config.yaml

THREADS: 32
FILTER:
  cutadapt:
    adapter: TGGAATTCTCGG
    # set quality-filter to 0 to deactivate quality filtering (default 20)
    quality-filter: 0
    minimum-adapters-overlap: 5
    minimum-length: 19
    maximum-length: 25
    # extra parameters to be passed on to cutadapt, such as another adapter as shown here:
    extra-params: "-a TCGTATGCCGTC -a AGATCGGAAGAGC"
MAPPING:
  # default
  # -k 1 (default): Report up to <int> valid alignments per read
  # options for mode are "unique" and "multi"
  m: 50 # passed on to bowtie as `bowtie -m <int>`. value as 1 only finds "unique" mappers!
  missmatches: 1 # passed on to bowtie as `bowtie -v <int>`
  reference: "data/index/genome.fa"
  # annotation: "path/to/annotation.gtf"
  # extra_params_bowtie: ""
  extra_params_bowtie: "-a --best --strata"
  # STAR parameters
STAR:
  star_idx_dir: "staridx"
  runMode: "alignReads"
  genomeLoad: "LoadAndKeep"
  outSAMtype: "BAM SortedByCoordinate"
  # outFileNamePrefix: "{sample}."
  alignEndsType: "EndToEnd"
  scoreDelOpen: -10000
  scoreInsOpen: -10000
  alignIntronMax: 1
  outFilterMismatchNmax: 0
  outFilterMultimapNmax: 50
  alignSJDBoverhangMin: 1000
  limitBAMsortRAM: 15000000000
  extra: ""

# Changed the Illumina small RNA sequence used for auto-detection to 'TGGAATTCTCGG' (from formerly 'ATGGAATTCTCG').
# ($nextera){
# $adapter = 'CTGTCTCTTATA';
# $adapter_name = 'Nextera Transposase sequence; user defined';
# }
# elsif($small_rna){
# $adapter = 'TGGAATTCTCGG';
# $adapter_name = 'Illumina small RNA adapter; user defined';
# }
# elsif($illumina){
# $adapter = 'AGATCGGAAGAGC';
# $adapter_name = 'Illumina TruSeq, Sanger iPCR; user defined';
#
# update:
# This adapter was found in some GEO dataset manually, but unsure about which protocol this is been used for:
# TCGTATGCCGTC