name: "popv"
namespace: "annotate"
version: "fix-integration-tests"
authors:
- name: "Matthias Beyens"
  roles:
  - "author"
  info:
    role: "Contributor"
    links:
      github: "MatthiasBeyens"
      orcid: "0000-0003-3304-0706"
      email: "matthias.beyens@gmail.com"
      linkedin: "mbeyens"
    organizations:
    - name: "Janssen Pharmaceuticals"
      href: "https://www.janssen.com"
      role: "Principal Scientist"
- name: "Robrecht Cannoodt"
  roles:
  - "author"
  info:
    role: "Core Team Member"
    links:
      email: "robrecht@data-intuitive.com"
      github: "rcannood"
      orcid: "0000-0003-3641-729X"
      linkedin: "robrechtcannoodt"
    organizations:
    - name: "Data Intuitive"
      href: "https://www.data-intuitive.com"
      role: "Data Science Engineer"
    - name: "Open Problems"
      href: "https://openproblems.bio"
      role: "Core Member"
argument_groups:
- name: "Inputs"
  description: "Arguments related to the input (aka query) dataset."
  arguments:
  - type: "file"
    name: "--input"
    alternatives:
    - "-i"
    description: "Input 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: "Which layer to use. If no value is provided, the counts are assumed\
      \ to be in the `.X` slot. Otherwise, count data is expected to be in `.layers[input_layer]`."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--input_obs_batch"
    description: "Key in obs field of input adata for batch information. If no value\
      \ is provided, batch label is assumed to be unknown."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--input_var_subset"
    description: "Subset the input object with this column."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--input_obs_label"
    description: "Key in obs field of input adata for label information. This is only\
      \ used for training scANVI. Unlabelled cells should be set to `\"unknown_celltype_label\"\
      `."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--unknown_celltype_label"
    description: "If `input_obs_label` is specified, cells with this value will be\
      \ treated as unknown and will be predicted by the model."
    info: null
    default:
    - "unknown"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Reference"
  description: "Arguments related to the reference dataset."
  arguments:
  - type: "file"
    name: "--reference"
    description: "User-provided reference tissue. The data that will be used as reference\
      \ to call cell types."
    info: null
    example:
    - "TS_Bladder_filtered.h5ad"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--reference_layer"
    description: "Which layer to use. If no value is provided, the counts are assumed\
      \ to be in the `.X` slot. Otherwise, count data is expected to be in `.layers[reference_layer]`."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--reference_obs_label"
    description: "Key in obs field of reference AnnData with cell-type information."
    info: null
    default:
    - "cell_ontology_class"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--reference_obs_batch"
    description: "Key in obs field of input adata for batch information."
    info: null
    default:
    - "donor_assay"
    required: false
    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: true
    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: ";"
- name: "Arguments"
  description: "Other arguments."
  arguments:
  - type: "string"
    name: "--methods"
    description: "Methods to call cell types. By default, runs to knn_on_scvi and\
      \ scanvi."
    info: null
    example:
    - "knn_on_scvi"
    - "scanvi"
    required: true
    choices:
    - "celltypist"
    - "knn_on_bbknn"
    - "knn_on_scanorama"
    - "knn_on_scvi"
    - "onclass"
    - "rf"
    - "scanvi"
    - "svm"
    direction: "input"
    multiple: true
    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: "Performs popular major vote cell typing on single cell sequence data\
  \ using multiple algorithms. Note that this is a one-shot version of PopV."
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:
    label:
    - "highmem"
    - "highcpu"
    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:3.9-slim"
  target_registry: "images.viash-hub.com"
  target_tag: "fix-integration-tests"
  namespace_separator: "/"
  setup:
  - type: "apt"
    packages:
    - "procps"
    - "git"
    - "build-essential"
    - "wget"
    interactive: false
  - type: "python"
    user: false
    packages:
    - "scanpy~=1.9.6"
    - "scvi-tools~=1.0.3"
    - "popv~=0.3.2"
    - "jax==0.4.10"
    - "jaxlib==0.4.10"
    - "ml-dtypes<0.3.0"
    - "scipy==1.12.0"
    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
  - type: "docker"
    run:
    - "cd /opt && git clone --depth 1 https://github.com/YosefLab/PopV.git && \\\n\
      \  cd PopV && git fetch --depth 1 origin tag v0.2 && git checkout v0.2\n"
  test_setup:
  - type: "python"
    user: false
    packages:
    - "viashpy==0.8.0"
    upgrade: true
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/annotate/popv/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/annotate/popv"
  executable: "target/executable/annotate/popv/popv"
  viash_version: "0.9.0"
  git_commit: "da62b4ffe30b6ef36fcb7ef5944f29d45d1138ff"
  git_remote: "https://x-access-token:ghs_WgbTvvspBKMSQ5BPucz45vMfHrxqK54Vys9e@github.com/openpipelines-bio/openpipeline"
  git_tag: "0.2.0-1939-gda62b4ff"
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"