Problem 5

Solution

/*
 * Process 1D: Create a file containing the filtered and recoded set of variants
 */

process '1D_prepare_vcf_file' {

  input:
      file(variantsFile) from variants_file (1)
      file(blacklisted) from blacklist_file (2)

  output:
      set file("${variantsFile.baseName}.filtered.recode.vcf.gz"), \
          file("${variantsFile.baseName}.filtered.recode.vcf.gz.tbi") into prepared_vcf_ch (3)

  script:
  """
  vcftools --gzvcf $variantsFile -c \
           --exclude-bed ${blacklisted} \
           --recode | bgzip -c \
           > ${variantsFile.baseName}.filtered.recode.vcf.gz (4)

  tabix ${variantsFile.baseName}.filtered.recode.vcf.gz (5)
  """
}

1	Take as input the variants file, assigning the name `${variantsFile}`.
2	Take as input the blacklisted file, assigning the name `${blacklisted}`.
3	Out a tuple (or set) of two files into the `prepared_vcf_ch` channel.
4	Defines the name of the first output file.
5	Generates the secound output file (with `.tbi` suffix).