htrnaseq/target/nextflow/workflows/runner/.config.vsh.yaml

name: "runner"
namespace: "workflows"
version: "main"
argument_groups:
- name: "Input arguments"
  arguments:
  - type: "file"
    name: "--input"
    description: "Base directory of the form `s3:/<bucket>/Sequencing/<Sequencer>/<RunID>/<demultiplex_dir>`.\n\
      Must contains FASTQ files in the format `PoolName_S*_L*_R1_001.fastq.gz` where\n\
      \  * PoolName is a unique ID for the microwell plates or combination thereof.\n\
      \  * S followed by a running number: the sample number based on the order\n\
      \    that samples are listed in the sample sheet (that was used to demultiplex\
      \ the pools)\n    starting with 1 (e.g. S1)\n  * (Optional) the lane number\
      \ (e.g. L001)\n  * _001 fixed suffix.\n"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--barcodesFasta"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--genomeDir"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--annotation"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--pools"
    description: "Filter the FASTQ files in the input directory to only include pools\
      \ from the provided list.\nPool names are inferred from the FASTQ file names\
      \ (see input argument for more information).\nBy default all pools are included.\n"
    info: null
    required: false
    direction: "input"
    multiple: true
    multiple_sep: ";"
  - type: "integer"
    name: "--umi_length"
    description: "Length of the UMI sequences\n"
    info: null
    default:
    - 10
    required: false
    min: 1
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Metadata arguments"
  arguments:
  - type: "string"
    name: "--id"
    description: "Unique identifier for the run"
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--project_id"
    description: "Project ID"
    info: null
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--experiment_id"
    description: "Experiment ID"
    info: null
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Publish arguments"
  arguments:
  - type: "string"
    name: "--fastq_publish_dir"
    info: null
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--results_publish_dir"
    info: null
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Output arguments"
  description: "Parameters that determine the structure of the output. These parameters\
    \ are provided for internal use only\nand their defaults should not be overwritten.\n"
  arguments:
  - type: "file"
    name: "--run_params"
    info: null
    default:
    - "params.yaml"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--star_output_dir"
    info: null
    default:
    - "star_output"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--nrReadsNrGenesPerChrom_dir"
    info: null
    default:
    - "nrReadsNrGenesPerChrom"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--star_qc_metrics_dir"
    info: null
    default:
    - "starLogs"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--eset_dir"
    info: null
    default:
    - "esets"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--f_data_dir"
    info: null
    default:
    - "fData"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--p_data_dir"
    info: null
    default:
    - "pData"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
resources:
- type: "nextflow_script"
  path: "main.nf"
  is_executable: true
  entrypoint: "run_wf"
- type: "file"
  path: "disable_publishfiles_process.config"
- type: "file"
  path: "nextflow_labels.config"
  dest: "nextflow_labels.config"
- type: "file"
  path: "_viash.yaml"
  dest: "_viash.yaml"
description: "Runner for HT RNA-seq pipeline"
test_resources:
- type: "nextflow_script"
  path: "test.nf"
  is_executable: true
  entrypoint: "test_wf"
- type: "nextflow_script"
  path: "test.nf"
  is_executable: true
  entrypoint: "test_wf_with_lanes"
- type: "nextflow_script"
  path: "test.nf"
  is_executable: true
  entrypoint: "test_wf_only_one_eset"
info: null
status: "enabled"
scope:
  image: "public"
  target: "public"
requirements:
  commands:
  - "ps"
dependencies:
- name: "utils/listInputDir"
  repository:
    type: "local"
- name: "workflows/htrnaseq"
  repository:
    type: "local"
- name: "io/publish_fastqs"
  repository:
    type: "local"
- name: "io/publish_results"
  repository:
    type: "local"
- name: "utils/save_params"
  repository:
    type: "local"
license: "MIT"
links:
  repository: "https://github.com/viash-hub/htrnaseq"
runners:
- 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(\"disable_publishfiles_process.config\")"
    - "includeConfig(\"nextflow_labels.config\")"
  debug: false
  container: "docker"
engines:
- type: "native"
  id: "native"
- type: "native"
  id: "native"
build_info:
  config: "src/workflows/runner/config.vsh.yaml"
  runner: "nextflow"
  engine: "native|native"
  output: "target/nextflow/workflows/runner"
  executable: "target/nextflow/workflows/runner/main.nf"
  viash_version: "0.9.4"
  git_commit: "5d5edb788838401c29a4de50b74bb75d5bce6b98"
  git_remote: "https://github.com/viash-hub/htrnaseq"
  dependencies:
  - "target/nextflow/utils/listInputDir"
  - "target/nextflow/workflows/htrnaseq"
  - "target/nextflow/io/publish_fastqs"
  - "target/nextflow/io/publish_results"
  - "target/nextflow/utils/save_params"
package_config:
  name: "htrnaseq"
  version: "main"
  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/v2"
      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 := 'main'"
  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"