example_samplesheet.yaml

# This is an exemplification of the accepted YAML syntax accepted by the bacannot pipeline
#
# The file must contain a header-line with the key "samplesheet:". All the
# input samples must be given nested to this key. Obs: The header-line and
# the nest indentation are REQUIRED.
#
# Each sample must initiate with the key "id:" listed with a "-". This value
# is what will be used as prefix for outputs. The input options (raw reads or
# assembled genomes) must be give right after this key, with the same indent
# without the "-".
#
# The possible inputs are:
#
# (obs: When using both paired and unpaired short reads for the same sample,
# the order: pair1, pair2, unpaired must be followed. Otherwise, just the
# unpaired read or the pairs 1 and 2)
# illumina: (illumina short reads)
#   - pair_1.fq
#   - pair_2.fq
#   - unpaired.fq
#
# nanopore: ont_nanopore.fastq (Oxford nanopore long reads)
# fast5: path/to/fast5_pass (Path to dir containing ONT FAST5s for methylation calling)
# If using an already assembled genome, users may give the nanopore and fast5 data to call methylation
#
# pacbio: pacbio.fastq (Pacbio long reads)
#
# assembly: assembled_genome.fasta (assembled genome)
#
# resfinder: species panel (one of the available resfinder species panels)
#
# Users can give for each sample either the assembled genome or a combination
# of short and long reads (to perform a short reads only, long reads only or
# hybrid assembly of raw reads before annotation)
#
# Obs: the combination of ONT and pacbio reads for the same sample is not supported,
# it must either be one or another.
#
# Obs: The "illumina:" key is the only one the MUST be give in new idented lines
# started by "-". All the others (nanopore, pacbio, assembly, fast5, resfinder)
# must be given right after the ":", without newlines, quotes or signs.
#
# A template (with the correct fields, syntax and indentation) is given below:

samplesheet:
  - id: sample_1
    illumina:
      - sample_1/1.fastq
      - sample_1/2.fastq
    nanopore: sample_1/ont.fastq
    resfinder: Escherichia coli   # this tells the pipeline that this specific sample should be treated as E. coli despite any other default set
  - id: sample_2
    assembly: sample_2/assembly.fasta
    nanopore: sample_2/ont.fastq
    fast5: sample_2/fast5_pass     # will call methylation on assembled genome
  - id: sample_3
    nanopore: sample_3/ont.fastq
    fast5: sample_3/fast5_pass     # will also call methylation flye genome assembly
  - id: sample_4
    pacbio: sample_4/pacbio.fastq
    illumina:
      - sample_4/merged_unpaired.fastq
  - id: sample_5
    illumina:
      - sample_5/1.fastq
      - sample_5/2.fastq
      - sample_5/merged.fastq