# ============================================================================
# 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.
# ============================================================================
sequana_wrappers: v24.1.14

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

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


apptainers:
    bamtools: https://zenodo.org/record/10211475/files/bamtools_2.5.2.img
    bedtools: https://zenodo.org/record/7341710/files/sequana_tools_0.14.5.img
    bowtie2: https://zenodo.org/record/7341710/files/sequana_tools_0.14.5.img
    bwa: https://zenodo.org/record/7341710/files/sequana_tools_0.14.5.img
    deeptools: https://zenodo.org/record/7341710/files/sequana_tools_0.14.5.img
    graphviz: https://zenodo.org/record/7928262/files/graphviz_7.0.5.img
    minimap2: https://zenodo.org/record/7341710/files/sequana_tools_0.14.5.img
    multiqc: https://zenodo.org/record/10205070/files/multiqc_1.16.0.img
    samtools: https://zenodo.org/record/7341710/files/sequana_tools_0.14.5.img
    sequana_coverage: https://zenodo.org/record/10460105/files/sequana_0.16.5.img
    seqkit: https://zenodo.org/record/7821924/files/seqkit_2.4.0.img
    subread: https://zenodo.org/record/7341710/files/sequana_tools_0.14.5.img



##############################################################################
# samtools_depth
#
# :Parameters:
#
# - max_depth: by default max depth is 20,000 but can be changed here
samtools_depth:
    max_depth: 20000
    resources:
        mem: 8G

##############################################################################
# BWA MEM indexing 
#
bwa_index:
    options: ''
    threads: 4
    resources:
        mem: 8G

##############################################################################
# BAM alignment indexing 
#
bam_indexing:
    resources:
        mem: 8G

bam2bigwig:
    resources:
        mem: 8G

filtering_bam:
    resources:
        mem: 8G


bwa:
    index_algorithm: is
    options: -T 30 -M
    threads: 4
    tmp_directory: ./tmp
    resources:
        mem: 8G

bwa_split:
    nreads: 1000000
    index_algorithm: is
    options: -T 30 -M
    threads: 4
    tmp_directory: ./tmp
    resources:
        mem: 8G



minimap2:
    options: ''
    threads: 4
    resources:
        mem: 8G

bowtie2:
    options: ''
    threads: 4
    resources:
        mem: 8G

bowtie2_index:
    options: ''
    threads: 4
    resources:
        mem: 8G

bamtools_stats:
    resources:
        mem: 8G


feature_counts:
    do: false
    options: ''
    gff: ''
    feature: gene
    attribute: ID
    threads: 4
    resources:
        mem: 8G

#############################################################################
#
# :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: true
    circular: true
    window_size: 10001
    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: ''
    options: ""
    resources:
        mem: 8G


#############################################################################
##   MultiQC aggregates results from bioinformatics analyses across many
##   samples into a single report.
##
## :Parameters:
##
## - options: any options recognised by multiqc
## - 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
    input_directory: .
    config_file: multiqc_config.yaml
    resources:
        mem: 8G