<tool id="hfp_nowayout" name="nowayout" version="0.5.0+galaxy24">
    <description>An automated workflow to identify Mitochondrial reads and classify Eukaryotes.</description>
    <requirements>
        <container type="docker">quay.io/biocontainers/nextflow:24.10.4--hdfd78af_0</container>
    </requirements> 
    <version_command>nextflow -version</version_command>
    <command detect_errors="exit_code"><![CDATA[
	input_path=\$(pwd)"/cpipes-input";
    mkdir -p "\${input_path}" || exit 1;
    #import re
    #if (str($input_read_type_cond.input_read_type) == "single_long"):
	    #for _, $unpaired in enumerate($input_read_type_cond.input):
            #set read1 = str($unpaired.name)
            #if not str($unpaired.name).endswith(('.fastq', '.fastq.gz')):
                #set read1_ext = re.sub('fastqsanger', 'fastq', str($unpaired.ext))
                #set read1 = str($unpaired.name) + str('.') + $read1_ext
            #end if
            ln -sf '$unpaired' "\${input_path}/$read1";
	    #end for
    #elif (str($input_read_type_cond.input_read_type) == "paired"):
	    #for _, $pair in enumerate($input_read_type_cond.input_pair)
            #set read_R1 = re.sub('\:forward', '_forward', str($pair.forward.name))
            #set read_R2 = re.sub('\:reverse', '_reverse', str($pair.reverse.name))
            #set read_R1_ext = re.sub('fastqsanger', 'fastq', str($pair.forward.ext))
            #set read_R2_ext = re.sub('fastqsanger', 'fastq', str($pair.reverse.ext))
            #if not str($pair.forward.name).endswith(('.fastq', '.fastq.gz')):
	            #set read_R1 = $read_R1 + str('.') + $read_R1_ext
            #end if
            #if not str($pair.reverse.name).endswith(('.fastq', '.fastq.gz')):
                #set read_R2 = $read_R2 + str('.') + $read_R2_ext
            #end if
	        ln -sf '$pair.forward' "\${input_path}/$read_R1";
	        ln -sf '$pair.reverse' "\${input_path}/$read_R2";
	    #end for
    #end if
	$__tool_directory__/0.5.0/cpipes
    --pipeline nowayout
    --input \${input_path}
	--output cpipes-output
    --fq_suffix '${input_read_type_cond.fq_suffix}'
    #if (str($input_read_type_cond.input_read_type) == "single_long"):
        --fq_single_end true
    #elif (str($input_read_type_cond.input_read_type) == "paired"):
        --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}'
    #end if
    --db_mode $nowo_db_mode
    --nowo_thresholds $nowo_thresholds
	--fq_filename_delim '${fq_filename_delim}'
	--fq_filename_delim_idx $fq_filename_delim_idx
	-profile gxkubernetes;
    mv './cpipes-output/nowayout-multiqc/multiqc_report.html' './multiqc_report.html' || exit 1;
    mv './cpipes-output/krona_ktimporttext/CPIPES_nowayout_krona.html './CPIPES_nowayout_krona.html' || exit 1;
    rm -rf ./cpipes-output || exit 1;
    rm -rf ./work || exit 1;
    ]]></command>
    <inputs>
        <conditional name="input_read_type_cond">
            <param name="input_read_type" type="select" label="Select the read collection type">
                <option value="single_long" selected="true">Single-End short reads</option>
                <option value="paired">Paired-End short reads</option>
            </param>
            <when value="single_long">
                <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
                    label="Dataset list of unpaired short reads or long reads" />
                <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Single-End FASTQ"/>
            </when>
            <when value="paired">
                <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" />
                <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"
                    help="For any data sets downloaded from NCBI into Galaxy, change this to _forward.fastq.gz suffix."/>
                <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"
                    help="For any data sets downloaded from NCBI into Galaxy, change this to _reverse.fastq.gz suffix."/>
            </when>
        </conditional>
        <param name="nowo_db_mode" type="select" label="Select the database with nowayout"
            help="Please see below about different databases.">
            <option value="mitomine" selected="true">mitomine</option>
            <option value="cytox1">cytox1</option>
            <option value="voucher">voucher</option>
            <option value="ganoderma">ganoderma</option>
            <option value="listeria">listeria</option>
        </param>
        <param name="nowo_thresholds" type="select" label="Enter the type of base quality thresholds to be set with nowayout"
            help="The default value sets strictest thresholds that tends to filter out most of the false positive hits.">
            <option value="strict" selected="true">strict</option>
            <option value="relax">relax</option>
        </param>
        <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)" 
            help="This is the delimitor by which samples are grouped together to display in the final MultiQC report. For example, if your input data sets are mango_replicate1.fastq.gz, mango_replicate2.fastq.gz, orange_replicate1_maryland.fastq.gz, orange_replicate2_maryland.fastq.gz, then to create 2 samples mango and orange, the value for --fq_filename_delim would be _ (underscore) and the value for --fq_filename_delim_idx would be 1, since you want to group by the first word (i.e. mango or orange) after splitting the filename based on _ (underscore)."/>
        <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
    </inputs>
    <outputs>
        <data name="krona_chart" format="html" label="nowayout: Krona Chart on ${on_string}" from_work_dir="CPIPES_nowayout_krona.html"/>
        <data name="multiqc_report" format="html" label="nowayout: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
    </outputs>
    <tests>
        <!--Test 01: long reads-->
        <test expect_num_outputs="2">
            <param name="input">
                <collection type="list">
                    <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
                    <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
                    <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
                </collection>
            </param>
            <param name="fq_suffix" value=".fastq.gz"/>
            <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
            <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**Purpose**

nowayout is a mitochondrial metagenomics classifier for Eukaryotes. 
It uses a custom kma database to identify mitochondrial reads and 
performs read classification followed by further read classification 
reinforcement using sourmash.

It is written in Nextflow and is part of the modular data analysis pipelines (CFSAN PIPELINES or CPIPES for short) at HFP.


----

.. class:: infomark

** Databases **

    - mitomine: Big database that works in almost all scenarios.
    - cytox1: Collection of only non-redundant COXI genes from NCBI.
    - voucher: Collection of only non-redundant voucher sequences from NCBI.
    - ganoderma: Collection of only non-redundant mtDNA sequences of Ganoderma fungi.
    - listeria: Collection of organelle sequences and other rRNA genes for Listeria.


----

.. class:: infomark

**Testing and Validation**

The CPIPES - nowayout Nextflow pipeline has been wrapped to make it work in Galaxy. 
It takes in either paired or unpaired short reads list as an input and generates a MultiQC report 
which contains relative abundances in context of number of mitochondrial reads identified. It also 
generates a Krona chart for each sample. The pipeline has been tested on multiple internal insect 
mixture samples. All the original testing and validation was done on the command line on the 
HFP Reedling HPC Cluster.


----

.. class:: infomark

** Please note **

    ::
    
        - nowayout only works on Illumina short reads (paired or unpaired).
        - nowayout uses a custom kma database named mitomine.
        - The custom database will be incrementally augmented and refined over time.
        - mitomine stats:
            Contains ~ 2.93M non-redundant mitochondrial and voucher sequences.
            Represents ~ 717K unique species.
        - Other databases are also available but will be seldom updated.

----

.. class:: infomark

**Outputs**

The main output file is a:

    ::

        - MultiQC Report: Contains a brief summary report including individual Mitochondrial reads identified
                          per sample and relative abundances in context of the total number of Mitochondrial reads
                          identified.
                          Please note that due to MultiQC customizations, the preview (eye icon) will not
                          work within Galaxy for the MultiQC report. Please download the file by clicking
                          on the floppy icon and view it in your browser on your local desktop/workstation.
                          You can export the tables and plots from the downloaded MultiQC report.

  ]]></help>
    <citations>
        <citation type="bibtex">
            @article{nowayout,
            author = {Konganti, Kranti},
            year = {2025},
            month = {May},
            title = {nowayout: An automated mitrochiondrial read classifier for Eukaryotes.},
            journal = {Manuscript in preparation},
            doi = {10.3389/xxxxxxxxxxxxxxxxxx},
            url = {https://xxxxxxx/articles/10.3389/xxxxxxxxxxxx/full}}
        </citation>
    </citations>
</tool>