configuration_example.yml

# YAML Configuration Filename: configuration.yml
input_parameters:
  # List of NCBI accession numbers.
  accession_numbers:
    - NC_055061.1
    - JX869059.2

  # Path to the local directory where the genome files (in FASTA or GenBank format) are stored.
  genomes_path: "C:/Users/username/Project/Genomes"

  # Type of execution: "parallel" to run tasks concurrently, "serial" to run tasks sequentially.
  execution_type: "parallel"

output_parameters:
  # Name of the  output file name (without extension).
  output_file_name: "phylo_results"

operational_parameters:
  # Directory where temporary files and intermediate results will be stored during execution.
  working_path: "C:/Users/username/Project/WorkingDirectory"

  # Whether to delete the contents of the working directory after the run.
  # Set to true to keep the folder clean.
  erase_working_folder: True

algorithm_parameters:
  # Distance formula used in the GBDP calculation.
  # Common options: "d0", "d4" or "d6".
  distance_formula: "d6"

  # Number of bootstrap replicates to perform for tree support values.
  # Set to 0 to skip bootstrapping.
  bootstrap_replicates: 0

tree_parameters:
  # Whether to generate a phylogenetic tree from the distance matrix.
  generate_tree: True

  # Whether to root the resulting phylogenetic tree.
  root_tree: False

  # Whether to use accession numbers as leaf names in the tree.
  # If false, genome names will be used.
  accession_name: False

  # Whether to generate a graphical image of the tree (PNG).
  generate_image: False

BLAST_parameters:
  # E-value threshold for BLAST hits.
  e_value: 0.001

  # Word size for BLAST alignment. 
  # Recomendation: 3 for nucleotides.
  word_size: 3

  # Set to 0 to disable filtering by positives; 1 to activate.
  positives: 0

entrez_parameters:
  # Email address used for Entrez queries (required by NCBI).
  user_email: "user@example.com"