config.yaml

pipeline_directory: /full/path/to/cloned/repo

# Sample file specifies sample names and names of files containing sample reads
# Format: Tab-delimited, three columns
# sample_name  read1_file  [read2_file]
# if paired end, all samples must be paired end
# if single end, all samples must be single end
# See example (samp_file.txt) in the testing folder
sample_file: /full/path/to/sample/file

# In which directory should results be outputted?
outdir: /full/path/to/output/directory

database: /full/path/to/downloaded/database

# Specifications for step one - classification of metagenomic reads
confidence_threshold: 0.1 # increase to reduce false positives - range from 0-1
gzipped: True # True or False - are the read files gzipped?
class_mem_mb: 32768 # memory in MB - minimum is the size of the Kraken2 database - must be at least 32 GB for the default database
class_threads: 16 # see usage instructions - can increase if you have more threads available; no need to change if you have fewer
single_end_krak: False # change if you would like to use the integrated prophage detection postprocessing script

# Specifications for step two - filtering false positive species
# essentially - what fraction of a viral genome should be covered to consider it a true positive?
cov_thresh_viral: 0.10
# how many unique minimizers should be covered in a viral genome ""?
minimizer_thresh_viral: 0
# same for bacteria
cov_thresh_bacterial: 0.01
minimizer_thresh_bacterial: 0
# archaea, eukaryotes
cov_thresh_arc: 0.01
minimizer_thresh_arc: 0
cov_thresh_euk: 0
minimizer_thresh_euk: 0

# Speciications for step three - per-species abundance estimation
read_length: 150 # if you change this, make sure you have an appropriate Bracken database built for this read length
filter_thresh: 10 # do not assign reads to species X if < this number of reads were classified to it

# Delete intermediate files? Examples in testing/classification/intermediate
delete_intermediate: True # True or False