input_demo.yaml

# Input file for the automated creation GGA docker stacks
# The file consists in a "list" of species for which the script will have to create these stacks/load data into galaxy/run workflows

ectocarpus_sp2_male:  # Dummy value the user gives to designate the species (isn't used by the script)
  # Species description, leave blank if unknown or you don't want it to be used
  # These parameters are used to set up the various urls and adresses in different containers
  # The script requires at least the genus to be specified
  description:
    genus: "ectocarpus"  # Mandatory!
    species: "sp4"
    sex: "male"
    strain: ""
    common_name: ""
    origin: ""
  # Data files scalars contain paths to the source files that have to be loaded into galaxy
  # WARNING: The paths must be absolute paths!
  # If any path is left blank and the "parent_directory" scalar is specified, this directory and ALL its subdirectories will be
  # scanned for files corresponding to the description provided for the species (i.e if the user specified
  # the sex and strain, the script will look for files containing the genus, species, sex and strain of the species)
  # If no file corresponding to the description is found, this path will be considered empty and the script will
  # proceed to the next step (create the directory tree for the GGA docker stack)
  # If a path is left blank and the "parent_directory" scalar is also blank, no file will be loaded for this "path" scalar
  # If the files are not named using this nomenclature, please provide all the paths in the corresponding scalars below
  data:
    # "parent_directory": (optional) directory from where to search files if a "***_path" scalar is empty
    # NOTE: Try to set a parent directory "close" to the data files so as not to increase runtime
    # If empty (""), the script will not search for files and no dataset will be loaded for the corresponding scalar
    parent_directory: "/path/to/closest/parent/dir"
    # "***_path": path to the file (optional if parent_directory is set and species "description" scalars are precised)
    # TODO Not implemented yet
    genome_path: "/path/to/fasta"
    transcripts_path: "/path/to/fasta"
    proteins_path: "/path/to/fasta"
    gff_path: "/path/to/gff"
    # If the user has several genomes to upload to galaxy, the next scalar is used by the script to differentiate
    # between these different versions and name directories according to it.
    # If left empty, the genome will be considered version "1.0"
    genome_version: "1.0"
    # Same as genome version, but for the analysis
    ogs_version: ""
    performed_by: ""