template.config

// EXECUTION SETTINGS AND GLOBAL DEFAULTS

// External config files import. DO NOT MODIFY THESE LINES!
includeConfig "${projectDir}/config/default.config"
includeConfig "${projectDir}/config/methods.config"
includeConfig "${projectDir}/nextflow.config"


// Inputs/parameters of the pipeline
params {
    dataset_id = ''
    blcds_registered_dataset = false // if you want the output to be registered

    output_dir = '/path/to/output/directory'

    // Set to false to disable the publish rule and delete intermediate files as they're no longer needed
    // Disable this option for large input BAMs where /scratch space may not be sufficient
    save_intermediate_files = false

    // Original aligner used to align BAMs
    // Provided as <aligner>-<aligner-version>
    // Accepted aligners: BWA-MEM2, HISAT2
    aligner = 'BWA-MEM2-2.2.1'

    // Whether to cache intermediate processes. Set to false by default
    // To enable caching, uncomment this option and set to true
    // cache_intermediate_pipeline_steps = false

    is_emit_original_quals = true // Set to true by default to emit original qualities

    is_DOC_run = false // Set to true to run GATK4 DepthOfCoverage, which is very time-consuming for large BAM

    // Target intervals to process for DNA panel/targeted sequencing samples
    // For WGS, leave this field blank. The intervals will be extracted automatically from the reference dictionary
    // For WXS/WES and targeted sequencing samples: provide path to targets in .list, .intervals, BED file, or VCF file format
    // Defaults to WGS mode
    intervals = ""

    // For large samples with disk space issues, uncomment and increase the compression below at the cost of runtime. Range: 0-9
    // gatk_ir_compression = 1

    // Reference - Used here hg38 decoy version
    // GATK requires the reference fasta to be accompanied by a .fai index and .dict dictionary associated with the fasta for fast random access
    // These can be found in the same folder as the reference here: /hot/resource/reference-genome/GRCh38-BI-20160721
    reference_fasta = "/hot/resource/reference-genome/GRCh38-BI-20160721/Homo_sapiens_assembly38.fasta"

    // Whether to parallelize the pipeline by chromosome or by splitting into equal-sized intervals
    // The scatter_count and extra args below only go into effect if parallelize_by_chromosome is disabled
    parallelize_by_chromosome = true
    scatter_count = 50
    split_intervals_extra_args = ''

    // GATK bundle - Used here hg38 decoy version
    bundle_mills_and_1000g_gold_standard_indels_vcf_gz = "/hot/resource/tool-specific-input/GATK/GRCh38/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz"
    bundle_known_indels_vcf_gz = "/hot/resource/tool-specific-input/GATK/GRCh38/Homo_sapiens_assembly38.known_indels.vcf.gz"
    bundle_v0_dbsnp138_vcf_gz = "/hot/resource/tool-specific-input/GATK/GRCh38/resources_broad_hg38_v0_Homo_sapiens_assembly38.dbsnp138.vcf.gz"
    bundle_contest_hapmap_3p3_vcf_gz = "/hot/resource/tool-specific-input/GATK/GRCh38/Biallelic/hapmap_3.3.hg38.BIALLELIC.PASS.2021-09-01.vcf.gz"

    // Base resource allocation updater
    // See README for adding parameters to update the base resource allocations
}

// Setup the pipeline config. DO NOT REMOVE THIS LINE!
methods.setup()