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

name: "build_bdrhap_reference"
namespace: "reference"
version: "v4.0.1"
authors:
- 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"
- name: "Weiwei Schultz"
  roles:
  - "contributor"
  info:
    role: "Contributor"
    organizations:
    - name: "Janssen R&D US"
      role: "Associate Director Data Sciences"
argument_groups:
- name: "Inputs"
  arguments:
  - type: "file"
    name: "--genome_fasta"
    description: "Reference genome file in FASTA or FASTA.GZ format. The BD Rhapsody\
      \ Sequencing Analysis Pipeline uses GRCh38 for Human and GRCm39 for Mouse."
    info:
      config_key: "Genome_fasta"
    example:
    - "genome_sequence.fa.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: true
    multiple_sep: ";"
  - type: "file"
    name: "--gtf"
    description: "File path to the transcript annotation files in GTF or GTF.GZ format.\
      \ The Sequence Analysis Pipeline requires the 'gene_name' or \n'gene_id' attribute\
      \ to be set on each gene and exon feature. Gene and exon feature lines must\
      \ have the same attribute, and exons\nmust have a corresponding gene with the\
      \ same value. For TCR/BCR assays, the TCR or BCR gene segments must have the\
      \ 'gene_type' or\n'gene_biotype' attribute set, and the value should begin with\
      \ 'TR' or 'IG', respectively.\n"
    info:
      config_key: "Gtf"
    example:
    - "transcriptome_annotation.gtf.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: true
    multiple_sep: ";"
  - type: "file"
    name: "--extra_sequences"
    description: "File path to additional sequences in FASTA format to use when building\
      \ the STAR index. (e.g. transgenes or CRISPR guide barcodes).\nGTF lines for\
      \ these sequences will be automatically generated and combined with the main\
      \ GTF.\n"
    info:
      config_key: "Extra_sequences"
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: true
    multiple_sep: ";"
- name: "Outputs"
  arguments:
  - type: "file"
    name: "--reference_archive"
    description: "A Compressed archive containing the Reference Genome Index and annotation\
      \ GTF files. This archive is meant to be used as an\ninput in the BD Rhapsody\
      \ Sequencing Analysis Pipeline.\n"
    info: null
    example:
    - "reference.tar.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "output"
    multiple: false
    multiple_sep: ";"
- name: "Arguments"
  arguments:
  - type: "string"
    name: "--mitochondrial_contigs"
    description: "Names of the Mitochondrial contigs in the provided Reference Genome.\
      \ Fragments originating from contigs other than these are\nidentified as 'nuclear\
      \ fragments' in the ATACseq analysis pipeline.\n"
    info:
      config_key: "Mitochondrial_contigs"
    default:
    - "chrM"
    - "chrMT"
    - "M"
    - "MT"
    required: false
    direction: "input"
    multiple: true
    multiple_sep: ";"
  - type: "boolean_true"
    name: "--filtering_off"
    description: "By default the input Transcript Annotation files are filtered based\
      \ on the gene_type/gene_biotype attribute. Only features \nhaving the following\
      \ attribute values are kept:\n\n  - protein_coding\n  - lncRNA \n  - IG_LV_gene\n\
      \  - IG_V_gene\n  - IG_V_pseudogene\n  - IG_D_gene\n  - IG_J_gene\n  - IG_J_pseudogene\n\
      \  - IG_C_gene\n  - IG_C_pseudogene\n  - TR_V_gene\n  - TR_V_pseudogene\n  -\
      \ TR_D_gene\n  - TR_J_gene\n  - TR_J_pseudogene\n  - TR_C_gene\n\n  If you have\
      \ already pre-filtered the input Annotation files and/or wish to turn-off the\
      \ filtering, please set this option to True.\n"
    info:
      config_key: "Filtering_off"
    direction: "input"
  - type: "boolean_true"
    name: "--wta_only_index"
    description: "Build a WTA only index, otherwise builds a WTA + ATAC index."
    info:
      config_key: "Wta_Only"
    direction: "input"
  - type: "string"
    name: "--extra_star_params"
    description: "Additional parameters to pass to STAR when building the genome index.\
      \ Specify exactly like how you would on the command line."
    info:
      config_key: "Extra_STAR_params"
    example:
    - "--limitGenomeGenerateRAM 48000 --genomeSAindexNbases 11"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
resources:
- type: "python_script"
  path: "script.py"
  is_executable: true
- type: "file"
  path: "make_rhap_reference_2.2.1_nodocker.cwl"
- type: "file"
  path: "nextflow_labels.config"
  dest: "nextflow_labels.config"
description: "The Reference Files Generator creates an archive containing Genome Index\n\
  and Transcriptome annotation files needed for the BD Rhapsody Sequencing\nAnalysis\
  \ Pipeline. The app takes as input one or more FASTA and GTF files\nand produces\
  \ a compressed archive in the form of a tar.gz file. The \narchive contains:\n \
  \ \n- STAR index\n- Filtered GTF file\n"
test_resources:
- type: "bash_script"
  path: "test.sh"
  is_executable: true
- type: "file"
  path: "reference.fa.gz"
- type: "file"
  path: "reference.gtf.gz"
info: null
status: "enabled"
scope:
  image: "public"
  target: "public"
license: "MIT"
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: "bdgenomics/rhapsody:2.2.1"
  target_registry: "images.viash-hub.com"
  target_tag: "v4.0.1"
  namespace_separator: "/"
  setup:
  - type: "apt"
    packages:
    - "procps"
    - "seqkit"
    interactive: false
  - type: "python"
    user: false
    packages:
    - "cwlref-runner"
    - "cwl-runner"
    upgrade: true
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/reference/build_bdrhap_reference/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/reference/build_bdrhap_reference"
  executable: "target/executable/reference/build_bdrhap_reference/build_bdrhap_reference"
  viash_version: "0.9.4"
  git_commit: "e943ae3d1512ded126303c9481cb554d0dd38c92"
  git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
  name: "openpipeline"
  version: "v4.0.1"
  summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
  description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
    \ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
    \nIn terms of workflows, the following has been made available, but keep in mind\
    \ that\nindividual tools and functionality can be executed as standalone components\
    \ as well.\n\n  * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n\
    \  * Ingestion: Read mapping and generating a count matrix.\n  * Single sample\
    \ processing: cell filtering and doublet detection.\n  * Multisample processing:\
    \ Count transformation, normalization, QC metric calulations.\n  * Integration:\
    \ Clustering, integration and batch correction using single and multimodal methods.\n\
    \  * Downstream analysis workflows\n"
  info:
    test_resources:
    - type: "s3"
      path: "s3://openpipelines-data"
      dest: "resources_test"
    nextflow_labels_ci:
    - path: "src/workflows/utils/labels_ci.config"
      description: "Adds the correct memory and CPU labels when running on the Viash\
        \ Hub CI."
  viash_version: "0.9.4"
  source: "src"
  target: "target"
  config_mods:
  - ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\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 := 'v4.0.1'"
  keywords:
  - "single-cell"
  - "multimodal"
  license: "MIT"
  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"