Build branch openpipeline_qc/v0.2 with version v0.2.2 to openpipeline_qc on branch v0.2 (9b81d31)

Build pipeline: openpipelines-bio.openpipeline-qc.v0.2.2-vcq67

Source commit: 9b81d310d0

Source message: update version

CHANGELOG.MD

@@ -1,5 +1,21 @@
+# openpipeline_qc 0.2.1
+
+## BUG FIX
+
+* Surface updated CosMx and Visium features.
+
+# openpipeline_qc 0.2.2
+
+## BUG FIX
+
+* `src/ingestion_qc/h5mu_to_qc_json`: Use float32 instead of float16 for CosMx staining metrics to prevent overflow to infinity (PR #17).
+
 # openpipeline_qc 0.2.0
 
+## NEW FEATURES
+
+* Add support for CosMx data in the QC Reporting workflow (PR #12).
+
 ## MINOR CHANGES
 
 * Added support for Visium data ingestion and QC reporting (PR #16).

_viash.yaml

@@ -1,5 +1,5 @@
 viash_version: 0.9.4
-version: v0.2.0
+version: v0.2.2
 source: src
 target: target
 name: openpipeline_qc

inspect_visium.py

@@ -0,0 +1,22 @@
+
+import mudata as mu
+import pandas as pd
+
+def inspect_h5mu(filepath, name):
+    print(f"--- Inspecting {name} ({filepath}) ---")
+    try:
+        mdata = mu.read_h5mu(filepath)
+        rna = mdata.mod['rna']
+        print(f"Obs columns ({len(rna.obs.columns)}):")
+        print(rna.obs.columns.tolist())
+        
+        print(f"\nObs head:")
+        print(rna.obs.head())
+        
+        print(f"\nObsm keys: {list(rna.obsm.keys())}")
+        
+    except Exception as e:
+        print(f"Error reading {filepath}: {e}")
+    print("\n")
+
+inspect_h5mu("resources_test/spatial_qc_sample_data/visium_tiny.qc.h5mu", "Visium")

resources_test_scripts/qc_sample_data.sh

@@ -147,6 +147,14 @@ viash run src/ingestion_qc/h5mu_to_qc_json/config.vsh.yaml --engine docker -- \
   --output "$OUT_DIR_SPATIAL"/xenium_dataset.json \
   --output_reporting_json "$OUT_DIR_SPATIAL"/xenium_report_structure.json
 
+viash run src/ingestion_qc/h5mu_to_qc_json/config.vsh.yaml --engine docker -- \
+  --input "$OUT_DIR_SPATIAL"/Lung5_Rep2_tiny.qc.h5mu \
+  --input "$OUT_DIR_SPATIAL"/Lung5_Rep2_tiny.qc.h5mu \
+  --ingestion_method cosmx \
+  --min_num_nonzero_vars 1 \
+  --output "$OUT_DIR_SPATIAL"/cosmx_dataset.json \
+  --output_reporting_json "$OUT_DIR_SPATIAL"/cosmx_report_structure.json
+
 viash run src/ingestion_qc/h5mu_to_qc_json/config.vsh.yaml --engine docker -- \
   --input "$OUT_DIR_SPATIAL"/visium_tiny.qc.h5mu \
   --input "$OUT_DIR_SPATIAL"/visium_tiny.qc.h5mu \

src/ingestion_qc/h5mu_to_qc_json/config.vsh.yaml

@@ -34,6 +34,7 @@ argument_groups:
         choices:
           - cellranger_multi
           - xenium
+          - cosmx
           - visium
         description: Method that was used to ingest the data - this will define the structure of the report that is generated.
       - name: --obs_sample_id
@@ -133,7 +134,41 @@ argument_groups:
         description: The key in the h5mu .obs field that contains the number of control codewords.
         default: control_codeword_counts  
 
-  # - name: Options for CosMx reports
+  - name: Options for CosMx reports
+    arguments:
+      - name: --obs_area
+        type: string
+        description: The key in the h5mu .obs field that contains the cell area.
+        default: Area
+      - name: --obs_aspect_ratio
+        type: string
+        description: The key in the h5mu .obs field that contains the aspect ratio.
+        default: AspectRatio
+      - name: --obs_dapi_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the DAPI stain intensity.
+        default: [Mean.DAPI, Max.DAPI]
+      - name: --obs_membrane_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the membrane stain intensity.
+        default: [Mean.MembraneStain, Max.MembraneStain]
+      - name: --obs_panck_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the PanCK stain intensity.
+        default: [Mean.PanCK, Max.PanCK]
+      - name: --obs_cd45_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the CD45 stain intensity.
+        default: [Mean.CD45, Max.CD45]
+      - name: --obs_cd3_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the CD3 stain intensity.
+        default: [Mean.CD3, Max.CD3]
 
 resources:
   - type: python_script

src/ingestion_qc/h5mu_to_qc_json/report_structure/cosmx.json

@@ -0,0 +1,211 @@
+{
+  "categories": [
+    {
+      "name": "Sample QC",
+      "key": "sample_summary_stats",
+      "additionalAxes": false,
+      "defaultFilters": []
+    },
+    {
+      "name": "Cell RNA QC",
+      "key": "cell_rna_stats",
+      "additionalAxes": true,
+      "defaultFilters": [
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "total_counts",
+          "label": "Total UMI per cell",
+          "description": "Total number of RNA molecules detected per cell. Low values typically indicate empty droplets or low-quality cells that should be filtered out.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "zoomMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "num_nonzero_vars",
+          "label": "Number of non-zero genes per cell",
+          "description": "Count of unique genes detected in each cell. Low gene counts often indicate poor-quality cells.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "zoomMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "fraction_mitochondrial",
+          "label": "Fraction UMI of mitochondrial genes per cell",
+          "description": "Proportion of cell's RNA from mitochondrial genes.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "fraction_ribosomal",
+          "label": "Fraction UMI of ribosomal genes per cell",
+          "description": "Proportion of cell's RNA from ribosomal protein genes. Extreme values may indicate stress responses or cell cycle abnormalities.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Area",
+          "label": "Cell Area",
+          "description": "Area of the segmented cells.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "AspectRatio",
+          "label": "Aspect Ratio",
+          "description": "Aspect ratio of the segmented cells.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.DAPI",
+          "label": "Mean DAPI Intensity",
+          "description": "Mean intensity of DAPI stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.MembraneStain",
+          "label": "Mean Membrane Stain Intensity",
+          "description": "Mean intensity of Membrane stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.PanCK",
+          "label": "Mean PanCK Intensity",
+          "description": "Mean intensity of PanCK stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.CD45",
+          "label": "Mean CD45 Intensity",
+          "description": "Mean intensity of CD45 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.CD3",
+          "label": "Mean CD3 Intensity",
+          "description": "Mean intensity of CD3 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.DAPI",
+          "label": "Max DAPI Intensity",
+          "description": "Maximum intensity of DAPI stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.MembraneStain",
+          "label": "Max Membrane Stain Intensity",
+          "description": "Maximum intensity of Membrane stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.PanCK",
+          "label": "Max PanCK Intensity",
+          "description": "Maximum intensity of PanCK stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.CD45",
+          "label": "Max CD45 Intensity",
+          "description": "Maximum intensity of CD45 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.CD3",
+          "label": "Max CD3 Intensity",
+          "description": "Maximum intensity of CD3 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        }
+      ]
+    }
+  ]
+}

src/ingestion_qc/h5mu_to_qc_json/script.py

@@ -39,7 +39,14 @@ par = {
     "obs_x_coord": "x_coord",
     "obs_y_coord": "y_coord",
     "obs_control_probe_counts": "control_probe_counts",
-    "obs_control_codeword_counts": "control_codeword_counts"
+    "obs_control_codeword_counts": "control_codeword_counts",
+    "obs_area": "Area",
+    "obs_aspect_ratio": "AspectRatio",
+    "obs_dapi_stain": ["Mean.DAPI", "Max.DAPI"],
+    "obs_membrane_stain": ["Mean.MembraneStain", "Max.MembraneStain"],
+    "obs_panck_stain": ["Mean.PanCK", "Max.PanCK"],
+    "obs_cd45_stain": ["Mean.CD45", "Max.CD45"],
+    "obs_cd3_stain": ["Mean.CD3", "Max.CD3"],
 }
 meta = {
     "resources_dir": os.path.abspath("src/ingestion_qc/h5mu_to_qc_json"),
@@ -56,6 +63,11 @@ from setup_logger import setup_logger
 logger = setup_logger()
 
 par["obs_cellbender"] = {} if not par["obs_cellbender"] else par["obs_cellbender"]
+par["obs_dapi_stain"] = [] if not par["obs_dapi_stain"] else par["obs_dapi_stain"]
+par["obs_membrane_stain"] = [] if not par["obs_membrane_stain"] else par["obs_membrane_stain"]
+par["obs_panck_stain"] = [] if not par["obs_panck_stain"] else par["obs_panck_stain"]
+par["obs_cd45_stain"] = [] if not par["obs_cd45_stain"] else par["obs_cd45_stain"]
+par["obs_cd3_stain"] = [] if not par["obs_cd3_stain"] else par["obs_cd3_stain"]
 
 
 def transform_df(df):
@@ -272,6 +284,60 @@ def generate_visium_stats(mod_obs, sample_id, required_keys):
     return cell_rna_stats
 
 
+def format_cosmx_columns(mod_obs):
+
+    cosmx_obs_keys = [par["obs_area"], par["obs_aspect_ratio"]]
+    
+    # Add multiple keys
+    for key_list in [par["obs_dapi_stain"], par["obs_membrane_stain"], par["obs_panck_stain"],
+                     par["obs_cd45_stain"], par["obs_cd3_stain"]]:
+                     if key_list:
+                         cosmx_obs_keys.extend(key_list)
+                     
+    # Check if keys are present
+    check_optional_obs_keys(mod_obs, cosmx_obs_keys, "CosMx metrics.")
+    
+    # Filter only existing keys
+    cosmx_formatted_columns = [key for key in cosmx_obs_keys if key in mod_obs]
+    
+    # Add coordinates
+    cosmx_formatted_columns.extend(["x_coord", "y_coord"])
+    
+    for key in cosmx_formatted_columns:
+        if key in mod_obs:
+            if not pd.api.types.is_float_dtype(mod_obs[key]):
+                try:
+                    mod_obs[key] = mod_obs[key].astype("float32")
+                except ValueError:
+                    logger.warning(f"Could not convert column {key} to a float dtype.")
+
+    return mod_obs, cosmx_formatted_columns
+
+
+def generate_cosmx_stats(mod_obs, sample_id, required_keys):
+    
+    # Format required columns
+    mod_obs = format_required_columns(required_keys, mod_obs)
+
+    # Format cosmx-specific columns
+    mod_obs, cosmx_formatted_columns = format_cosmx_columns(mod_obs)
+
+    # Fetch and format  all categorical columns for grouping
+    metadata_obs_keys, mod_obs = format_categorical_columns(mod_obs)
+
+    # Create cell RNA stats dataframe
+    cell_rna_stats = pd.DataFrame(
+        {
+            "sample_id": pd.Categorical(sample_id),
+            **{key: mod_obs[key] for key in required_keys},
+            **{key: mod_obs[key] for key in cosmx_formatted_columns},
+            **{key: mod_obs[key] for key in metadata_obs_keys}
+        }
+    )
+
+    return cell_rna_stats
+
+
 def concatenate_dataframes(dfs):
     '''Concatenates a list of dataframes into a single dataframe, preserving categorical columns.'''
     df = pd.concat(dfs, ignore_index=True)
@@ -311,7 +377,7 @@ def main(par):
         barcodes_original_count = mod_obs.shape[0]
 
         # Add coordinates to obs before filtering
-        if par["ingestion_method"] == "xenium" or par["ingestion_method"] == "visium":
+        if par["ingestion_method"] == "xenium" or par["ingestion_method"] == "visium" or par["ingestion_method"] == "cosmx":
             mod_obs["x_coord"] = mod_obsm["spatial"][:, 0]
             mod_obs["y_coord"] = mod_obsm["spatial"][:, 1]
 
@@ -368,6 +434,9 @@ def main(par):
         
         if par["ingestion_method"] == "visium":
             cell_rna_stats = generate_visium_stats(mod_obs, sample_id, required_keys)
+        
+        if par["ingestion_method"] == "cosmx":
+            cell_rna_stats = generate_cosmx_stats(mod_obs, sample_id, required_keys)
 
         cell_stats_dfs.append(cell_rna_stats)
         sample_stats_dfs.append(sample_summary_stats)
@@ -403,7 +472,8 @@ def main(par):
     report_structures = {
         "cellranger_multi": os.path.join(meta["resources_dir"], "report_structure/cellranger.json"),
         "xenium": os.path.join(meta["resources_dir"], "report_structure/xenium.json"),
-        "visium": os.path.join(meta["resources_dir"], "report_structure/visium.json")
+        "visium": os.path.join(meta["resources_dir"], "report_structure/visium.json"),
+        "cosmx": os.path.join(meta["resources_dir"], "report_structure/cosmx.json")
     }
 
     logger.info(f"Writing output report structure json to {par['output_reporting_json']}")

src/ingestion_qc/h5mu_to_qc_json/test.py

@@ -140,5 +140,43 @@ def test_xenium_execution(run_component, tmp_path):
             assert {"name", "dtype", "data"}.issubset(col.keys())
 
 
+def test_cosmx_execution(run_component, tmp_path):
+    output_json_path = tmp_path / "output.json"
+    output_reporting_json_path = tmp_path / "output_reporting.json"
+
+    run_component(
+        [
+            "--input", meta["resources_dir"] + "/resources_test/spatial_qc_sample_data/Lung5_Rep2_tiny.qc.h5mu",
+            "--ingestion_method", "cosmx",
+            "--min_num_nonzero_vars", "1",
+            "--output", output_json_path,
+            "--output_reporting_json", output_reporting_json_path
+        ]
+    )
+
+    assert os.path.exists(output_json_path), "Output file was not created"
+
+    with open(output_json_path, "r") as f:
+        output_json_dict = json.load(f)
+
+    assert output_json_dict.keys() == {"cell_rna_stats", "sample_summary_stats"}
+    assert "metrics_cellranger_stats" not in output_json_dict.keys()
+
+    column_names_cell = [col["name"] for col in output_json_dict["cell_rna_stats"]["columns"]]
+    expected_column_names = [
+        "sample_id", "total_counts", "num_nonzero_vars",
+        "fraction_mitochondrial",  "fraction_ribosomal",
+        "Area", "AspectRatio",
+        "Mean.DAPI", "Mean.MembraneStain",
+        "x_coord", "y_coord", "fov"
+        ]
+    assert np.all([column in column_names_cell for column in expected_column_names])
+
+    for key in output_json_dict.keys():
+        assert output_json_dict[key].keys() == {"num_rows", "num_cols", "min_total_counts", "min_num_nonzero_vars", "columns"}
+        for col in output_json_dict[key]["columns"]:
+            assert {"name", "dtype", "data"}.issubset(col.keys())
+
+
 if __name__ == "__main__":
     sys.exit(pytest.main([__file__]))

src/workflows/generate_qc_report/config.vsh.yaml

@@ -35,6 +35,7 @@ argument_groups:
         choices:
           - cellranger_multi
           - xenium
+          - cosmx
           - visium
       - name: --sample_metadata
         type: file
@@ -103,6 +104,42 @@ argument_groups:
         required: false
         description: Number of epochs to train cellbender. 
         default: 150
+
+  - name: Options for CosMx reports
+    arguments:
+      - name: --obs_area
+        type: string
+        description: The key in the h5mu .obs field that contains the cell area.
+        default: Area
+      - name: --obs_aspect_ratio
+        type: string
+        description: The key in the h5mu .obs field that contains the aspect ratio.
+        default: AspectRatio
+      - name: --obs_dapi_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the DAPI stain intensity.
+        default: [Mean.DAPI, Max.DAPI]
+      - name: --obs_membrane_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the membrane stain intensity.
+        default: [Mean.MembraneStain, Max.MembraneStain]
+      - name: --obs_panck_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the PanCK stain intensity.
+        default: [Mean.PanCK, Max.PanCK]
+      - name: --obs_cd45_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the CD45 stain intensity.
+        default: [Mean.CD45, Max.CD45]
+      - name: --obs_cd3_stain
+        type: string
+        multiple: true
+        description: The keys in the h5mu .obs field that contains the CD3 stain intensity.
+        default: [Mean.CD3, Max.CD3]
   
   - name: Outputs
     arguments:
@@ -137,6 +174,7 @@ test_resources:
     entrypoint: test_xenium
   - type: nextflow_script
     path: test.nf
+    entrypoint: test_cosmx
     entrypoint: test_visium
 
 dependencies:

src/workflows/generate_qc_report/integration_test.sh

@@ -35,10 +35,16 @@ nextflow run . \
   -entry test_multiple_reports \
   -c src/configs/labels_ci.config \
   -resume
-
 nextflow run . \
   -main-script src/workflows/generate_qc_report/test.nf \
   -profile docker,no_publish,local \
   -entry test_visium \
   -c src/configs/labels_ci.config \
   -resume
+
+nextflow run . \
+  -main-script src/workflows/generate_qc_report/test.nf \
+  -profile docker,no_publish,local \
+  -entry test_cosmx \
+  -c src/configs/labels_ci.config \
+  -resume

src/workflows/generate_qc_report/main.nf

@@ -154,7 +154,14 @@ workflow run_wf {
         ingestion_method: "ingestion_method",
         obs_metadata: "obs_metadata",
         min_total_counts: "min_total_counts",
-        min_num_nonzero_vars: "min_num_nonzero_vars"
+        min_num_nonzero_vars: "min_num_nonzero_vars",
+        obs_area: "obs_area",
+        obs_aspect_ratio: "obs_aspect_ratio",
+        obs_dapi_stain: "obs_dapi_stain",
+        obs_membrane_stain: "obs_membrane_stain",
+        obs_panck_stain: "obs_panck_stain",
+        obs_cd45_stain: "obs_cd45_stain",
+        obs_cd3_stain: "obs_cd3_stain",
       ],
       args: [
         obs_sample_id: "sample_id",

src/workflows/generate_qc_report/test.nf

@@ -266,3 +266,48 @@ workflow test_visium {
         "Output: $output"
     }
 }
+
+workflow test_cosmx {
+
+  resources_test_file = file(params.resources_test)
+
+  output_ch = Channel.fromList([
+      [
+        id: "sample_one",
+        input: resources_test_file.resolve("spatial_qc_sample_data/Lung5_Rep2_tiny.qc.h5mu"),
+        run_cellbender: false,
+        ingestion_method: "cosmx",
+        min_num_nonzero_vars: "1",
+        output_html: "report.html",
+        publish_dir: "test_out"
+      ],
+      [
+        id: "sample_two",
+        input: resources_test_file.resolve("spatial_qc_sample_data/Lung5_Rep2_tiny.qc.h5mu"),
+        ingestion_method: "cosmx",
+        min_num_nonzero_vars: "1",
+        run_cellbender: false,
+        output_html: "report.html",
+        publish_dir: "test_out"
+      ]
+    ])
+
+    | map{ state -> [state.id, state] }
+    | generate_qc_report
+
+    | view { output ->
+        assert output.size() == 2 : "Outputs should contain two elements; [id, state]"
+        def id = output[0]
+        def state = output [1]
+        assert id == "combined": "Output ID should be `combined`"
+        assert state instanceof Map : "State should be a map. Found: ${state}"
+        assert state.containsKey("output_qc_report"): "Output should contain key `output_qc_report`"
+        assert state.containsKey("output_processed_h5mu"): "Output should contain key `output_processed_h5mu`"
+        assert state.output_qc_report.size() == 1 : "Expected exactly one output HTML file to be generated"
+        assert state.output_qc_report.every { it.isFile()} : "All output HTML report files should exist"
+        assert state.output_processed_h5mu.isDirectory() : "Output directory should exist"
+        def files = state.output_processed_h5mu.listFiles().findAll { it.isFile() }
+        assert files.size() == 2 : "Output directory should contain exactly 2 files, but found ${files.size()} files"
+        "Output: $output"
+    }
+}

target/_private/executable/ingestion_qc/h5mu_to_qc_json/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "h5mu_to_qc_json"
 namespace: "ingestion_qc"
-version: "v0.2.0"
+version: "v0.2.2"
 authors:
 - name: "Jakub Majercik"
   roles:
@@ -87,6 +87,7 @@ argument_groups:
     choices:
     - "cellranger_multi"
     - "xenium"
+    - "cosmx"
     - "visium"
     direction: "input"
     multiple: false
@@ -293,6 +294,84 @@ argument_groups:
     direction: "input"
     multiple: false
     multiple_sep: ";"
+- name: "Options for CosMx reports"
+  arguments:
+  - type: "string"
+    name: "--obs_area"
+    description: "The key in the h5mu .obs field that contains the cell area."
+    info: null
+    default:
+    - "Area"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_aspect_ratio"
+    description: "The key in the h5mu .obs field that contains the aspect ratio."
+    info: null
+    default:
+    - "AspectRatio"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_dapi_stain"
+    description: "The keys in the h5mu .obs field that contains the DAPI stain intensity."
+    info: null
+    default:
+    - "Mean.DAPI"
+    - "Max.DAPI"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_membrane_stain"
+    description: "The keys in the h5mu .obs field that contains the membrane stain\
+      \ intensity."
+    info: null
+    default:
+    - "Mean.MembraneStain"
+    - "Max.MembraneStain"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_panck_stain"
+    description: "The keys in the h5mu .obs field that contains the PanCK stain intensity."
+    info: null
+    default:
+    - "Mean.PanCK"
+    - "Max.PanCK"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_cd45_stain"
+    description: "The keys in the h5mu .obs field that contains the CD45 stain intensity."
+    info: null
+    default:
+    - "Mean.CD45"
+    - "Max.CD45"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_cd3_stain"
+    description: "The keys in the h5mu .obs field that contains the CD3 stain intensity."
+    info: null
+    default:
+    - "Mean.CD3"
+    - "Max.CD3"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
 resources:
 - type: "python_script"
   path: "script.py"
@@ -409,7 +488,7 @@ engines:
   id: "docker"
   image: "python:3.12-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v0.2.0"
+  target_tag: "v0.2.2"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -448,11 +527,11 @@ build_info:
   output: "target/_private/executable/ingestion_qc/h5mu_to_qc_json"
   executable: "target/_private/executable/ingestion_qc/h5mu_to_qc_json/h5mu_to_qc_json"
   viash_version: "0.9.4"
-  git_commit: "a4ab5f509f731422ffc79b739a89b9d11fb4e440"
+  git_commit: "9b81d310d031b120755e39001cc40f8ec51bc7c2"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_qc"
 package_config:
   name: "openpipeline_qc"
-  version: "v0.2.0"
+  version: "v0.2.2"
   info:
     test_resources:
     - type: "s3"
@@ -477,7 +556,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+  - ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
   organization: "vsh"
   links:
     repository: "https://github.com/openpipelines-bio/openpipeline_qc"

target/_private/executable/ingestion_qc/h5mu_to_qc_json/h5mu_to_qc_json

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-# h5mu_to_qc_json v0.2.0
+# h5mu_to_qc_json v0.2.2
 # 
 # This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
 # work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
@@ -461,10 +461,10 @@ RUN pip install --upgrade pip && \
 
 LABEL org.opencontainers.image.authors="Jakub Majercik, Dorien Roosen, Robrecht Cannoodt, Weiwei Schultz"
 LABEL org.opencontainers.image.description="Companion container for running component ingestion_qc h5mu_to_qc_json"
-LABEL org.opencontainers.image.created="2026-02-02T16:26:04Z"
+LABEL org.opencontainers.image.created="2026-02-03T16:37:26Z"
 LABEL org.opencontainers.image.source="https://github.com/openpipelines-bio/openpipeline_qc"
-LABEL org.opencontainers.image.revision="a4ab5f509f731422ffc79b739a89b9d11fb4e440"
-LABEL org.opencontainers.image.version="v0.2.0"
+LABEL org.opencontainers.image.revision="9b81d310d031b120755e39001cc40f8ec51bc7c2"
+LABEL org.opencontainers.image.version="v0.2.2"
 
 VIASHDOCKER
   fi
@@ -581,7 +581,7 @@ VIASH_DOCKER_RUN_ARGS=(-i --rm)
 
 # ViashHelp: Display helpful explanation about this executable
 function ViashHelp {
-  echo "h5mu_to_qc_json v0.2.0"
+  echo "h5mu_to_qc_json v0.2.2"
   echo ""
   echo "Takes H5MU files that have been ingested by CellRanger, Xenium or CosMx and"
   echo "processed by the QC workflow, and generates:"
@@ -601,7 +601,7 @@ function ViashHelp {
   echo ""
   echo "    --ingestion_method"
   echo "        type: string, required parameter"
-  echo "        choices: [ cellranger_multi, xenium, visium ]"
+  echo "        choices: [ cellranger_multi, xenium, cosmx, visium ]"
   echo "        Method that was used to ingest the data - this will define the structure"
   echo "        of the report that is generated."
   echo ""
@@ -705,6 +705,43 @@ function ViashHelp {
   echo "        The key in the h5mu .obs field that contains the number of control"
   echo "        codewords."
   echo ""
+  echo "Options for CosMx reports:"
+  echo "    --obs_area"
+  echo "        type: string"
+  echo "        default: Area"
+  echo "        The key in the h5mu .obs field that contains the cell area."
+  echo ""
+  echo "    --obs_aspect_ratio"
+  echo "        type: string"
+  echo "        default: AspectRatio"
+  echo "        The key in the h5mu .obs field that contains the aspect ratio."
+  echo ""
+  echo "    --obs_dapi_stain"
+  echo "        type: string, multiple values allowed"
+  echo "        default: Mean.DAPI;Max.DAPI"
+  echo "        The keys in the h5mu .obs field that contains the DAPI stain intensity."
+  echo ""
+  echo "    --obs_membrane_stain"
+  echo "        type: string, multiple values allowed"
+  echo "        default: Mean.MembraneStain;Max.MembraneStain"
+  echo "        The keys in the h5mu .obs field that contains the membrane stain"
+  echo "        intensity."
+  echo ""
+  echo "    --obs_panck_stain"
+  echo "        type: string, multiple values allowed"
+  echo "        default: Mean.PanCK;Max.PanCK"
+  echo "        The keys in the h5mu .obs field that contains the PanCK stain intensity."
+  echo ""
+  echo "    --obs_cd45_stain"
+  echo "        type: string, multiple values allowed"
+  echo "        default: Mean.CD45;Max.CD45"
+  echo "        The keys in the h5mu .obs field that contains the CD45 stain intensity."
+  echo ""
+  echo "    --obs_cd3_stain"
+  echo "        type: string, multiple values allowed"
+  echo "        default: Mean.CD3;Max.CD3"
+  echo "        The keys in the h5mu .obs field that contains the CD3 stain intensity."
+  echo ""
   echo "Viash built in Computational Requirements:"
   echo "    ---cpus=INT"
   echo "        Number of CPUs to use"
@@ -752,7 +789,7 @@ while [[ $# -gt 0 ]]; do
             shift 1
             ;;
         --version)
-            echo "h5mu_to_qc_json v0.2.0"
+            echo "h5mu_to_qc_json v0.2.2"
             exit
             ;;
         --input)
@@ -1004,6 +1041,113 @@ while [[ $# -gt 0 ]]; do
             VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS=$(ViashRemoveFlags "$1")
             shift 1
             ;;
+        --obs_area)
+            [ -n "$VIASH_PAR_OBS_AREA" ] && ViashError Bad arguments for option \'--obs_area\': \'$VIASH_PAR_OBS_AREA\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
+            VIASH_PAR_OBS_AREA="$2"
+            [ $# -lt 2 ] && ViashError Not enough arguments passed to --obs_area. Use "--help" to get more information on the parameters. && exit 1
+            shift 2
+            ;;
+        --obs_area=*)
+            [ -n "$VIASH_PAR_OBS_AREA" ] && ViashError Bad arguments for option \'--obs_area=*\': \'$VIASH_PAR_OBS_AREA\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
+            VIASH_PAR_OBS_AREA=$(ViashRemoveFlags "$1")
+            shift 1
+            ;;
+        --obs_aspect_ratio)
+            [ -n "$VIASH_PAR_OBS_ASPECT_RATIO" ] && ViashError Bad arguments for option \'--obs_aspect_ratio\': \'$VIASH_PAR_OBS_ASPECT_RATIO\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
+            VIASH_PAR_OBS_ASPECT_RATIO="$2"
+            [ $# -lt 2 ] && ViashError Not enough arguments passed to --obs_aspect_ratio. Use "--help" to get more information on the parameters. && exit 1
+            shift 2
+            ;;
+        --obs_aspect_ratio=*)
+            [ -n "$VIASH_PAR_OBS_ASPECT_RATIO" ] && ViashError Bad arguments for option \'--obs_aspect_ratio=*\': \'$VIASH_PAR_OBS_ASPECT_RATIO\' \& \'$2\' - you should provide exactly one argument for this option. && exit 1
+            VIASH_PAR_OBS_ASPECT_RATIO=$(ViashRemoveFlags "$1")
+            shift 1
+            ;;
+        --obs_dapi_stain)
+            if [ -z "$VIASH_PAR_OBS_DAPI_STAIN" ]; then
+              VIASH_PAR_OBS_DAPI_STAIN="$2"
+            else
+              VIASH_PAR_OBS_DAPI_STAIN="$VIASH_PAR_OBS_DAPI_STAIN;""$2"
+            fi
+            [ $# -lt 2 ] && ViashError Not enough arguments passed to --obs_dapi_stain. Use "--help" to get more information on the parameters. && exit 1
+            shift 2
+            ;;
+        --obs_dapi_stain=*)
+            if [ -z "$VIASH_PAR_OBS_DAPI_STAIN" ]; then
+              VIASH_PAR_OBS_DAPI_STAIN=$(ViashRemoveFlags "$1")
+            else
+              VIASH_PAR_OBS_DAPI_STAIN="$VIASH_PAR_OBS_DAPI_STAIN;"$(ViashRemoveFlags "$1")
+            fi
+            shift 1
+            ;;
+        --obs_membrane_stain)
+            if [ -z "$VIASH_PAR_OBS_MEMBRANE_STAIN" ]; then
+              VIASH_PAR_OBS_MEMBRANE_STAIN="$2"
+            else
+              VIASH_PAR_OBS_MEMBRANE_STAIN="$VIASH_PAR_OBS_MEMBRANE_STAIN;""$2"
+            fi
+            [ $# -lt 2 ] && ViashError Not enough arguments passed to --obs_membrane_stain. Use "--help" to get more information on the parameters. && exit 1
+            shift 2
+            ;;
+        --obs_membrane_stain=*)
+            if [ -z "$VIASH_PAR_OBS_MEMBRANE_STAIN" ]; then
+              VIASH_PAR_OBS_MEMBRANE_STAIN=$(ViashRemoveFlags "$1")
+            else
+              VIASH_PAR_OBS_MEMBRANE_STAIN="$VIASH_PAR_OBS_MEMBRANE_STAIN;"$(ViashRemoveFlags "$1")
+            fi
+            shift 1
+            ;;
+        --obs_panck_stain)
+            if [ -z "$VIASH_PAR_OBS_PANCK_STAIN" ]; then
+              VIASH_PAR_OBS_PANCK_STAIN="$2"
+            else
+              VIASH_PAR_OBS_PANCK_STAIN="$VIASH_PAR_OBS_PANCK_STAIN;""$2"
+            fi
+            [ $# -lt 2 ] && ViashError Not enough arguments passed to --obs_panck_stain. Use "--help" to get more information on the parameters. && exit 1
+            shift 2
+            ;;
+        --obs_panck_stain=*)
+            if [ -z "$VIASH_PAR_OBS_PANCK_STAIN" ]; then
+              VIASH_PAR_OBS_PANCK_STAIN=$(ViashRemoveFlags "$1")
+            else
+              VIASH_PAR_OBS_PANCK_STAIN="$VIASH_PAR_OBS_PANCK_STAIN;"$(ViashRemoveFlags "$1")
+            fi
+            shift 1
+            ;;
+        --obs_cd45_stain)
+            if [ -z "$VIASH_PAR_OBS_CD45_STAIN" ]; then
+              VIASH_PAR_OBS_CD45_STAIN="$2"
+            else
+              VIASH_PAR_OBS_CD45_STAIN="$VIASH_PAR_OBS_CD45_STAIN;""$2"
+            fi
+            [ $# -lt 2 ] && ViashError Not enough arguments passed to --obs_cd45_stain. Use "--help" to get more information on the parameters. && exit 1
+            shift 2
+            ;;
+        --obs_cd45_stain=*)
+            if [ -z "$VIASH_PAR_OBS_CD45_STAIN" ]; then
+              VIASH_PAR_OBS_CD45_STAIN=$(ViashRemoveFlags "$1")
+            else
+              VIASH_PAR_OBS_CD45_STAIN="$VIASH_PAR_OBS_CD45_STAIN;"$(ViashRemoveFlags "$1")
+            fi
+            shift 1
+            ;;
+        --obs_cd3_stain)
+            if [ -z "$VIASH_PAR_OBS_CD3_STAIN" ]; then
+              VIASH_PAR_OBS_CD3_STAIN="$2"
+            else
+              VIASH_PAR_OBS_CD3_STAIN="$VIASH_PAR_OBS_CD3_STAIN;""$2"
+            fi
+            [ $# -lt 2 ] && ViashError Not enough arguments passed to --obs_cd3_stain. Use "--help" to get more information on the parameters. && exit 1
+            shift 2
+            ;;
+        --obs_cd3_stain=*)
+            if [ -z "$VIASH_PAR_OBS_CD3_STAIN" ]; then
+              VIASH_PAR_OBS_CD3_STAIN=$(ViashRemoveFlags "$1")
+            else
+              VIASH_PAR_OBS_CD3_STAIN="$VIASH_PAR_OBS_CD3_STAIN;"$(ViashRemoveFlags "$1")
+            fi
+            shift 1
+            ;;
         ---engine)
             VIASH_ENGINE_ID="$2"
             shift 2
@@ -1092,7 +1236,7 @@ if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then
 
   # determine docker image id
   if [[ "$VIASH_ENGINE_ID" == 'docker' ]]; then
-    VIASH_DOCKER_IMAGE_ID='images.viash-hub.com/vsh/openpipeline_qc/ingestion_qc/h5mu_to_qc_json:v0.2.0'
+    VIASH_DOCKER_IMAGE_ID='images.viash-hub.com/vsh/openpipeline_qc/ingestion_qc/h5mu_to_qc_json:v0.2.2'
   fi
 
   # print dockerfile
@@ -1266,6 +1410,27 @@ fi
 if [ -z ${VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS+x} ]; then
   VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS="control_codeword_counts"
 fi
+if [ -z ${VIASH_PAR_OBS_AREA+x} ]; then
+  VIASH_PAR_OBS_AREA="Area"
+fi
+if [ -z ${VIASH_PAR_OBS_ASPECT_RATIO+x} ]; then
+  VIASH_PAR_OBS_ASPECT_RATIO="AspectRatio"
+fi
+if [ -z ${VIASH_PAR_OBS_DAPI_STAIN+x} ]; then
+  VIASH_PAR_OBS_DAPI_STAIN="Mean.DAPI;Max.DAPI"
+fi
+if [ -z ${VIASH_PAR_OBS_MEMBRANE_STAIN+x} ]; then
+  VIASH_PAR_OBS_MEMBRANE_STAIN="Mean.MembraneStain;Max.MembraneStain"
+fi
+if [ -z ${VIASH_PAR_OBS_PANCK_STAIN+x} ]; then
+  VIASH_PAR_OBS_PANCK_STAIN="Mean.PanCK;Max.PanCK"
+fi
+if [ -z ${VIASH_PAR_OBS_CD45_STAIN+x} ]; then
+  VIASH_PAR_OBS_CD45_STAIN="Mean.CD45;Max.CD45"
+fi
+if [ -z ${VIASH_PAR_OBS_CD3_STAIN+x} ]; then
+  VIASH_PAR_OBS_CD3_STAIN="Mean.CD3;Max.CD3"
+fi
 
 # check whether required files exist
 if [ ! -z "$VIASH_PAR_INPUT" ]; then
@@ -1369,7 +1534,7 @@ fi
 
 # check whether value is belongs to a set of choices
 if [ ! -z "$VIASH_PAR_INGESTION_METHOD" ]; then
-  VIASH_PAR_INGESTION_METHOD_CHOICES=("cellranger_multi;xenium;visium")
+  VIASH_PAR_INGESTION_METHOD_CHOICES=("cellranger_multi;xenium;cosmx;visium")
   IFS=';'
   set -f
   if ! [[ ";${VIASH_PAR_INGESTION_METHOD_CHOICES[*]};" =~ ";$VIASH_PAR_INGESTION_METHOD;" ]]; then
@@ -1520,7 +1685,14 @@ par = {
   'obs_x_coord': $( if [ ! -z ${VIASH_PAR_OBS_X_COORD+x} ]; then echo "r'${VIASH_PAR_OBS_X_COORD//\'/\'\"\'\"r\'}'"; else echo None; fi ),
   'obs_y_coord': $( if [ ! -z ${VIASH_PAR_OBS_Y_COORD+x} ]; then echo "r'${VIASH_PAR_OBS_Y_COORD//\'/\'\"\'\"r\'}'"; else echo None; fi ),
   'obs_control_probe_counts': $( if [ ! -z ${VIASH_PAR_OBS_CONTROL_PROBE_COUNTS+x} ]; then echo "r'${VIASH_PAR_OBS_CONTROL_PROBE_COUNTS//\'/\'\"\'\"r\'}'"; else echo None; fi ),
-  'obs_control_codeword_counts': $( if [ ! -z ${VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS+x} ]; then echo "r'${VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS//\'/\'\"\'\"r\'}'"; else echo None; fi )
+  'obs_control_codeword_counts': $( if [ ! -z ${VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS+x} ]; then echo "r'${VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS//\'/\'\"\'\"r\'}'"; else echo None; fi ),
+  'obs_area': $( if [ ! -z ${VIASH_PAR_OBS_AREA+x} ]; then echo "r'${VIASH_PAR_OBS_AREA//\'/\'\"\'\"r\'}'"; else echo None; fi ),
+  'obs_aspect_ratio': $( if [ ! -z ${VIASH_PAR_OBS_ASPECT_RATIO+x} ]; then echo "r'${VIASH_PAR_OBS_ASPECT_RATIO//\'/\'\"\'\"r\'}'"; else echo None; fi ),
+  'obs_dapi_stain': $( if [ ! -z ${VIASH_PAR_OBS_DAPI_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_DAPI_STAIN//\'/\'\"\'\"r\'}'.split(';')"; else echo None; fi ),
+  'obs_membrane_stain': $( if [ ! -z ${VIASH_PAR_OBS_MEMBRANE_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_MEMBRANE_STAIN//\'/\'\"\'\"r\'}'.split(';')"; else echo None; fi ),
+  'obs_panck_stain': $( if [ ! -z ${VIASH_PAR_OBS_PANCK_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_PANCK_STAIN//\'/\'\"\'\"r\'}'.split(';')"; else echo None; fi ),
+  'obs_cd45_stain': $( if [ ! -z ${VIASH_PAR_OBS_CD45_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_CD45_STAIN//\'/\'\"\'\"r\'}'.split(';')"; else echo None; fi ),
+  'obs_cd3_stain': $( if [ ! -z ${VIASH_PAR_OBS_CD3_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_CD3_STAIN//\'/\'\"\'\"r\'}'.split(';')"; else echo None; fi )
 }
 meta = {
   'name': $( if [ ! -z ${VIASH_META_NAME+x} ]; then echo "r'${VIASH_META_NAME//\'/\'\"\'\"r\'}'"; else echo None; fi ),
@@ -1554,6 +1726,11 @@ from setup_logger import setup_logger
 logger = setup_logger()
 
 par["obs_cellbender"] = {} if not par["obs_cellbender"] else par["obs_cellbender"]
+par["obs_dapi_stain"] = [] if not par["obs_dapi_stain"] else par["obs_dapi_stain"]
+par["obs_membrane_stain"] = [] if not par["obs_membrane_stain"] else par["obs_membrane_stain"]
+par["obs_panck_stain"] = [] if not par["obs_panck_stain"] else par["obs_panck_stain"]
+par["obs_cd45_stain"] = [] if not par["obs_cd45_stain"] else par["obs_cd45_stain"]
+par["obs_cd3_stain"] = [] if not par["obs_cd3_stain"] else par["obs_cd3_stain"]
 
 
 def transform_df(df):
@@ -1770,6 +1947,60 @@ def generate_visium_stats(mod_obs, sample_id, required_keys):
     return cell_rna_stats
 
 
+def format_cosmx_columns(mod_obs):
+
+    cosmx_obs_keys = [par["obs_area"], par["obs_aspect_ratio"]]
+    
+    # Add multiple keys
+    for key_list in [par["obs_dapi_stain"], par["obs_membrane_stain"], par["obs_panck_stain"],
+                     par["obs_cd45_stain"], par["obs_cd3_stain"]]:
+                     if key_list:
+                         cosmx_obs_keys.extend(key_list)
+                     
+    # Check if keys are present
+    check_optional_obs_keys(mod_obs, cosmx_obs_keys, "CosMx metrics.")
+    
+    # Filter only existing keys
+    cosmx_formatted_columns = [key for key in cosmx_obs_keys if key in mod_obs]
+    
+    # Add coordinates
+    cosmx_formatted_columns.extend(["x_coord", "y_coord"])
+    
+    for key in cosmx_formatted_columns:
+        if key in mod_obs:
+            if not pd.api.types.is_float_dtype(mod_obs[key]):
+                try:
+                    mod_obs[key] = mod_obs[key].astype("float32")
+                except ValueError:
+                    logger.warning(f"Could not convert column {key} to a float dtype.")
+
+    return mod_obs, cosmx_formatted_columns
+
+
+def generate_cosmx_stats(mod_obs, sample_id, required_keys):
+    
+    # Format required columns
+    mod_obs = format_required_columns(required_keys, mod_obs)
+
+    # Format cosmx-specific columns
+    mod_obs, cosmx_formatted_columns = format_cosmx_columns(mod_obs)
+
+    # Fetch and format  all categorical columns for grouping
+    metadata_obs_keys, mod_obs = format_categorical_columns(mod_obs)
+
+    # Create cell RNA stats dataframe
+    cell_rna_stats = pd.DataFrame(
+        {
+            "sample_id": pd.Categorical(sample_id),
+            **{key: mod_obs[key] for key in required_keys},
+            **{key: mod_obs[key] for key in cosmx_formatted_columns},
+            **{key: mod_obs[key] for key in metadata_obs_keys}
+        }
+    )
+
+    return cell_rna_stats
+
+
 def concatenate_dataframes(dfs):
     '''Concatenates a list of dataframes into a single dataframe, preserving categorical columns.'''
     df = pd.concat(dfs, ignore_index=True)
@@ -1809,7 +2040,7 @@ def main(par):
         barcodes_original_count = mod_obs.shape[0]
 
         # Add coordinates to obs before filtering
-        if par["ingestion_method"] == "xenium" or par["ingestion_method"] == "visium":
+        if par["ingestion_method"] == "xenium" or par["ingestion_method"] == "visium" or par["ingestion_method"] == "cosmx":
             mod_obs["x_coord"] = mod_obsm["spatial"][:, 0]
             mod_obs["y_coord"] = mod_obsm["spatial"][:, 1]
 
@@ -1866,6 +2097,9 @@ def main(par):
         
         if par["ingestion_method"] == "visium":
             cell_rna_stats = generate_visium_stats(mod_obs, sample_id, required_keys)
+        
+        if par["ingestion_method"] == "cosmx":
+            cell_rna_stats = generate_cosmx_stats(mod_obs, sample_id, required_keys)
 
         cell_stats_dfs.append(cell_rna_stats)
         sample_stats_dfs.append(sample_summary_stats)
@@ -1901,7 +2135,8 @@ def main(par):
     report_structures = {
         "cellranger_multi": os.path.join(meta["resources_dir"], "report_structure/cellranger.json"),
         "xenium": os.path.join(meta["resources_dir"], "report_structure/xenium.json"),
-        "visium": os.path.join(meta["resources_dir"], "report_structure/visium.json")
+        "visium": os.path.join(meta["resources_dir"], "report_structure/visium.json"),
+        "cosmx": os.path.join(meta["resources_dir"], "report_structure/cosmx.json")
     }
 
     logger.info(f"Writing output report structure json to {par['output_reporting_json']}")

target/_private/executable/ingestion_qc/h5mu_to_qc_json/report_structure/cosmx.json

@@ -0,0 +1,211 @@
+{
+  "categories": [
+    {
+      "name": "Sample QC",
+      "key": "sample_summary_stats",
+      "additionalAxes": false,
+      "defaultFilters": []
+    },
+    {
+      "name": "Cell RNA QC",
+      "key": "cell_rna_stats",
+      "additionalAxes": true,
+      "defaultFilters": [
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "total_counts",
+          "label": "Total UMI per cell",
+          "description": "Total number of RNA molecules detected per cell. Low values typically indicate empty droplets or low-quality cells that should be filtered out.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "zoomMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "num_nonzero_vars",
+          "label": "Number of non-zero genes per cell",
+          "description": "Count of unique genes detected in each cell. Low gene counts often indicate poor-quality cells.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "zoomMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "fraction_mitochondrial",
+          "label": "Fraction UMI of mitochondrial genes per cell",
+          "description": "Proportion of cell's RNA from mitochondrial genes.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "fraction_ribosomal",
+          "label": "Fraction UMI of ribosomal genes per cell",
+          "description": "Proportion of cell's RNA from ribosomal protein genes. Extreme values may indicate stress responses or cell cycle abnormalities.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Area",
+          "label": "Cell Area",
+          "description": "Area of the segmented cells.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "AspectRatio",
+          "label": "Aspect Ratio",
+          "description": "Aspect ratio of the segmented cells.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.DAPI",
+          "label": "Mean DAPI Intensity",
+          "description": "Mean intensity of DAPI stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.MembraneStain",
+          "label": "Mean Membrane Stain Intensity",
+          "description": "Mean intensity of Membrane stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.PanCK",
+          "label": "Mean PanCK Intensity",
+          "description": "Mean intensity of PanCK stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.CD45",
+          "label": "Mean CD45 Intensity",
+          "description": "Mean intensity of CD45 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.CD3",
+          "label": "Mean CD3 Intensity",
+          "description": "Mean intensity of CD3 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.DAPI",
+          "label": "Max DAPI Intensity",
+          "description": "Maximum intensity of DAPI stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.MembraneStain",
+          "label": "Max Membrane Stain Intensity",
+          "description": "Maximum intensity of Membrane stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.PanCK",
+          "label": "Max PanCK Intensity",
+          "description": "Maximum intensity of PanCK stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.CD45",
+          "label": "Max CD45 Intensity",
+          "description": "Maximum intensity of CD45 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.CD3",
+          "label": "Max CD3 Intensity",
+          "description": "Maximum intensity of CD3 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        }
+      ]
+    }
+  ]
+}

target/_private/nextflow/ingestion_qc/h5mu_to_qc_json/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "h5mu_to_qc_json"
 namespace: "ingestion_qc"
-version: "v0.2.0"
+version: "v0.2.2"
 authors:
 - name: "Jakub Majercik"
   roles:
@@ -87,6 +87,7 @@ argument_groups:
     choices:
     - "cellranger_multi"
     - "xenium"
+    - "cosmx"
     - "visium"
     direction: "input"
     multiple: false
@@ -293,6 +294,84 @@ argument_groups:
     direction: "input"
     multiple: false
     multiple_sep: ";"
+- name: "Options for CosMx reports"
+  arguments:
+  - type: "string"
+    name: "--obs_area"
+    description: "The key in the h5mu .obs field that contains the cell area."
+    info: null
+    default:
+    - "Area"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_aspect_ratio"
+    description: "The key in the h5mu .obs field that contains the aspect ratio."
+    info: null
+    default:
+    - "AspectRatio"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_dapi_stain"
+    description: "The keys in the h5mu .obs field that contains the DAPI stain intensity."
+    info: null
+    default:
+    - "Mean.DAPI"
+    - "Max.DAPI"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_membrane_stain"
+    description: "The keys in the h5mu .obs field that contains the membrane stain\
+      \ intensity."
+    info: null
+    default:
+    - "Mean.MembraneStain"
+    - "Max.MembraneStain"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_panck_stain"
+    description: "The keys in the h5mu .obs field that contains the PanCK stain intensity."
+    info: null
+    default:
+    - "Mean.PanCK"
+    - "Max.PanCK"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_cd45_stain"
+    description: "The keys in the h5mu .obs field that contains the CD45 stain intensity."
+    info: null
+    default:
+    - "Mean.CD45"
+    - "Max.CD45"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_cd3_stain"
+    description: "The keys in the h5mu .obs field that contains the CD3 stain intensity."
+    info: null
+    default:
+    - "Mean.CD3"
+    - "Max.CD3"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
 resources:
 - type: "python_script"
   path: "script.py"
@@ -409,7 +488,7 @@ engines:
   id: "docker"
   image: "python:3.12-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v0.2.0"
+  target_tag: "v0.2.2"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -448,11 +527,11 @@ build_info:
   output: "target/_private/nextflow/ingestion_qc/h5mu_to_qc_json"
   executable: "target/_private/nextflow/ingestion_qc/h5mu_to_qc_json/main.nf"
   viash_version: "0.9.4"
-  git_commit: "a4ab5f509f731422ffc79b739a89b9d11fb4e440"
+  git_commit: "9b81d310d031b120755e39001cc40f8ec51bc7c2"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_qc"
 package_config:
   name: "openpipeline_qc"
-  version: "v0.2.0"
+  version: "v0.2.2"
   info:
     test_resources:
     - type: "s3"
@@ -477,7 +556,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+  - ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
   organization: "vsh"
   links:
     repository: "https://github.com/openpipelines-bio/openpipeline_qc"

target/_private/nextflow/ingestion_qc/h5mu_to_qc_json/main.nf

@@ -1,4 +1,4 @@
-// h5mu_to_qc_json v0.2.0
+// h5mu_to_qc_json v0.2.2
 // 
 // This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
@@ -3038,7 +3038,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "h5mu_to_qc_json",
   "namespace" : "ingestion_qc",
-  "version" : "v0.2.0",
+  "version" : "v0.2.2",
   "authors" : [
     {
       "name" : "Jakub Majercik",
@@ -3163,6 +3163,7 @@ meta = [
           "choices" : [
             "cellranger_multi",
             "xenium",
+            "cosmx",
             "visium"
           ],
           "direction" : "input",
@@ -3413,6 +3414,100 @@ meta = [
           "multiple_sep" : ";"
         }
       ]
+    },
+    {
+      "name" : "Options for CosMx reports",
+      "arguments" : [
+        {
+          "type" : "string",
+          "name" : "--obs_area",
+          "description" : "The key in the h5mu .obs field that contains the cell area.",
+          "default" : [
+            "Area"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_aspect_ratio",
+          "description" : "The key in the h5mu .obs field that contains the aspect ratio.",
+          "default" : [
+            "AspectRatio"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_dapi_stain",
+          "description" : "The keys in the h5mu .obs field that contains the DAPI stain intensity.",
+          "default" : [
+            "Mean.DAPI",
+            "Max.DAPI"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_membrane_stain",
+          "description" : "The keys in the h5mu .obs field that contains the membrane stain intensity.",
+          "default" : [
+            "Mean.MembraneStain",
+            "Max.MembraneStain"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_panck_stain",
+          "description" : "The keys in the h5mu .obs field that contains the PanCK stain intensity.",
+          "default" : [
+            "Mean.PanCK",
+            "Max.PanCK"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_cd45_stain",
+          "description" : "The keys in the h5mu .obs field that contains the CD45 stain intensity.",
+          "default" : [
+            "Mean.CD45",
+            "Max.CD45"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_cd3_stain",
+          "description" : "The keys in the h5mu .obs field that contains the CD3 stain intensity.",
+          "default" : [
+            "Mean.CD3",
+            "Max.CD3"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        }
+      ]
     }
   ],
   "resources" : [
@@ -3562,7 +3657,7 @@ meta = [
       "id" : "docker",
       "image" : "python:3.12-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v0.2.0",
+      "target_tag" : "v0.2.2",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3617,12 +3712,12 @@ meta = [
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/_private/nextflow/ingestion_qc/h5mu_to_qc_json",
     "viash_version" : "0.9.4",
-    "git_commit" : "a4ab5f509f731422ffc79b739a89b9d11fb4e440",
+    "git_commit" : "9b81d310d031b120755e39001cc40f8ec51bc7c2",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline_qc"
   },
   "package_config" : {
     "name" : "openpipeline_qc",
-    "version" : "v0.2.0",
+    "version" : "v0.2.2",
     "info" : {
       "test_resources" : [
         {
@@ -3653,7 +3748,7 @@ meta = [
       ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].directives.tag := '$id'\n.resources += {path: '/src/configs/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+      ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
     ],
     "organization" : "vsh",
     "links" : {
@@ -3705,7 +3800,14 @@ par = {
   'obs_x_coord': $( if [ ! -z ${VIASH_PAR_OBS_X_COORD+x} ]; then echo "r'${VIASH_PAR_OBS_X_COORD//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'obs_y_coord': $( if [ ! -z ${VIASH_PAR_OBS_Y_COORD+x} ]; then echo "r'${VIASH_PAR_OBS_Y_COORD//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
   'obs_control_probe_counts': $( if [ ! -z ${VIASH_PAR_OBS_CONTROL_PROBE_COUNTS+x} ]; then echo "r'${VIASH_PAR_OBS_CONTROL_PROBE_COUNTS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
-  'obs_control_codeword_counts': $( if [ ! -z ${VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS+x} ]; then echo "r'${VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi )
+  'obs_control_codeword_counts': $( if [ ! -z ${VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS+x} ]; then echo "r'${VIASH_PAR_OBS_CONTROL_CODEWORD_COUNTS//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
+  'obs_area': $( if [ ! -z ${VIASH_PAR_OBS_AREA+x} ]; then echo "r'${VIASH_PAR_OBS_AREA//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
+  'obs_aspect_ratio': $( if [ ! -z ${VIASH_PAR_OBS_ASPECT_RATIO+x} ]; then echo "r'${VIASH_PAR_OBS_ASPECT_RATIO//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
+  'obs_dapi_stain': $( if [ ! -z ${VIASH_PAR_OBS_DAPI_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_DAPI_STAIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ),
+  'obs_membrane_stain': $( if [ ! -z ${VIASH_PAR_OBS_MEMBRANE_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_MEMBRANE_STAIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ),
+  'obs_panck_stain': $( if [ ! -z ${VIASH_PAR_OBS_PANCK_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_PANCK_STAIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ),
+  'obs_cd45_stain': $( if [ ! -z ${VIASH_PAR_OBS_CD45_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_CD45_STAIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi ),
+  'obs_cd3_stain': $( if [ ! -z ${VIASH_PAR_OBS_CD3_STAIN+x} ]; then echo "r'${VIASH_PAR_OBS_CD3_STAIN//\\'/\\'\\"\\'\\"r\\'}'.split(';')"; else echo None; fi )
 }
 meta = {
   'name': $( if [ ! -z ${VIASH_META_NAME+x} ]; then echo "r'${VIASH_META_NAME//\\'/\\'\\"\\'\\"r\\'}'"; else echo None; fi ),
@@ -3739,6 +3841,11 @@ from setup_logger import setup_logger
 logger = setup_logger()
 
 par["obs_cellbender"] = {} if not par["obs_cellbender"] else par["obs_cellbender"]
+par["obs_dapi_stain"] = [] if not par["obs_dapi_stain"] else par["obs_dapi_stain"]
+par["obs_membrane_stain"] = [] if not par["obs_membrane_stain"] else par["obs_membrane_stain"]
+par["obs_panck_stain"] = [] if not par["obs_panck_stain"] else par["obs_panck_stain"]
+par["obs_cd45_stain"] = [] if not par["obs_cd45_stain"] else par["obs_cd45_stain"]
+par["obs_cd3_stain"] = [] if not par["obs_cd3_stain"] else par["obs_cd3_stain"]
 
 
 def transform_df(df):
@@ -3955,6 +4062,60 @@ def generate_visium_stats(mod_obs, sample_id, required_keys):
     return cell_rna_stats
 
 
+def format_cosmx_columns(mod_obs):
+
+    cosmx_obs_keys = [par["obs_area"], par["obs_aspect_ratio"]]
+    
+    # Add multiple keys
+    for key_list in [par["obs_dapi_stain"], par["obs_membrane_stain"], par["obs_panck_stain"],
+                     par["obs_cd45_stain"], par["obs_cd3_stain"]]:
+                     if key_list:
+                         cosmx_obs_keys.extend(key_list)
+                     
+    # Check if keys are present
+    check_optional_obs_keys(mod_obs, cosmx_obs_keys, "CosMx metrics.")
+    
+    # Filter only existing keys
+    cosmx_formatted_columns = [key for key in cosmx_obs_keys if key in mod_obs]
+    
+    # Add coordinates
+    cosmx_formatted_columns.extend(["x_coord", "y_coord"])
+    
+    for key in cosmx_formatted_columns:
+        if key in mod_obs:
+            if not pd.api.types.is_float_dtype(mod_obs[key]):
+                try:
+                    mod_obs[key] = mod_obs[key].astype("float32")
+                except ValueError:
+                    logger.warning(f"Could not convert column {key} to a float dtype.")
+
+    return mod_obs, cosmx_formatted_columns
+
+
+def generate_cosmx_stats(mod_obs, sample_id, required_keys):
+    
+    # Format required columns
+    mod_obs = format_required_columns(required_keys, mod_obs)
+
+    # Format cosmx-specific columns
+    mod_obs, cosmx_formatted_columns = format_cosmx_columns(mod_obs)
+
+    # Fetch and format  all categorical columns for grouping
+    metadata_obs_keys, mod_obs = format_categorical_columns(mod_obs)
+
+    # Create cell RNA stats dataframe
+    cell_rna_stats = pd.DataFrame(
+        {
+            "sample_id": pd.Categorical(sample_id),
+            **{key: mod_obs[key] for key in required_keys},
+            **{key: mod_obs[key] for key in cosmx_formatted_columns},
+            **{key: mod_obs[key] for key in metadata_obs_keys}
+        }
+    )
+
+    return cell_rna_stats
+
+
 def concatenate_dataframes(dfs):
     \'\'\'Concatenates a list of dataframes into a single dataframe, preserving categorical columns.\'\'\'
     df = pd.concat(dfs, ignore_index=True)
@@ -3994,7 +4155,7 @@ def main(par):
         barcodes_original_count = mod_obs.shape[0]
 
         # Add coordinates to obs before filtering
-        if par["ingestion_method"] == "xenium" or par["ingestion_method"] == "visium":
+        if par["ingestion_method"] == "xenium" or par["ingestion_method"] == "visium" or par["ingestion_method"] == "cosmx":
             mod_obs["x_coord"] = mod_obsm["spatial"][:, 0]
             mod_obs["y_coord"] = mod_obsm["spatial"][:, 1]
 
@@ -4051,6 +4212,9 @@ def main(par):
         
         if par["ingestion_method"] == "visium":
             cell_rna_stats = generate_visium_stats(mod_obs, sample_id, required_keys)
+        
+        if par["ingestion_method"] == "cosmx":
+            cell_rna_stats = generate_cosmx_stats(mod_obs, sample_id, required_keys)
 
         cell_stats_dfs.append(cell_rna_stats)
         sample_stats_dfs.append(sample_summary_stats)
@@ -4086,7 +4250,8 @@ def main(par):
     report_structures = {
         "cellranger_multi": os.path.join(meta["resources_dir"], "report_structure/cellranger.json"),
         "xenium": os.path.join(meta["resources_dir"], "report_structure/xenium.json"),
-        "visium": os.path.join(meta["resources_dir"], "report_structure/visium.json")
+        "visium": os.path.join(meta["resources_dir"], "report_structure/visium.json"),
+        "cosmx": os.path.join(meta["resources_dir"], "report_structure/cosmx.json")
     }
 
     logger.info(f"Writing output report structure json to {par['output_reporting_json']}")
@@ -4477,7 +4642,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline_qc/ingestion_qc/h5mu_to_qc_json",
-    "tag" : "v0.2.0"
+    "tag" : "v0.2.2"
   },
   "label" : [
     "midmem",

target/_private/nextflow/ingestion_qc/h5mu_to_qc_json/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'ingestion_qc/h5mu_to_qc_json'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v0.2.0'
+  version = 'v0.2.2'
   description = 'Takes H5MU files that have been ingested by CellRanger, Xenium or CosMx and processed by the QC workflow, and generates:\n- A JSON file that contains the combined data for the QC report\n- A JSON file that defines the layout and structure of the QC report\n'
   author = 'Jakub Majercik, Dorien Roosen, Robrecht Cannoodt, Weiwei Schultz'
 }

target/_private/nextflow/ingestion_qc/h5mu_to_qc_json/report_structure/cosmx.json

@@ -0,0 +1,211 @@
+{
+  "categories": [
+    {
+      "name": "Sample QC",
+      "key": "sample_summary_stats",
+      "additionalAxes": false,
+      "defaultFilters": []
+    },
+    {
+      "name": "Cell RNA QC",
+      "key": "cell_rna_stats",
+      "additionalAxes": true,
+      "defaultFilters": [
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "total_counts",
+          "label": "Total UMI per cell",
+          "description": "Total number of RNA molecules detected per cell. Low values typically indicate empty droplets or low-quality cells that should be filtered out.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "zoomMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "num_nonzero_vars",
+          "label": "Number of non-zero genes per cell",
+          "description": "Count of unique genes detected in each cell. Low gene counts often indicate poor-quality cells.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "zoomMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "fraction_mitochondrial",
+          "label": "Fraction UMI of mitochondrial genes per cell",
+          "description": "Proportion of cell's RNA from mitochondrial genes.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "fraction_ribosomal",
+          "label": "Fraction UMI of ribosomal genes per cell",
+          "description": "Proportion of cell's RNA from ribosomal protein genes. Extreme values may indicate stress responses or cell cycle abnormalities.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Area",
+          "label": "Cell Area",
+          "description": "Area of the segmented cells.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "AspectRatio",
+          "label": "Aspect Ratio",
+          "description": "Aspect ratio of the segmented cells.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.DAPI",
+          "label": "Mean DAPI Intensity",
+          "description": "Mean intensity of DAPI stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.MembraneStain",
+          "label": "Mean Membrane Stain Intensity",
+          "description": "Mean intensity of Membrane stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.PanCK",
+          "label": "Mean PanCK Intensity",
+          "description": "Mean intensity of PanCK stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.CD45",
+          "label": "Mean CD45 Intensity",
+          "description": "Mean intensity of CD45 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Mean.CD3",
+          "label": "Mean CD3 Intensity",
+          "description": "Mean intensity of CD3 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.DAPI",
+          "label": "Max DAPI Intensity",
+          "description": "Maximum intensity of DAPI stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.MembraneStain",
+          "label": "Max Membrane Stain Intensity",
+          "description": "Maximum intensity of Membrane stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.PanCK",
+          "label": "Max PanCK Intensity",
+          "description": "Maximum intensity of PanCK stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.CD45",
+          "label": "Max CD45 Intensity",
+          "description": "Maximum intensity of CD45 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        },
+        {
+          "type": "histogram",
+          "visualizationType": "histogram",
+          "field": "Max.CD3",
+          "label": "Max CD3 Intensity",
+          "description": "Maximum intensity of CD3 stain.",
+          "cutoffMin": null,
+          "cutoffMax": null,
+          "nBins": 50,
+          "groupBy": "sample_id",
+          "yAxisType": "linear"
+        }
+      ]
+    }
+  ]
+}

target/executable/ingestion_qc/detect_ingestion_method/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "detect_ingestion_method"
 namespace: "ingestion_qc"
-version: "v0.2.0"
+version: "v0.2.2"
 authors:
 - name: "Dorien Roosen"
   roles:
@@ -190,7 +190,7 @@ engines:
   id: "docker"
   image: "python:3.12-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v0.2.0"
+  target_tag: "v0.2.2"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -229,11 +229,11 @@ build_info:
   output: "target/executable/ingestion_qc/detect_ingestion_method"
   executable: "target/executable/ingestion_qc/detect_ingestion_method/detect_ingestion_method"
   viash_version: "0.9.4"
-  git_commit: "a4ab5f509f731422ffc79b739a89b9d11fb4e440"
+  git_commit: "9b81d310d031b120755e39001cc40f8ec51bc7c2"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_qc"
 package_config:
   name: "openpipeline_qc"
-  version: "v0.2.0"
+  version: "v0.2.2"
   info:
     test_resources:
     - type: "s3"
@@ -258,7 +258,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+  - ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
   organization: "vsh"
   links:
     repository: "https://github.com/openpipelines-bio/openpipeline_qc"

target/executable/ingestion_qc/detect_ingestion_method/detect_ingestion_method

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-# detect_ingestion_method v0.2.0
+# detect_ingestion_method v0.2.2
 # 
 # This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
 # work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
@@ -459,10 +459,10 @@ RUN pip install --upgrade pip && \
 
 LABEL org.opencontainers.image.authors="Dorien Roosen, Weiwei Schultz"
 LABEL org.opencontainers.image.description="Companion container for running component ingestion_qc detect_ingestion_method"
-LABEL org.opencontainers.image.created="2026-02-02T16:26:05Z"
+LABEL org.opencontainers.image.created="2026-02-03T16:37:27Z"
 LABEL org.opencontainers.image.source="https://github.com/openpipelines-bio/openpipeline_qc"
-LABEL org.opencontainers.image.revision="a4ab5f509f731422ffc79b739a89b9d11fb4e440"
-LABEL org.opencontainers.image.version="v0.2.0"
+LABEL org.opencontainers.image.revision="9b81d310d031b120755e39001cc40f8ec51bc7c2"
+LABEL org.opencontainers.image.version="v0.2.2"
 
 VIASHDOCKER
   fi
@@ -579,7 +579,7 @@ VIASH_DOCKER_RUN_ARGS=(-i --rm)
 
 # ViashHelp: Display helpful explanation about this executable
 function ViashHelp {
-  echo "detect_ingestion_method v0.2.0"
+  echo "detect_ingestion_method v0.2.2"
   echo ""
   echo "Detects the ingestion method of a dataset."
   echo "Currently detects either 10X CellRanger Multi, 10X Xenium or Nanostring CosMx,"
@@ -656,7 +656,7 @@ while [[ $# -gt 0 ]]; do
             shift 1
             ;;
         --version)
-            echo "detect_ingestion_method v0.2.0"
+            echo "detect_ingestion_method v0.2.2"
             exit
             ;;
         --input)
@@ -791,7 +791,7 @@ if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then
 
   # determine docker image id
   if [[ "$VIASH_ENGINE_ID" == 'docker' ]]; then
-    VIASH_DOCKER_IMAGE_ID='images.viash-hub.com/vsh/openpipeline_qc/ingestion_qc/detect_ingestion_method:v0.2.0'
+    VIASH_DOCKER_IMAGE_ID='images.viash-hub.com/vsh/openpipeline_qc/ingestion_qc/detect_ingestion_method:v0.2.2'
   fi
 
   # print dockerfile

target/executable/ingestion_qc/generate_html/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "generate_html"
 namespace: "ingestion_qc"
-version: "v0.2.0"
+version: "v0.2.2"
 authors:
 - name: "Jakub Majercik"
   roles:
@@ -209,7 +209,7 @@ engines:
   id: "docker"
   image: "node:latest"
   target_registry: "images.viash-hub.com"
-  target_tag: "v0.2.0"
+  target_tag: "v0.2.2"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -231,11 +231,11 @@ build_info:
   output: "target/executable/ingestion_qc/generate_html"
   executable: "target/executable/ingestion_qc/generate_html/generate_html"
   viash_version: "0.9.4"
-  git_commit: "a4ab5f509f731422ffc79b739a89b9d11fb4e440"
+  git_commit: "9b81d310d031b120755e39001cc40f8ec51bc7c2"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_qc"
 package_config:
   name: "openpipeline_qc"
-  version: "v0.2.0"
+  version: "v0.2.2"
   info:
     test_resources:
     - type: "s3"
@@ -260,7 +260,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+  - ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
   organization: "vsh"
   links:
     repository: "https://github.com/openpipelines-bio/openpipeline_qc"

target/executable/ingestion_qc/generate_html/generate_html

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-# generate_html v0.2.0
+# generate_html v0.2.2
 # 
 # This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
 # work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
@@ -461,10 +461,10 @@ RUN cd /opt && git clone -b v0.2.1 https://github.com/openpipelines-bio/siqc.git
 
 LABEL org.opencontainers.image.authors="Jakub Majercik, Dorien Roosen, Robrecht Cannoodt, Weiwei Schultz"
 LABEL org.opencontainers.image.description="Companion container for running component ingestion_qc generate_html"
-LABEL org.opencontainers.image.created="2026-02-02T16:26:04Z"
+LABEL org.opencontainers.image.created="2026-02-03T16:37:27Z"
 LABEL org.opencontainers.image.source="https://github.com/openpipelines-bio/openpipeline_qc"
-LABEL org.opencontainers.image.revision="a4ab5f509f731422ffc79b739a89b9d11fb4e440"
-LABEL org.opencontainers.image.version="v0.2.0"
+LABEL org.opencontainers.image.revision="9b81d310d031b120755e39001cc40f8ec51bc7c2"
+LABEL org.opencontainers.image.version="v0.2.2"
 
 VIASHDOCKER
   fi
@@ -581,7 +581,7 @@ VIASH_DOCKER_RUN_ARGS=(-i --rm)
 
 # ViashHelp: Display helpful explanation about this executable
 function ViashHelp {
-  echo "generate_html v0.2.0"
+  echo "generate_html v0.2.2"
   echo ""
   echo "Generate an HTML report from the QC metrics"
   echo ""
@@ -649,7 +649,7 @@ while [[ $# -gt 0 ]]; do
             shift 1
             ;;
         --version)
-            echo "generate_html v0.2.0"
+            echo "generate_html v0.2.2"
             exit
             ;;
         --input_data)
@@ -773,7 +773,7 @@ if [[ "$VIASH_ENGINE_TYPE" == "docker" ]]; then
 
   # determine docker image id
   if [[ "$VIASH_ENGINE_ID" == 'docker' ]]; then
-    VIASH_DOCKER_IMAGE_ID='images.viash-hub.com/vsh/openpipeline_qc/ingestion_qc/generate_html:v0.2.0'
+    VIASH_DOCKER_IMAGE_ID='images.viash-hub.com/vsh/openpipeline_qc/ingestion_qc/generate_html:v0.2.2'
   fi
 
   # print dockerfile

target/nextflow/ingestion_qc/detect_ingestion_method/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "detect_ingestion_method"
 namespace: "ingestion_qc"
-version: "v0.2.0"
+version: "v0.2.2"
 authors:
 - name: "Dorien Roosen"
   roles:
@@ -190,7 +190,7 @@ engines:
   id: "docker"
   image: "python:3.12-slim"
   target_registry: "images.viash-hub.com"
-  target_tag: "v0.2.0"
+  target_tag: "v0.2.2"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -229,11 +229,11 @@ build_info:
   output: "target/nextflow/ingestion_qc/detect_ingestion_method"
   executable: "target/nextflow/ingestion_qc/detect_ingestion_method/main.nf"
   viash_version: "0.9.4"
-  git_commit: "a4ab5f509f731422ffc79b739a89b9d11fb4e440"
+  git_commit: "9b81d310d031b120755e39001cc40f8ec51bc7c2"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_qc"
 package_config:
   name: "openpipeline_qc"
-  version: "v0.2.0"
+  version: "v0.2.2"
   info:
     test_resources:
     - type: "s3"
@@ -258,7 +258,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+  - ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
   organization: "vsh"
   links:
     repository: "https://github.com/openpipelines-bio/openpipeline_qc"

target/nextflow/ingestion_qc/detect_ingestion_method/main.nf

@@ -1,4 +1,4 @@
-// detect_ingestion_method v0.2.0
+// detect_ingestion_method v0.2.2
 // 
 // This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
@@ -3036,7 +3036,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "detect_ingestion_method",
   "namespace" : "ingestion_qc",
-  "version" : "v0.2.0",
+  "version" : "v0.2.2",
   "authors" : [
     {
       "name" : "Dorien Roosen",
@@ -3290,7 +3290,7 @@ meta = [
       "id" : "docker",
       "image" : "python:3.12-slim",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v0.2.0",
+      "target_tag" : "v0.2.2",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3345,12 +3345,12 @@ meta = [
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/ingestion_qc/detect_ingestion_method",
     "viash_version" : "0.9.4",
-    "git_commit" : "a4ab5f509f731422ffc79b739a89b9d11fb4e440",
+    "git_commit" : "9b81d310d031b120755e39001cc40f8ec51bc7c2",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline_qc"
   },
   "package_config" : {
     "name" : "openpipeline_qc",
-    "version" : "v0.2.0",
+    "version" : "v0.2.2",
     "info" : {
       "test_resources" : [
         {
@@ -3381,7 +3381,7 @@ meta = [
       ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].directives.tag := '$id'\n.resources += {path: '/src/configs/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+      ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
     ],
     "organization" : "vsh",
     "links" : {
@@ -3872,7 +3872,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline_qc/ingestion_qc/detect_ingestion_method",
-    "tag" : "v0.2.0"
+    "tag" : "v0.2.2"
   },
   "label" : [
     "lowmem",

target/nextflow/ingestion_qc/detect_ingestion_method/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'ingestion_qc/detect_ingestion_method'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v0.2.0'
+  version = 'v0.2.2'
   description = 'Detects the ingestion method of a dataset.\nCurrently detects either 10X CellRanger Multi, 10X Xenium or Nanostring CosMx, but can be extended to other technologies upon request.\n'
   author = 'Dorien Roosen, Weiwei Schultz'
 }

target/nextflow/ingestion_qc/generate_html/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "generate_html"
 namespace: "ingestion_qc"
-version: "v0.2.0"
+version: "v0.2.2"
 authors:
 - name: "Jakub Majercik"
   roles:
@@ -209,7 +209,7 @@ engines:
   id: "docker"
   image: "node:latest"
   target_registry: "images.viash-hub.com"
-  target_tag: "v0.2.0"
+  target_tag: "v0.2.2"
   namespace_separator: "/"
   setup:
   - type: "apt"
@@ -231,11 +231,11 @@ build_info:
   output: "target/nextflow/ingestion_qc/generate_html"
   executable: "target/nextflow/ingestion_qc/generate_html/main.nf"
   viash_version: "0.9.4"
-  git_commit: "a4ab5f509f731422ffc79b739a89b9d11fb4e440"
+  git_commit: "9b81d310d031b120755e39001cc40f8ec51bc7c2"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_qc"
 package_config:
   name: "openpipeline_qc"
-  version: "v0.2.0"
+  version: "v0.2.2"
   info:
     test_resources:
     - type: "s3"
@@ -260,7 +260,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+  - ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
   organization: "vsh"
   links:
     repository: "https://github.com/openpipelines-bio/openpipeline_qc"

target/nextflow/ingestion_qc/generate_html/main.nf

@@ -1,4 +1,4 @@
-// generate_html v0.2.0
+// generate_html v0.2.2
 // 
 // This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
@@ -3038,7 +3038,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "generate_html",
   "namespace" : "ingestion_qc",
-  "version" : "v0.2.0",
+  "version" : "v0.2.2",
   "authors" : [
     {
       "name" : "Jakub Majercik",
@@ -3330,7 +3330,7 @@ meta = [
       "id" : "docker",
       "image" : "node:latest",
       "target_registry" : "images.viash-hub.com",
-      "target_tag" : "v0.2.0",
+      "target_tag" : "v0.2.2",
       "namespace_separator" : "/",
       "setup" : [
         {
@@ -3359,12 +3359,12 @@ meta = [
     "engine" : "docker|native",
     "output" : "/workdir/root/repo/target/nextflow/ingestion_qc/generate_html",
     "viash_version" : "0.9.4",
-    "git_commit" : "a4ab5f509f731422ffc79b739a89b9d11fb4e440",
+    "git_commit" : "9b81d310d031b120755e39001cc40f8ec51bc7c2",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline_qc"
   },
   "package_config" : {
     "name" : "openpipeline_qc",
-    "version" : "v0.2.0",
+    "version" : "v0.2.2",
     "info" : {
       "test_resources" : [
         {
@@ -3395,7 +3395,7 @@ meta = [
       ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].directives.tag := '$id'\n.resources += {path: '/src/configs/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+      ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
     ],
     "organization" : "vsh",
     "links" : {
@@ -3830,7 +3830,7 @@ meta["defaults"] = [
   "container" : {
     "registry" : "images.viash-hub.com",
     "image" : "vsh/openpipeline_qc/ingestion_qc/generate_html",
-    "tag" : "v0.2.0"
+    "tag" : "v0.2.2"
   },
   "label" : [
     "lowmem",

target/nextflow/ingestion_qc/generate_html/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'ingestion_qc/generate_html'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v0.2.0'
+  version = 'v0.2.2'
   description = 'Generate an HTML report from the QC metrics'
   author = 'Jakub Majercik, Dorien Roosen, Robrecht Cannoodt, Weiwei Schultz'
 }

target/nextflow/workflows/generate_qc_report/.config.vsh.yaml

@@ -1,6 +1,6 @@
 name: "generate_qc_report"
 namespace: "workflows"
-version: "v0.2.0"
+version: "v0.2.2"
 authors:
 - name: "Jakub Majercik"
   roles:
@@ -86,6 +86,7 @@ argument_groups:
     choices:
     - "cellranger_multi"
     - "xenium"
+    - "cosmx"
     - "visium"
     direction: "input"
     multiple: false
@@ -212,6 +213,84 @@ argument_groups:
     direction: "input"
     multiple: false
     multiple_sep: ";"
+- name: "Options for CosMx reports"
+  arguments:
+  - type: "string"
+    name: "--obs_area"
+    description: "The key in the h5mu .obs field that contains the cell area."
+    info: null
+    default:
+    - "Area"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_aspect_ratio"
+    description: "The key in the h5mu .obs field that contains the aspect ratio."
+    info: null
+    default:
+    - "AspectRatio"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_dapi_stain"
+    description: "The keys in the h5mu .obs field that contains the DAPI stain intensity."
+    info: null
+    default:
+    - "Mean.DAPI"
+    - "Max.DAPI"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_membrane_stain"
+    description: "The keys in the h5mu .obs field that contains the membrane stain\
+      \ intensity."
+    info: null
+    default:
+    - "Mean.MembraneStain"
+    - "Max.MembraneStain"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_panck_stain"
+    description: "The keys in the h5mu .obs field that contains the PanCK stain intensity."
+    info: null
+    default:
+    - "Mean.PanCK"
+    - "Max.PanCK"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_cd45_stain"
+    description: "The keys in the h5mu .obs field that contains the CD45 stain intensity."
+    info: null
+    default:
+    - "Mean.CD45"
+    - "Max.CD45"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+  - type: "string"
+    name: "--obs_cd3_stain"
+    description: "The keys in the h5mu .obs field that contains the CD3 stain intensity."
+    info: null
+    default:
+    - "Mean.CD3"
+    - "Max.CD3"
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
 - name: "Outputs"
   arguments:
   - type: "file"
@@ -386,7 +465,7 @@ build_info:
   output: "target/nextflow/workflows/generate_qc_report"
   executable: "target/nextflow/workflows/generate_qc_report/main.nf"
   viash_version: "0.9.4"
-  git_commit: "a4ab5f509f731422ffc79b739a89b9d11fb4e440"
+  git_commit: "9b81d310d031b120755e39001cc40f8ec51bc7c2"
   git_remote: "https://github.com/openpipelines-bio/openpipeline_qc"
   dependencies:
   - "target/dependencies/vsh/vsh/openpipeline/v4.0.0/nextflow/metadata/add_id"
@@ -397,7 +476,7 @@ build_info:
   - "target/dependencies/vsh/vsh/craftbox/v0.2.0/nextflow/move_files_to_directory"
 package_config:
   name: "openpipeline_qc"
-  version: "v0.2.0"
+  version: "v0.2.2"
   info:
     test_resources:
     - type: "s3"
@@ -422,7 +501,7 @@ package_config:
     )'"
   - ".engines += { type: \"native\" }"
   - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
-  - ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+  - ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
   organization: "vsh"
   links:
     repository: "https://github.com/openpipelines-bio/openpipeline_qc"

target/nextflow/workflows/generate_qc_report/main.nf

@@ -1,4 +1,4 @@
-// generate_qc_report v0.2.0
+// generate_qc_report v0.2.2
 // 
 // This wrapper script is auto-generated by viash 0.9.4 and is thus a derivative
 // work thereof. This software comes with ABSOLUTELY NO WARRANTY from Data
@@ -3038,7 +3038,7 @@ meta = [
   "config": processConfig(readJsonBlob('''{
   "name" : "generate_qc_report",
   "namespace" : "workflows",
-  "version" : "v0.2.0",
+  "version" : "v0.2.2",
   "authors" : [
     {
       "name" : "Jakub Majercik",
@@ -3162,6 +3162,7 @@ meta = [
           "choices" : [
             "cellranger_multi",
             "xenium",
+            "cosmx",
             "visium"
           ],
           "direction" : "input",
@@ -3314,6 +3315,100 @@ meta = [
         }
       ]
     },
+    {
+      "name" : "Options for CosMx reports",
+      "arguments" : [
+        {
+          "type" : "string",
+          "name" : "--obs_area",
+          "description" : "The key in the h5mu .obs field that contains the cell area.",
+          "default" : [
+            "Area"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_aspect_ratio",
+          "description" : "The key in the h5mu .obs field that contains the aspect ratio.",
+          "default" : [
+            "AspectRatio"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : false,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_dapi_stain",
+          "description" : "The keys in the h5mu .obs field that contains the DAPI stain intensity.",
+          "default" : [
+            "Mean.DAPI",
+            "Max.DAPI"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_membrane_stain",
+          "description" : "The keys in the h5mu .obs field that contains the membrane stain intensity.",
+          "default" : [
+            "Mean.MembraneStain",
+            "Max.MembraneStain"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_panck_stain",
+          "description" : "The keys in the h5mu .obs field that contains the PanCK stain intensity.",
+          "default" : [
+            "Mean.PanCK",
+            "Max.PanCK"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_cd45_stain",
+          "description" : "The keys in the h5mu .obs field that contains the CD45 stain intensity.",
+          "default" : [
+            "Mean.CD45",
+            "Max.CD45"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        },
+        {
+          "type" : "string",
+          "name" : "--obs_cd3_stain",
+          "description" : "The keys in the h5mu .obs field that contains the CD3 stain intensity.",
+          "default" : [
+            "Mean.CD3",
+            "Max.CD3"
+          ],
+          "required" : false,
+          "direction" : "input",
+          "multiple" : true,
+          "multiple_sep" : ";"
+        }
+      ]
+    },
     {
       "name" : "Outputs",
       "arguments" : [
@@ -3547,12 +3642,12 @@ meta = [
     "engine" : "native",
     "output" : "/workdir/root/repo/target/nextflow/workflows/generate_qc_report",
     "viash_version" : "0.9.4",
-    "git_commit" : "a4ab5f509f731422ffc79b739a89b9d11fb4e440",
+    "git_commit" : "9b81d310d031b120755e39001cc40f8ec51bc7c2",
     "git_remote" : "https://github.com/openpipelines-bio/openpipeline_qc"
   },
   "package_config" : {
     "name" : "openpipeline_qc",
-    "version" : "v0.2.0",
+    "version" : "v0.2.2",
     "info" : {
       "test_resources" : [
         {
@@ -3583,7 +3678,7 @@ meta = [
       ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].directives.tag := '$id'\n.resources += {path: '/src/configs/labels.config', dest: 'nextflow_labels.config'}\n.runners[.type == 'nextflow'].config.script := 'includeConfig(\\"nextflow_labels.config\\")'",
       ".engines += { type: \\"native\\" }",
       ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'",
-      ".engines[.type == 'docker'].target_tag := 'v0.2.0'"
+      ".engines[.type == 'docker'].target_tag := 'v0.2.2'"
     ],
     "organization" : "vsh",
     "links" : {
@@ -3762,7 +3857,14 @@ workflow run_wf {
         ingestion_method: "ingestion_method",
         obs_metadata: "obs_metadata",
         min_total_counts: "min_total_counts",
-        min_num_nonzero_vars: "min_num_nonzero_vars"
+        min_num_nonzero_vars: "min_num_nonzero_vars",
+        obs_area: "obs_area",
+        obs_aspect_ratio: "obs_aspect_ratio",
+        obs_dapi_stain: "obs_dapi_stain",
+        obs_membrane_stain: "obs_membrane_stain",
+        obs_panck_stain: "obs_panck_stain",
+        obs_cd45_stain: "obs_cd45_stain",
+        obs_cd3_stain: "obs_cd3_stain",
       ],
       args: [
         obs_sample_id: "sample_id",

target/nextflow/workflows/generate_qc_report/nextflow.config

@@ -2,7 +2,7 @@ manifest {
   name = 'workflows/generate_qc_report'
   mainScript = 'main.nf'
   nextflowVersion = '!>=20.12.1-edge'
-  version = 'v0.2.0'
+  version = 'v0.2.2'
   description = 'Run the ingestion QC report generation'
   author = 'Jakub Majercik, Dorien Roosen, Robrecht Cannoodt, Weiwei Schultz'
 }

target/nextflow/workflows/generate_qc_report/nextflow_schema.json

@@ -1,175 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "title": "generate_qc_report",
-  "description": "Run the ingestion QC report generation",
-  "type": "object",
-  "$defs": {
-    "inputs": {
-      "title": "Inputs",
-      "type": "object",
-      "description": "No description",
-      "properties": {
-        "id": {
-          "type": "string",
-          "description": "The sample IDs to include in the report",
-          "help_text": "Type: `string`, multiple: `False`, example: `\"sample1\"`. "
-        },
-        "input": {
-          "type": "string",
-          "format": "path",
-          "exists": true,
-          "description": "The input h5mu files.",
-          "help_text": "Type: `file`, multiple: `False`, required, direction: `input`, example: `\"path/to/file1.h5mu\"`. "
-        },
-        "ingestion_method": {
-          "type": "string",
-          "description": "",
-          "help_text": "Type: `string`, multiple: `False`, required, choices: ``cellranger_multi`, `xenium`, `visium``. ",
-          "enum": [
-            "cellranger_multi",
-            "xenium",
-            "visium"
-          ]
-        },
-        "sample_metadata": {
-          "type": "string",
-          "format": "path",
-          "description": "The sample metadata file corresponding to .obs fields in the h5mu input files, to be used for grouping in the report.\n",
-          "help_text": "Type: `file`, multiple: `False`, direction: `input`, example: `\"path/to/file.csv\"`. "
-        },
-        "max_samples_per_report": {
-          "type": "integer",
-          "description": "The maximum number of samples to be included per report",
-          "help_text": "Type: `integer`, multiple: `False`, default: `20`. ",
-          "default": 20
-        }
-      }
-    },
-    "outputs": {
-      "title": "Outputs",
-      "type": "object",
-      "description": "No description",
-      "properties": {
-        "output_qc_report": {
-          "type": "array",
-          "items": {
-            "type": "string"
-          },
-          "format": "path",
-          "description": "The output HTML report",
-          "help_text": "Type: `file`, multiple: `True`, required, default: `\"$id.$key.output_qc_report_*.html\"`, direction: `output`, example: `[\"path/to/file.html\"]`. ",
-          "default": "$id.$key.output_qc_report_*.html"
-        },
-        "output_processed_h5mu": {
-          "type": "string",
-          "format": "path",
-          "description": "Folder containing the processed h5mu files.",
-          "help_text": "Type: `file`, multiple: `False`, required, default: `\"qc_h5mu\"`, direction: `output`. ",
-          "default": "qc_h5mu"
-        }
-      }
-    },
-    "options": {
-      "title": "Options",
-      "type": "object",
-      "description": "No description",
-      "properties": {
-        "var_gene_names": {
-          "type": "string",
-          "description": "The column name in the .var h5mu files that contains the gene names",
-          "help_text": "Type: `string`, multiple: `False`, example: `\"gene_symbol\"`. "
-        },
-        "obs_metadata": {
-          "type": "array",
-          "items": {
-            "type": "string"
-          },
-          "description": "The metadata keys in the h5mu .obs to include in the report.",
-          "help_text": "Type: `string`, multiple: `True`, example: `[\"donor_id\";\"cell_type\";\"batch\";\"condition\"]`. "
-        }
-      }
-    },
-    "qc options": {
-      "title": "QC options",
-      "type": "object",
-      "description": "No description",
-      "properties": {
-        "var_name_mitochondrial_genes": {
-          "type": "string",
-          "description": "In which .var slot to store a boolean array corresponding the mitochondrial genes.\n",
-          "help_text": "Type: `string`, multiple: `False`, default: `\"mitochondrial\"`. ",
-          "default": "mitochondrial"
-        },
-        "var_name_ribosomal_genes": {
-          "type": "string",
-          "description": "In which .var slot to store a boolean array corresponding the ribosomal genes.\n",
-          "help_text": "Type: `string`, multiple: `False`, default: `\"ribosomal\"`. ",
-          "default": "ribosomal"
-        },
-        "min_total_counts": {
-          "type": "integer",
-          "description": "Minimum total counts for a cell to be included in the output.\n",
-          "help_text": "Type: `integer`, multiple: `False`, default: `10`. ",
-          "default": 10
-        },
-        "min_num_nonzero_vars": {
-          "type": "integer",
-          "description": "Minimum number of nonzero vars for a cell to be included in the output.\n",
-          "help_text": "Type: `integer`, multiple: `False`, default: `10`. ",
-          "default": 10
-        }
-      }
-    },
-    "cellbender options": {
-      "title": "Cellbender options",
-      "type": "object",
-      "description": "No description",
-      "properties": {
-        "run_cellbender": {
-          "type": "boolean",
-          "description": "Whether to run cellbender or not.",
-          "help_text": "Type: `boolean`, multiple: `False`, default: `false`. ",
-          "default": false
-        },
-        "cellbender_epochs": {
-          "type": "integer",
-          "description": "Number of epochs to train cellbender.",
-          "help_text": "Type: `integer`, multiple: `False`, default: `150`. ",
-          "default": 150
-        }
-      }
-    },
-    "nextflow input-output arguments": {
-      "title": "Nextflow input-output arguments",
-      "type": "object",
-      "description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.",
-      "properties": {
-        "publish_dir": {
-          "type": "string",
-          "description": "Path to an output directory.",
-          "help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. "
-        }
-      }
-    }
-  },
-  "allOf": [
-    {
-      "$ref": "#/$defs/inputs"
-    },
-    {
-      "$ref": "#/$defs/outputs"
-    },
-    {
-      "$ref": "#/$defs/options"
-    },
-    {
-      "$ref": "#/$defs/qc options"
-    },
-    {
-      "$ref": "#/$defs/cellbender options"
-    },
-    {
-      "$ref": "#/$defs/nextflow input-output arguments"
-    }
-  ]
-}