<tool id="porechop" name="Porechop" version="0.2.2">

    <description>Demux and adapter removal</description>

    <!-- ***************************************************************** -->
   
    <!-- not yet working with Bioconda
    <requirements>
        <requirement type="package" version="0.2.1">porechop</requirement>
    </requirements>
    -->

    <!-- ***************************************************************** -->

    <version_command>porechop --version</version_command>

    <!-- ***************************************************************** -->

    <command detect_errors="aggressive">
    <![CDATA[

    #set filename = str($input.name)

    mkdir out && 

    porechop

        --input ${input}

        --format ${out_format}

        #if str($demux_section.demux_options.demux) == "yes":
            --barcode_dir out
        #else:
            --output "out/$filename"
        #end if

        --threads  \${GALAXY_SLOTS:-1}

    ##--Demultiplex Options--------------------------

        #if str($demux_section.demux_options.demux) == "yes":

            --barcode_threshold $demux_section.demux_options.barcode_threshold
            --barcode_diff $demux_section.demux_options.barcode_diff
            $demux_section.demux_options.require_two_barcodes
            $demux_section.demux_options.discard_unassigned

        #end if

    ##--Adapter Trim Options--------------------------

        #if str($trim_section.trim) == "no":
            --untrimmed
        #end if

            --adapter_threshold $adapter_section.adapter_threshold
            --check_reads $adapter_section.check_reads
            --scoring_scheme $adapter_section.scoring_scheme

            --end_size $adapter_section.end_size
            --end_threshold $adapter_section.end_threshold
            --min_trim_size $adapter_section.min_trim_size
            --extra_end_trim $adapter_section.extra_end_trim

            $adapter_section.discard_middle
            --middle_threshold $adapter_section.middle_threshold
            --extra_middle_trim_good_side $adapter_section.extra_middle_trim_good_side
            --extra_middle_trim_bad_side $adapter_section.extra_middle_trim_bad_side
            --min_split_read_size $adapter_section.min_split_read_size


        | perl $__tool_directory__/porechop_summarize.pl
        > $result_table

    ]]>
    </command>

    <!-- ***************************************************************** -->

    <inputs>

        <param argument="--input" type="data" format="fastq,fasta" label="Input reads" />

        <param name="out_format" type="select" label="Output format">
            <option value="fastq" selected="true">fastq</option>
            <option value="fasta">fasta</option>
        </param>

        <section name="demux_section" title="Demultiplexing Options" expanded="True">
            <conditional name="demux_options">
            <param name="demux" type="select" label="Perform demultiplexing" help="">
                <option value="no" selected="true">no</option>
                <option value="yes">yes</option>
            </param>
            <when value="no" />
            <when value="yes">
                <param argument="--barcode_threshold" size="5" type="float" value="75.0" min="0" max="100" label="Barcode threshold identity" />
                <param argument="--barcode_diff" size="5" type="float" value="5.0" min="0" max="100" label="Barcode threshold difference" />
                <param argument="--require_two_barcodes" type="boolean" truevalue="--require_two_barcodes" falsevalue="" checked="false" label="Require two barcodes" />
                <param argument="--discard_unassigned" type="boolean" truevalue="--discard_unassigned" falsevalue="" checked="false" label="Discard unassigned reads" />
            </when>
            </conditional>
        </section>

        <section name="trim_section" title="Trimming Options" expanded="True">
            <param name="trim" type="select" label="Perform adapter trimming" help="">
                <option value="no" selected="true">no</option>
                <option value="yes">yes</option>
            </param>
        </section>
        <section name="adapter_section" title="Adapter Options" expanded="False">
            <param argument="--adapter_threshold" size="4" type="float" value="90.0" min="0" max="100" label="Adapter set threshold identity" />
            <param argument="--check_reads" size="7" type="integer" value="10000" label="Number of reads to check to determine adapter sets" />
            <param argument="--scoring_scheme" type="text" value="3,-6,-5,-2" label="Scoring scheme" />
            <param argument="--end_size" size="4" type="integer" value="150" label="Number of terminal bases to search" />
            <param argument="--min_trim_size" size="4" type="integer" value="4" label="Minimum adapter match length" />
            <param argument="--extra_end_trim" size="4" type="integer" value="2" label="Adjacent bases to trim " />
            <param argument="--end_threshold" size="4" type="float" value="75.0" min="0" max="100" label="End adapter trim threshold identity" />

            <param argument="--discard_middle" type="boolean" truevalue="--discard_middle" falsevalue="" checked="false" label="Discard reads with middle adapters" />
            <param argument="--middle_threshold" size="4" type="float" value="85.0" min="0" max="100" label="Middle adapter trim threshold identity" />
            <param argument="--extra_middle_trim_good_side" size="4" type="integer" value="10" label="Adjacent bases to trim on good side" />
            <param argument="--extra_middle_trim_bad_side" size="4" type="integer" value="100" label="Adjacent bases to trim on bad side" />
            <param argument="--min_split_read_size" size="4" type="integer" value="1000" label="Minimum length of split reads to keep" />
        </section>

    </inputs>

    <!-- ***************************************************************** -->

    <outputs>

        <!-- Demuxed -->
        <collection type="list" name="output_collection_fastq" label="${tool.name} on ${on_string}">
            <filter>out_format == 'fastq'</filter>
            <filter>demux_section['demux_options']['demux'] == 'yes'</filter>
            <discover_datasets pattern="__designation_and_ext__" directory="out" format="fastqsanger" />
        </collection>
        <collection type="list" name="output_collection_fasta" label="${tool.name} on ${on_string}">
            <filter>out_format == 'fasta'</filter>
            <filter>demux_section['demux_options']['demux'] == 'yes'</filter>
            <discover_datasets pattern="__designation_and_ext__" directory="out" format="fasta" />
        </collection>
        <data format="tabular" name="result_table" label="${tool.name} on ${on_string} (summary)">
            <filter>demux_section['demux_options']['demux'] == 'yes'</filter>
        </data>

        <!-- Not Demuxed -->
        <data format="fastq" name="ouput_fastq">
              <discover_datasets directory='out' pattern="(?P&lt;designation&gt;.+)" ext="fastq" visible="true" assign_primary_output="true" />
            <filter>out_format == 'fastq'</filter>
            <filter>demux_section['demux_options']['demux'] == 'no'</filter>
        </data>
        <data format="fasta" name="ouput_fasta">
              <discover_datasets directory='out' pattern="(?P&lt;designation&gt;.+)" ext="fasta" visible="true" assign_primary_output="true" />
            <filter>out_format == 'fasta'</filter>
            <filter>demux_section['demux_options']['demux'] == 'no'</filter>
        </data>

    </outputs>

    <!-- ***************************************************************** -->

    <tests>
        <test>
            <param name="input" value="test_barcodes.fastq" ftype="fastq" />
            <param name="demux" value="yes" />
            <output_collection name="output_collection_fastq" type="list" count="4">
                <element name="BC01" file="bar1/BC01.fastq" compare="diff" decompress="true"/>
                <element name="BC02" file="bar1/BC02.fastq" compare="diff" decompress="true"/>
                <element name="BC03" file="bar1/BC03.fastq" compare="diff" decompress="true"/>
                <element name="none" file="bar1/none.fastq" compare="diff" decompress="true"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test_barcodes.fastq" ftype="fastq" />
            <param name="demux" value="yes" />
            <param name="require_two_barcodes" value="True" />
            <output_collection name="output_collection_fastq" type="list" count="4">
                <element name="BC01" file="bar2/BC01.fastq" compare="diff" decompress="true"/>
                <element name="BC02" file="bar2/BC02.fastq" compare="diff" decompress="true"/>
                <element name="BC03" file="bar2/BC03.fastq" compare="diff" decompress="true"/>
                <element name="none" file="bar2/none.fastq" compare="diff" decompress="true"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test_barcodes.fastq" ftype="fastq" />
            <param name="demux" value="yes" />
            <param name="trim" value="yes" />
            <param name="discard_unassigned" value="yes" />
            <output_collection name="output_collection_fastq" type="list" count="3">
                <element name="BC01" file="bar1_trim/BC01.fastq" compare="diff" decompress="true"/>
                <element name="BC02" file="bar1_trim/BC02.fastq" compare="diff" decompress="true"/>
                <element name="BC03" file="bar1_trim/BC03.fastq" compare="diff" decompress="true"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test_barcodes.fastq" ftype="fastq" />
            <param name="demux" value="no" />
            <param name="trim" value="yes" />
            <param name="out_format" value="fasta" />
            <output name="output_fasta" file="no_demux.fasta" compare="diff" />
        </test>
    </tests>

    <!-- ***************************************************************** -->

    <help>
    <![CDATA[

**Description**

Porechop is a tool for finding and removing adapters from Oxford Nanopore
reads. Adapters on the ends of reads are trimmed off, and when a read has an
adapter in its middle, it is treated as chimeric and chopped into separate
reads. Porechop performs thorough alignments to effectively find adapters,
even at low sequence identity.

Porechop also supports demultiplexing of Nanopore reads that were barcoded
with the Native Barcoding Kit, PCR Barcoding Kit or Rapid Barcoding Kit.

**Options**
::

  *** Barcode binning settings ***

  -b BARCODE_DIR, --barcode_dir BARCODE_DIR
                                    Reads will be binned based on their barcode and saved to separate
                                    files in this directory (incompatible with --output)
  --barcode_threshold BARCODE_THRESHOLD
                                    A read must have at least this percent identity to a barcode to be
                                    binned (default: 75.0)
  --barcode_diff BARCODE_DIFF       If the difference between a read's best barcode identity and its
                                    second-best barcode identity is less than this value, it will not be
                                    put in a barcode bin (to exclude cases which are too close to call)
                                    (default: 5.0)
  --require_two_barcodes            Reads will only be put in barcode bins if they have a strong match for
                                    the barcode on both their start and end (default: a read can be binned
                                    with a match at its start or end)
  --untrimmed                       Bin reads but do not trim the ends (appropriate if reads are to be
                                    used with Nanopolish) (default: False)

  *** Adapter search settings ***

  --adapter_threshold ADAPTER_THRESHOLD
                                    An adapter set has to have at least this percent identity to be
                                    labelled as present and trimmed off (0 to 100) (default: 90.0)
  --check_reads CHECK_READS         This many reads will be aligned to all possible adapters to determine
                                    which adapter sets are present (default: 10000)
  --scoring_scheme SCORING_SCHEME   Comma-delimited string of alignment scores: match,mismatch, gap open,
                                    gap extend (default: 3,-6,-5,-2)

  *** End adapter settings ***

  --end_size END_SIZE               The number of base pairs at each end of the read which will be
                                    searched for adapter sequences (default: 150)
  --min_trim_size MIN_TRIM_SIZE     Adapter alignments smaller than this will be ignored (default: 4)
  --extra_end_trim EXTRA_END_TRIM   This many additional bases will be removed next to adapters found at
                                    the ends of reads (default: 2)
  --end_threshold END_THRESHOLD     Adapters at the ends of reads must have at least this percent identity
                                    to be removed (0 to 100) (default: 75.0)

  *** Middle adapter settings ***

  --discard_middle                  Reads with middle adapters will be discarded (default: reads with
                                    middle adapters are split) (this option is on by default when
                                    outputting reads into barcode bins)
  --middle_threshold MIDDLE_THRESHOLD
                                    Adapters in the middle of reads must have at least this percent
                                    identity to be found (0 to 100) (default: 85.0)
  --extra_middle_trim_good_side EXTRA_MIDDLE_TRIM_GOOD_SIDE
                                    This many additional bases will be removed next to middle adapters on
                                    their "good" side (default: 10)
  --extra_middle_trim_bad_side EXTRA_MIDDLE_TRIM_BAD_SIDE
                                    This many additional bases will be removed next to middle adapters on
                                    their "bad" side (default: 100)
  --min_split_read_size MIN_SPLIT_READ_SIZE
                                    Post-split read pieces smaller than this many base pairs will not be
                                    outputted (default: 1000)


    ]]>
    </help>

    <!-- ***************************************************************** -->
    
    <citations>
    </citations>

</tool>