Unable to save subsetted Xenium sdata to .zarr #821

import spatialdata as sd
import spatialdata_io
import squidpy as sq
import spatialdata_plot

sdata = sd.read_zarr("/path/to/data_aligned.zarr/")

subset = sdata.query.bounding_box(
    axes=["x", "y"],
    min_coordinate=[0,0],
    max_coordinate=[15000,13000],
    target_coordinate_system="global",
)

subset.write(f'../data/xenium/subset_test/subset.zarr', overwrite=True)

subset3 = sdata.query.bounding_box(
    axes=["x", "y"],
    min_coordinate=[0,0],
    max_coordinate=[20000,13000],
    target_coordinate_system="global",
)

subset3.write(f'../data/xenium/subset_test/subset3.zarr', overwrite=True)

subset2 = sdata.query.bounding_box(
    axes=["x", "y"],
    min_coordinate=[15000,0],
    max_coordinate=[35000,13000],
    target_coordinate_system="global",
)

subset2.write(f'../data/xenium/subset_test/subset2.zarr', overwrite=True)

subset4 = sdata.query.bounding_box(
    axes=["x", "y"],
    min_coordinate=[10000,0],
    max_coordinate=[30000,13000],
    target_coordinate_system="global",
)
subset4.write(f'../data/xenium/subset_test/subset4.zarr', overwrite=True)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[48], line 1
----> 1 subset4.write(f'../data/xenium/subset_test/subset4.zarr', overwrite=True)
<conda_env_loc>
File [<conda_env_loc>/lib/python3.12/site-packages/spatialdata/_core/spatialdata.py:1186](<conda_env_loc>/lib/python3.12/site-packages/spatialdata/_core/spatialdata.py#line=1185), in SpatialData.write(self, file_path, overwrite, consolidate_metadata, format)
   1183 store.close()
   1185 for element_type, element_name, element in self.gen_elements():
-> 1186     self._write_element(
   1187         element=element,
   1188         zarr_container_path=file_path,
   1189         element_type=element_type,
   1190         element_name=element_name,
   1191         overwrite=False,
   1192         format=format,
   1193     )
   1195 if self.path != file_path:
   1196     old_path = self.path

File [<conda_env_loc>/lib/python3.12/site-packages/spatialdata/_core/spatialdata.py:1230](<conda_env_loc>/lib/python3.12/site-packages/spatialdata/_core/spatialdata.py#line=1229), in SpatialData._write_element(self, element, zarr_container_path, element_type, element_name, overwrite, format)
   1227 parsed = _parse_formats(formats=format)
   1229 if element_type == "images":
-> 1230     write_image(image=element, group=element_type_group, name=element_name, format=parsed["raster"])
   1231 elif element_type == "labels":
   1232     write_labels(labels=element, group=root_group, name=element_name, format=parsed["raster"])

File [<conda_env_loc>/lib/python3.12/site-packages/spatialdata/_io/io_raster.py:242](<conda_env_loc>/lib/python3.12/site-packages/spatialdata/_io/io_raster.py#line=241), in write_image(image, group, name, format, storage_options, **metadata)
    234 def write_image(
    235     image: DataArray | DataTree,
    236     group: zarr.Group,
   (...)
    240     **metadata: str | JSONDict | list[JSONDict],
    241 ) -> None:
--> 242     _write_raster(
    243         raster_type="image",
    244         raster_data=image,
    245         group=group,
    246         name=name,
    247         format=format,
    248         storage_options=storage_options,
    249         **metadata,
    250     )

File [<conda_env_loc>/lib/python3.12/site-packages/spatialdata/_io/io_raster.py:202](<conda_env_loc>/lib/python3.12/site-packages/spatialdata/_io/io_raster.py#line=201), in _write_raster(raster_type, raster_data, group, name, format, storage_options, label_metadata, **metadata)
    200 parsed_axes = _get_valid_axes(axes=list(input_axes), fmt=format)
    201 storage_options = [{"chunks": chunk} for chunk in chunks]
--> 202 dask_delayed = write_multi_scale_ngff(
    203     pyramid=data,
    204     group=group_data,
    205     fmt=format,
    206     axes=parsed_axes,
    207     coordinate_transformations=None,
    208     storage_options=storage_options,
    209     **metadata,
    210     compute=False,
    211 )
    212 # Compute all pyramid levels at once to allow Dask to optimize the computational graph.
    213 da.compute(*dask_delayed)

File [<conda_env_loc>/lib/python3.12/site-packages/ome_zarr/writer.py:253](<conda_env_loc>/lib/python3.12/site-packages/ome_zarr/writer.py#line=252), in write_multiscale(pyramid, group, chunks, fmt, axes, coordinate_transformations, storage_options, name, compute, **metadata)
    251     data = da.array(data).rechunk(chunks=chunks_opt)
    252     options["chunks"] = chunks_opt
--> 253 da_delayed = da.to_zarr(
    254     arr=data,
    255     url=group.store,
    256     component=str(Path(group.path, str(path))),
    257     storage_options=options,
    258     compressor=options.get("compressor", zarr.storage.default_compressor),
    259     dimension_separator=group._store._dimension_separator,
    260     compute=compute,
    261 )
    263 if not compute:
    264     dask_delayed.append(da_delayed)

File [<conda_env_loc>/lib/python3.12/site-packages/dask/array/core.py:3875](<conda_env_loc>/lib/python3.12/site-packages/dask/array/core.py#line=3874), in to_zarr(arr, url, component, storage_options, overwrite, region, compute, return_stored, **kwargs)
   3872     raise ValueError("Cannot use `region` keyword when url is not a `zarr.Array`.")
   3874 if not _check_regular_chunks(arr.chunks):
-> 3875     raise ValueError(
   3876         "Attempt to save array to zarr with irregular "
   3877         "chunking, please call `arr.rechunk(...)` first."
   3878     )
   3880 storage_options = storage_options or {}
   3882 if storage_options:

ValueError: Attempt to save array to zarr with irregular chunking, please call `arr.rechunk(...)` first.

Click to add a cell.