config.vsh.yaml

# The API specifies which type of component this is.
# It contains specifications for:
#   - The input/output files
#   - Common parameters
#   - A unit test
__merge__: ../../api/comp_metric.yaml

# A unique identifier for your component (required).
# Can contain only lowercase letters or underscores.
name: emd

# Metadata for your component
info:
  metrics:
      # A unique identifier for your metric (required).
      # Can contain only lowercase letters or underscores.
    - name: emd_mean_ct_horiz
      # A relatively short label, used when rendering visualisarions (required)
      label: EMD Mean CT Horizontal
      # A one sentence summary of how this metric works (required). Used when 
      # rendering summary tables.
      summary: "Mean Earth Mover Distance calculated horizontally across donors for each cell type and marker."
      # A multi-line description of how this component works (required). Used
      # when rendering reference documentation.
      description: |
        Earth Mover Distance (EMD), also known as the Wasserstein metric, measures the difference 
        between two probability distributions. 
        
        Here, EMD is used to compare marker expression distributions between paired samples from the same donor 
        quantified across two different batches. 
        For each paired sample, cell type, and marker, the marker expression values are first converted into 
        probability distributions. 
        This is done by binning the expression values into a range from -100 to 100 with a bin width of 0.1.
        The `wasserstein_distance` function from SciPy is then used to calculate the EMD between the two 
        probability distributions belonging to the same cell type, marker, and a given paired samples.
        This is then repeated for every cell type, marker, and paired sample.
        Finally, the average of all these EMD values is computed and reported as the metric score.

        A high score indicates large overall differences in the distributions of marker expressions 
        between the paired samples, suggesting poor batch integration.
        A low score means the small differences in marker expression distributions between batches, 
        indicating good batch integration.

      references:
        doi: 
          - 10.1023/A:1026543900054
      links:
        # URL to the documentation for this metric (required).
        documentation: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.wasserstein_distance.html
        # URL to the code repository for this metric (required).
        repository: https://github.com/scipy/scipy
      # The minimum possible value for this metric (required)
      min: 0
      # The maximum possible value for this metric (required)
      max: .inf
      # Whether a higher value represents a 'better' solution (required)
      maximize: false

      # A unique identifier for your metric (required).
      # Can contain only lowercase letters or underscores.
    - name: emd_mean_ct_vert
      # A relatively short label, used when rendering visualisarions (required)
      label: EMD Mean CT Vertical
      # A one sentence summary of how this metric works (required). Used when 
      # rendering summary tables.
      summary: "Mean Earth Mover Distance across batch corrected samples, cell types, and markers."
      # A multi-line description of how this component works (required). Used
      # when rendering reference documentation.
      description: |
        Earth Mover Distance (EMD), also known as the Wasserstein metric, measures the difference 
        between two probability distributions. 
        
        Here, EMD is used to compare marker expression distributions between all integrated 
        samples from the same group.
        For each pair of samples, cell type, and marker, the marker expression values are first converted into 
        probability distributions. 
        This is done by binning the expression values into a range from -100 to 100 with a bin width of 0.1.
        The `wasserstein_distance` function from SciPy is then used to calculate the EMD between the two 
        probability distributions belonging to the same cell type, marker, and a given paired samples.
        This is then repeated for every cell type, marker, and paired sample.
        Finally, the average of all these EMD values is computed and reported as the metric score.

        A high score indicates overall, there is a large difference in distribution of marker expression after batch integration.
        A low score means that overall, the samples are well integrated.
      references:
        doi: 
          - 10.1023/A:1026543900054
      links:
        # URL to the documentation for this metric (required).
        documentation: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.wasserstein_distance.html
        # URL to the code repository for this metric (required).
        repository: https://github.com/scipy/scipy
      # The minimum possible value for this metric (required)
      min: 0
      # The maximum possible value for this metric (required)
      max: .inf
      # Whether a higher value represents a 'better' solution (required)
      maximize: false

# Resources required to run the component
resources:
  # The script of your component (required)
  - type: python_script
    path: script.py
  - path: helper.py
  - path: /src/utils/helper_functions.py

engines:
  # Specifications for the Docker image for this component.
  - type: docker
    image: openproblems/base_python:1
    # Add custom dependencies here (optional). For more information, see
    # https://viash.io/reference/config/engines/docker/#setup .

runners:
  # This platform allows running the component natively
  - type: executable
  # Allows turning the component into a Nextflow module / pipeline.
  - type: nextflow
    directives:
      label: [lowtime,lowmem,lowcpu]