spatialproteomics 0.8.3__tar.gz → 0.8.5__tar.gz

{spatialproteomics-0.8.3/spatialproteomics.egg-info → spatialproteomics-0.8.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spatialproteomics
-Version: 0.8.3
+Version: 0.8.5
 Summary: Spatialproteomics is an interoperable toolbox for analyzing highly multiplexed fluorescence image data
 Author: Matthias Meyer-Bender, Harald Vohringer
 Requires-Python: >=3.10
@@ -97,8 +97,4 @@ matplotlib
 ```
 
 ## Citation
-Spatialproteomics - an interoperable toolbox for analyzing highly multiplexed fluorescence image data
-
-Matthias Fabian Meyer-Bender, Harald Sager Voehringer, Christina Schniederjohann, Sarah Patricia Koziel, Erin Kim Chung, Ekaterina Popova, Alexander Brobeil, Lisa-Maria Held, Aamir Munir, Scverse Community, Sascha Dietrich, Peter-Martin Bruch, Wolfgang Huber
-
-bioRxiv 2025.04.29.651202; doi: https://doi.org/10.1101/2025.04.29.651202
+> Meyer-Bender, M., Voehringer, H., Schniederjohann, C., Koziel, S., Chung, E., Popova, E., ... & Huber, W. (2026). Spatialproteomics: an interoperable toolbox for analyzing highly multiplexed fluorescence image data. Nature Methods, 1-10.

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5}/README.md

@@ -47,8 +47,4 @@ matplotlib
 ```
 
 ## Citation
-Spatialproteomics - an interoperable toolbox for analyzing highly multiplexed fluorescence image data
-
-Matthias Fabian Meyer-Bender, Harald Sager Voehringer, Christina Schniederjohann, Sarah Patricia Koziel, Erin Kim Chung, Ekaterina Popova, Alexander Brobeil, Lisa-Maria Held, Aamir Munir, Scverse Community, Sascha Dietrich, Peter-Martin Bruch, Wolfgang Huber
-
-bioRxiv 2025.04.29.651202; doi: https://doi.org/10.1101/2025.04.29.651202
+> Meyer-Bender, M., Voehringer, H., Schniederjohann, C., Koziel, S., Chung, E., Popova, E., ... & Huber, W. (2026). Spatialproteomics: an interoperable toolbox for analyzing highly multiplexed fluorescence image data. Nature Methods, 1-10.

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "spatialproteomics"
-version = "0.8.3"
+version = "0.8.5"
 description = "Spatialproteomics is an interoperable toolbox for analyzing highly multiplexed fluorescence image data"
 readme = "README.md"
 requires-python = ">=3.10"

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5}/spatialproteomics/container.py

@@ -106,9 +106,6 @@ def load_image_data(
             if neighborhood is not None:
                 dataset = dataset.nh.add_neighborhoods_from_dataframe(neighborhood, neighborhood_col=neighborhood_col)
 
-    else:
-        dataset = xr.Dataset(data_vars={Layers.IMAGE: im})
-
     return dataset
 
 

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5}/spatialproteomics/la/label.py

@@ -76,6 +76,7 @@ def threshold_labels(
 def predict_cell_types_argmax(
     sdata,
     marker_dict: dict,
+    min_intensity: float = 0.0,
     table_key: str = SDLayers.TABLE,
     label_key: str = SDFeatures.LABELS,
     copy: bool = False,
@@ -90,6 +91,7 @@ def predict_cell_types_argmax(
     Args:
         sdata (spatialdata.SpatialData): The spatialdata object containing the expression matrix.
         marker_dict (dict): A dictionary containing the marker genes for each cell type.
+        min_intensity (float, optional): The minimum intensity threshold for assigning cells to a type. Cells with all marker intensities below this threshold will be assigned to "Unlabeled". Defaults to 0.0.
         table_key (str, optional): The key under which the expression matrix is stored in the tables attribute of the spatialdata object. Defaults to "table".
         label_key (str, optional): The key under which the cell type labels are stored in the obs attribute of the spatialdata object. Defaults to "celltype".
         copy (bool, optional): Whether to create a copy of the spatialdata object. Defaults to False.
@@ -102,7 +104,9 @@ def predict_cell_types_argmax(
     assert (
         len(set(marker_dict.keys()) - set(expression_df.columns)) == 0
     ), f"The following markers were not found in quantification layer: {set(marker_dict.keys()) - set(expression_df.columns)}."
-    celltypes = _predict_cell_types_argmax(expression_df, list(marker_dict.keys()), list(marker_dict.values()))
+    celltypes = _predict_cell_types_argmax(
+        expression_df, list(marker_dict.keys()), list(marker_dict.values()), min_intensity=min_intensity
+    )
     adata.obs[label_key] = celltypes
     adata.obs[label_key] = adata.obs[label_key].astype("category")
 
@@ -792,6 +796,7 @@ class LabelAccessor:
         overwrite_existing_labels: bool = False,
         cell_col: str = "cell",
         label_col: str = "label",
+        min_intensity: float = 0.0,
     ):
         """
         Predicts cell types based on the argmax classification of marker intensities.
@@ -802,6 +807,7 @@ class LabelAccessor:
             overwrite_existing_labels (bool, optional): Whether to overwrite existing labels. Defaults to False.
             cell_col (str, optional): The name of the column to store cell IDs in the output dataframe. Defaults to "cell".
             label_col (str, optional): The name of the column to store predicted cell types in the output dataframe. Defaults to "label".
+            min_intensity (float, optional): The minimum intensity threshold for assigning cells to a type. Defaults to 0.0.
 
         Returns:
             xr.Dataset: A new spatialproteomics object with the predicted cell types added as labels.
@@ -825,7 +831,10 @@ class LabelAccessor:
         obj = self._obj.copy()
 
         celltypes_argmax = _predict_cell_types_argmax(
-            pd.DataFrame(obj.pp[markers][key].values, columns=markers), markers=markers, celltypes=celltypes
+            pd.DataFrame(obj.pp[markers][key].values, columns=markers),
+            markers=markers,
+            celltypes=celltypes,
+            min_intensity=min_intensity,
         )
 
         # putting everything into a dataframe

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5}/spatialproteomics/la/utils.py

@@ -4,6 +4,8 @@ import numpy as np
 import pandas as pd
 from skimage.segmentation import relabel_sequential
 
+from spatialproteomics.constants import Labels
+
 from ..base_logger import logger
 
 
@@ -160,11 +162,17 @@ def _predict_cell_types_argmax(
     expression_df: pd.DataFrame,
     markers: List,
     celltypes: List,
+    min_intensity: float = 0.0,
 ):
     # getting the argmax for each cell
     argmax_classification = np.argmax(expression_df[markers], axis=1)
 
     # translating the argmax classification into cell types
-    celltypes_argmax = np.array(celltypes)[argmax_classification]
+    celltypes_argmax = np.array(celltypes, dtype=object)[argmax_classification]
+
+    # if all markers are below the minimum intensity, assign UNASSIGNED
+    if min_intensity > 0.0:
+        below_threshold = (expression_df[markers].max(axis=1) < min_intensity).values
+        celltypes_argmax[below_threshold] = Labels.UNLABELED
 
     return celltypes_argmax

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5}/spatialproteomics/pp/preprocessing.py

@@ -866,7 +866,7 @@ class PreprocessingAccessor:
             from_layer = segmentation
             segmentation = self._obj[segmentation].values.squeeze()
 
-        assert segmentation.ndim == 2, "A segmentation mask must 2 dimensional."
+        assert segmentation.ndim == 2, "A segmentation mask must be 2-dimensional."
         assert ~np.any(segmentation < 0), "A segmentation mask may not contain negative numbers."
 
         y_dim, x_dim = segmentation.shape
@@ -939,14 +939,14 @@ class PreprocessingAccessor:
         """
         # checking that the layer does not exist yet
         assert key_added not in self._obj, f"Layer {key_added} already exists."
-        assert array.ndim in [2, 3], "The array to add mask must 2 or 3-dimensional."
+        assert array.ndim in [2, 3], "The array to add mask must be 2- or 3-dimensional."
 
         if array.ndim == 2:
             # in the case of a 2D array
             y_dim, x_dim = array.shape
             assert (x_dim == self._obj.sizes[Dims.X]) & (
                 y_dim == self._obj.sizes[Dims.Y]
-            ), f"The shape of array does not match that of the image. Image has shape ({self._obj.sizes[Dims.Y]}, {self._obj.sizes[Dims.X]}), array has shape {array.shape}."
+            ), f"The shape of the array does not match that of the image. Image has shape ({self._obj.sizes[Dims.Y]}, {self._obj.sizes[Dims.X]}), array has shape {array.shape}."
 
             # create a data array with the new layer
             da = xr.DataArray(

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5}/spatialproteomics/pp/utils.py

@@ -659,11 +659,13 @@ def _threshold(
         if intensity.size == 1:
             intensity = np.full(len(all_channels), intensity.item(), dtype=img_dtype)
         else:
-            # cast each provided value to image dtype
-            intensity = np.asarray(intensity, dtype=img_dtype)
+            # casting to float here to allow for NAs (important when using the channels argument)
+            intensity = np.asarray(intensity, dtype=float)
 
         max_val = np.max(img)
-        assert np.all(intensity <= max_val), "Intensity values must be smaller than the maximum intensity."
+        assert np.all(
+            intensity[~np.isnan(intensity)] <= max_val
+        ), "Intensity values must be smaller than the maximum intensity."
 
     filtered = None
 

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5}/spatialproteomics/tl/tool.py

@@ -588,6 +588,7 @@ class ToolAccessor:
         expression_matrix_key: str = Layers.INTENSITY,
         obs_key: str = Layers.OBS,
         additional_layers: Optional[dict] = None,
+        additional_obsm: Optional[dict] = None,
         additional_uns: Optional[dict] = None,
     ):
         """
@@ -601,6 +602,8 @@ class ToolAccessor:
             The key of the observation data in the spatialproteomics object. Default is '_obs'.
         additional_layers : dict, optional
             Additional layers to include in the anndata.AnnData object. The keys are the names of the layers and the values are the corresponding keys in the spatialproteomics object.
+        additional_obsm : dict, optional
+            Additional obsm data to include in the anndata.AnnData object. The keys are the names of the obsm data and the values are the corresponding keys in the spatialproteomics object.
         additional_uns : dict, optional
             Additional uns data to include in the anndata.AnnData object. The keys are the names of the uns data and the values are the corresponding keys in the spatialproteomics object.
 
@@ -612,7 +615,7 @@ class ToolAccessor:
         Raises
         ------
         AssertionError
-            If the expression matrix key or additional layers are not found in the spatialproteomics object.
+            If additional layers, obsm entries, or uns entries are not found in the spatialproteomics object, or if additional layers or obsm entries have incompatible shapes.
 
         Notes
         -----
@@ -633,6 +636,11 @@ class ToolAccessor:
             for key, layer in additional_layers.items():
                 # checking that the additional layer is present in the object
                 assert layer in self._obj, f"Layer {layer} not found in the object."
+                # checking that layer has the same shape as the expression matrix
+                assert self._obj[layer].shape == expression_matrix.shape, (
+                    f"Layer {layer} has shape {self._obj[layer].shape}, but AnnData layers must match "
+                    f"the shape of the expression matrix {expression_matrix.shape}."
+                )
                 adata.layers[key] = self._obj[layer].values
         adata.var_names = self._obj.coords[Dims.CHANNELS].values
 
@@ -661,9 +669,21 @@ class ToolAccessor:
                 adata.obs[Features.Y] = adata.obs[Features.Y].astype(float)
                 adata.obsm["spatial"] = np.array(adata.obs[[Features.X, Features.Y]])
 
+        if additional_obsm:
+            for key, layer in additional_obsm.items():
+                # checking that the additional obsm source layer is present in the object
+                assert layer in self._obj, f"Layer {layer} not found in the object."
+                # checking that the additional obsm layer has the same number of observations as the expression matrix
+                assert self._obj[layer].shape[0] == expression_matrix.shape[0], (
+                    f"Layer {layer} has {self._obj[layer].shape[0]} observations, but the expression "
+                    f"matrix has {expression_matrix.shape[0]} observations. AnnData obsm entries must match "
+                    "the number of observations in the expression matrix."
+                )
+                adata.obsm[key] = self._obj[layer].values
+
         if additional_uns:
             for key, layer in additional_uns.items():
-                # checking that the additional layer is present in the object
+                # checking that the additional uns source layer is present in the object
                 assert layer in self._obj, f"Layer {layer} not found in the object."
                 adata.uns[key] = self._obj.pp.get_layer_as_df(layer)
 

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5/spatialproteomics.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spatialproteomics
-Version: 0.8.3
+Version: 0.8.5
 Summary: Spatialproteomics is an interoperable toolbox for analyzing highly multiplexed fluorescence image data
 Author: Matthias Meyer-Bender, Harald Vohringer
 Requires-Python: >=3.10
@@ -97,8 +97,4 @@ matplotlib
 ```
 
 ## Citation
-Spatialproteomics - an interoperable toolbox for analyzing highly multiplexed fluorescence image data
-
-Matthias Fabian Meyer-Bender, Harald Sager Voehringer, Christina Schniederjohann, Sarah Patricia Koziel, Erin Kim Chung, Ekaterina Popova, Alexander Brobeil, Lisa-Maria Held, Aamir Munir, Scverse Community, Sascha Dietrich, Peter-Martin Bruch, Wolfgang Huber
-
-bioRxiv 2025.04.29.651202; doi: https://doi.org/10.1101/2025.04.29.651202
+> Meyer-Bender, M., Voehringer, H., Schniederjohann, C., Koziel, S., Chung, E., Popova, E., ... & Huber, W. (2026). Spatialproteomics: an interoperable toolbox for analyzing highly multiplexed fluorescence image data. Nature Methods, 1-10.

{spatialproteomics-0.8.3 → spatialproteomics-0.8.5}/tests/test_to_zarr.py

@@ -7,7 +7,7 @@ def test_to_zarr_image(ds_image):
     with tempfile.TemporaryDirectory() as temp_dir:
         output_path = os.path.join(temp_dir, "zarr_writing_test.zarr")
         try:
-            ds_image.drop_encoding().to_zarr(output_path)
+            ds_image.drop_encoding().to_zarr(output_path, consolidated=False)
             assert os.path.exists(output_path) and os.path.isdir(
                 output_path
             ), f"Directory {output_path} was not created."
@@ -21,7 +21,7 @@ def test_to_zarr_segmentation(ds_segmentation):
     with tempfile.TemporaryDirectory() as temp_dir:
         output_path = os.path.join(temp_dir, "zarr_writing_test.zarr")
         try:
-            ds_segmentation.drop_encoding().to_zarr(output_path)
+            ds_segmentation.drop_encoding().to_zarr(output_path, consolidated=False)
             assert os.path.exists(output_path) and os.path.isdir(
                 output_path
             ), f"Directory {output_path} was not created."
@@ -35,7 +35,7 @@ def test_to_zarr_labels(ds_labels):
     with tempfile.TemporaryDirectory() as temp_dir:
         output_path = os.path.join(temp_dir, "zarr_writing_test.zarr")
         try:
-            ds_labels.drop_encoding().to_zarr(output_path)
+            ds_labels.drop_encoding().to_zarr(output_path, consolidated=False)
             assert os.path.exists(output_path) and os.path.isdir(
                 output_path
             ), f"Directory {output_path} was not created."
@@ -49,7 +49,7 @@ def test_to_zarr_neighborhoods(ds_neighborhoods):
     with tempfile.TemporaryDirectory() as temp_dir:
         output_path = os.path.join(temp_dir, "zarr_writing_test.zarr")
         try:
-            ds_neighborhoods.drop_encoding().to_zarr(output_path)
+            ds_neighborhoods.drop_encoding().to_zarr(output_path, consolidated=False)
             assert os.path.exists(output_path) and os.path.isdir(
                 output_path
             ), f"Directory {output_path} was not created."