blank_config.yaml

---
# PathOGiST configuration file.
# This configuration file is in YAML file format, release 1.2 (Third Edition).
# Google yaml for the specification.
# Un-comment example files to use
# Directory to save temporary files.
temp: #tests/integration_tests/temp_dir
# Number of threads on your computer
threads: 1
# Select what tools to run: 1 to run and 0 to not run.
run:
  snippy: 1
  kwip: 1
  prince: 1
  spotyping: 1
  mentalist: 1
# Command line options for tools to genotype your raw reads
genotyping:
  input_reads:
    forward_reads: #/home/usr/forwards.txt
    reverse_reads: #/home/usr/reverse.txt
  mentalist:
    # Choose 1 of the following option for mentalist to obtain a mlst database by selecting 1 and 0 for the others
    db_loc:
      local_file: 0
      build_db: 0
      download_pubmlst: 0
      download_cgmlst: 1
      download_enterobase: 0
    local_file:
      database: #/home/usr/mlst.db
    build_db:
      options:
        ## kmer size
        k:
        ## FASTA files with the MLST scheme
        fasta_files:
        ## profile file for known genotypes
        profile:
    download_pubmlst:
      options:
        ## Kmer size
        k:
        ## Species name or scheme ID
        scheme:
    download_cgmlst:
      options:
        ## Kmer size
        k: 31
        ## Species name or scheme ID
        scheme: 741110
    download_enterobase:
      options:
        ## Kmer size
        k:
        ## Letter identifying which scheme: 
        ## (S)almonella, (Y)ersinia, or (E)scherichia/Shigella
        scheme:
        ## Choose the type: 'cg' or 'wg' for cgMLST or wgMLST, respectively.
        type:
    call:
      options:
        ## Maximum number of mutations when looking for novel alleles 
        mutation_threshold: 6
        ## Minimum number of times a kmer is seen to be considered present in the sample 
        ## (solid)
        kt: 10
      flags:
        ## Outputs the results for the original voting algorithm. 
        #- output_votes
        ## Outputs a FASTA file with the alleles from 'special cases' such as incomplete 
        ## coverage, novel, and multiple alleles. 
        #- output_special
  kwip:
    khmer_options:
      N: 1
      x: 1e9
      # k-mer size to use
      ksize: 31
      # approximate number of unique kmers in the input set
      unique-kmers: 0
    kwip_options:
      #weights:
    kwip_flags:
      #- unweighted
      #- calc_weights
  prince:
    options:
      # VNTR templates. Default is for M.TB
      #templates:
  snippy:
    options:
      # Reference genome. Supports FASTA, GenBank, EMBL (not GFF)
      reference: #/home/usr/ref.fa
      # Minimum read mapping quality to consider
      mapqual: 60
      # Minimum base quality to consider
      basequal: 20
      # Minimum coverage of variant site
      mincov: 10
      # Minimum proportion for variant evidence
      minfrac: 0.9
      # Use this @RG ID: in the bam header
      #rgid:
      # Extra BWA MEM options, e.g. -x pacbio
      #bwaopt:
    flags:
      ## Keep unmapped reads in BAM and write FASTQ.
      #- unmapped
  spotyping:
    options:
      #swift: on
      #min: 5
      #rmin: 6
      #outdir: ./
      #output: SpoTyping
    flags:
      #- seq
      #- noQuery
      #- filter
      #- sorted
# Do not remove the sections 'genotyping', 'distances', 'thresholds', 'all_constraints', or 'output'.
# Remove all key-value pairs in the sections 'calls' or 'distances' if you want them blank.
# Remove all list items in the section 'fine_clusterings' if you want that blank, too.
# Keys from 'genotyping' and 'distances' sections should not overlap.
clustering:
  # Output prefix for final consensus clustering and visualization
  output_prefix: tests/integration_tests/test_data/yersinia_final_clustering
  # Raw genotyping data from which to create distance matrices.
  # Accepted values are paths to text files containing  paths to genotyping files.
  # Currently only compatible with SNPs from snippy, MLSTs from MentaLiST, and CNVs from PRINCE
  genotyping: 
    MLST: #/home/usr/mentalist_calls.txt
    CNV: #/home/usr/prince_calls.txt
    spoligotyping: #/home/usr/spotyping_calls.txt
    SNP: #/home/usr/snippy_calls.txt
  # Bed file to filter snps before distance matrix generation( applies to both existing or newly generated snp calls).
  genotyping_options:
    bed_filter: #/home/usr/filter.bed
  # Paths to pre-constructed distance matrices in tsv format.
  # You can also specify SNP, MLST, spoligotypoing and CNV distance matrices here if you 
  # pre-constructed them, but then they shouldn't appear in the section 'genotyping'.
  distances:
    kWIP: #/home/usr/kwip_dist.tsv
  # The genotyping datatypes that are considered to be the "finest".
  fine_clusterings:
    - SNP
  # Threshold values for performing correlation clustering on genotyping data types given above
  # Every key appearing in the sections 'genotyping' and 'distances' should appear 
  # here with a value. 
  thresholds:
    SNP: 2500
    CNV: 100
    kWIP: 0.4
    MLST: 300
    spoligotyping: 8
  # Use all constraints when performing correlation and consensus clustering
  all_constraints: True
  # Method to use for the clustering algorithm; choices are `C4` or `ILP`
  method: C4
  presolve: True
  # Visualize Clusters; choices are `True` or `False`
  visualize: False
...