# ============================================================================
# Config file for Sequana_mapper pipeline
# ==========================================[ Sections for the users ]========
#
# One of input_directory, input_pattern and input_samples must be provided
# If input_directory provided, use it otherwise if input_pattern provided,
# use it, otherwise use input_samples.
# ============================================================================

input_directory:
input_readtag: "_R[12]_"
input_pattern: '*fastq.gz'

##########################################################
#
general:
    mapper: bwa
    reference_file:
    annotation_file:
    create_bigwig: false

bwa:
    index_algorithm: is
    options: -T 30 -M
    threads: 4
    tmp_directory: ./tmp

minimap2:
    options: ''
    threads: 4

bowtie2:
    options: ''
    threads: 4

bowtie2_index:
    options: ''
    threads: 4

bwa_index:
    options: ''
    threads: 4

feature_counts:
  do: False
  options: ''
  gff: ''
  threads: 4

#############################################################################
#
# :Parameters:
#
# :param circular: is your genome circular or not ?
# :param double_threshold: double threshold for clustering. Keep 0.5 if you do
#     not know. Otherwise, checkout the online documentation on
#     sequana.readthedocs.io
# :param genbank_file: optional genbank
# :param high_threshold:
# :param low_threshold:
# :param mixture_models: keep to 2.
# :param reference_file: optional fasta file corresponding to you mapped
#i  data. Used for GC plot only
# :param window: the W parameter of the running median. Keep as long as twice
#     the deleted/depleted/duplicated you want to identify or to avoid. short
#     genome will be set to genome length divided by 5 automatically.
# :param chunksize: for large genomes, split the data into chunks
# :param binning: for large genomes, merge data into bins of this size. You will
#     loose resolution: bins are merged and averaged indeed
# :param cnv_clustering: further clustering to merge detected events whose
#     distance is smaller than this parameter
#
sequana_coverage:
    do: false
    circular: true
    window_size: 20001
    chunksize: 5000000
    double_threshold: 0.5
    gc_window_size: 201
    genbank_file: ''
    high_threshold: 4.0
    low_threshold: -4.0
    mixture_models: 2
    reference_file: ''


#############################################################################
##   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_coverage bowtie2 bowtie1 featureCounts
  input_directory: "."
  config_file: "multiqc_config.yaml"