add cosmx ingestion

CHANGELOG.MD

@@ -1,5 +1,9 @@
 # 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).

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"
+        }
+      ]
+    }
+  ]
+}