config.yaml

run:
  project: "NA12878"
  samples: samples.tsv
  units: units.tsv
  ped: "" # leave this string empty if there is no ped
  panel: "" # leave this string empty if there is no panel
  hpo: "" # leave this string empty is there are no hpo terms
  flank: 100000

tools:
  svscore_script: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/SVScore/svscore.pl"
  annotsv: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/crg2-non-conda-tools/AnnotSV_2.1"
  cre: "~/cre"
  crg: "~/crg"

ref:
  name: GRCh37.75
  no_decoy_name: GRCh37
  genome: /hpf/largeprojects/ccm_dccforge/dccdipg/Common/genomes/GRCh37d5/GRCh37d5.fa
  known-variants: /hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/dbsnp.b147.20160601.tidy.vcf.gz
  no_decoy: /hpf/largeprojects/ccm_dccforge/dccdipg/Common/genomes/GRCh37/GRCh37.fa
  decoy_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/pipelines/cre/data/grch37d5.decoy.bed"
  canon_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/genomes/grch37.canon.bed"

filtering:
  vqsr: false
  hard:
    # hard filtering as outlined in GATK docs
    # (https://gatkforums.broadinstitute.org/gatk/discussion/2806/howto-apply-hard-filters-to-a-call-set)
    snvs:
      "QD < 2.0 || FS > 60.0 || MQ < 40.0 || MQRankSum < -12.5 || ReadPosRankSum < -8.0"
    indels:
      "QD < 2.0 || FS > 200.0 || ReadPosRankSum < -20.0"

processing:
  remove-duplicates: false
  # Uncomment and point to a bed file with, e.g., captured regions if necessary,
  # see https://gatkforums.broadinstitute.org/gatk/discussion/4133/when-should-i-use-l-to-pass-in-a-list-of-intervals.
  # restrict-regions: captured_regions.bed
  # If regions are restricted, uncomment this to enlarge them by the given value in order to include
  # flanking areas.
  # region-padding: 100

annotation:
  vcfanno:
    conf: "~/crg/crg.vcfanno.conf" 
    lua_script: "~/crg/crg.vcfanno.lua"
    base_path: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/vcfanno"
  vep:
    dir: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/snakemake/6ea37454/share/ensembl-vep-101.0-0/"
    dir_cache: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/vep-cache"
    maxentscan: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/snakemake/6ea37454/share/ensembl-vep-101.0-0/maxEntScan"
    human_ancestor_fasta: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/human_ancestor.fa.gz"
  snpeff:
    dataDir: "/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/snpeff"
  svscore:
    exon_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/SVScore/refGene.exons.bed.gz"
    intron_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/SVScore/refGene.introns.bed.gz"
    cadd: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/SVScore/whole_genome_SNVs.tsv.gz"
  svreport:
    hgmd: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/HGMD_2018/hgmd_pro.db"
    protein_coding_genes: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/grch37.p13.ensembl.sorted.protein.coding.genes.bed"
    exon_bed: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/exons/hg19_UCSC_exons_canonical.bed"
    exac: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/ExAC/fordist_cleaned_nonpsych_z_pli_rec_null_data.txt"
    omim: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/OMIM_2020-04-09/genemap2.txt"
    gnomad: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/gnomad_v2_sv.sites.bed"
    biomart: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/BioMaRt.GrCh37.75.ensembl.mim.hgnc.entrez.txt"
    mssng_manta_counts: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/MSSNG_COUNTS/Canadian_MSSNG_parent_SVs.Manta.counts.txt"
    mssng_lumpy_counts: "/hpf/largeprojects/ccm_dccforge/dccdipg/Common/annotation/MSSNG_COUNTS/Canadian_MSSNG_parent_SVs.LUMPY.counts.txt"

params:
  bwa:
    verbosity: "-v 1"
    markSplitReads: "-M"
    maxMem: ""
  gatk:
    java_opts: "-Xms500m -Xmx9555m"
    HaplotypeCaller: ""
    BaseRecalibrator: ""
    #BaseRecalibrator: "--interval-set-rule INTERSECTION -U LENIENT-VCF-PROCESSING --read-filter BadCigar --read-filter NotzPrimaryAlignment"
    GenotypeGVCFs: ""
    VariantRecalibrator: ""
  picard:
    MarkDuplicates: "REMOVE_DUPLICATES=false"
  qualimap:
    mem: "20G"
    nw: 400
    c: "-c"
    hm: 3
    extra: ""
  verifybamid2:
    svd_prefix: "1000g.phase3 100k b37"
    extra: ""
  snpeff:
    java_opts: "-Xms750m -Xmx20g"
  svscore:
    operations: "max,sum,top5,top10,mean"