example_data.yaml

general:
  filename: dna_aeon
  primertable: dna_aeon.csv
  units: units.tsv
  cores: 20
  demultiplexing: false
  read_sorting: false
  already_assembled: false
  paired_End: true
  name_ext: R1
  clustering: true
  in_vivo: false # Using in-vivo data, the data will be blasted against the carrier organism and hits will be discarded, followed by contig assembly using SPAdes

constraint_filtering:
  constraints:
  - homopolymer
  - undesired_subsequences
  - windowed_gc_content
  inplace_repair: false
  maximum_repair_cycles: 100
  repair_quality_score: 33
  repair_after_assembly: true
  use_quality_mapping: true
  after_assembly: true
  primer_length: 20
  sequence_length: 156
  homopolymer:
    count: 4
  windowed_gc_content:
    gc_min: 0.4
    gc_max: 0.6
    window_size: 50
  overall_gc_content:
    gc_min: 0.3
    gc_max: 0.7
  undesired_subsequences:
    file: scripts/constraints/undesired_subsequences.txt
  kmer_counting:
    k: 100
    upper_bound: 20
    active: false

contig_assembly:
        blast_db:
                sinorhizobium: blast_db/mosla_db
                bacillus: blast_db/mosla_db_bacillus

qc:
  threshold: 0.3
  minoverlap: 15
  minqual: 1
  minlen: 100
  maxlen: 165
  primer_offset: false
  mq: 10
  trim_to_length : 180
  barcode_removed: true
  all_primer: false

derep:
  centroid_selection: quality
  clustering_id: 0.97
  clustering: true
  minsize: 1