config.example.yaml

# insert project name
project_prefix: exampleproject

#toggle individual components of the workflow on/off
use_metamaps: False
use_kraken_and_bracken: True
use_blast: False
use_amr: False
use_vf: False
use_markergene_alignments: False
use_assembly: False
use_eukaryota_verification: False
use_crassphage_verification: False
use_guttrsnp: False

#db folders are relative to input/databases
db_metamaps: metamaps
db_kraken: kraken #Can get automatically generated if required
db_kraken_flat: full_db.mmi #minimap2 index based on all references used to generate kraken2 database
db_card: card
db_vf: vf/VFDB_setB_nt.fas
db_blast_use_remote: False
db_blast: blast_screenshot_03_08_20_nt/nt #Alternative if no internet access is available or this is not feasible, a local database can be used for BLAST search of unmapped sequences
db_species_level_marker_genes: marker_genes.fa
db_crassphage: crassphage/1556_crAss_like_genome_sequences.fasta
db_eukaryota: eukaryota
db_zymo: zymo/zymo.fasta

#basecalling
guppy_bin_folder: ont-guppy-cpu/bin #Folder containing the guppy executables
guppy_module: Guppy/5.0.7 #Overwrites bin folder
guppy_use_gpu: True

#assembly
flye_genome-size: '1m' # '1g'
prokka_gcode: '4'
prokka_kingdom: Bacteria

#filtering
db_human: 'GRCh38_full-analysis_set_plus_decoy_hla_chm13v2.mmi'

#mapping
bracken_read_length: '100'

#gene
## minimum length of an alignment to be used for gene identification
gene_min_alignment_length: 500
## minimum length of surrounding left or right sequence to be used gene taxon association
gene_min_length_sus: 100
gene_max_n_alignment: 50

#minimap2 verification
mm2_perc_aligned : 0.7 #Percentage of how much of a read needs to align
mm2_perc_identity : 0.7 #How much of the aligned portion needs to agree with the reference
mm2_uniqueness_mq : 5 #Percentage to assign a read specifically to a crassphage

#population level (strain) analysis
guttrsnp_filter_vertical: 10 #Read depth required to consider position for subspecies distance
guttrsnp_filter_horizontal: 0.8 #Vertical coverage required to consider reference covered