config.yaml

# path to output directory
output_dir: "/mnt/nfs/bioinfdata/home/NIOO/fleurg/projects/epigbs-snakemake-3.0-final-ref/output-ref"

# input directory where raw reads are
input_dir       : "/mnt/nfs/bioinfdata/home/NIOO/fleurg/epiGBS/data"

# name of sequence read files
Read1 : "RRBS_KD17072296_H53KHCCXY_L5_1.fq.gz"
Read2 : "RRBS_KD17072296_H53KHCCXY_L5_2.fq.gz"

# number of sequencing cycles (the same as read length in Illumina sequencing)
cycles        : 150

# barcode file(barcode file should be kept inside input directory) and enzymes will be included in barcode file
barcodes: "barcodes.tsv"

# the pipeline produces some temporary files. Please indicate the tmp location on your server (in most cases /tmp)
tmpdir        : "/tmp"

# mode of running pipeline (set denovo, reference or legacy. PLEASE NOTE: legacy is not supported)
mode: "reference"

# genome directory (leaave it blank in denovo mode)
ref_dir: "/home/NIOO.INT/fleurg/epiGBS/analysis/output_denovo_test_data"

# genome name (leaave it blank in denovo mode)
genome: "consensus_cluster.renamed.fa"

# advanced users have the possibility to change different parameter, leave them blank or write "default" to run them in default mode

# parameters in the denovo reference creation:
# identity: percentage of sequence identity in the last clustering step, in decimal number e.g. for 95% identity write 0.95, default 0.97
# min-depth: minimal cluster depth in the first clustering step to include a cluster, default 10
# max-depth: maximal cluster depth in the first clustering step to include a cluster, default 10000
param_denovo:
  identity: ""
  min-depth: ""
  max-depth: ""