Support nf-core/mcmicro output in the mcmicro reader

.github/workflows/prepare_test_data.yaml

@@ -66,6 +66,13 @@ jobs:
                   # OMAP10 for format v0.x.x
                   curl -o OMAP10_small.zip "https://zenodo.org/api/records/18196366/files-archive"
 
+                  # -------
+                  # nf-core/mcmicro 2.0.0 `test` profile output (WSI, single sample, mccellpose segmentation).
+                  # Derived from nf-core/test-datasets:mcmicro (lunaphore_example, MIT-licensed; source data
+                  # Wuennemann et al. 2024, syn51471704, CC BY 4.0). Reproduce with:
+                  #   nextflow run nf-core/mcmicro -r 2.0.0 -profile test,docker --outdir out
+                  curl -L -o mcmicro-nfcore-wsi-test.zip "https://github.com/mc2-center/spatialdata-io/releases/download/test-data/mcmicro-nfcore-wsi-test.zip"
+
             - name: Unzip files
               run: |
                   cd ./data

src/spatialdata_io/__main__.py

@@ -252,6 +252,18 @@ def iss_wrapper(
     "--input", "-i", type=click.Path(exists=True), help="Path to the mcmicro project directory.", required=True
 )
 @click.option("--output", "-o", type=click.Path(), help="Path to the output.zarr file.", required=True)
+@click.option(
+    "--pipeline",
+    type=click.Choice(["labsyspharm", "nfcore"]),
+    default=None,
+    help="Which mcmicro pipeline produced the output. [default: auto-detect]",
+)
+@click.option(
+    "--markers-file",
+    type=click.Path(),
+    default=None,
+    help="Path to the markers CSV. [default: auto-detect]",
+)
 @click.option(
     "--imread-kwargs",
     type=str,
@@ -273,6 +285,8 @@ def iss_wrapper(
 def mcmicro_wrapper(
     input: str,
     output: str,
+    pipeline: str | None = None,
+    markers_file: str | None = None,
     imread_kwargs: str = "{}",
     image_models_kwargs: str = "{}",
     labels_models_kwargs: str = "{}",
@@ -282,6 +296,8 @@ def mcmicro_wrapper(
 
     sdata = mcmicro(
         input,
+        pipeline=pipeline,
+        markers_file=markers_file,
         imread_kwargs=_parse_json_param(imread_kwargs, "imread_kwargs"),
         image_models_kwargs=_parse_json_param(image_models_kwargs, "image_models_kwargs"),
         labels_models_kwargs=_parse_json_param(labels_models_kwargs, "labels_models_kwargs"),

src/spatialdata_io/_constants/_constants.py

@@ -275,11 +275,19 @@ class StereoseqKeys(ModeEnum):
     RESOLUTION = "resolution"
 
 
+@unique
+class McmicroPipeline(ModeEnum):
+    """The two mcmicro pipeline flavors whose output layouts the reader understands."""
+
+    LABSYSPHARM = "labsyspharm"  # original labsyspharm/mcmicro Nextflow pipeline
+    NFCORE = "nfcore"  # nf-core/mcmicro pipeline
+
+
 @unique
 class McmicroKeys(ModeEnum):
     """Keys for *Mcmicro* formatted dataset."""
 
-    # files and directories
+    # files and directories (labsyspharm/mcmicro layout)
     QUANTIFICATION_DIR = "quantification"
     MARKERS_FILE = "markers.csv"
     IMAGES_DIR_WSI = "registration"
@@ -292,7 +300,21 @@ class McmicroKeys(ModeEnum):
     COREOGRAPH_CENTROIDS = "qc/coreograph/centroidsY-X.txt"
     COREOGRAPH_TMA_MAP = "qc/coreograph/TMA_MAP.tif"
 
+    # files and directories (nf-core/mcmicro layout)
+    NFCORE_IMAGES_DIR_WSI = "registration/ashlar"
+    NFCORE_IMAGES_DIR_TMA = "tma_dearray"
+    NFCORE_QUANTIFICATION_DIR = "quantification/mcquant"
+    NFCORE_COREOGRAPH_CENTROIDS = "tma_dearray/centroidsY-X.txt"
+    NFCORE_PIPELINE_INFO = "pipeline_info"
+    NFCORE_PARAMS_GLOB = "params*.json"
+    NFCORE_BACKSUB_DIR = "backsub"
+    NFCORE_BACKSUB_MARKERS_GLOB = "*_backsub.csv"
+    NFCORE_MARKERSHEET_GLOBS = "summary/*markersheet*.tsv;prelude/*markersheet*.tsv"
+    NFCORE_TMA_MAP_STEM = "TMA_MAP"
+
     # metadata
+    MARKER_NAME = "marker_name"
+    CHANNEL_NUMBER = "channel_number"
     COORDS_X = "X_centroid"
     COORDS_Y = "Y_centroid"
     INSTANCE_KEY = "CellID"