sequana_wrappers: "v23.12.5"

input_directory:
input_pattern: '*fastq.gz'
reference_file:
annotation_file:


# if you have some samples starting with prefix to bed removed,
# uncomment this line and fill the list
extra_prefixes_to_strip: ["lima_output"]

# do not change:
data_type_choice: "lima.ccs.fastq"

#
#
# data_type_choice__ = ["lima.ccs.fastq", "lima.ccs.bam", "subreads.bam"]
#input:
#    data_type_choice: lima.ccs.fastq

apptainers:
    graphviz: https://zenodo.org/record/7928262/files/graphviz_7.0.5.img
    raxml: https://zenodo.org/record/7968244/files/raxml_8.2.12.img
    sequana_tools: https://zenodo.org/record/7963917/files/sequana_tools_0.15.1.img
    multiqc: https://zenodo.org/record/10205070/files/multiqc_1.16.0.img
    ccs:  https://zenodo.org/record/7817325/files/ccs_6.4.0.img
    laa: https://zenodo.org/record/10404979/files/pblaa_2.4.2.img
    samtools: https://zenodo.org/record/7437898/files/samtools_1.16.1.img

# for populations, and ploidy of 1, a population SNP found in a population
# will have a score of 0. Here setting to 2 is a trick. Alternative is
# to set freebayes scores to 0
# Useful options: 
# --min-alternate-count set to 0.01 (default is 0.05) allows detection of SNPs
# with frequency as low as 1% but this may lead to False positive. Useful for
# hypervariable virus population.
# -- legacy-gls could be use if SNPs have zero score whereas they look good
# --noindels clean up the final VCF with only SNPs but not recommended by
# freebayes
#
# With new freebayes if min alternate is low, some SNPs 
# bcftools norm performs left-align and normalize indels; check if REF alleles match the reference;
# split multiallelic sites into multiple rows; recover multiallelics from multiple rows.
#
freebayes:
    do: true
    ploidy: 2
    options: --min-alternate-fraction 0.01 --legacy-gls
    split_multiallelic: true


snpeff:
    do: false
    options: -no-downstream -no-upstream
    build_options: # -noCheckCds -noCheckProtein


kraken:
    do: false
    databases:
        -

freebayes_vcf_filter:
    do: true
    freebayes_score: 0
    frequency: 0.0
    min_depth: 10
    forward_depth: 3
    reverse_depth: 3
    strand_ratio: 0.2
raxml_mltree:
    N: 100
    options: ''


raxml_bootstrap:
    N: 100
    options: ''

itol:
  do: false



#############################################################################
##   MultiQC aggregates results from bioinformatics analyses across many
##   samples into a single report.
##
## :Parameters:
##
## - options: any options recognised by multiqc
## - output-directory: Create report in the specified output directory
## - config_file: by default, we use sequana RNA-seq multiqc_config file.
##       If you want your own multiqc, fill this entry
multiqc:
    options: "-p -f"
    modules: sequana_bamtools_stats sequana_laa
    input_directory: "."
    config_file: "multiqc_config.yaml"