name: "highly_variable_features_scanpy"
namespace: "feature_annotation"
version: "fix-integration-tests"
authors:
- name: "Dries De Maeyer"
  roles:
  - "contributor"
  info:
    role: "Core Team Member"
    links:
      email: "ddemaeyer@gmail.com"
      github: "ddemaeyer"
      linkedin: "dries-de-maeyer-b46a814"
    organizations:
    - name: "Janssen Pharmaceuticals"
      href: "https://www.janssen.com"
      role: "Principal Scientist"
- name: "Robrecht Cannoodt"
  roles:
  - "maintainer"
  - "contributor"
  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: "Arguments"
  arguments:
  - type: "file"
    name: "--input"
    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"
    info: null
    default:
    - "rna"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--layer"
    description: "use adata.layers[layer] for expression values instead of adata.X."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - 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"
    description: "The compression format to be used on the output h5mu object."
    info: null
    example:
    - "gzip"
    required: false
    choices:
    - "gzip"
    - "lzf"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--var_name_filter"
    description: "In which .var slot to store a boolean array corresponding to which\
      \ observations should be filtered out."
    info: null
    default:
    - "filter_with_hvg"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--varm_name"
    description: "In which .varm slot to store additional metadata."
    info: null
    default:
    - "hvg"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--flavor"
    description: "Choose the flavor for identifying highly variable features. For\
      \ the dispersion based methods\nin their default workflows, Seurat passes the\
      \ cutoffs whereas Cell Ranger passes n_top_features.\n"
    info: null
    default:
    - "seurat"
    required: false
    choices:
    - "seurat"
    - "cell_ranger"
    - "seurat_v3"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--n_top_features"
    description: "Number of highly-variable features to keep. Mandatory if flavor='seurat_v3'."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--min_mean"
    description: "If n_top_features is defined, this and all other cutoffs for the\
      \ means and the normalized dispersions are ignored. Ignored if flavor='seurat_v3'."
    info: null
    default:
    - 0.0125
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--max_mean"
    description: "If n_top_features is defined, this and all other cutoffs for the\
      \ means and the normalized dispersions are ignored. Ignored if flavor='seurat_v3'."
    info: null
    default:
    - 3.0
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--min_disp"
    description: "If n_top_features is defined, this and all other cutoffs for the\
      \ means and the normalized dispersions are ignored. Ignored if flavor='seurat_v3'."
    info: null
    default:
    - 0.5
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--max_disp"
    description: "If n_top_features is defined, this and all other cutoffs for the\
      \ means and the normalized dispersions are ignored. Ignored if flavor='seurat_v3'.\
      \ Default is +inf."
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--span"
    description: "The fraction of the data (cells) used when estimating the variance\
      \ in the loess model fit if flavor='seurat_v3'."
    info: null
    default:
    - 0.3
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--n_bins"
    description: "Number of bins for binning the mean feature expression. Normalization\
      \ is done with respect to each bin. If just a single feature falls into a bin,\
      \ the normalized dispersion is artificially set to 1."
    info: null
    default:
    - 20
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--obs_batch_key"
    description: "If specified, highly-variable features are selected within each\
      \ batch separately and merged. This simple \nprocess avoids the selection of\
      \ batch-specific features and acts as a lightweight batch correction method.\
      \ \nFor all flavors, features are first sorted by how many batches they are\
      \ a HVG. For dispersion-based flavors \nties are broken by normalized dispersion.\
      \ If flavor = 'seurat_v3', ties are broken by the median (across\nbatches) rank\
      \ based on within-batch normalized variance.\n"
    info: null
    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: "Annotate highly variable features [Satija15] [Zheng17] [Stuart19].\n\
  \nExpects logarithmized data, except when flavor='seurat_v3' in which count data\
  \ is expected.\n\nDepending on flavor, this reproduces the R-implementations of\
  \ Seurat [Satija15], Cell Ranger [Zheng17], and Seurat v3 [Stuart19].\n\nFor the\
  \ dispersion-based methods ([Satija15] and [Zheng17]), the normalized dispersion\
  \ is obtained by scaling with the mean and standard deviation of the dispersions\
  \ for features falling into a given bin for mean expression of features. This means\
  \ that for each bin of mean expression, highly variable features are selected.\n\
  \nFor [Stuart19], a normalized variance for each feature is computed. First, the\
  \ data are standardized (i.e., z-score normalization per feature) with a regularized\
  \ standard deviation. Next, the normalized variance is computed as the variance\
  \ of each feature after the transformation. Features are ranked by the normalized\
  \ variance.\n"
test_resources:
- type: "python_script"
  path: "test.py"
  is_executable: true
- 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:
    - "singlecpu"
    - "lowmem"
    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"
  target_registry: "images.viash-hub.com"
  target_tag: "fix-integration-tests"
  namespace_separator: "/"
  setup:
  - type: "python"
    user: false
    packages:
    - "anndata==0.10.8"
    - "mudata~=0.2.4"
    - "pandas!=2.1.2"
    - "numpy<2.0.0"
    - "scanpy~=1.9.6"
    - "scikit-misc"
    upgrade: true
  test_setup:
  - type: "python"
    user: false
    packages:
    - "viashpy==0.8.0"
    upgrade: true
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/feature_annotation/highly_variable_features_scanpy/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/feature_annotation/highly_variable_features_scanpy"
  executable: "target/executable/feature_annotation/highly_variable_features_scanpy/highly_variable_features_scanpy"
  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"