spatialdata-io 0.1.4__tar.gz → 0.1.6__tar.gz

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/.flake8

@@ -38,6 +38,8 @@ ignore =
     D400
     # First line should be in imperative mood; try rephrasing
     D401
+    # Abstract base class without abstractmethod.
+    B024
 exclude = .git,__pycache__,build,docs/_build,dist
 per-file-ignores =
     tests/*: D

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/.github/workflows/test.yaml

@@ -18,7 +18,7 @@ jobs:
         strategy:
             fail-fast: false
             matrix:
-                python: ["3.9", "3.10"]
+                python: ["3.10", "3.12"]
                 os: [ubuntu-latest]
 
         env:
@@ -52,7 +52,7 @@ jobs:
                   pip install --pre -e ".[dev,test]"
 
             - name: Download artifact of test data
-              if: matrix.python == '3.10'
+              if: matrix.python == '3.12'
               uses: dawidd6/action-download-artifact@v2
               with:
                   workflow: prepare_test_data.yaml
@@ -60,7 +60,7 @@ jobs:
                   path: ./data
 
             - name: List the data directory
-              if: matrix.python == '3.10'
+              if: matrix.python == '3.12'
               run: |
                   ls -l ./data
                   pwd

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/.mypy.ini

@@ -1,5 +1,5 @@
 [mypy]
-python_version = 3.9
+python_version = 3.10
 plugins = numpy.typing.mypy_plugin
 
 ignore_errors = False

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/.pre-commit-config.yaml

@@ -2,8 +2,8 @@ fail_fast: false
 default_language_version:
     python: python3
 default_stages:
-    - commit
-    - push
+    - pre-commit
+    - pre-push
 minimum_pre_commit_version: 2.16.0
 repos:
     - repo: https://github.com/psf/black
@@ -73,7 +73,7 @@ repos:
       rev: v3.17.0
       hooks:
           - id: pyupgrade
-            args: [--py3-plus, --py39-plus, --keep-runtime-typing]
+            args: [--py3-plus, --py310-plus, --keep-runtime-typing]
     - repo: local
       hooks:
           - id: forbid-to-commit

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/.readthedocs.yaml

@@ -3,7 +3,7 @@ version: 2
 build:
     os: ubuntu-20.04
     tools:
-        python: "3.9"
+        python: "3.10"
 sphinx:
     configuration: docs/conf.py
     fail_on_warning: true

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/CHANGELOG.md

@@ -8,7 +8,24 @@ and this project adheres to [Semantic Versioning][].
 [keep a changelog]: https://keepachangelog.com/en/1.0.0/
 [semantic versioning]: https://semver.org/spec/v2.0.0.html
 
-## [0.1.4] - xxxx-xx-xx
+## [0.1.6] - 2024-11-26
+
+-   (MERSCOPE) added `feature_key` attribute for points (i.e., the `'gene'` column) #210
+-   (Visium HD) get transformation matrices even when only images are parsed #215
+-   Support for `xarray.DataTree` (which was moved from `datatree.DataTree`) #232
+
+## [0.1.5] - 2024-09-25
+
+### Added
+
+-   (Xenium) added `dims` parameter for more control in `xenium_aligned_image()`
+
+### Fixed
+
+-   Passing `rgb=None` to image model parser for both visium and visiumhd, leading to 3-4 channel images being
+    interpreted as RGB(A)
+-   Fix header bug Visium data #200
+-   (Visium HD) Fix path parsing when images are missing #204 #206
 
 ## [0.1.4] - 2024-08-07
 

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: spatialdata-io
-Version: 0.1.4
+Version: 0.1.6
 Summary: SpatialData IO for common techs
 Project-URL: Documentation, https://spatialdata-io.readthedocs.io/
 Project-URL: Source, https://github.com/scverse/spatialdata-io
@@ -36,8 +36,7 @@ License: BSD 3-Clause License
         CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
         OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
         OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-License-File: LICENSE
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Requires-Dist: anndata
 Requires-Dist: dask-image
 Requires-Dist: h5py
@@ -48,7 +47,7 @@ Requires-Dist: pyarrow
 Requires-Dist: readfcs
 Requires-Dist: scanpy
 Requires-Dist: scikit-image
-Requires-Dist: spatialdata>=0.2.1
+Requires-Dist: spatialdata>=0.2.6
 Requires-Dist: tifffile>=2023.8.12
 Provides-Extra: dev
 Requires-Dist: bump2version; extra == 'dev'

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.4'
-__version_tuple__ = version_tuple = (0, 1, 4)
+__version__ = version = '0.1.6'
+__version_tuple__ = version_tuple = (0, 1, 6)

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/docs/conf.py

@@ -90,6 +90,7 @@ source_suffix = {
 }
 
 intersphinx_mapping = {
+    "python": ("https://docs.python.org/3", None),
     "anndata": ("https://anndata.readthedocs.io/en/stable/", None),
     "spatialdata": ("https://scverse-spatialdata.readthedocs.io/en/latest/", None),
     "numpy": ("https://numpy.org/doc/stable/", None),

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/pyproject.toml

@@ -10,7 +10,7 @@ dynamic= [
 ]
 description = "SpatialData IO for common techs"
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 license = {file = "LICENSE"}
 authors = [
     {name = "scverse"},
@@ -25,7 +25,7 @@ dependencies = [
     "anndata",
     "numpy",
     "scanpy",
-    "spatialdata>=0.2.1",
+    "spatialdata>=0.2.6",
     "scikit-image",
     "h5py",
     "joblib",
@@ -83,7 +83,7 @@ skip_glob = ["docs/*"]
 
 [tool.black]
 line-length = 120
-target-version = ['py39']
+target-version = ['py310']
 include = '\.pyi?$'
 exclude = '''
 (

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/_constants/_constants.py

@@ -322,6 +322,7 @@ class MerscopeKeys(ModeEnum):
     GLOBAL_Z = "global_z"
     Z_INDEX = "ZIndex"
     REGION_KEY = "cells_region"
+    GENE_KEY = "gene"
 
 
 @unique
@@ -353,9 +354,9 @@ class VisiumHDKeys(ModeEnum):
     TISSUE_POSITIONS_FILE = "tissue_positions.parquet"
 
     # images
-    IMAGE_HIRES_FILE = "spatial/tissue_hires_image.png"
-    IMAGE_LOWRES_FILE = "spatial/tissue_lowres_image.png"
-    IMAGE_CYTASSIST = "spatial/cytassist_image.tiff"
+    IMAGE_HIRES_FILE = "tissue_hires_image.png"
+    IMAGE_LOWRES_FILE = "tissue_lowres_image.png"
+    IMAGE_CYTASSIST = "cytassist_image.tiff"
 
     # scalefactors
     SCALEFACTORS_FILE = "scalefactors_json.json"

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/_constants/_enum.py

@@ -1,7 +1,8 @@
 from abc import ABC, ABCMeta
+from collections.abc import Callable
 from enum import Enum, EnumMeta
 from functools import wraps
-from typing import Any, Callable
+from typing import Any
 
 
 class PrettyEnum(Enum):

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/_docs.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
+from collections.abc import Callable
 from textwrap import dedent
-from typing import Any, Callable
+from typing import Any
 
 
 def inject_docs(**kwargs: Any) -> Callable[..., Any]:  # noqa: D103

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/_utils.py

@@ -2,7 +2,8 @@ from __future__ import annotations
 
 import functools
 import warnings
-from typing import Any, Callable, TypeVar
+from collections.abc import Callable
+from typing import Any, TypeVar
 
 RT = TypeVar("RT")
 

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/_utils/_read_10x_h5.py

@@ -31,7 +31,7 @@
 # code below taken from https://github.com/scverse/scanpy/blob/master/scanpy/readwrite.py
 
 from pathlib import Path
-from typing import Any, Optional, Union
+from typing import Any
 
 import h5py
 import numpy as np
@@ -40,8 +40,8 @@ from spatialdata._logging import logger
 
 
 def _read_10x_h5(
-    filename: Union[str, Path],
-    genome: Optional[str] = None,
+    filename: str | Path,
+    genome: str | None = None,
     gex_only: bool = True,
 ) -> AnnData:
     """
@@ -96,7 +96,7 @@ def _read_10x_h5(
     return adata
 
 
-def _read_v3_10x_h5(filename: Union[str, Path], *, start: Optional[Any] = None) -> AnnData:
+def _read_v3_10x_h5(filename: str | Path, *, start: Any | None = None) -> AnnData:
     """Read hdf5 file from Cell Ranger v3 or later versions."""
     with h5py.File(str(filename), "r") as f:
         try:

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/_utils/_utils.py

@@ -3,9 +3,8 @@ from __future__ import annotations
 import os
 from collections.abc import Mapping
 from pathlib import Path
-from typing import Any, Optional, Union
+from typing import Any, Union
 
-import numpy as np
 from anndata import AnnData, read_text
 from h5py import File
 
@@ -13,19 +12,11 @@ from spatialdata_io.readers._utils._read_10x_h5 import _read_10x_h5
 
 PathLike = Union[os.PathLike, str]  # type:ignore[type-arg]
 
-try:
-    from numpy.typing import NDArray
-
-    NDArrayA = NDArray[Any]
-except (ImportError, TypeError):
-    NDArray = np.ndarray  # type: ignore[misc]
-    NDArrayA = np.ndarray  # type: ignore[misc]
-
 
 def _read_counts(
     path: str | Path,
     counts_file: str,
-    library_id: Optional[str] = None,
+    library_id: str | None = None,
     **kwargs: Any,
 ) -> tuple[AnnData, str]:
     path = Path(path)

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/codex.py

@@ -80,6 +80,7 @@ def codex(
             "images": Image2DModel.parse(
                 image,
                 scale_factors=[2, 2],
+                rgb=None,
             )
         }
         sdata = SpatialData(images=images, shapes={str(region): shapes}, table=table)

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/cosmx.py

@@ -5,7 +5,7 @@ import re
 from collections.abc import Mapping
 from pathlib import Path
 from types import MappingProxyType
-from typing import Any, Optional
+from typing import Any
 
 import dask.array as da
 import numpy as np
@@ -38,7 +38,7 @@ __all__ = ["cosmx"]
 @inject_docs(cx=CosmxKeys)
 def cosmx(
     path: str | Path,
-    dataset_id: Optional[str] = None,
+    dataset_id: str | None = None,
     transcripts: bool = True,
     imread_kwargs: Mapping[str, Any] = MappingProxyType({}),
     image_models_kwargs: Mapping[str, Any] = MappingProxyType({}),
@@ -200,6 +200,7 @@ def cosmx(
                         "global_only_image": aff,
                     },
                     dims=("y", "x", "c"),
+                    rgb=None,
                     **image_models_kwargs,
                 )
                 images[f"{fov}_image"] = parsed_im

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/dbit.py

@@ -4,7 +4,6 @@ import os
 import re
 from pathlib import Path
 from re import Pattern
-from typing import Optional, Union
 
 import anndata as ad
 import numpy as np
@@ -27,9 +26,9 @@ def _check_path(
     path: Path,
     pattern: Pattern[str],
     key: DbitKeys,
-    path_specific: Optional[str | Path] = None,
+    path_specific: str | Path | None = None,
     optional_arg: bool = False,
-) -> tuple[Union[Path, None], bool]:
+) -> tuple[Path | None, bool]:
     """
     Check that the path is valid and match a regex pattern.
 
@@ -218,11 +217,11 @@ def _xy2edges(xy: list[int], scale: float = 1.0, border: bool = True, border_sca
 
 @inject_docs(vx=DbitKeys)
 def dbit(
-    path: Optional[str | Path] = None,
-    anndata_path: Optional[str] = None,
-    barcode_position: Optional[str] = None,
-    image_path: Optional[str] = None,
-    dataset_id: Optional[str] = None,
+    path: str | Path | None = None,
+    anndata_path: str | None = None,
+    barcode_position: str | None = None,
+    image_path: str | None = None,
+    dataset_id: str | None = None,
     border: bool = True,
     border_scale: float = 1,
 ) -> SpatialData:

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/mcmicro.py

@@ -100,7 +100,7 @@ def mcmicro(
         assert len(samples) == 1
         data = imread(samples[0], **imread_kwargs)
         # , scale_factors=[2, 2]
-        data = Image2DModel.parse(data, transformations=_get_transformation(), **image_models_kwargs)
+        data = Image2DModel.parse(data, transformations=_get_transformation(), rgb=None, **image_models_kwargs)
         images["tma_map"] = data
 
         image_dir = path / McmicroKeys.IMAGES_DIR_TMA
@@ -116,7 +116,7 @@ def mcmicro(
             image_id = core_id
 
         data = imread(sample, **imread_kwargs)
-        data = Image2DModel.parse(data, c_coords=marker_names, **image_models_kwargs)
+        data = Image2DModel.parse(data, c_coords=marker_names, rgb=None, **image_models_kwargs)
         transformations = _get_transformation(
             tma=int(core_id) if tma else None, tma_centroids=tma_centroids, raster_data=data
         )
@@ -131,7 +131,9 @@ def mcmicro(
             raw_name = raw_image.with_name(raw_image.stem).with_suffix("").stem
 
             data = imread(raw_image, **imread_kwargs)
-            images[raw_name] = Image2DModel.parse(data, transformations={raw_name: Identity()}, **image_models_kwargs)
+            images[raw_name] = Image2DModel.parse(
+                data, transformations={raw_name: Identity()}, rgb=None, **image_models_kwargs
+            )
 
     illumination_dir = path / McmicroKeys.ILLUMINATION_DIR
     if illumination_dir.exists():
@@ -143,7 +145,7 @@ def mcmicro(
 
             data = imread(illumination_image, **imread_kwargs)
             images[illumination_name] = Image2DModel.parse(
-                data, transformations={raw_name: Identity()}, **image_models_kwargs
+                data, transformations={raw_name: Identity()}, rgb=None, **image_models_kwargs
             )
 
     samples_labels = list((path / McmicroKeys.LABELS_DIR).glob("*/*" + McmicroKeys.IMAGE_SUFFIX))

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/merscope.py

@@ -2,10 +2,10 @@ from __future__ import annotations
 
 import re
 import warnings
-from collections.abc import Mapping
+from collections.abc import Callable, Mapping
 from pathlib import Path
 from types import MappingProxyType
-from typing import Any, Callable, Literal
+from typing import Any, Literal
 
 import anndata
 import dask.dataframe as dd
@@ -273,7 +273,7 @@ def _rioxarray_load_merscope(
         dim="c",
     )
 
-    return Image2DModel.parse(im, c_coords=stainings, **image_models_kwargs)
+    return Image2DModel.parse(im, c_coords=stainings, rgb=None, **image_models_kwargs)
 
 
 def _dask_image_load_merscope(
@@ -292,6 +292,7 @@ def _dask_image_load_merscope(
         im,
         dims=("c", "y", "x"),
         c_coords=stainings,
+        rgb=None,
         **image_models_kwargs,
     )
 
@@ -302,6 +303,7 @@ def _get_points(transcript_path: Path, transformations: dict[str, BaseTransforma
         transcript_df,
         coordinates={"x": MerscopeKeys.GLOBAL_X, "y": MerscopeKeys.GLOBAL_Y},
         transformations=transformations,
+        feature_key=MerscopeKeys.GENE_KEY,
     )
     transcripts["gene"] = transcripts["gene"].astype("category")
     return transcripts

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/steinbock.py

@@ -4,7 +4,7 @@ import os
 from collections.abc import Mapping
 from pathlib import Path
 from types import MappingProxyType
-from typing import Any, Literal, Union
+from typing import Any, Literal
 
 import anndata as ad
 from dask_image.imread import imread
@@ -95,9 +95,9 @@ def _get_images(
     sample: str,
     imread_kwargs: Mapping[str, Any] = MappingProxyType({}),
     image_models_kwargs: Mapping[str, Any] = MappingProxyType({}),
-) -> Union[SpatialImage, MultiscaleSpatialImage]:
+) -> SpatialImage | MultiscaleSpatialImage:
     image = imread(path / SteinbockKeys.IMAGES_DIR / f"{sample}{SteinbockKeys.IMAGE_SUFFIX}", **imread_kwargs)
-    return Image2DModel.parse(data=image, transformations={sample: Identity()}, **image_models_kwargs)
+    return Image2DModel.parse(data=image, transformations={sample: Identity()}, rgb=None, **image_models_kwargs)
 
 
 def _get_labels(
@@ -106,6 +106,6 @@ def _get_labels(
     labels_kind: str,
     imread_kwargs: Mapping[str, Any] = MappingProxyType({}),
     image_models_kwargs: Mapping[str, Any] = MappingProxyType({}),
-) -> Union[SpatialImage, MultiscaleSpatialImage]:
+) -> SpatialImage | MultiscaleSpatialImage:
     image = imread(path / labels_kind / f"{sample}{SteinbockKeys.LABEL_SUFFIX}", **imread_kwargs).squeeze()
     return Labels2DModel.parse(data=image, transformations={sample: Identity()}, **image_models_kwargs)

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/stereoseq.py

@@ -5,7 +5,7 @@ import re
 from collections.abc import Mapping
 from pathlib import Path
 from types import MappingProxyType
-from typing import Any, Union
+from typing import Any
 
 import anndata as ad
 import h5py
@@ -29,7 +29,7 @@ __all__ = ["stereoseq"]
 @inject_docs(xx=SK)
 def stereoseq(
     path: str | Path,
-    dataset_id: Union[str, None] = None,
+    dataset_id: str | None = None,
     read_square_bin: bool = True,
     optional_tif: bool = False,
     imread_kwargs: Mapping[str, Any] = MappingProxyType({}),

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/visium.py

@@ -4,7 +4,6 @@ import json
 import os
 import re
 from collections.abc import Mapping
-from functools import partial
 from pathlib import Path
 from types import MappingProxyType
 from typing import Any
@@ -138,7 +137,6 @@ def visium(
     if (path / "spatial" / VisiumKeys.SPOTS_FILE_1).exists() or (
         tissue_positions_file is not None and str(VisiumKeys.SPOTS_FILE_1) in str(tissue_positions_file)
     ):
-        read_coords = partial(pd.read_csv, header=None, index_col=0)
         tissue_positions_file = (
             path / "spatial" / VisiumKeys.SPOTS_FILE_1
             if tissue_positions_file is None
@@ -147,7 +145,6 @@ def visium(
     elif (path / "spatial" / VisiumKeys.SPOTS_FILE_2).exists() or (
         tissue_positions_file is not None and str(VisiumKeys.SPOTS_FILE_2) in str(tissue_positions_file)
     ):
-        read_coords = partial(pd.read_csv, header=0, index_col=0)
         tissue_positions_file = (
             path / "spatial" / VisiumKeys.SPOTS_FILE_2
             if tissue_positions_file is None
@@ -155,11 +152,18 @@ def visium(
         )
     else:
         raise ValueError(f"Cannot find `tissue_positions` file in `{path}`.")
-    coords = read_coords(tissue_positions_file)
+    coords = pd.read_csv(tissue_positions_file, header=None, index_col=0)
 
-    # to handle spaceranger_version < 2.0.0, where no column names are provided
-    if "in_tissue" not in coords.columns:
-        coords.columns = ["in_tissue", "array_row", "array_col", "pxl_row_in_fullres", "pxl_col_in_fullres"]
+    if tissue_positions_file.name == VisiumKeys.SPOTS_FILE_1:
+        # spaceranger_version < 2.0.0 but header detected: https://github.com/scverse/spatialdata-io/issues/146
+        if "in_tissue" in coords.iloc[0].tolist():
+            coords = pd.read_csv(tissue_positions_file, header=0, index_col=0)
+        else:
+            assert "in_tissue" not in coords.columns
+            coords.columns = ["in_tissue", "array_row", "array_col", "pxl_row_in_fullres", "pxl_col_in_fullres"]
+    else:
+        assert tissue_positions_file.name == VisiumKeys.SPOTS_FILE_2
+        coords = pd.read_csv(tissue_positions_file, header=0, index_col=0)
 
     adata.obs = pd.merge(adata.obs, coords, how="left", left_index=True, right_index=True)
     coords = adata.obs[[VisiumKeys.SPOTS_X, VisiumKeys.SPOTS_Y]].values
@@ -217,6 +221,7 @@ def visium(
                 full_image,
                 scale_factors=[2, 2, 2, 2],
                 transformations={"global": transform_original},
+                rgb=None,
                 **image_models_kwargs,
             )
         else:
@@ -226,13 +231,15 @@ def visium(
         image_hires = imread(path / VisiumKeys.IMAGE_HIRES_FILE, **imread_kwargs).squeeze().transpose(2, 0, 1)
         image_hires = DataArray(image_hires, dims=("c", "y", "x"))
         images[dataset_id + "_hires_image"] = Image2DModel.parse(
-            image_hires, transformations={"downscaled_hires": Identity()}
+            image_hires, transformations={"downscaled_hires": Identity()}, rgb=None
         )
     if (path / VisiumKeys.IMAGE_LOWRES_FILE).exists():
         image_lowres = imread(path / VisiumKeys.IMAGE_LOWRES_FILE, **imread_kwargs).squeeze().transpose(2, 0, 1)
         image_lowres = DataArray(image_lowres, dims=("c", "y", "x"))
         images[dataset_id + "_lowres_image"] = Image2DModel.parse(
-            image_lowres, transformations={"downscaled_lowres": Identity()}
+            image_lowres,
+            transformations={"downscaled_lowres": Identity()},
+            rgb=None,
         )
 
     return SpatialData(images=images, shapes=shapes, table=table)

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/visium_hd.py

@@ -79,22 +79,21 @@ def visium_hd(
     image_models_kwargs
         Keyword arguments for :class:`spatialdata.models.Image2DModel`.
     anndata_kwargs
-        Keyword arguments for :func:`anndata.read_h5ad`.
+        Keyword arguments for :func:`anndata.io.read_h5ad`.
 
     Returns
     -------
     SpatialData object for the Visium HD data.
     """
     path = Path(path)
+    all_files = [file for file in path.rglob("*") if file.is_file()]
     tables = {}
     shapes = {}
     images: dict[str, Any] = {}
 
     if dataset_id is None:
         dataset_id = _infer_dataset_id(path)
-        filename_prefix = f"{dataset_id}_"
-    else:
-        filename_prefix = ""
+    filename_prefix = f"{dataset_id}_"
 
     def load_image(path: Path, suffix: str, scale_factors: list[int] | None = None) -> None:
         _load_image(
@@ -108,7 +107,6 @@ def visium_hd(
         )
 
     metadata, hd_layout = _parse_metadata(path, filename_prefix)
-    transform_matrices = _get_transform_matrices(metadata, hd_layout)
     file_format = hd_layout[VisiumHDKeys.FILE_FORMAT]
     if file_format != "1.0":
         warnings.warn(
@@ -127,8 +125,12 @@ def visium_hd(
             ]
         )
 
-    if VisiumHDKeys.BINNED_OUTPUTS in os.listdir(path):
-        path_bins = path / VisiumHDKeys.BINNED_OUTPUTS
+    all_path_bins = [path_bin for path_bin in all_files if VisiumHDKeys.BINNED_OUTPUTS in str(path_bin)]
+    if len(all_path_bins) != 0:
+        path_bins_parts = all_path_bins[
+            -1
+        ].parts  # just choosing last one here as users might have tar file which would be first
+        path_bins = Path(*path_bins_parts[: path_bins_parts.index(VisiumHDKeys.BINNED_OUTPUTS) + 1])
     else:
         path_bins = path
     all_bin_sizes = _get_bins(path_bins)
@@ -266,15 +268,26 @@ def visium_hd(
             fullres_image_filenames = [
                 f for f in os.listdir(path_fullres) if os.path.isfile(os.path.join(path_fullres, f))
             ]
-            if len(fullres_image_filenames) > 1:
-                warnings.warn(
-                    f"Multiple files found in {path_fullres}, using the first one: {fullres_image_filenames[0]}. Please"
-                    " specify the path to the full resolution image manually using the `fullres_image_file` argument.",
-                    UserWarning,
-                    stacklevel=2,
-                )
-            fullres_image_filename = fullres_image_filenames[0]
-            fullres_image_file = path_fullres / fullres_image_filename
+            fullres_image_paths = [path_fullres / image_filename for image_filename in fullres_image_filenames]
+        elif list((path_fullres := (path / f"{filename_prefix}tissue_image")).parent.glob(f"{path_fullres.name}.*")):
+            fullres_image_paths = list(path_fullres.parent.glob(f"{path_fullres.name}.*"))
+        else:
+            fullres_image_paths = []
+        if len(fullres_image_paths) > 1:
+            warnings.warn(
+                f"Multiple files found in {path_fullres}, using the first one: {fullres_image_paths[0].stem}. Please"
+                " specify the path to the full resolution image manually using the `fullres_image_file` argument.",
+                UserWarning,
+                stacklevel=2,
+            )
+        if len(fullres_image_paths) == 0:
+            warnings.warn(
+                "No full resolution image found. If incorrect, please specify the path in the "
+                "`fullres_image_file` parameter when calling the `visium_hd` reader function.",
+                UserWarning,
+                stacklevel=2,
+            )
+        fullres_image_file = fullres_image_paths[0] if len(fullres_image_paths) > 0 else None
 
     if fullres_image_file is not None:
         load_image(
@@ -284,8 +297,15 @@ def visium_hd(
         )
 
     # hires image
+    hires_image_path = [path for path in all_files if VisiumHDKeys.IMAGE_HIRES_FILE in str(path)]
+    if len(hires_image_path) == 0:
+        warnings.warn(
+            f"No image path found containing the hires image: {VisiumHDKeys.IMAGE_HIRES_FILE}",
+            UserWarning,
+            stacklevel=2,
+        )
     load_image(
-        path=path / VisiumHDKeys.IMAGE_HIRES_FILE,
+        path=hires_image_path[0],
         suffix="_hires_image",
     )
     set_transformation(
@@ -295,8 +315,15 @@ def visium_hd(
     )
 
     # lowres image
+    lowres_image_path = [path for path in all_files if VisiumHDKeys.IMAGE_LOWRES_FILE in str(path)]
+    if len(lowres_image_path) == 0:
+        warnings.warn(
+            f"No image path found containing the lowres image: {VisiumHDKeys.IMAGE_LOWRES_FILE}",
+            UserWarning,
+            stacklevel=2,
+        )
     load_image(
-        path=path / VisiumHDKeys.IMAGE_LOWRES_FILE,
+        path=lowres_image_path[0],
         suffix="_lowres_image",
     )
     set_transformation(
@@ -306,12 +333,20 @@ def visium_hd(
     )
 
     # cytassist image
+    cytassist_path = [path for path in all_files if VisiumHDKeys.IMAGE_CYTASSIST in str(path)]
+    if len(cytassist_path) == 0:
+        warnings.warn(
+            f"No image path found containing the cytassist image: {VisiumHDKeys.IMAGE_CYTASSIST}",
+            UserWarning,
+            stacklevel=2,
+        )
     if load_all_images:
         load_image(
-            path=path / VisiumHDKeys.IMAGE_CYTASSIST,
+            path=cytassist_path[0],
             suffix="_cytassist_image",
         )
         image = images[dataset_id + "_cytassist_image"]
+        transform_matrices = _get_transform_matrices(metadata, hd_layout)
         affine0 = transform_matrices["cytassist_colrow_to_spot_colrow"]
         affine1 = transform_matrices["spot_colrow_to_microscope_colrow"]
         set_transformation(image, Sequence([affine0, affine1]), "global")
@@ -352,7 +387,7 @@ def _load_image(
             # dask_image doesn't recognize .btf automatically and imageio v3 throws error due to pixel limit -> use imageio v2
             data = imread2(path, **imread_kwargs).squeeze().transpose(2, 0, 1)
         image = DataArray(data, dims=("c", "y", "x"))
-        parsed = Image2DModel.parse(image, scale_factors=scale_factors, **image_models_kwargs)
+        parsed = Image2DModel.parse(image, scale_factors=scale_factors, rgb=None, **image_models_kwargs)
         images[dataset_id + suffix] = parsed
     else:
         warnings.warn(f"File {path} does not exist, skipping it.", UserWarning, stacklevel=2)

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/src/spatialdata_io/readers/xenium.py

@@ -10,7 +10,7 @@ import zipfile
 from collections.abc import Mapping
 from pathlib import Path
 from types import MappingProxyType
-from typing import Any, Optional
+from typing import Any
 
 import dask.array as da
 import numpy as np
@@ -24,10 +24,8 @@ from dask.dataframe import read_parquet
 from dask_image.imread import imread
 from geopandas import GeoDataFrame
 from joblib import Parallel, delayed
-from multiscale_spatial_image.multiscale_spatial_image import MultiscaleSpatialImage
 from pyarrow import Table
 from shapely import Polygon
-from spatial_image import SpatialImage
 from spatialdata import SpatialData
 from spatialdata._core.query.relational_query import get_element_instances
 from spatialdata._types import ArrayLike
@@ -39,6 +37,7 @@ from spatialdata.models import (
     TableModel,
 )
 from spatialdata.transformations.transformations import Affine, Identity, Scale
+from xarray import DataArray, DataTree
 
 from spatialdata_io._constants._constants import XeniumKeys
 from spatialdata_io._docs import inject_docs
@@ -111,7 +110,9 @@ def xenium(
     morphology_focus
         Whether to read the morphology focus image.
     aligned_images
-        Whether to also parse, when available, additional H&E or IF aligned images.
+        Whether to also parse, when available, additional H&E or IF aligned images. For more control over the aligned
+        images being read, in particular, to specify the axes of the aligned images, please set this parameter to
+        `False` and use the `xenium_aligned_image` function directly.
     cells_table
         Whether to read the cell annotations in the `AnnData` table.
     n_jobs
@@ -362,7 +363,7 @@ def _decode_cell_id_column(cell_id_column: pd.Series) -> pd.Series:
 
 
 def _get_polygons(
-    path: Path, file: str, specs: dict[str, Any], n_jobs: int, idx: Optional[ArrayLike] = None
+    path: Path, file: str, specs: dict[str, Any], n_jobs: int, idx: ArrayLike | None = None
 ) -> GeoDataFrame:
     def _poly(arr: ArrayLike) -> Polygon:
         return Polygon(arr[:-1])
@@ -513,6 +514,7 @@ def _get_points(path: Path, specs: dict[str, Any]) -> Table:
         feature_key=XeniumKeys.FEATURE_NAME,
         instance_key=XeniumKeys.CELL_ID,
         transformations={"global": transform},
+        sort=True,
     )
     return points
 
@@ -550,7 +552,7 @@ def _get_images(
     file: str,
     imread_kwargs: Mapping[str, Any] = MappingProxyType({}),
     image_models_kwargs: Mapping[str, Any] = MappingProxyType({}),
-) -> SpatialImage | MultiscaleSpatialImage:
+) -> DataArray | DataTree:
     image = imread(path / file, **imread_kwargs)
     if "c_coords" in image_models_kwargs and "dummy" in image_models_kwargs["c_coords"]:
         # Napari currently interprets 4 channel images as RGB; a series of PRs to fix this is almost ready but they will
@@ -559,7 +561,7 @@ def _get_images(
         # let's add a dummy channel as a temporary workaround.
         image = da.concatenate([image, da.zeros_like(image[0:1])], axis=0)
     return Image2DModel.parse(
-        image, transformations={"global": Identity()}, dims=("c", "y", "x"), **image_models_kwargs
+        image, transformations={"global": Identity()}, dims=("c", "y", "x"), rgb=None, **image_models_kwargs
     )
 
 
@@ -567,7 +569,7 @@ def _add_aligned_images(
     path: Path,
     imread_kwargs: Mapping[str, Any] = MappingProxyType({}),
     image_models_kwargs: Mapping[str, Any] = MappingProxyType({}),
-) -> dict[str, MultiscaleSpatialImage]:
+) -> dict[str, DataTree]:
     """Discover and parse aligned images."""
     images = {}
     ome_tif_files = list(path.glob("*.ome.tif"))
@@ -598,7 +600,8 @@ def xenium_aligned_image(
     alignment_file: str | Path | None,
     imread_kwargs: Mapping[str, Any] = MappingProxyType({}),
     image_models_kwargs: Mapping[str, Any] = MappingProxyType({}),
-) -> MultiscaleSpatialImage:
+    dims: tuple[str, ...] | None = None,
+) -> DataTree:
     """
     Read an image aligned to a Xenium dataset, with an optional alignment file.
 
@@ -610,6 +613,12 @@ def xenium_aligned_image(
         Path to the alignment file, if not passed it is assumed that the image is aligned.
     image_models_kwargs
         Keyword arguments to pass to the image models.
+    dims
+        Dimensions of the image (tuple of axes names); valid strings are "c", "x" and "y". If not passed, the function
+        will try to infer the dimensions from the image shape. Please use this argument when the default behavior fails.
+        Example: for an image with shape (1, y, 1, x, 3), use dims=("anystring", "y", "dummy", "x", "c"). Values that
+        are not "c", "x" or "y" are considered dummy dimensions and will be squeezed (the data must have len 1 for
+        those axes).
 
     Returns
     -------
@@ -627,19 +636,28 @@ def xenium_aligned_image(
     # In fact, it could be that the len(image.shape) == 4 has actually dimes (1, x, y, c) and not (1, y, x, c). This is
     # not a problem because the transformation is constructed to be consistent, but if is the case, the data orientation
     # would be transposed compared to the original image, not ideal.
-    if len(image.shape) == 4:
-        assert image.shape[0] == 1
-        assert image.shape[-1] == 3
-        image = image.squeeze(0)
-        dims = ("y", "x", "c")
+    if dims is None:
+        if len(image.shape) == 4:
+            assert image.shape[0] == 1
+            assert image.shape[-1] == 3
+            image = image.squeeze(0)
+            dims = ("y", "x", "c")
+        else:
+            assert len(image.shape) == 3
+            assert image.shape[0] in [3, 4]
+            if image.shape[0] == 4:
+                # as explained before in _get_images(), we need to add a dummy channel until we support 4-channel images as
+                # non-RGBA images in napari
+                image = da.concatenate([image, da.zeros_like(image[0:1])], axis=0)
+            dims = ("c", "y", "x")
     else:
-        assert len(image.shape) == 3
-        assert image.shape[0] in [3, 4]
-        if image.shape[0] == 4:
-            # as explained before in _get_images(), we need to add a dummy channel until we support 4-channel images as
-            # non-RGBA images in napari
-            image = da.concatenate([image, da.zeros_like(image[0:1])], axis=0)
-        dims = ("c", "y", "x")
+        logging.info(f"Image has shape {image.shape}, parsing with dims={dims}.")
+        image = DataArray(image, dims=dims)
+        # squeeze spurious dimensions away
+        to_squeeze = [dim for dim in dims if dim not in ["c", "x", "y"]]
+        dims = tuple(dim for dim in dims if dim in ["c", "x", "y"])
+        for dim in to_squeeze:
+            image = image.squeeze(dim)
 
     if alignment_file is None:
         transformation = Identity()
@@ -762,3 +780,6 @@ def prefix_suffix_uint32_from_cell_id_str(cell_id_str: ArrayLike) -> tuple[Array
     cell_id_prefix = [int(x, 16) for x in cell_id_prefix_hex]
 
     return np.array(cell_id_prefix, dtype=np.uint32), np.array(dataset_suffix_int)
+
+
+##

{spatialdata_io-0.1.4 → spatialdata_io-0.1.6}/tests/test_xenium.py

@@ -46,7 +46,7 @@ def test_roundtrip_with_data_limits() -> None:
 # pointing to "data".
 # The GitHub workflow "prepare_test_data.yaml" takes care of downloading the datasets and uploading an artifact for the
 # tests to use
-@pytest.mark.skipif(sys.version_info < (3, 10), reason="Test requires Python 3.10 or higher")
+@pytest.mark.skipif(sys.version_info < (3, 12), reason="Test requires Python 3.10 or higher")
 @pytest.mark.parametrize(
     "dataset,expected",
     [