config.vsh.yaml

__merge__: /src/api/comp_method_transcript_assignment.yaml

name: pciseq
label: "pciSeq Transcript Assignment"
summary: "Assign transcripts to cells using the pciSeq method from Qian et. al. (2020)"
description: "Uses a reference sc-RNAseq dataset to probabalistically assign cell types and transcripts to cells ."
links:
  documentation: "https://github.com/acycliq/pciSeq"
  repository: "https://github.com/acycliq/pciSeq"
references:
  doi: "10.1038/s41592-019-0631-4"

arguments:
  - name: --transcripts_key
    type: string
    description: The key of the transcripts within the points of the spatial data
    default: transcripts
  - name: --coordinate_system
    type: string
    description: The key of the pixel space coordinate system within the spatial data
    default: global
  # - name: --sc_cell_type_key
  #   type: string
  #   default: cell_type
  #   required: true
  #   direction: input
  #   description: The name of column in the SC-RNAseq AnnData .obs with the cell type of each cell

  # - name: --exclude_genes
  #   type: string
  #   required: false
  #   description: "list of genes to be excluded during cell-typing, e.g ['Aldoc', 'Id2'] to exclude all spots from Aldoc and Id2"
  #   direction: input 
  #   default: None

  - name: --max_iter
    type: integer
    required: false
    description: "Maximum number of loops allowed for the Variational Bayes to run"
    direction: input 
    default: 1000

  - name: --CellCallTolerance
    type: double
    required: false
    description: "Convergence achieved if assignment probabilities between two successive loops is less than the tolerance"
    direction: input 
    default: 0.02
  
  - name: --rGene
    type: double
    required: false
    description: |
      "A gamma distribution expresses the efficiency of the in-situ sequencing for each gene. It tries to capture
      the ratio of the observed over the theoretical counts for a given gene. rGene controls the variance and
      Inefficiency is the average of this assumed Gamma distribution"
    direction: input 
    default: 20

  - name: --Inefficiency
    type: double
    required: false
    description: " "
    direction: input 
    default: 0.2

  - name: --InsideCellBonus
    type: double
    required: false
    description: |
      "If a spot is inside the cell boundaries this bonus will give the likelihood an extra boost
      in order to make the spot more probable to get assigned to the cell than another spot positioned
      outside the cell boundaries"
    direction: input 
    default: 2

  - name: --MisreadDensity
    type: double
    required: false
    description: |
      "To account for spots far from the some a uniform distribution is introduced to describe those misreads.
      By default this uniform distribution has a density of 1e-5 misreads per pixel."
    direction: input 
    default: 0.00001

  - name: --SpotReg
    type: double
    required: false
    description: |
      "Gene detection might come with irregularities due to technical errors. A small value is introduced
      here to account for these errors. It is an additive factor, applied to the single cell expression
      counts when the mean counts per class and per gene are calculated."
    direction: input 
    default: 0.1

  - name: --nNeighbors
    type: integer
    required: false
    description: |
      "By default only the 3 nearest cells will be considered as possible parent cells for any given spot.
      There is also one extra 'super-neighbor', which is always a neighbor to the spots so we can assign
      the misreads to. Could be seen as the background. Hence, by default the algorithm tries examines
      whether any of the 3 nearest cells is a possible parent cell to a given cell or whether the spot is
      a misread"
    direction: input 
    default: 3

  # 
  - name: --rSpot
    type: double
    required: false
    description: |
      "A gamma distributed variate from Gamma(rSpot, 1) is applied to the mean expression, hence the counts
      are distributed according to a Negative Binomial distribution.
      The value for rSpot will control the variance/dispersion of the counts"
    direction: input 
    default: 2

  - name: --save_data
    type: boolean
    required: false
    description: "Boolean, if True the output will be saved as tsv files in a folder named 'pciSeq' in your system's temp dir."
    direction: input 
    default: False

  # output directory 'default' will save to temp location
  # - name: output_path
  #   default: ['default']

  # 
  # - name: --dtype
  #   type: string
  #   required: false
  #   description: |
  #     "Use either np.float16 or np.float32 to reduce memory usage. In most cases RAM consumption shouldnt
  #     need more than 32Gb RAM. If you have a dataset from a full coronal mouse slice with a high number of
  #     segmented cells (around 150,000) a gene panel of more than 250 genes and 100 or more different
  #     cell types (aka clusters, aka classes) in the single cell data then you might need at least 64GB on
  #     your machine. Changing the datatype to a float16 or float32 will help keeping RAM usage to a lower
  #     level"
  #   direction: input 
  #   default: np.float64



resources:
  - type: python_script
    path: script.py

engines:
  - type: docker
    image: openproblems/base_python:1
    __merge__: 
      - /src/base/setup_txsim_partial.yaml
      - /src/base/setup_spatialdata_partial.yaml
    setup:
      - type: python
        github: [acycliq/pciSeq@issue_14]
      #  pypi: [pciseq] # See https://github.com/acycliq/pciSeq/issues/14
  - type: native

runners:
  - type: executable
  - type: nextflow
    directives:
      label: [ veryhightime, midcpu, veryhighmem ]