config.yaml

# path or URL to sample sheet (TSV format, columns: sample, condition, ...)
#samples: samples_sars-cov-2.tsv
# path or URL to sequencing unit sheet (TSV format, columns: sample, unit, fq1, fq2,
# strandedness). Units are technical replicates (e.g. lanes, or resequencing of the
# same biological sample).If the column "strandedness" is present (which is optional),
# can be empty or has one of these values: none, yes or reverse. none is for unstranded
# protocols, yes an reverse follow the nomenclature used in `htseq-count --reverse`
# which is referenced in STAR manual section 7, "Counting number of reads per gene".

units: units.tsv

trimming:
  # skip trimming: false or true
  skip: false
  # the sequencing adapter: Illumina universal
  adapter: AGATCGGAAGAGC
  polya: A{10}N{30} # see cutadapt documentation for this suggestion

ref:
  # fasta (for HISAT2)
  sars_fasta: "/data/rajewsky/genomes/GRCh38_sars-cov-2/GRCh38_sars-cov-2.fa"
  # the STAR index
  star_index: "/data/rajewsky/indices/GRCh38_sars-cov-2_star_2.7.8a_overhang150/GenomeDir"
  # gtf file with transcripts
  annotation: "/data/rajewsky/genomes/GRCh38_sars-cov-2/gencode.v33.annotation_sars-cov-2.gtf"
  bwa_index: "/data/rajewsky/indices/GRCh38_sars-cov-2_bwa_0.7.17/GRCh38_sars-cov-2"
  bowtie_index: "/data/rajewsky/indices/GRCh38_sars-cov-2_bowtie-1.3.0/GRCh38_sars-cov-2_bowtie-1.3.0"

#hisat_dir: "sars2_hisat2_index"
#sars_prefix: SARSCoV2 # also name in the fasta file

pca:
  labels:
    # columns of sample sheet to use for PCA
    - condition

diffexp:
  # contrasts for the deseq2 results method
  contrasts:
    treated-vs-untreated:
      - mock-4h
      - S2-12h

params:
  star: "--genomeLoad LoadAndRemove " # decrease memory on murphy
  cutadapt-se: "--minimum-length 15 -q 20 "
  cutadapt-pe: "--minimum-length 15 -q 20 "
  cutadapt-se-clontech: >- # c.f. /data/rajewsky/coronavirus/sequencing/smallRNA/WHATIDID.sh
    --minimum-length 15 --no-indels --times 1 --action trim --error-rate 0.1 --overlap 4 --quality-cutoff 30
    --quality-base 33 --trim-n --max-n 0 --nextseq-trim 20
  cutadapt-polya: >- # format with wc
    --no-indels --minimum-length 18 --times 1 --action trim --error-rate 0.1
    --overlap 3 --cut 3 --untrimmed-output trimmed/{wc.sample}-{wc.unit}_polya_untrimmed.fastq.gz

snakemake_wrapper_version: "v0.75.0"

runs:
  vis010: "/data/rajewsky/sequencing/human/210709_A00643_0274_BHG3HHDRXY/210709_A00643_0274_BHG3HHDRXY"