config.vsh.yaml

name: onclass
namespace: annotate
scope: "public"
description: |
  OnClass is a python package for single-cell cell type annotation. It uses the Cell Ontology to capture the cell type similarity. 
  These similarities enable OnClass to annotate cell types that are never seen in the training data.
authors:
  - __merge__: /src/authors/jakub_majercik.yaml
    roles: [ author ]

argument_groups:
  - name: Inputs
    description: Input dataset (query) arguments
    arguments:
      - name: "--input"
        alternatives: [-i]
        type: file
        description: The input (query) data to be labeled. Should be a .h5mu file.
        direction: input
        required: true
        example: input.h5mu
      - name: "--modality"
        description: Which modality to process.
        type: string
        default: "rna"
        required: false
      - name: "--input_layer"
        type: string
        description: The layer in the input data to be used for cell type annotation if .X is not to be used.
        required: false
      - name: "--input_var_gene_names"
        type: string
        required: false
        description: |
          The name of the adata var column in the input data containing gene names; when no gene_name_layer is provided, the var index will be used.
      - name: "--input_reference_gene_overlap"
        type: integer
        default: 100
        min: 1
        description: | 
          The minimum number of genes present in both the reference and query datasets.

  - name: Ongoloty
    description: Ontology input files
    arguments:
      - name: "--cl_nlp_emb_file"
        type: file
        description: The .nlp.emb file with the cell type embeddings.
        required: true
      - name: "--cl_ontology_file"
        type: file
        description: The .ontology file with the cell type ontology.
        required: true
      - name: "--cl_obo_file"
        type: file
        description: The .obo file with the cell type ontology.
        required: true

  - name: Reference
    description: Arguments related to the reference dataset.
    arguments:
      - name: "--reference"
        type: file
        description: "The reference data to train the CellTypist classifiers on. Only required if a pre-trained --model is not provided."
        example: reference.h5mu
        direction: input
        required: false
      - name: "--reference_layer"
        type: string
        description: The layer in the reference data to be used for cell type annotation if .X is not to be used.
        required: false
      - name: "--reference_obs_target"
        type: string
        description: The name of the adata obs column in the reference data containing cell type annotations.
        example: "cell_ontology_class"
        required: true
      - name:  "--reference_var_gene_names"
        type: string
        required: false
        description: |
          The name of the adata var column in the reference data containing gene names; when no gene_name_layer is provided, the var index will be used.
      - name: "--reference_var_input"
        type: string
        required: false
        description: |
          .var column containing highly variable genes. By default, do not subset genes.
      - name: "--unknown_celltype"
        type: string
        default: "Unknown"
        required: false
        description: |
          Label for unknown cell types.

  - name: Outputs
    description: Output arguments.
    arguments:
      - name: "--output"
        type: file
        description: Output h5mu file.
        direction: output
        example: output.h5mu
      - name: "--output_obs_predictions"
        type: string
        default: onclass_pred
        required: false
        description: |
          In which `.obs` slots to store the predicted information.
      - name: "--output_obs_probability"
        type: string
        default: onclass_prob 
        required: false
        description: |
          In which `.obs` slots to store the probability of the predictions.
    __merge__: [., /src/base/h5_compression_argument.yaml]

  - name: Model arguments
    description: Model arguments
    arguments:
      - name: "--model"
        type: string
        description: | 
          "Pretrained model path without a file extension. If not provided, the model will be trained 
          on the reference data and --reference should be provided. The path namespace should contain:
            - a .npz or .pkl file
            - a .data file
            - a .meta file
            - a .index file
          e.g. /path/to/model/pretrained_model_target1 as saved by OnClass."
        required: false
        direction: input
      - name: "--max_iter"
        type: integer
        default: 30
        required: false
        description: Maximum number of iterations for training the model.

resources:
  - type: python_script
    path: script.py
  - path: /src/utils/setup_logger.py
  - path: /src/utils/cross_check_genes.py
  - path: /src/utils/subset_vars.py
  - path: /src/utils/set_var_index.py

test_resources:
  - type: python_script
    path: test.py
  - path: /resources_test/annotation_test_data/
  - path: /resources_test/pbmc_1k_protein_v3/

engines:
  - type: docker
    image: python:3.11
    setup:
      - type: python
        packages:
          - OnClass~=1.3
          - tensorflow
          - obonet
        __merge__: [/src/base/requirements/anndata_mudata.yaml, .]
    __merge__: [ /src/base/requirements/python_test_setup.yaml, .]
runners:
  - type: executable
  - type: nextflow
    directives:
      label: [highcpu, highmem, highdisk]