example_config.yml

---
#add dataset directory name instead of "example_dataset" and the number of lanes used by this Illumina run; more than one dataset can be added
datasets: 
   example_dataset:
      lanes: [1]

#see README for the download links of these references
references:
   fasta: "reference_index/hs37d5.fa" # path to reference genome (here 1000G phase2 human reference)
   bwa: "reference_index/hs37d5.fa" # name of bwa index for this reference sequence, can be the same as "fasta" depending where your BWA index files are or whether you defined another name
   inv: "input/example_dataset/hemomips_inv_ref.fa" #path to inversion fasta file including bwa index, not needed if parameters:inv: "no"
   annotation: "known_variants/phase1_release_v3.20101123.snps_indels_svs.on_target.vcf.gz"
   fasta2: "vep_cache/homo_sapiens/98_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa.gz" # path to reference fasta within VEP cache (see also output from installing the cache)

tools:
   vep_cache: "vep_cache/" # Cache folder for Ensembl VEP

parameters:
   inv: "yes" #set to "yes" when inversion design is provided
   paired_end_reads: "yes" #set to "yes" when paired-end sequencing is applied
   double_index: "no" #set to yes when double indexing is applied
   vep-version: 98 #vep version, recommended v98
   vep-species: "homo_sapiens" #vep cache species
   vep-assembly: "GRCh37" # vep cache genome assembly
   transcripts: "#|ENST00000360256|ENST00000218099" # list of considered transcripts separated by pipes, do not remove the leading hash and pipe.
  
GATK:
  - gatk4
#  - gatk3
...