openpipeline/target/executable/dataflow/concatenate_h5mu/.config.vsh.yaml

name: "concatenate_h5mu"
namespace: "dataflow"
version: "fix-integration-tests"
authors:
- name: "Dries Schaumont"
  roles:
  - "maintainer"
  info:
    role: "Core Team Member"
    links:
      email: "dries@data-intuitive.com"
      github: "DriesSchaumont"
      orcid: "0000-0002-4389-0440"
      linkedin: "dries-schaumont"
    organizations:
    - name: "Data Intuitive"
      href: "https://www.data-intuitive.com"
      role: "Data Scientist"
argument_groups:
- name: "Arguments"
  arguments:
  - type: "file"
    name: "--input"
    alternatives:
    - "-i"
    description: "Paths to the different samples to be concatenated."
    info: null
    example:
    - "sample_paths"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: true
    multiple_sep: ";"
  - type: "string"
    name: "--input_id"
    description: "Names of the different samples that have to be concatenated.  Must\
      \ be specified when using '--mode move'.\nIn this case, the ids will be used\
      \ for the columns names of the dataframes registring the conflicts.\nIf specified,\
      \ must be of same length as `--input`.\n"
    info: null
    required: false
    direction: "input"
    multiple: true
    multiple_sep: ";"
  - type: "file"
    name: "--output"
    alternatives:
    - "-o"
    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: "--obs_sample_name"
    description: "Name of the .obs key under which to add the sample names."
    info: null
    default:
    - "sample_id"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--other_axis_mode"
    description: "How to handle the merging of other axis (var, obs, ...).\n\n  -\
      \ None: keep no data\n  - same: only keep elements of the matrices which are\
      \ the same in each of the samples\n  - unique: only keep elements for which\
      \ there is only 1 possible value (1 value that can occur in multiple samples)\n\
      \  - first: keep the annotation from the first sample\n  - only: keep elements\
      \ that show up in only one of the objects (1 unique element in only 1 sample)\n\
      \  - move: identical to 'same', but moving the conflicting values to .varm or\
      \ .obsm\n"
    info: null
    default:
    - "move"
    required: false
    choices:
    - "same"
    - "unique"
    - "first"
    - "only"
    - "concat"
    - "move"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--uns_merge_mode"
    description: "How to handle the merging of .uns across modalities\n  - None: keep\
      \ no data\n  - same: only keep elements of the matrices which are the same in\
      \ each of the samples\n  - unique: only keep elements for which there is only\
      \ 1 possible value (1 value that can occur in multiple samples)\n  - first:\
      \ keep the annotation from the first sample\n  - only: keep elements that show\
      \ up in only one of the objects (1 unique element in only 1 sample)\n  - make_unique:\
      \ identical to 'unique', but keys which are not unique are made unique by prefixing\
      \ them with the sample id.\n"
    info: null
    default:
    - "make_unique"
    required: false
    choices:
    - "same"
    - "unique"
    - "first"
    - "only"
    - "make_unique"
    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: "Concatenate observations from samples in several (uni- and/or multi-modal)\
  \ MuData files into a single file.\n"
test_resources:
- type: "python_script"
  path: "test.py"
  is_executable: true
- type: "file"
  path: "e18_mouse_brain_fresh_5k_filtered_feature_bc_matrix_subset_unique_obs.h5mu"
- type: "file"
  path: "human_brain_3k_filtered_feature_bc_matrix_subset_unique_obs.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:
    label:
    - "midcpu"
    - "highmem"
    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:3.11-slim"
  target_registry: "images.viash-hub.com"
  target_tag: "fix-integration-tests"
  namespace_separator: "/"
  setup:
  - type: "apt"
    packages:
    - "procps"
    interactive: false
  - type: "python"
    user: false
    packages:
    - "anndata==0.10.8"
    - "mudata~=0.2.4"
    - "pandas!=2.1.2"
    - "numpy<2.0.0"
    - "pandas~=2.1.1"
    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
  - type: "python"
    user: false
    packages:
    - "viashpy==0.8.0"
    upgrade: true
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/dataflow/concatenate_h5mu/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/dataflow/concatenate_h5mu"
  executable: "target/executable/dataflow/concatenate_h5mu/concatenate_h5mu"
  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"