htrnaseq/target/executable/eset/create_pdata/.config.vsh.yaml

name: "create_pdata"
namespace: "eset"
version: "main"
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: "Marijke Van Moerbeke"
  roles:
  - "contributor"
  info:
    links:
      github: "mvanmoerbeke"
      orcid: "0000-0002-3097-5621"
      linkedin: "marijke-van-moerbeke-84303a34"
    organizations:
    - name: "OpenAnalytics"
      href: "https://www.openanalytics.eu"
      role: "Statistical Consultant"
argument_groups:
- name: "Arguments"
  arguments:
  - type: "file"
    name: "--star_stats_file"
    description: "Tab-delimited text file containing statistics (per column) that\
      \ were generated\nfrom the STAR log files (Log.final.out, Summary.csv, ReadsPerGene.out.tab).\n\
      Each entry (row) in the file describes the values for one well (barcode).\n"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--nrReadsNrGenesPerChromPool"
    description: "Pivot table in tsv format of the combined nrReadsNrGenesPerChrom\
      \ files from STAR. \nDescribes per chromosome (as columns) the number of reads,\
      \ as well as the total number \nof reads per cell barcode and the percentage\
      \ of nuclear, ERCC and mitochondrial\nreads.\n"
    info: null
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "file"
    name: "--output"
    info: null
    default:
    - "pData.$id.txt"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
resources:
- type: "python_script"
  path: "create_pdata.py"
  is_executable: true
- type: "file"
  path: "nextflow_labels.config"
  dest: "nextflow_labels.config"
description: "Create a pdata file by combining the mapping statistics \n"
test_resources:
- type: "python_script"
  path: "test.py"
  is_executable: true
- type: "file"
  path: "nrReadsNrGenesPerChromPool.txt"
- type: "file"
  path: "starLogs.txt"
info: null
status: "enabled"
requirements:
  commands:
  - "ps"
license: "MIT"
links:
  repository: "https://github.com/viash-hub/htrnaseq"
runners:
- type: "executable"
  id: "executable"
  docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
  id: "nextflow"
  directives:
    tag: "$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: "python:3.12-slim"
  target_registry: "images.viash-hub.com"
  target_tag: "main"
  namespace_separator: "/"
  setup:
  - type: "apt"
    packages:
    - "procps"
    interactive: false
  - type: "python"
    user: false
    packages:
    - "pandas"
    upgrade: true
  test_setup:
  - type: "python"
    user: false
    packages:
    - "viashpy"
    upgrade: true
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/eset/create_pdata/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/eset/create_pdata"
  executable: "target/executable/eset/create_pdata/create_pdata"
  viash_version: "0.9.0"
  git_commit: "bd5b2d41718677ee367d3829447241df9733c8d3"
  git_remote: "https://github.com/viash-hub/htrnaseq"
package_config:
  name: "htrnaseq"
  version: "main"
  description: "High-throughput pipeline [WIP]\n"
  info:
    test_resources:
    - path: "gs://viash-hub-test-data/htrnaseq/v1/"
      dest: "resources_test"
  viash_version: "0.9.0"
  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"
  - ".engines += { type: \"native\" }"
  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
  - ".engines[.type == 'docker'].target_tag := 'main'"
  keywords:
  - "bioinformatics"
  - "sequence"
  - "high-throughput"
  - "mapping"
  - "counting"
  - "pipeline"
  license: "MIT"
  organization: "vsh"
  links:
    repository: "https://github.com/viash-hub/htrnaseq"
    issue_tracker: "https://github.com/viash-hub/htrnaseq/issues"