openpipeline/target/executable/reference/make_reference/.config.vsh.yaml

name: "make_reference"
namespace: "reference"
version: "fix-integration-tests"
authors:
- name: "Angela Oliveira Pisco"
  roles:
  - "author"
  info:
    role: "Contributor"
    links:
      github: "aopisco"
      orcid: "0000-0003-0142-2355"
      linkedin: "aopisco"
    organizations:
    - name: "Insitro"
      href: "https://insitro.com"
      role: "Director of Computational Biology"
    - name: "Open Problems"
      href: "https://openproblems.bio"
      role: "Core Member"
- name: "Robrecht Cannoodt"
  roles:
  - "author"
  - "maintainer"
  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: "--genome_fasta"
    description: "Reference genome fasta. Example: "
    info: null
    example:
    - "genome_fasta.fa.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--transcriptome_gtf"
    description: "Reference transcriptome annotation."
    info: null
    example:
    - "transcriptome.gtf.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--ercc"
    description: "ERCC sequence and annotation file."
    info: null
    example:
    - "ercc.zip"
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--subset_regex"
    description: "Will subset the reference chromosomes using the given regex."
    info: null
    example:
    - "(ERCC-00002|chr1)"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--output_fasta"
    description: "Output genome sequence fasta."
    info: null
    example:
    - "genome_sequence.fa.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--output_gtf"
    description: "Output transcriptome annotation gtf."
    info: null
    example:
    - "transcriptome_annotation.gtf.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "output"
    multiple: false
    multiple_sep: ";"
resources:
- type: "bash_script"
  path: "script.sh"
  is_executable: true
- type: "file"
  path: "nextflow_labels.config"
  dest: "nextflow_labels.config"
description: "Preprocess and build a transcriptome reference.\n\nExample input files\
  \ are:\n  - `genome_fasta`: https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_41/GRCh38.primary_assembly.genome.fa.gz\n\
  \  - `transcriptome_gtf`: https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_41/gencode.v41.annotation.gtf.gz\n\
  \  - `ercc`: https://assets.thermofisher.com/TFS-Assets/LSG/manuals/ERCC92.zip\n"
test_resources:
- type: "bash_script"
  path: "test.sh"
  is_executable: true
- 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: "ubuntu:22.04"
  target_registry: "images.viash-hub.com"
  target_tag: "fix-integration-tests"
  namespace_separator: "/"
  setup:
  - type: "apt"
    packages:
    - "pigz"
    - "seqkit"
    - "curl"
    - "wget"
    - "unzip"
    - "file"
    interactive: false
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/reference/make_reference/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/reference/make_reference"
  executable: "target/executable/reference/make_reference/make_reference"
  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"