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

name: "build_cellranger_arc_reference"
namespace: "reference"
version: "main"
authors:
- name: "Vladimir Shitov"
  roles:
  - "author"
  info:
    role: "Contributor"
    links:
      email: "vladimir.shitov@helmholtz-muenchen.de"
      github: "vladimirshitov"
      orcid: "0000-0002-1960-8812"
      linkedin: "vladimir-shitov-9a659513b"
    organizations:
    - name: "Helmholtz Munich"
      href: "https://www.helmholtz-munich.de"
      role: "PhD Candidate"
argument_groups:
- name: "Arguments"
  arguments:
  - type: "file"
    name: "--genome_fasta"
    description: "Reference genome fasta."
    info: null
    example:
    - "genome_sequence.fa.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--annotation_gtf"
    description: "Reference annotation."
    info: null
    example:
    - "annotation.gtf.gz"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--motifs_file"
    description: "Transcription factor motifs in JASPAR format. See https://support.10xgenomics.com/single-cell-multiome-atac-gex/software/pipelines/latest/advanced/references"
    info: null
    example:
    - "JASPAR2024_CORE_non-redundant_pfms_jaspar.txt.modified"
    must_exist: true
    create_parent: true
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--non_nuclear_contigs"
    description: "Name(s) of contig(s) that do not have any chromatin structure, for\
      \ example, mitochondria or plastids. These contigs are excluded from peak calling\
      \ since the entire contig will be \"open\" due to a lack of chromatin structure.\
      \ Leave empty if there are no such contigs."
    info: null
    example:
    - "chrM"
    default:
    - "chrM"
    required: false
    direction: "input"
    multiple: true
    multiple_sep: ";"
  - type: "file"
    name: "--output"
    description: "Output folder"
    info: null
    example:
    - "cellranger_reference"
    must_exist: true
    create_parent: true
    required: true
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--genome"
    description: "Name of the genome. This will be the name of the intermediate output\
      \ folder"
    info: null
    example:
    - "GRCh38"
    default:
    - "output"
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--organism"
    description: "Name of the organism. This is displayed in the web summary but is\
      \ otherwise not used in the analysis."
    info: null
    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: ";"
resources:
- type: "bash_script"
  path: "script.sh"
  is_executable: true
- type: "file"
  path: "nextflow_labels.config"
  dest: "nextflow_labels.config"
description: "Build a Cell Ranger-arc and -atac compatible reference folder from user-supplied\
  \ genome FASTA and gene GTF files. Creates a new folder named after the genome."
test_resources:
- type: "bash_script"
  path: "test.sh"
  is_executable: true
- type: "file"
  path: "reference_gencodev41_chr1"
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: "ghcr.io/data-intuitive/cellranger_arc:2.0"
  target_registry: "images.viash-hub.com"
  target_tag: "main"
  namespace_separator: "/"
  setup:
  - type: "docker"
    run:
    - "DEBIAN_FRONTEND=noninteractive apt update && \\\napt upgrade -y && apt install\
      \ -y procps pigz && rm -rf /var/lib/apt/lists/*\n"
  test_setup:
  - type: "docker"
  - type: "apt"
    packages:
    - "git"
    - "wget"
    interactive: false
  - type: "docker"
    run:
    - "TARGETARCH=\"${TARGETARCH:-$(dpkg --print-architecture)}\" && \\\nTARGETOS=\"\
      ${TARGETOS:-linux}\" && \\\nPATH=\"${PATH}:/usr/local/go/bin\" && \\\nwget https://go.dev/dl/go1.21.4.$TARGETOS-$TARGETARCH.tar.gz\
      \ && tar -C /usr/local/ -xzf go1.21.4.$TARGETOS-$TARGETARCH.tar.gz && \\\nrm\
      \ go1.21.4.$TARGETOS-$TARGETARCH.tar.gz && \\\ngit clone --branch v2.5.0 https://github.com/shenwei356/seqkit.git\
      \ && \\\ncd seqkit/seqkit/ && go build && cp seqkit /usr/bin/ && cd ../../ &&\
      \ rm -rf seqkit && rm -r /usr/local/go\n"
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/reference/build_cellranger_arc_reference/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/reference/build_cellranger_arc_reference"
  executable: "target/executable/reference/build_cellranger_arc_reference/build_cellranger_arc_reference"
  viash_version: "0.9.4"
  git_commit: "173327cc5670aa8bd5cf473827de80b602c90092"
  git_remote: "https://github.com/openpipelines-bio/openpipeline"
  git_tag: "0.2.0-2055-g173327cc"
package_config:
  name: "openpipeline"
  version: "main"
  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\"\
    )'\n"
  - ".engines += { type: \"native\" }"
  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
  - ".engines[.type == 'docker'].target_tag := 'main'"
  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"