Merge branch 'main' into xenium-labels-dask

Author: LucaMarconato

.github/workflows/prepare_test_data.yaml

@@ -49,7 +49,7 @@ jobs:
                   # the Visium HD dataset is licensed as CC BY 4.0, as shown here
                   # https://www.10xgenomics.com/support/software/space-ranger/latest/resources/visium-hd-example-data
 
-                  # 10x Genomics Visium HD 4.0.1 3' Mouse Brain
+                  # 10x Genomics Visium HD 4.0.1 3' Mouse Brain Chunk
                   curl -O https://cf.10xgenomics.com/samples/spatial-exp/4.0.1/Visium_HD_Tiny_3prime_Dataset/Visium_HD_Tiny_3prime_Dataset_outs.zip
 
                   # -------

.gitignore

@@ -36,5 +36,9 @@ node_modules/
 .code-workspace
 
 # test datasets (e.g. Xenium ones)
+# symlinks
+data
+# data folder
 data/
 tests/data
+uv.lock

.pre-commit-config.yaml

@@ -7,17 +7,17 @@ default_stages:
 minimum_pre_commit_version: 2.16.0
 repos:
     - repo: https://github.com/rbubley/mirrors-prettier
-      rev: v3.6.2
+      rev: v3.7.4
       hooks:
           - id: prettier
     - repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.14.1
+      rev: v0.14.10
       hooks:
           - id: ruff
             args: [--fix, --exit-non-zero-on-fix, --unsafe-fixes]
           - id: ruff-format
     - repo: https://github.com/pre-commit/mirrors-mypy
-      rev: v1.18.2
+      rev: v1.19.1
       hooks:
           - id: mypy
             additional_dependencies: [numpy, types-PyYAML]

pyproject.toml

@@ -36,6 +36,7 @@ dependencies = [
     "readfcs",
     "tifffile>=2023.8.12",
     "ome-types",
+    "xmltodict",
 ]
 
 [project.optional-dependencies]
@@ -59,6 +60,8 @@ doc = [
 test = [
     "pytest",
     "pytest-cov",
+    # https://github.com/scverse/spatialdata-io/issues/334
+    "pyarrow!=22"
 ]
 # this will be used by readthedocs and will make pip also look for pre-releases, generally installing the latest available version
 # update: readthedocs doens't seem to try to install pre-releases even if when trying to install the pre optional-dependency. For

src/spatialdata_io/__main__.py

@@ -412,11 +412,24 @@ def visium_wrapper(
     default=False,
     help="If true, annotates the table by labels. [default: False]",
 )
+@click.option(
+    "--load-segmentations-only",
+    default=None,
+    help="If `True`, only the segmented cell boundaries and their associated counts will be loaded. All binned data will be skipped. [default: None, which will fall back to `False` with a deprecation warning]",
+)
+@click.option(
+    "--load-nucleus-segmentations",
+    type=bool,
+    default=False,
+    help="If `True` and nucleus segmentation files are present, load nucleus segmentation polygons and the corresponding nucleus-filtered count table. [default: False]",
+)
 def visium_hd_wrapper(
     input: str,
     output: str,
     dataset_id: str | None = None,
     filtered_counts_file: bool = True,
+    load_segmentations_only: bool | None = None,
+    load_nucleus_segmentations: bool = False,
     bin_size: int | list[int] | None = None,
     bins_as_squares: bool = True,
     fullres_image_file: str | Path | None = None,
@@ -428,6 +441,8 @@ def visium_hd_wrapper(
         path=input,
         dataset_id=dataset_id,
         filtered_counts_file=filtered_counts_file,
+        load_segmentations_only=load_segmentations_only,
+        load_nucleus_segmentations=load_nucleus_segmentations,
         bin_size=bin_size,
         bins_as_squares=bins_as_squares,
         fullres_image_file=fullres_image_file,

src/spatialdata_io/_constants/_constants.py

@@ -68,7 +68,6 @@ class SeqfishKeys(ModeEnum):
     TIFF_FILE = ".tiff"
     GEOJSON_FILE = ".geojson"
     # file identifiers
-    ROI = "Roi"
     TRANSCRIPT_COORDINATES = "TranscriptList"
     DAPI = "DAPI"
     COUNTS_FILE = "CellxGene"
@@ -78,6 +77,7 @@ class SeqfishKeys(ModeEnum):
     # transcripts
     TRANSCRIPTS_X = "x"
     TRANSCRIPTS_Y = "y"
+    TRANSCRIPTS_Z = "z"
     FEATURE_KEY = "name"
     INSTANCE_KEY_POINTS = "cell"
     # cells
@@ -88,8 +88,6 @@ class SeqfishKeys(ModeEnum):
     SPATIAL_KEY = "spatial"
     REGION_KEY = "region"
     INSTANCE_KEY_TABLE = "instance_id"
-    SCALEFEFACTOR_X = "PhysicalSizeX"
-    SCALEFEFACTOR_Y = "PhysicalSizeY"
 
 
 @unique
@@ -356,11 +354,16 @@ class VisiumHDKeys(ModeEnum):
     BIN_PREFIX = "square_"
     MICROSCOPE_IMAGE = "microscope_image"
     BINNED_OUTPUTS = "binned_outputs"
+    SEGMENTATION_OUTPUTS = "segmented_outputs"
 
     # counts and locations files
     FILTERED_COUNTS_FILE = "filtered_feature_bc_matrix.h5"
     RAW_COUNTS_FILE = "raw_feature_bc_matrix.h5"
     TISSUE_POSITIONS_FILE = "tissue_positions.parquet"
+    BARCODE_MAPPINGS_FILE = "barcode_mappings.parquet"
+    FILTERED_CELL_COUNTS_FILE = "filtered_feature_cell_matrix.h5"
+    CELL_SEGMENTATION_GEOJSON_PATH = "cell_segmentations.geojson"
+    NUCLEUS_SEGMENTATION_GEOJSON_PATH = "nucleus_segmentations.geojson"
 
     # images
     IMAGE_HIRES_FILE = "tissue_hires_image.png"
@@ -402,3 +405,7 @@ class VisiumHDKeys(ModeEnum):
     MICROSCOPE_COLROW_TO_SPOT_COLROW = ("microscope_colrow_to_spot_colrow",)
     SPOT_COLROW_TO_MICROSCOPE_COLROW = ("spot_colrow_to_microscope_colrow",)
     FILE_FORMAT = "file_format"
+
+    # Cell Segmentation keys
+    CELL_SEG_KEY_HD = "cell_segmentations"
+    NUCLEUS_SEG_KEY_HD = "nucleus_segmentations"

src/spatialdata_io/readers/_utils/_utils.py

@@ -4,6 +4,7 @@
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Union
 
+from anndata import AnnData
 from anndata.io import read_text
 from h5py import File
 from ome_types import from_tiff

src/spatialdata_io/readers/cosmx.py

@@ -289,4 +289,4 @@ def cosmx(
     #             logg.warning(f"FOV `{str(fov)}` does not exist, skipping it.")
     #             continue
 
-    return SpatialData(images=images, labels=labels, points=points, table=table)
+    return SpatialData(images=images, labels=labels, points=points, tables={"table": table})