name: "random_forest_annotation"
namespace: "annotate"
version: "fix-integration-tests"
authors:
- name: "Jakub Majercik"
  roles:
  - "author"
  info:
    role: "Contributor"
    links:
      email: "jakub@data-intuitive.com"
      github: "jakubmajercik"
      linkedin: "jakubmajercik"
    organizations:
    - name: "Data Intuitive"
      href: "https://www.data-intuitive.com"
      role: "Bioinformatics Engineer"
argument_groups:
- name: "Inputs"
  description: "Input dataset (query) arguments"
  arguments:
  - type: "file"
    name: "--input"
    description: "The input (query) data to be labeled. Should be a .h5mu file."
    info: null
    example:
    - "input.h5mu"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--modality"
    description: "Which modality to process."
    info: null
    default:
    - "rna"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--input_layer"
    description: "The layer in the input data to be used for cell type annotation\
      \ if .X is not to be used."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Reference"
  description: "Arguments related to the reference dataset."
  arguments:
  - type: "file"
    name: "--reference"
    description: "The reference data to train the CellTypist classifiers on. Only\
      \ required if a pre-trained --model is not provided."
    info: null
    example:
    - "reference.h5mu"
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--reference_layer"
    description: "The layer in the reference data to be used for cell type annotation\
      \ if .X is not to be used. Data are expected to be processed in the same way\
      \ as the --input query dataset."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--reference_obs_target"
    description: "Key in obs field of reference modality with cell-type information."
    info: null
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Outputs"
  description: "Output arguments."
  arguments:
  - type: "file"
    name: "--output"
    description: "Output h5mu file."
    info: null
    example:
    - "output.h5mu"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--output_compression"
    info: null
    example:
    - "gzip"
    required: false
    choices:
    - "gzip"
    - "lzf"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--output_obs_predictions"
    description: "In which `.obs` slots to store the predicted information.\n"
    info: null
    default:
    - "random_forest_pred"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--output_obs_probability"
    description: "In which `.obs` slots to store the probability of the predictions.\n"
    info: null
    default:
    - "random_forest_probability"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Model arguments"
  description: "Model arguments."
  arguments:
  - type: "file"
    name: "--model"
    description: "Pretrained model in pkl format. If not provided, the model will\
      \ be trained on the reference data and --reference should be provided."
    info: null
    example:
    - "pretrained_model.pkl"
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--n_estimators"
    description: "Number of trees in the random forest."
    info: null
    default:
    - 100
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--max_depth"
    description: "Maximum depth of the trees in the random forest. \nIf not provided,\
      \ the nodes are expanded until all leaves only contain a single sample.\n"
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--criterion"
    description: "The function to measure the quality of a split."
    info: null
    default:
    - "gini"
    required: false
    choices:
    - "gini"
    - "entropy"
    - "log_loss"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--class_weight"
    description: "Weights associated with classes.\nThe `balanced` mode uses the values\
      \ of y to automatically adjust weights inversely proportional to class frequencies\
      \ in the input data.\nThe `balanced_subsample` mode is the same as `balanced`\
      \ except that weights are computed based on the bootstrap sample for every tree\
      \ grown.\nThe `uniform` mode gives all classes a weight  of one.\n"
    info: null
    default:
    - "balanced_subsample"
    required: false
    choices:
    - "balanced"
    - "balanced_subsample"
    - "uniform"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--max_features"
    description: "The number of features to consider when looking for the best split.\
      \ The value can either be a positive integer or one of `sqrt`, `log2` or `all`.\n\
      If integer: consider max_features features at each split.\nIf `sqrt`: max_features\
      \ is the squareroot of all input features.\nIf `log2`: max_features is the log2\
      \ of all input features.\nIf `all`: max features equals all input features.\n"
    info: null
    default:
    - "200"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
resources:
- type: "python_script"
  path: "script.py"
  is_executable: true
- type: "file"
  path: "setup_logger.py"
- type: "file"
  path: "nextflow_labels.config"
  dest: "nextflow_labels.config"
description: "Automated cell type annotation tool for scRNA-seq datasets on the basis\
  \ of random forest."
test_resources:
- type: "python_script"
  path: "test.py"
  is_executable: true
- type: "file"
  path: "TS_Blood_filtered.h5mu"
- type: "file"
  path: "pbmc_1k_protein_v3_filtered_feature_bc_matrix.h5mu"
- type: "file"
  path: "openpipelinetestutils"
  dest: "openpipelinetestutils"
info: null
status: "enabled"
links:
  repository: "https://github.com/openpipelines-bio/openpipeline"
  docker_registry: "ghcr.io"
runners:
- type: "executable"
  id: "executable"
  docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
  id: "nextflow"
  directives:
    tag: "$id"
  auto:
    simplifyInput: true
    simplifyOutput: false
    transcript: false
    publish: false
  config:
    labels:
      mem1gb: "memory = 1000000000.B"
      mem2gb: "memory = 2000000000.B"
      mem5gb: "memory = 5000000000.B"
      mem10gb: "memory = 10000000000.B"
      mem20gb: "memory = 20000000000.B"
      mem50gb: "memory = 50000000000.B"
      mem100gb: "memory = 100000000000.B"
      mem200gb: "memory = 200000000000.B"
      mem500gb: "memory = 500000000000.B"
      mem1tb: "memory = 1000000000000.B"
      mem2tb: "memory = 2000000000000.B"
      mem5tb: "memory = 5000000000000.B"
      mem10tb: "memory = 10000000000000.B"
      mem20tb: "memory = 20000000000000.B"
      mem50tb: "memory = 50000000000000.B"
      mem100tb: "memory = 100000000000000.B"
      mem200tb: "memory = 200000000000000.B"
      mem500tb: "memory = 500000000000000.B"
      mem1gib: "memory = 1073741824.B"
      mem2gib: "memory = 2147483648.B"
      mem4gib: "memory = 4294967296.B"
      mem8gib: "memory = 8589934592.B"
      mem16gib: "memory = 17179869184.B"
      mem32gib: "memory = 34359738368.B"
      mem64gib: "memory = 68719476736.B"
      mem128gib: "memory = 137438953472.B"
      mem256gib: "memory = 274877906944.B"
      mem512gib: "memory = 549755813888.B"
      mem1tib: "memory = 1099511627776.B"
      mem2tib: "memory = 2199023255552.B"
      mem4tib: "memory = 4398046511104.B"
      mem8tib: "memory = 8796093022208.B"
      mem16tib: "memory = 17592186044416.B"
      mem32tib: "memory = 35184372088832.B"
      mem64tib: "memory = 70368744177664.B"
      mem128tib: "memory = 140737488355328.B"
      mem256tib: "memory = 281474976710656.B"
      mem512tib: "memory = 562949953421312.B"
      cpu1: "cpus = 1"
      cpu2: "cpus = 2"
      cpu5: "cpus = 5"
      cpu10: "cpus = 10"
      cpu20: "cpus = 20"
      cpu50: "cpus = 50"
      cpu100: "cpus = 100"
      cpu200: "cpus = 200"
      cpu500: "cpus = 500"
      cpu1000: "cpus = 1000"
    script:
    - "includeConfig(\"nextflow_labels.config\")"
  debug: false
  container: "docker"
engines:
- type: "docker"
  id: "docker"
  image: "python:3.12-slim"
  target_registry: "images.viash-hub.com"
  target_tag: "fix-integration-tests"
  namespace_separator: "/"
  setup:
  - type: "apt"
    packages:
    - "libhdf5-dev"
    - "procps"
    interactive: false
  - type: "python"
    user: false
    packages:
    - "scikit-learn==1.4.2"
    upgrade: true
  - type: "python"
    user: false
    packages:
    - "anndata==0.10.8"
    - "mudata~=0.2.4"
    - "pandas!=2.1.2"
    - "numpy<2.0.0"
    upgrade: true
  test_setup:
  - type: "docker"
    copy:
    - "openpipelinetestutils /opt/openpipelinetestutils"
  - type: "python"
    user: false
    packages:
    - "/opt/openpipelinetestutils"
    upgrade: true
  - type: "python"
    user: false
    packages:
    - "viashpy==0.8.0"
    upgrade: true
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/annotate/random_forest_annotation/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/annotate/random_forest_annotation"
  executable: "target/executable/annotate/random_forest_annotation/random_forest_annotation"
  viash_version: "0.9.0"
  git_commit: "5e3f3231456facaf14da57fa563d4de58492ca82"
  git_remote: "https://x-access-token:ghs_EujrUcz58S6J44CLSvromEPEcaMxTc30MU1j@github.com/openpipelines-bio/openpipeline"
  git_tag: "0.2.0-1942-g5e3f3231"
package_config:
  name: "openpipeline"
  version: "fix-integration-tests"
  info:
    test_resources:
    - type: "s3"
      path: "s3://openpipelines-data"
      dest: "resources_test"
  viash_version: "0.9.0"
  source: "src"
  target: "target"
  config_mods:
  - ".test_resources += {path: '/src/base/openpipelinetestutils', dest: 'openpipelinetestutils'}\n\
    .resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n\
    .runners[.type == 'nextflow'].directives.tag := '$id'\n.runners[.type == 'nextflow'].config.script\
    \ := 'includeConfig(\"nextflow_labels.config\")'\n"
  - ".engines += { type: \"native\" }"
  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
  - ".engines[.type == 'docker'].target_tag := 'fix-integration-tests'"
  organization: "vsh"
  links:
    repository: "https://github.com/openpipelines-bio/openpipeline"
    docker_registry: "ghcr.io"
    homepage: "https://openpipelines.bio"
    documentation: "https://openpipelines.bio/fundamentals"
    issue_tracker: "https://github.com/openpipelines-bio/openpipeline/issues"