<tool id="canu" name="Canu" version="1.6">

    <description>Assembler optimized for long error-prone reads</description>

    <!-- ***************************************************************** -->
   
    <!--
    <requirements>
        <requirement type="package" version="1.6">canu</requirement>
    </requirements>
    -->

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

    <version_command>canu --version | perl -wnE'print "$1\n" for /^Canu (?:snapshot v)?(\S+)/g'</version_command>


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

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

    canu
        
        -p canu_galaxy
        -d out_dir
        useGrid=false
        genomeSize=$genome_size
        rawErrorRate=$raw_error_rate
        correctedErrorRate=$corrected_error_rate
        minReadLength=$min_read_length
        minOverlapLength=$min_overlap
        minThreads=\${GALAXY_SLOTS:-1}
        maxThreads=\${GALAXY_SLOTS:-1}
        gnuplotTested=true
        useGrid=false
        $mode
        $input


    ]]>
    </command>

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

    <inputs>

        <param name="input" type="data" format="fasta,fasta.gz,fastq,fastq.gz" label="Input reads" />
        <param name="mode" type="select">
            <option value="-nanopore-raw" selected="true">nanopore raw</option>
            <option value="-pacbio-raw">pacbio raw</option>
            <option value="-nanopore-corrected">nanopore corrected</option>
            <option value="-pacbio-corrected">pacbio corrected</option>
        </param>
        <param name="genome_size" type="text" size="5" label="Estimated genome size (e.g. 80m, 15k, 2g)" />
        <param name="raw_error_rate" type="float" value="0.500" min="0" max="1" size="5" label="Maximum raw overlap mismatch (0-1)" />
        <param name="corrected_error_rate" type="float" value="0.144" min="0" max="1" size="5" label="Maximum corrected overlap mismatch (0-1)" />
        <param name="min_read_length" type="integer" value="1000" min="1" size="5" label="Minimum read length" />
        <param name="min_overlap" type="integer" value="500" min="1" size="5" label="Minimum overlap" />

    </inputs>

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

    <outputs>

        <data name="contigs" format="fasta" from_work_dir="out_dir/canu_galaxy.contigs.fasta" label="${tool.name} on ${on_string} (contigs)" />
        <data name="unitigs" format="fasta" from_work_dir="out_dir/canu_galaxy.unitigs.fasta" label="${tool.name} on ${on_string} (unitigs)" />

    </outputs>

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

    <!--
    <tests>
        <test>
            <param name="input" value="test_data.fast5.tar.gz" ftype="fast5_archive" />
            <output name="output" file="test_data.fastq" compare="sim_size" delta="0"/>
        </test>
    </tests>
    -->

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

    <help>
    <![CDATA[

**Description**

Nanopolish is a software package for signal-level analysis of Oxford Nanopore
sequencing data. Nanopolish can calculate an improved consensus sequence for a
draft genome assembly, detect base modifications, call SNPs and indels with
respect to a reference genome and more.

The Galaxy wrapper has modified nanopolish to take a gzip tarball of FAST5 reads
as input, such as can be produced by `poretools combine`, and always outputs a
single FASTQ file.

This is the `extract` module.

    ]]>
    </help>

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

</tool>