example_samplesheet.yml

# This is an exemplification of the accepted YAML syntax accepted by the MpGAP 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 (two white spaces) 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 keys must be given 
# right after this id key, with the same indent without the "-".
#
# Please read the https://mpgap.readthedocs.io/en/latest/samplesheet.html documentation page
# in order to understand how to properly set it up and which are the available/expected keys
#
# A template (with the correct fields, syntax and indentation) is given below:

samplesheet:
- id: sample_1
  illumina:
  - dataset/reads_1.fastq.gz
  - dataset/reads_2.fastq.gz
- id: sample_2
  illumina:
  - dataset/reads_unpaired.fastq.gz
- id: sample_3
  illumina:
  - dataset/reads_1.fastq.gz
  - dataset/reads_2.fastq.gz
  - dataset/pairs_merged.fastq.gz
- id: sample_4
  nanopore: dataset/ont_reads.fastq.gz
  corrected_longreads: true
  nanopolish_fast5: dataset/kleb/fast5_pass
  genome_size: 5.5m
- id: sample_5
  pacbio: dataset/pacbio_reads.fastq.gz
  pacbio_bam: dataset/pacbio_reads.subreads.bam
  wtdbg2_technology: rs
- id: sample_6
  illumina:
  - dataset/reads_1.fastq.gz
  - dataset/reads_2.fastq.gz
  nanopore: dataset/ont_reads.fastq.gz
  hybrid_strategy: both