inputs_pairwise_example.yml

# Sample Input File for Pairwise Comparison
#
# This example shows how to run the sample matching workflow with
# a CSV file specifying pairs of BAM files to compare.
#
# Usage:
#   cwltool main.cwl inputs_pairwise_example.yml

bam_directory:
  class: Directory
  path: /path/to/bam/directory
  # Replace with the actual path to your directory containing BAM files
  # The directory can contain subdirectories - the workflow will scan recursively

pairs_csv:
  class: File
  path: /path/to/pairs.csv
  # CSV file with two columns (no header):
  # left_filename,right_filename
  # Example content:
  #   sample1.bam,sample2.bam
  #   sample3.bam,sample4.bam

reference_genome:
  class: File
  path: /path/to/reference/genome.fasta
  # Reference genome in FASTA format
  # Example: hg38.fasta, GRCh38.fasta, etc.

haplotype_map:
  class: File
  path: /path/to/haplotype_map.txt
  # Haplotype map file required by Picard
  # Available from Broad Institute:
  # https://github.com/broadinstitute/picard/tree/master/src/main/resources/picard/fingerprint

# regex_split: "[_\\.]"
# Optional: Regular expression pattern to split BAM filenames for sample name extraction
# If not provided, uses basename (everything before .bam extension)
# Common patterns:
#   "[_\\.]"  - Split on underscore or dot
#   "_"       - Split only on underscore
#   "\\."     - Split only on dot
#   "-"       - Split on hyphen
# Example: For "Sample123_L001.bam" with regex "[_\\.]"
#          Sample name will be "Sample123"
# Example: For "Sample123_L001.bam" without regex_split
#          Sample name will be "Sample123_L001"

# cpu: 16
# Optional: Number of CPU cores to allocate for crosscheck_fingerprints step
# Default: 16 cores

# ram: 38000
# Optional: Amount of RAM in MiB to allocate for crosscheck_fingerprints step
# Default: 38000 MiB (38 GB)
# Increase if you get out-of-memory errors with large datasets