config.yaml

#-- I/O --#
samples_file: tests/data/Pectobacterium.tsv

# output location
output_dir: tests/output_pecto/

# temporary file directory (your username will be added automatically)
tmp_dir: /ebio/abt3_scratch/

# provide email to get notifications
email: Skip

#-- software parameters --#
# See the README for a description
params:
  ionice: -c 3
  cgp:
    prokka: ""
    mmseqs:
      method: cluster    # or linclust (faster)
      run: --min-seq-id 0.9 -c 0.8
    vsearch: --id 0.94
    core_genes:
      cds: --perc-genomes-cds 100 --copies-per-genome-cds 1 --max-clusters-cds 10 #500
      rRNA: --perc-genomes-rrna 100 --copies-per-genome-rrna 10 --max-clusters-rrna 500
    align:
      method: linsi
      params: --auto --maxiterate 1000
    primer3:
      consensus: --consensus-threshold 0.34
      number: --num-raw-primers 1000 --num-final-primers 10
      size: --opt-size 20 --min-size 18 --max-size 26
      product: --opt-prod-size 150 --min-prod-size 100 --max-prod-size 250
      Tm: --opt-tm 62 --min-tm 54 --max-tm 70 --max-tm-diff 2.5
      PCR: --oligo-DNA 50 --salt-monovalent 50 --salt-divalent 1.5 --dNTPs 0.2
      GC: --opt-gc 50 --min-gc 25 --max-gc 75
      degeneracy: --max-degeneracy 128 --max-degeneracy-3prime 6 --window-3prime 5
      internal_oligo: --make-oligo 0 --int-opt-size 20 --int-opt-tm 60
    blast_nontarget:
      run_locally: False
      cds: -evalue 1e-5 -max_target_seqs 30
      rRNA: -evalue 1e-5 -max_target_seqs 30
    blastn: -max_target_seqs 500 -perc_identity 90
    blast_filter: --perc-len 80 --min-amplicon-len 30 --max-amplicon-len 2000
    seqkit_amplicon: ""

#-- database --#
databases:
  blast:
    nucl: /ebio/abt3_projects/databases_no-backup/NCBI_blastdb/nt
    prot: /ebio/abt3_projects/databases_no-backup/NCBI_blastdb/nr
    rRNA:
      SSU: /ebio/abt3_projects/databases_no-backup/NCBI_rRNA/2021-01/SSU/16S_ribosomal_RNA
      LSU: /ebio/abt3_projects/databases_no-backup/NCBI_rRNA/2021-01/LSU/LSU_prokaryote_rRNA
    gene_names: /ebio/abt3_projects/databases_no-backup/NCBI_nr_geneIDs/2021-01/nr_accession-geneNames.pkl
  taxonomy:
    names: /ebio/abt3_projects/databases_no-backup/NCBI_taxonomy/2020-12-23/names.dmp
    nodes: /ebio/abt3_projects/databases_no-backup/NCBI_taxonomy/2020-12-23/nodes.dmp

#-- snakemake pipeline --#
pipeline:
  snakemake_folder: ./
  script_folder: bin/scripts/
  name: CoreGenomePrimers