mapping_config_defaults.yaml

#---------------------------------------- general pipeline parameters
pipeline_param:
  # adjust pattern of stored files
  out_path_pattern: mapping/{step}/{sample}.{mate}/out/{step}.{sample}.{mate}.{extension}
  log_path_pattern: mapping/{step}/{sample}.{mate}/report/{step}.{sample}.{mate}.{extension}
  in_path_pattern: ../input/{sample}/{sample}.{mate}
  
  # adjust which files to produce
  mapping_results:
    - salmon-transcript_counts
    - star-gene_counts
    - ciri-circRNA
  QC_results:
    - fastqc
    - dupradar
    - infer_experiment
    - qualimap_rnaseq
    - qualimap_bamqc
    #- rna_seqc
    - preseq_c_curve
    - preseq_lc_extrap
    #- bw_from_bed
    
  #ATAC_Seq:
  #  - macs2

 
  test_config: true
  report_snippets: ""

#---------------------------------------- organism annotation
organism_defaults: null

#---------------------------------------- parameters for rules
rule_options:
  star: 
    cmd_opt: "--outSAMunmapped Within --outFilterType BySJout --outFilterMultimapNmax 20 --alignSJoverhangMin 8 --alignSJDBoverhangMin 1 --outFilterMismatchNmax 999 --outFilterMismatchNoverLmax 0.04 --alignIntronMin 20 --alignIntronMax 1000000 --alignMatesGapMax 1000000 --genomeLoad NoSharedMemory --outSAMattributes NH HI AS NM MD --outSAMtype BAM Unsorted"
    trim: yes
  star_index: 
    cmd_opt: "--sjdbOverhang 49" # optimally sjdbOverhang = <read_length> - 1
  salmon_index:
    cmd_opt: "-k 31"             # (k the default k-mer size of 31 is suitable for read length around 75)
  salmon: 
    cmd_opt: ""
    trim: yes
  rna_seqc:
    cmd_opt: ""
  ciri:
    cmd_opt: "-low -S 500000"
  bwa:
    cmd_opt: "-T 19"
    trim: yes
    run_stats: yes
  bwa_index:
    cmd_opt: ""
  feature_counts:
    cmd_opt: ""

#---------------------------------------- parameters for the report
report:
  multiqc:
    title: SeA-SnaP mapping pipeline QC report
    subtitle: run at the BIH CUBI
    intro_text: The reports summarises results of several analyses
    custom_logo: documentation/pictures/SeA-SnaP_logo.png
    sp:
      fastqc/zip:
        fn: '*_fastqc.zip'
      qualimap/rnaseq/rnaseq_results:
        fn: '*rnaseq_qc_results.txt'
      qualimap/rnaseq/coverage:
        fn: '*coverage_profile_along_genes_(total).txt'
      qualimap/bamqc/genome_results:
        fn: '*genome_results.txt'
      qualimap/bamqc/coverage:
        fn: '*coverage_histogram.txt'
      qualimap/bamqc/insert_size:
        fn: '*insert_size_histogram.txt'
      qualimap/bamqc/genome_fraction:
        fn: '*genome_fraction_coverage.txt'
      qualimap/bamqc/gc_dist:
        fn: '*mapped_reads_gc-content_distribution.txt'
      salmon/meta:
        fn: '*meta_info.json'
        contents: 'salmon_version'
      salmon/fld:
        fn: '*flenDist.txt'
        
#---------------------------------------- configuration for export
export:
  blueprint:
    file: SODAR_export_blueprint.txt
    command: |
      imkdir -p $(dirname {dest} )
      irsync -a -K {src} i:{dest}
  path_pattern:
    - __SODAR__/{sample}/{GENOME}/%Y_%m_%d/{files:ngs_mapping:out}/{step}/out/{step}.{sample}.{extension}
    - __SODAR__/{sample}/{GENOME}/%Y_%m_%d/{files:ngs_mapping:rep}/{step}/report.zip
    - __SODAR__/{sample}/{GENOME}/%Y_%m_%d/{files:gene_expression_quantification}/{step}/out/{step}.{sample}.{extension}
  ngs_mapping_out:
    - files: {step: star, extension: bam}
  ngs_mapping_rep:
    - dir: {step: star, log: true}
      compress: zip
  gene_expression_quantification:
    - files: {step: star, extension: gene_counts.tab}
    - files: {step: salmon, extension: sf}


UCSC_export:
  blueprint: false
  path_pattern:
    - my_UCSC_track_hub/{GENOME}/{files:mapped_reads}.{step}.{sample}.{extension}
  mapped_reads:
    - files: {step: star, mate: all_mates, extension: bam}
    - files: {step: star, mate: all_mates, extension: bam.bai}

#---------------------------------------- circRNA report
circRNA_report:
  snippet_parameters: {}
  defaults: {}
  report_snippets: []