config.vsh.yaml

name: h5mu_to_qc_json
namespace: ingestion_qc
scope: private
description: |
  Takes H5MU files that have been ingested by CellRanger, Xenium or CosMx and processed by the QC workflow, and generates:
  - A JSON file that contains the combined data for the QC report
  - A JSON file that defines the layout and structure of the QC report
authors: 
  - __merge__: /src/authors/jakub_majercik.yaml
    roles: [author]
  - __merge__: /src/authors/dorien_roosen.yaml
    roles: [author]
  - __merge__: /src/authors/robrecht_cannoodt.yaml
    roles: [author]
  - __merge__: /src/authors/weiwei_schultz.yaml
    roles: [contributor]
argument_groups:
  - name: Inputs
    arguments:
      - name: --input
        type: file
        multiple: true
        required: true
        direction: input
        description: The input h5mu file(s)
        example: path/to/file.h5mu
      - name: --modality
        type: string
        description: The modality to use
        default: rna
      - name: --ingestion_method
        type: string
        required: true
        choices:
          - cellranger_multi
          - xenium
          - 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
        type: string
        description: The key in the h5mu file that contains the sample ID. If not provided, each H5MU file will be considered as a separate sample.
        default: sample_id
      - name: --obs_total_counts
        type: string
        description: The key in the h5mu .obs field that contains the total counts.
        default: total_counts
      - name: --obs_num_nonzero_vars
        type: string
        description: The key in the h5mu .obs field that contains the number of nonzero vars.
        default: num_nonzero_vars
      - name: --obs_fraction_mitochondrial
        type: string
        description: The key in the h5mu .obs field that contains the fraction mitochondrial genes.
        default: fraction_mitochondrial
      - name: --obs_fraction_ribosomal
        type: string
        description: The key in the h5mu .obs field that contains the fraction ribosomal genes.
        default: fraction_ribosomal

  - name: Outputs
    arguments:
      - name: --output
        type: file
        required: true
        direction: output
        description: The output JSON file
        example: path/to/file.json
      - name: --output_reporting_json
        type: file
        required: true
        description: The output JSON file that defines the QC report
        direction: output
        example: path/to/file.json

  - name: Filtering & grouping options
    arguments:
      - name: --min_total_counts
        type: integer
        description: Minimum total counts for a cell to be included in the output
        default: 10
      - name: --min_num_nonzero_vars
        type: integer
        description: Minimum number of nonzero vars for a cell to be included in the output
        default: 10
      - name: --obs_metadata
        type: string
        multiple: true
        description: The metadata keys in the h5mu .obs to include in the output JSON.
        example: "donor_id;cell_type;batch;condition"

  - name: Options for CellRanger reports
    arguments:
      - name: --obs_cellbender
        type: string
        multiple: true
        description: The cellbender keys in the h5mu .obs to include in the output JSON
        default: [
          "cellbender_background_fraction",
          "cellbender_cell_probability",
          "cellbender_cell_size",
          "cellbender_droplet_efficiency"
          ]
      - name: --uns_cellranger_metrics
        type: string
        description: The key in the h5mu file .uns that contains the cellranger metrics
        default: metrics_cellranger


  - name: Options for Xenium reports
    arguments:
      - name: --obs_nucleus_area
        type: string
        description: The key in the h5mu .obs field that contains the nucleus area.
        default: nucleus_area
      - name: --obs_cell_area
        type: string
        description: The key in the h5mu .obs field that contains the cell area.
        default: cell_area
      - name: --obs_x_coord
        type: string
        description: The key in the h5mu .obs field that contains the x coordinate.
        default: x_coord
      - name: --obs_y_coord
        type: string
        description: The key in the h5mu .obs field that contains the y coordinate.
        default: y_coord
      - name: --obs_control_probe_counts
        type: string
        description: The key in the h5mu .obs field that contains the number of control probes.
        default: control_probe_counts
      - name: --obs_control_codeword_counts
        type: string
        description: The key in the h5mu .obs field that contains the number of control codewords.
        default: control_codeword_counts  

  # - name: Options for CosMx reports

resources:
  - type: python_script
    path: script.py
  - path: /src/utils/setup_logger.py
  - path: report_structure
test_resources:
  - type: python_script
    path: test.py
  - type: file
    path: /resources_test
engines:
  - type: docker
    image: python:3.12-slim
    setup:
      - type: apt
        packages:
          - procps
      - type: python
        __merge__: [ /src/base/requirements/anndata_mudata.yaml ]
    test_setup:
    - type: apt
      packages:
        - git
    - type: python
      __merge__: [/src/base/requirements/viashpy.yaml]
      github: openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils

runners:
  - type: executable
  - type: nextflow
    directives:
      label: [midmem, middisk]