Merge branch 'main' into fix/macsima_pad_images_of_differing_dimensions

Author: LucaMarconato

.gitignore

@@ -35,6 +35,8 @@ __pycache__/
 _version.py
 node_modules/
 .code-workspace
+.asv/
+uv.lock
 
 # memray report
 *.bin
@@ -43,11 +45,7 @@ node_modules/
 profile.speedscope.json
 
 # test datasets (e.g. Xenium ones)
-# symlinks
-data
 # data folder
 data/
 tests/data
-uv.lock
-.asv/
-.venv/
+.venv

.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: v3.8.1
+      rev: v3.8.3
       hooks:
           - id: prettier
     - repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.15.2
+      rev: v0.15.12
       hooks:
           - id: ruff
             args: [--fix, --exit-non-zero-on-fix, --unsafe-fixes]
           - id: ruff-format
     - repo: https://github.com/pre-commit/mirrors-mypy
-      rev: v1.19.1
+      rev: v1.20.2
       hooks:
           - id: mypy
             additional_dependencies: [numpy, types-PyYAML]

src/spatialdata_io/readers/_utils/_read_10x_h5.py

@@ -2,15 +2,13 @@
 
 import os
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Union
+from typing import TYPE_CHECKING, Any
 
-from anndata import AnnData
+import scanpy as sc
 from anndata.io import read_text
 from h5py import File
 from spatialdata._logging import logger
 
-from spatialdata_io.readers._utils._read_10x_h5 import _read_10x_h5
-
 if TYPE_CHECKING:
     from collections.abc import Mapping
 
@@ -29,7 +27,7 @@ def _read_counts(
 ) -> tuple[AnnData, str]:
     path = Path(path)
     if counts_file.endswith(".h5"):
-        adata: AnnData = _read_10x_h5(path / counts_file, **kwargs)
+        adata: AnnData = sc.read_10x_h5(path / counts_file, **kwargs)
         with File(path / counts_file, mode="r") as f:
             attrs = dict(f.attrs)
             if library_id is None:

src/spatialdata_io/readers/_utils/_utils.py

@@ -105,10 +105,10 @@ def cosmx(
     if not labels_dir.exists():
         raise FileNotFoundError(f"Labels directory not found: {labels_dir}.")
 
-    counts = pd.read_csv(path / counts_file, header=0, index_col=CosmxKeys.INSTANCE_KEY)
+    counts = pd.read_csv(counts_file, header=0, index_col=CosmxKeys.INSTANCE_KEY)
     counts.index = counts.index.astype(str).str.cat(counts.pop(CosmxKeys.FOV).astype(str).values, sep="_")
 
-    obs = pd.read_csv(path / meta_file, header=0, index_col=CosmxKeys.INSTANCE_KEY)
+    obs = pd.read_csv(meta_file, header=0, index_col=CosmxKeys.INSTANCE_KEY)
     obs[CosmxKeys.FOV] = pd.Categorical(obs[CosmxKeys.FOV].astype(str))
     obs[CosmxKeys.REGION_KEY] = pd.Categorical(obs[CosmxKeys.FOV].astype(str).apply(lambda s: s + "_labels"))
     obs[CosmxKeys.INSTANCE_KEY] = obs.index.astype(np.int64)
@@ -254,9 +254,9 @@ def cosmx(
         import pyarrow.parquet as pq
 
         with tempfile.TemporaryDirectory() as tmpdir:
-            print("converting .csv to .parquet to improve the speed of the slicing operations... ", end="")
+            print("converting .csv to .parquet to improve the speed of the slicing operations... ", end="", flush=True)
             assert transcripts_file is not None
-            transcripts_data = pd.read_csv(path / transcripts_file, header=0)
+            transcripts_data = pd.read_csv(transcripts_file, header=0)
             transcripts_data.to_parquet(Path(tmpdir) / "transcripts.parquet")
             print("done")
 

src/spatialdata_io/readers/cosmx.py

@@ -38,7 +38,7 @@
     "B": "bleach",  # v1
     "AntigenCycle": "stain",  # v0
     "S": "stain",  # v1
-    "AF": "autofluorescence",
+    "AF": "autofluorescence",  # v1
 }
 
 
@@ -552,7 +552,7 @@ def _parse_v0_ome_metadata(ome: OME) -> dict[str, Any]:
 
     # Harmonize imagetype across versions
     if metadata["imagetype"]:
-        metadata["imagetype"] = IMAGETYPE_DICT[metadata["imagetype"]]
+        metadata["imagetype"] = IMAGETYPE_DICT.get(metadata["imagetype"], metadata["imagetype"])
 
     return metadata
 
@@ -632,7 +632,7 @@ def _parse_v1_ome_metadata(ome: OME) -> dict[str, Any]:
 
     # Harmonize imagetype across versions
     if metadata["imagetype"]:
-        metadata["imagetype"] = IMAGETYPE_DICT[metadata["imagetype"]]
+        metadata["imagetype"] = IMAGETYPE_DICT.get(metadata["imagetype"], metadata["imagetype"])
 
     return metadata
 

src/spatialdata_io/readers/macsima.py

@@ -50,6 +50,29 @@ def steinbock(
     Returns
     -------
     :class:`spatialdata.SpatialData`
+
+    Notes
+    -----
+    Mandatory outputs of the Steinbock pipeline required by this reader:
+
+    - ``cells.h5ad``: the AnnData object in the main working directory
+    - ``ome/``: directory containing the steinbock OME-TIFF images (``*.ome.tiff``)
+    - ``masks_deepcell/`` or ``masks_ilastik/``: the masks directory, selected via the
+      ``labels_kind`` parameter (only one is used at a time)
+
+    When exporting to AnnData with ``steinbock export anndata``, the ``--info`` option
+    (default: ``images.csv``) controls whether image metadata is embedded. When present,
+    steinbock copies the ``image`` column from ``images.csv`` into ``adata.obs.image`` for
+    every cell; this reader requires that column to map cells to their source image. Without
+    it, ``adata.obs.image`` will not exist and the reader will fail. ``images.csv`` is
+    generated automatically by ``steinbock preprocess imc images`` when starting from
+    ``.mcd`` files. Users who start from TIFF images must hand-craft ``images.csv`` with at
+    least the columns ``image``, ``width_px``, ``height_px``, and ``num_channels`` as
+    described in the
+    `Steinbock file types documentation <https://bodenmillergroup.github.io/steinbock/latest/file-types/>`_.
+
+    All AnnData tables, masks, and OME-TIFFs must follow the steinbock naming conventions so
+    that the reader can correctly match all instances.
     """
     path = Path(path)