config.yaml

# Database generation parameters
window_size: "50000"
window_step_size: "10000"
# Must be one of: `derived_in_archaic` or `derived_in_archaic_or_modern`
informative_site_method: "derived_in_archaic"

# Use windows from the database that have informative site counts within RANGE
# of the query windows informative site count to determine the null
# distribution. If value is a float, it is multiplied by the count to
#determine the range.
informative_site_range: "0"

null_dataset:
    name: "migration_null_10k"
    # Other null file paths are assumed to be sudirectories
    directory: "data/model/null"

    # Specify pattern as shown for snakemake's `glob_wildcards` function:
    # https://snakemake.readthedocs.io/en/stable/project_info/faq.html#glob-wildcards
    vcf_file_pattern: "vcfs/{sample}.mod.vcf.gz"
    chrom_sizes: "1000000"
    population_file: "Tenn.popfile"
    archaic_populations:
        - "Neand1"
    modern_populations:
        - "AFR"
        - "EUR"

test_dataset:
    name: "0.05_pct"
    # Other null file paths are assumed to be sudirectories
    directory: "data/model/0.05_pct"

    # Specify pattern as shown for snakemake's `glob_wildcards` function:
    # https://snakemake.readthedocs.io/en/stable/project_info/faq.html#glob-wildcards
    vcf_file_pattern: "vcfs/{sample}.mod.vcf.gz"
    chrom_sizes: "1000000"
    population_file: "Tenn.popfile"
    archaic_populations:
        - "Neand1"
    modern_populations:
        - "AFR"
        - "EUR"
    # Introgressed Regions
    regions_bed_pattern: "TreeCalls/Tenn_nonAfr_{id}_n1_0.05_n2_0.0.bed.merged.gz"
    haplotype_to_sample_map: "Tenn_haplotype_to_sample.txt"
    regions_bed_combined: "TreeCalls/Tenn_nonAfr_ALL_n1_0.05_n2_0.0.bed.gz"