Skip to content

xenium: use cell_id name for shapes index #399

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
LucaMarconato merged 1 commit into from
May 15, 2026
Merged

xenium: use cell_id name for shapes index #399

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions src/spatialdata_io/readers/xenium.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -605,6 +605,7 @@ def _get_polygons(
else:
# Use cell_id (str) as GeoDataFrame index.
geo_df = GeoDataFrame({"geometry": geoms}, index=indices_mapping["cell_id"].values)
geo_df.index.name = "cell_id"
else:
# Fall back to extracting unique cell IDs from parquet (slow for large_string columns).
# Triggered when indices_mapping is None: v < 1.3.0 (both nuclei and cells, because
Expand All @@ -617,6 +618,7 @@ def _get_polygons(
unique_ids = id_col.filter(np.concatenate([[True], change_mask])).to_pylist()
index = _decode_cell_id_column(pd.Series(unique_ids))
geo_df = GeoDataFrame({"geometry": geoms}, index=index.values)
geo_df.index.name = "cell_id"

scale = Scale([1.0 / specs["pixel_size"], 1.0 / specs["pixel_size"]], axes=("x", "y"))
return ShapesModel.parse(geo_df, transformations={"global": scale})
Expand Down
3 changes: 3 additions & 0 deletions tests/test_xenium.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,6 +114,7 @@ def test_example_data_index_integrity(dataset: str) -> None:
assert sdata["nucleus_labels"]["scale0"]["image"].sel(y=3515.5, x=4618.5).data.compute() == 6392
assert np.allclose(sdata['transcripts'].compute().loc[[0, 10000, 1113949]]['x'], [2.608911, 194.917831, 1227.499268])
assert np.isclose(sdata['cell_boundaries'].loc['oipggjko-1'].geometry.centroid.x,736.4864931162789)
assert sdata['cell_boundaries'].index.name == 'cell_id'
index = sdata['nucleus_boundaries']['cell_id'].index[sdata['nucleus_boundaries']['cell_id'].eq('oipggjko-1')][0]
assert np.isclose(sdata['nucleus_boundaries'].loc[index].geometry.centroid.x,736.4931256878282)
assert np.array_equal(sdata['table'].X.indices[:3], [1, 3, 34])
Expand All @@ -140,6 +141,7 @@ def test_example_data_index_integrity(dataset: str) -> None:
assert sdata["nucleus_labels"]["scale0"]["image"].sel(y=18.5, x=3015.5).data.compute() == 2764
assert np.allclose(sdata['transcripts'].compute().loc[[0, 10000, 20000]]['x'], [174.258392, 12.210024, 214.759186])
assert np.isclose(sdata['cell_boundaries'].loc['aaanbaof-1'].geometry.centroid.x, 43.96894317275074)
assert sdata['cell_boundaries'].index.name == 'cell_id'
index = sdata['nucleus_boundaries']['cell_id'].index[sdata['nucleus_boundaries']['cell_id'].eq('aaanbaof-1')][0]
assert np.isclose(sdata['nucleus_boundaries'].loc[index].geometry.centroid.x,43.31874577809517)
assert np.array_equal(sdata['table'].X.indices[:3], [1, 8, 19])
Expand Down Expand Up @@ -167,6 +169,7 @@ def test_example_data_index_integrity(dataset: str) -> None:
assert sdata["nucleus_labels"]["scale0"]["image"].sel(y=4039.5, x=93.5).data.compute() == 274
assert np.allclose(sdata['transcripts'].compute().loc[[0, 10000, 20000]]['x'], [43.296875, 62.484375, 93.125])
assert np.isclose(sdata['cell_boundaries'].loc['aadmbfof-1'].geometry.centroid.x, 64.54541104696033)
assert sdata['cell_boundaries'].index.name == 'cell_id'
index = sdata['nucleus_boundaries']['cell_id'].index[sdata['nucleus_boundaries']['cell_id'].eq('aadmbfof-1')][0]
assert np.isclose(sdata['nucleus_boundaries'].loc[index].geometry.centroid.x, 65.43305896114295)
assert np.array_equal(sdata['table'].X.indices[:3], [3, 49, 53])
Expand Down
Loading