name: "parallel_map"
version: "non_alphanumerical_sample_names"
authors:
- name: "Dries Schaumont"
  roles:
  - "maintainer"
  info:
    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"
- name: "Toni Verbeiren"
  roles:
  - "author"
  - "maintainer"
  info:
    role: "Core Team Member"
    links:
      github: "tverbeiren"
      linkedin: "verbeiren"
    organizations:
    - name: "Data Intuitive"
      href: "https://www.data-intuitive.com"
      role: "Data Scientist and CEO"
argument_groups:
- name: "Input arguments"
  arguments:
  - type: "file"
    name: "--input_r1"
    description: "Input FASTQ files for the forward reads. All FASTQ file names must\
      \ start with the prefix '{well_id}_R1', where\n'well_id' can be found as the\
      \ sequence identifier in the barcodes FASTA file (see 'barcodesFasta' argument).\n\
      For each FASTQ file, a matching FASTQ file for the reverse reads must be provided\
      \ to the 'input_r2' argument,\nmeaning that their 'well_id' prefix must match.\
      \ The number of items provided for 'input_r1' must be equal\nto the number of\
      \ items for 'input_r2'.\n"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: true
    multiple_sep: ";"
  - type: "file"
    name: "--input_r2"
    description: "Input FASTQ files for the reverse reads. All FASTQ file names must\
      \ start with the prefix '{well_id}_R2', where\n'well_id' can be found as the\
      \ sequence identifier in the barcodes FASTA file (see 'barcodesFasta' argument).\n\
      For each FASTQ file, a matching FASTQ file for the reverse reads must be provided\
      \ to the 'input_r1' argument,\nmeaning that their 'well_id' prefix must match.\
      \ The number of items provided for 'input_r1' must be equal\nto the number of\
      \ items for 'input_r2'.\n"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: true
    multiple_sep: ";"
  - type: "file"
    name: "--genomeDir"
    description: "Reference genome to match to. Can be generated from genomic FASTA\
      \ sequences and a genome annotation\nby using STAR with '--runMode genomeGenerate'.\n"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--barcodesFasta"
    description: "FASTA file where each entry specifies a unique barcode sequence\
      \ present at the start of the forward input reads\n(input_r1). The IDs of each\
      \ barcode (the start of the FASTA headers up until the first whitespace character)\
      \ must\nmatch with the start of one input FASTQ pair.\n"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Barcode arguments"
  arguments:
  - type: "integer"
    name: "--umiLength"
    description: "Length of the Unique Molecular Identifiers (UMI). The UMI are expected\
      \ to be located after the barcodes in the\nforwards reads.\n"
    info: null
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--limitBAMsortRAM"
    info: null
    default:
    - "10000000000"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Runtime arguments"
  arguments:
  - type: "integer"
    name: "--runThreadN"
    description: "Number of threads to use for a single STAR execution."
    info: null
    default:
    - 1
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Output arguments"
  arguments:
  - type: "file"
    name: "--output"
    description: "A list of output folders which are the result of using STAR to map\
      \ each input FASTQ pair STAR to the reference genome.\nThe order of the items\
      \ DO NOT match with the order of the entries in the barcodes FASTA file or the\
      \ input FASTQ pairs. \n"
    info: null
    default:
    - "./*"
    must_exist: true
    create_parent: true
    required: true
    direction: "output"
    multiple: true
    multiple_sep: ";"
  - type: "file"
    name: "--joblog"
    description: "Where to store the log file listing all the jobs."
    info: null
    default:
    - "execution_log.txt"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
resources:
- type: "bash_script"
  path: "script.sh"
  is_executable: true
- type: "file"
  path: "STAR"
- type: "file"
  path: "nextflow_labels.config"
  dest: "nextflow_labels.config"
- type: "file"
  path: "_viash.yaml"
  dest: "_viash.yaml"
description: "Map wells in batch, using STAR\nSpliced Transcripts Alignment to a Reference\
  \ (C) Alexander Dobin\nhttps://github.com/alexdobin/STAR\n"
test_resources:
- type: "bash_script"
  path: "test.sh"
  is_executable: true
info: null
status: "enabled"
scope:
  image: "public"
  target: "public"
requirements:
  commands:
  - "ps"
license: "MIT"
links:
  repository: "https://github.com/viash-hub/htrnaseq"
runners:
- type: "executable"
  id: "executable"
  docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
  id: "nextflow"
  directives:
    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: "debian:stable-slim"
  target_registry: "images.viash-hub.com"
  target_tag: "non_alphanumerical_sample_names"
  namespace_separator: "/"
  setup:
  - type: "apt"
    packages:
    - "procps"
    - "wget"
    - "automake"
    - "make"
    - "gcc"
    - "g++"
    - "zlib1g-dev"
    - "parallel"
    - "file"
    - "seqkit"
    interactive: false
  - type: "docker"
    copy:
    - "STAR /usr/local/bin/$STAR_BINARY"
    build_args:
    - "STAR_V=2.7.6a"
    env:
    - "STAR_SOURCE=\"https://github.com/alexdobin/STAR/archive/refs/tags/$STAR_V.tar.gz\""
    - "STAR_TARGET=\"/app/star-$STAR_V.tar.gz\""
    - "STAR_INSTALL_DIR=\"/app/STAR-$STAR_V\""
    - "STAR_BINARY=STAR"
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/parallel_map/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/parallel_map"
  executable: "target/executable/parallel_map/parallel_map"
  viash_version: "0.9.4"
  git_commit: "61bdd2eff7622d9d8626e9a3514b832d89dcf2f2"
  git_remote: "https://github.com/viash-hub/htrnaseq"
  git_tag: "v0.7.2-14-g61bdd2e"
package_config:
  name: "htrnaseq"
  version: "non_alphanumerical_sample_names"
  summary: "A workflow for high-throughput RNA-seq data analyses.\n"
  description: "This workflow is designed to process high-throughput RNA-seq data,\
    \ where every\nwell of a microarray plate is a sample. A fasta file provided as\
    \ input\ndefines the mapping between sample barcodes and wells.\n\nThe workflow\
    \ is built in a modular fashion, where most of the base functionality\nis provided\
    \ by components from [`biobox`](https://www.viash-hub.com/packages/biobox/latest)\n\
    supplemented by custom base components and workflow components in this package.\n\
    \nThe full workflow is split in two major subworkflows that can be run independently:\n\
    \n* **Well-demultiplexing:** Split the input (plate/pool level) fastq files per\
    \ well.\n* **Mapping, counting and QC:** Run per-well mapping, counting and generate\
    \ QC reports.\n\nEach of those can be started individually, or the full workflow\
    \ can be run in two ways:\n\n1. Run the [main workflow](https://www.viash-hub.com/packages/htrnaseq/v0.3.0/components/workflows/htrnaseq)\
    \ \ncontaining the main functionality.\n2. Run the [(opinionated) `runner`](https://www.viash-hub.com/packages/htrnaseq/v0.3.0/components/workflows/runner)\
    \ where a\nnumber of choices (input/output structure and location) have been made.\n\
    \nInput for the workflow has to be `fastq` files (zipped or not). For bcl or other\
    \ formats, please consider running\n[demultiplex](https://www.viash-hub.com/packages/demultiplex)\
    \ first.\n"
  info:
    test_resources:
    - path: "gs://viash-hub-resources/htrnaseq/v1"
      dest: "resources_test"
  viash_version: "0.9.4"
  source: "src"
  target: "target"
  config_mods:
  - ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].config.script\
    \ := 'includeConfig(\"nextflow_labels.config\")'\n.resources += {path: '/src/config/labels.config',\
    \ dest: 'nextflow_labels.config'}\n.resources += {path: '/_viash.yaml', dest:\
    \ '_viash.yaml'}\n"
  - ".engines += { type: \"native\" }"
  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
  - ".engines[.type == 'docker'].target_tag := 'non_alphanumerical_sample_names'"
  keywords:
  - "bioinformatics"
  - "sequencing"
  - "high-throughput"
  - "RNAseq"
  - "mapping"
  - "counting"
  - "pipeline"
  - "workflow"
  license: "MIT"
  organization: "vsh"
  links:
    repository: "https://github.com/viash-hub/htrnaseq"
    issue_tracker: "https://github.com/viash-hub/htrnaseq/issues"