @@ dev = [
     "safety>=2.1.1",
     "typing_extensions>=4.16",  # to avoid anndata issues
 ]
-all = ["spatialdata", "cellpose", "stardist", "astir"]
+all = ["spatialdata", "cellpose", "stardist", "astir", "spotiflow", "instanseg-torch>=0.1.0"]
 
 [build-system]
-requires = ["setuptools>=61.0,<81.0"]
-build-backend = "setuptools.build_meta"
+requires = ["hatchling>=1.26"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["spatialproteomics"]
+
+[tool.hatch.build.targets.sdist]
+# only ship the package and the tests, not the docs (notebooks with outputs) or the data folder
+include = ["spatialproteomics", "tests", "README.md", "LICENSE"]
 
 
 [tool.black]

{spatialproteomics-0.8.6 → spatialproteomics-0.9.0}/spatialproteomics/__init__.py

@@ -48,7 +48,7 @@ from .pp import (
     threshold,
     transform_expression_matrix,
 )
-from .tl import ToolAccessor, astir, cellpose, mesmer, stardist
+from .tl import ToolAccessor, astir, cellpose, instanseg, stardist
 
 __all__ = [
     "load_image_data",
@@ -57,19 +57,17 @@ __all__ = [
     "PreprocessingAccessor",
     "LabelAccessor",
     "PlotAccessor",
-    "SegmentationAccessor",
     "ToolAccessor",
     "NeighborhoodAccessor",
     "Layers",
     "Dims",
     "Features",
     "Props",
-    "merge_segmentation",
     "percentage_positive",
     "is_positive",
     "cellpose",
     "stardist",
-    "mesmer",
+    "instanseg",
     "add_observations",
     "add_quantification",
     "apply",

{spatialproteomics-0.8.6 → spatialproteomics-0.9.0}/spatialproteomics/container.py

@@ -125,6 +125,7 @@ def read_from_spatialdata(
         spatial_data_object (spatialdata.SpatialData, str): The spatialdata object to read data from. If str, spatialdata is used to read the file from that path.
         image_key (str): The key of the image in the spatialdata object.
         segmentation_key (str): The key of the segmentation in the spatialdata object.
+        table_key (str): The key of the table in the spatialdata object. If it does not exist, the observations are computed from the segmentation.
         data_key (Optional[str], optional): The key for the image data in the spatialdata object. If None, the image_key will be used. Defaults to None.
         consolidate_segmentation (bool, optional): If True, the segmentation will be consolidated to only include cells that are present in the table. Defaults to False.
         cell_id (Optional[str], optional): The column name for the cell ID in the table. Defaults to "id".
@@ -132,12 +133,7 @@ def read_from_spatialdata(
         spatialproteomics_object (xr.Dataset): The spatialproteomics object.
     """
     import spatialdata
-    from spatialdata.transformations import (
-        Affine,
-        Identity,
-        Translation,
-        get_transformation,
-    )
+    from spatialdata.transformations import get_transformation
 
     if isinstance(spatial_data_object, str):
         spatial_data_object = spatialdata.read_zarr(spatial_data_object)
@@ -160,30 +156,20 @@ def read_from_spatialdata(
     y_coords = np.arange(image.shape[1])
     x_coords = np.arange(image.shape[2])
 
-    # apply transform if exists
-    if isinstance(transform, Identity):
-        pass  # Identity transform — do nothing
-
-    elif isinstance(transform, Translation):
-        shift_y, shift_x = transform.translation
-        y_coords = y_coords + shift_y
-        x_coords = x_coords + shift_x
-
-    elif isinstance(transform, Affine):
-        matrix = transform.matrix
-
-        a, b, c = matrix[0, :]
-        d, e, f = matrix[1, :]
-
-        if not np.isclose(b, 0) or not np.isclose(d, 0):
-            logger.warning(
-                "Affine transformation has shear components, which are not supported in spatialproteomics. Resetting coordinates to start from 0."
-            )
-        else:
-            x_coords = a * x_coords + c
-            y_coords = e * y_coords + f
+    # express any transform (Identity, Translation, Scale, Affine, Sequence, ...) as a 2D x/y affine.
+    # do not read transform.matrix directly: after a zarr round trip spatialdata stores the affine on
+    # the element axes, e.g. (c, y, x -> c, x, y), so the raw matrix is 4x4 and its row order varies.
+    matrix = transform.to_affine_matrix(input_axes=("x", "y"), output_axes=("x", "y"))
+    a, b, c = matrix[0, :]
+    d, e, f = matrix[1, :]
+    if not np.isclose(b, 0) or not np.isclose(d, 0):
+        logger.warning(
+            "Affine transformation has shear components, which are not supported in spatialproteomics. "
+            "Resetting coordinates to start from 0."
+        )
     else:
-        logger.warning(f"Unsupported transform {transform}, resetting coordinates for the spatialproteomics object.")
+        x_coords = a * x_coords + c
+        y_coords = e * y_coords + f
 
     # create the spatialproteomics object
     obj = load_image_data(image, channel_coords=markers, x_coords=x_coords, y_coords=y_coords)
@@ -213,35 +199,49 @@ def read_from_spatialdata(
             )  # Cast back to original dtype
 
         # if there are obs in the spatialdata object, we just use those and do not recompute them
-        add_obs_from_sdata = len(spatial_data_object.tables.keys()) > 0
+        add_obs_from_sdata = table_key in spatial_data_object.tables
+        if not add_obs_from_sdata and len(spatial_data_object.tables.keys()) > 0:
+            logger.warning(
+                f"Table key {table_key} not found in spatial data object (available keys: {list(spatial_data_object.tables.keys())}). "
+                "Computing the observations from the segmentation instead."
+            )
 
-        # obs (from anndata)
         if add_obs_from_sdata:
-            obs = spatial_data_object.tables[table_key].obs
-            if not consolidate_segmentation:
-                assert (
-                    obs.shape[0] == len(np.unique(segmentation)) - 1
-                ), f"The number of cells in the segmentation does not match the number of observations in the table.\nNumber of cells in the segmentation mask: {len(np.unique(segmentation)) - 1}\nNumber of observations: {obs.shape[0]}\nIf you wish to proceed regardless, set `consolidate_segmentation=True`, which will only keep cells appearing both in the segmentation mask and the table."
-            else:
-                # Consolidate segmentation to only include cells that are present in the table and the segmentation mask
-                # Step 1: Get IDs in both segmentation and obs
-                ids_in_segmentation = np.unique(segmentation).astype(int)
-                ids_in_obs = obs[cell_id].astype(int).unique()
+            # copying, so that the table of the input object is not modified
+            obs = spatial_data_object.tables[table_key].obs.copy()
+            assert (
+                cell_id in obs.columns
+            ), f"Column {cell_id} not found in the table. It is required to match the rows of the table to the cells in the segmentation mask. Available columns: {list(obs.columns)}."
+            obs[cell_id] = obs[cell_id].astype(int)
 
-                # Step 2: Keep only valid IDs (appear in both)
-                valid_ids = np.intersect1d(ids_in_segmentation, ids_in_obs, assume_unique=True)
+            if consolidate_segmentation:
+                # Consolidate segmentation to only include cells that are present in the table and the segmentation mask
+                # Step 1: Keep only valid IDs (appear in both the segmentation and the table)
+                valid_ids = np.intersect1d(np.unique(segmentation).astype(int), obs[cell_id].unique())
 
-                # Step 3: Filter segmentation mask to keep only valid IDs
+                # Step 2: Filter segmentation mask to keep only valid IDs
                 segmentation = np.where(np.isin(segmentation, valid_ids), segmentation, 0)
 
-                # Step 4: Filter obs to keep only cells present in segmentation
-                obs[cell_id] = obs[cell_id].astype(int)
-                obs = obs[obs[cell_id].isin(valid_ids)].copy()
+                # Step 3: Filter obs to keep only cells present in segmentation
+                obs = obs[obs[cell_id].isin(valid_ids)]
+
+            obj = obj.pp.add_segmentation(segmentation, add_obs=False, reindex=False)
+
+            # the cells coordinate is sorted by cell id, while the rows of the table can be in any order
+            # hence we align the table to the cells by their id instead of relying on the row order
+            cells = obj.coords[Dims.CELLS].values
+            table_ids = obs[cell_id].values
+            cells_without_row = np.setdiff1d(cells, table_ids)
+            rows_without_cell = np.setdiff1d(table_ids, cells)
+            has_duplicates = obs[cell_id].duplicated().any()
+            assert (
+                len(cells_without_row) == 0 and len(rows_without_cell) == 0 and not has_duplicates
+            ), f"The cell ids in the table do not match the cells in the segmentation mask.\nCells in the segmentation mask without a row in the table: {len(cells_without_row)}\nRows in the table without a cell in the segmentation mask: {len(rows_without_cell)}\nDuplicate ids in the table: {has_duplicates}\nIf you wish to proceed regardless, set `consolidate_segmentation=True`, which will only keep cells appearing both in the segmentation mask and the table."
+            obs = obs.set_index(cell_id, drop=False).loc[cells].rename_axis(None)
 
-            obj = obj.pp.add_segmentation(segmentation, add_obs=not add_obs_from_sdata, reindex=False)
             # next to adding the obs from the dataframe, we also add default obs to the object to ensure that obs includes the centroids
             obj = obj.pp.add_obs_from_dataframe(obs).pp.add_observations()
         else:
-            obj = obj.pp.add_segmentation(segmentation, add_obs=not add_obs_from_sdata, reindex=False)
+            obj = obj.pp.add_segmentation(segmentation, add_obs=True, reindex=False)
 
     return obj

{spatialproteomics-0.8.6 → spatialproteomics-0.9.0}/spatialproteomics/image_container/ImageContainer.py

@@ -1,12 +1,12 @@
 from typing import Dict
 
-import numpy as np
 import pandas as pd
 import xarray as xr
 from sklearn.cluster import KMeans
 from sklearn.preprocessing import StandardScaler
 
-from ..constants import COLORS, Features, Layers
+from ..constants import Features, Layers
+from ..pl.utils import _sample_colors
 
 
 class ImageContainer:
@@ -114,7 +114,7 @@ class ImageContainer:
         self.kmeans_df = kmeans_df
 
         # === ADDING CLUSTERS TO OBJECTS ===
-        colors = np.random.choice(COLORS, size=k, replace=False)
+        colors = _sample_colors(k)
         for id, sp_obj in self.objects.items():
             # obtaining the number of cells contained in the object we are currently looking at
             num_cells = sp_obj.sizes["cells"]
@@ -160,7 +160,7 @@ class ImageContainer:
             self._compute_dataframes_from_existing_neighborhoods(neighborhood_col=neighborhood_col)
 
         # computing the composition of neighborhoods (grouping by the neighborhood labels and summing them up)
-        neighborhood_composition = self.neighborhood_df
+        neighborhood_composition = self.neighborhood_df.copy()
         neighborhood_composition[Features.NEIGHBORHOODS] = self.kmeans_df[Features.NEIGHBORHOODS].values
 
         neighborhood_composition = neighborhood_composition.groupby(Features.NEIGHBORHOODS).mean()
@@ -189,7 +189,12 @@ class ImageContainer:
             assert (
                 neighborhood_col in self.objects[id].pp.get_layer_as_df().columns
             ), f"Column {neighborhood_col} not found in the object. Please set the column with the parameter 'neighborhood_col'. Available columns are {self.objects[id].pp.get_layer_as_df().columns}"
-            kmeans_df.append(self.objects[id].pp.get_layer_as_df()[[neighborhood_col]])
+            # the column is renamed, so that the cluster annotations can be accessed in the same way as after compute_neighborhoods()
+            kmeans_df.append(
+                self.objects[id]
+                .pp.get_layer_as_df()[[neighborhood_col]]
+                .rename(columns={neighborhood_col: Features.NEIGHBORHOODS})
+            )
 
         # replacing nans with 0s (this means that the ct was never called in that specific sample)
         neighborhood_df = pd.concat(neighborhood_df).fillna(0)