name: "onclass"
namespace: "annotate"
version: "dev"
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"
    alternatives:
    - "-i"
    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: ";"
  - type: "file"
    name: "--cl_nlp_emb_file"
    description: "The .nlp.emb file with the cell type embeddings."
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--cl_ontology_file"
    description: "The .ontology file with the cell type ontology."
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--cl_obo_file"
    description: "The .obo file with the cell type ontology."
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--var_query_gene_names"
    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.\n"
    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."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--reference_obs_target"
    description: "The name of the adata obs column in the reference data containing\
      \ cell type annotations."
    info: null
    example:
    - "cell_ontology_class"
    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:
    - "onclass_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:
    - "onclass_prob"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Model arguments"
  description: "Model arguments"
  arguments:
  - type: "string"
    name: "--model"
    description: "\"Pretrained model path without a file extension. If not provided,\
      \ the model will be trained \non the reference data and --reference should be\
      \ provided. The path namespace should contain:\n  - a .npz or .pkl file\n  -\
      \ a .data file\n  - a .meta file\n  - a .index file\ne.g. /path/to/model/pretrained_model_target1\
      \ as saved by OnClass.\"\n"
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--max_iter"
    description: "Maximum number of iterations for training the model."
    info: null
    default:
    - 30
    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: "OnClass is a python package for single-cell cell type annotation. It\
  \ uses the Cell Ontology to capture the cell type similarity. \nThese similarities\
  \ enable OnClass to annotate cell types that are never seen in the training data.\n"
test_resources:
- type: "python_script"
  path: "test.py"
  is_executable: true
- type: "file"
  path: "annotation_test_data"
- type: "file"
  path: "pbmc_1k_protein_v3"
- 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:3.8"
  target_registry: "images.viash-hub.com"
  target_tag: "dev"
  namespace_separator: "/"
  setup:
  - type: "python"
    user: false
    packages:
    - "scikit-learn==0.24.0"
    - "OnClass==1.2"
    - "tensorflow==2.13.1"
    - "obonet==1.1.0"
    - "mudata"
    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/onclass/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/annotate/onclass"
  executable: "target/executable/annotate/onclass/onclass"
  viash_version: "0.9.0"
  git_commit: "2dbe3b7231f9abb4baa628e76e8abc686e627087"
  git_remote: "https://x-access-token:ghs_NVsRTpmVPn6SfFQ131njHQOgn6tt7b1bmmJj@github.com/openpipelines-bio/openpipeline"
  git_tag: "0.2.0-1926-g2dbe3b72"
package_config:
  name: "openpipeline"
  version: "dev"
  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\")'"
  - ".engines += { type: \"native\" }"
  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
  - ".engines[.type == 'docker'].target_tag := 'dev'"
  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"