craftbox/target/executable/csv2fasta/.config.vsh.yaml

name: "csv2fasta"
version: "update_concat_text"
authors:
- name: "Dries Schaumont"
  roles:
  - "author"
  - "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: "Robrecht Cannoodt"
  roles:
  - "reviewer"
  info:
    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"
argument_groups:
- name: "Inputs"
  arguments:
  - type: "file"
    name: "--input"
    description: "CSV file to be processed."
    info: null
    example:
    - "barcodes.csv"
    must_exist: true
    create_parent: true
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "boolean_true"
    name: "--header"
    description: "Parse the first line of the CSV file as a header.\n"
    info: null
    direction: "input"
- name: "CSV dialect options"
  description: "Options that can be used to override the automatically detected\n\
    dialect of the CSV file.\n"
  arguments:
  - type: "string"
    name: "--delimiter"
    description: "Overwrite the column delimiter character.\n"
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--quote_character"
    description: "Overwrite the character used to denote the start and end of a quoted\
      \ item.\n"
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "CSV column arguments"
  description: "Parameters for the selection of columns from the CSV file.\nOnly required\
    \ when your CSV file contains more than 2 columns,\notherwise the first column\
    \ will be used for the FASTA header\nand the second for the FASTA nucleotide sequences.\
    \ This default\ncan still be overwritten by using the options below.\n"
  arguments:
  - type: "string"
    name: "--sequence_column"
    description: "Name of the column containing the sequences. Implies 'header'.\n\
      Cannot be used together with 'sequence_column_index'.\n"
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--name_column"
    description: "Name of the column describing the FASTA headers. Implies 'header'.\n\
      Cannot be used together with 'name_column_index'.\n"
    info: null
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--sequence_column_index"
    description: "Index of the column to use as the FASTA sequences, counter from\
      \ the left and\nstarting from 0. Cannot be used in combination with the 'sequence_column'\
      \ argument.\n"
    info: null
    required: false
    min: 0
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--name_column_index"
    description: "Index of the column to use as the FASTA headers, counter from the\
      \ left and\nstarting from 0. Cannot be used in combination with 'name_column'.\n"
    info: null
    required: false
    min: 0
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Outputs"
  arguments:
  - type: "file"
    name: "--output"
    description: "Output fasta file."
    info: null
    example:
    - "barcodes.fasta"
    must_exist: true
    create_parent: true
    required: false
    direction: "output"
    multiple: false
    multiple_sep: ";"
resources:
- type: "python_script"
  path: "script.py"
  is_executable: true
summary: "Convert a CSV file to FASTA entries"
description: "Convert two columns from a CSV file to FASTA entries. The CSV file can\n\
  contain an optional header and each row (other than the header) becomes\na single\
  \ FASTA record. One of the two columns will be used as the names\nfor the FASTA\
  \ entries, while the other become the sequences. The sequences\ncolumn must only\
  \ contain characters that are valid IUPAC notation for \nnucleotides or a group\
  \ thereof (wildcard characters).\n"
test_resources:
- type: "python_script"
  path: "test_csv2fasta.py"
  is_executable: true
info: null
status: "enabled"
scope:
  image: "public"
  target: "public"
requirements:
  commands:
  - "ps"
license: "MIT"
links:
  repository: "https://github.com/viash-hub/craftbox"
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"
  debug: false
  container: "docker"
engines:
- type: "docker"
  id: "docker"
  image: "python:slim"
  target_registry: "images.viash-hub.com"
  target_tag: "update_concat_text"
  namespace_separator: "/"
  setup:
  - type: "apt"
    packages:
    - "procps"
    interactive: false
  - type: "python"
    user: false
    packages:
    - "dnaio"
    upgrade: true
  test_setup:
  - type: "python"
    user: false
    packages:
    - "pytest"
    - "viashpy"
    upgrade: true
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/csv2fasta/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/csv2fasta"
  executable: "target/executable/csv2fasta/csv2fasta"
  viash_version: "0.9.4"
  git_commit: "bc2a5a1d99c9fa2657d8d351c447794107540697"
  git_remote: "https://github.com/viash-hub/craftbox"
  git_tag: "v0.1.0-8-gbc2a5a1"
package_config:
  name: "craftbox"
  version: "update_concat_text"
  summary: "A collection of custom-tailored scripts and applied utilities built with\
    \ Viash.\n"
  description: "`craftbox` is a curated collection of custom scripts and utilities\
    \ designed to tackle context-specific tasks.\n\nEmphasizing the Viash principles,\
    \ `craftbox` components aim for **reusability**, **reproducibility**, and adherence\
    \ to **best practices**. Key features generally include:\n\n* **Standalone & Nextflow\
    \ Ready:** Components are built to run directly via the command line or be smoothly\
    \ integrated into Nextflow workflows.\n* **Custom Implementations:** Contains\
    \ scripts and tools developed for particular tasks that may not be found in broader\
    \ collections.\n* **High Quality Standards (promoted by Viash):**\n    * Clear\
    \ documentation for components and their parameters.\n    * Full exposure of underlying\
    \ script/tool arguments for fine-grained control.\n    * Containerized (Docker)\
    \ to ensure dependency management and a consistent, reproducible runtime environment.\n\
    \    * Unit tested where applicable to ensure components function as expected.\n"
  info: null
  viash_version: "0.9.4"
  source: "src"
  target: "target"
  config_mods:
  - ".requirements.commands := ['ps']\n"
  - ".engines += { type: \"native\" }"
  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
  - ".engines[.type == 'docker'].target_tag := 'update_concat_text'"
  keywords:
  - "scripts"
  - "custom"
  - "implementations"
  - "utilities"
  license: "MIT"
  organization: "vsh"
  links:
    repository: "https://github.com/viash-hub/craftbox"
    issue_tracker: "https://github.com/viash-hub/craftbox/issues"