<tool id="mash_screen" name="mash screen" version="@TOOL_VERSION@+galaxy1" profile="19.01">
    <description>determines how well query sequences are contained within a pool of sequences.</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">mash</requirement>
    </requirements>
    <version_command>mash --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
        ln -s '$queries' queries.msh &&
        mash screen
             $winner_takes_all
             -i $minimum_identity_to_report
             -v $maximum_p_value_to_report
             queries.msh
             #if str( $pool_input.pool_input_selector ) == "paired"
               '$pool_input.pool_1' '$pool_input.pool_2'
             #end if
             #if str( $pool_input.pool_input_selector ) == "paired_collection"
               '$pool_input.pool.forward' '$pool_input.pool.reverse'
             #end if
             #if str( $pool_input.pool_input_selector ) == "single"
               '$pool_input.pool'
             #end if
             > '$output'
    ]]></command>
    <inputs>
        <conditional name="pool_input">
            <param name="pool_input_selector" type="select" label="Single or Paired-end reads" help="Select between paired and single end data">
                <option value="paired">Paired</option>
                <option value="single">Single</option>
                <option value="paired_collection">Paired Collection</option>
            </param>
            <when value="paired">
                <param name="pool_1" type="data" format="@INTYPES@" label="Select first set of reads" help="Specify dataset with forward reads"/>
                <param name="pool_2" type="data" format="@INTYPES@" label="Select second set of reads" help="Specify dataset with reverse reads"/>
            </when>
            <when value="single">
                <param name="pool" type="data" format="@INTYPES@" label="Select fastq dataset" help="Specify dataset with single reads"/>
            </when>
            <when value="paired_collection">
                <param name="pool" format="@INTYPES@" type="data_collection" collection_type="paired" label="Select a paired collection" help="See help section for an explanation of dataset collections"/>
            </when>
        </conditional>
        <param name="queries" type="data" format="msh" />
        <param type="boolean" name="winner_takes_all" argument="-w" truevalue="-w" falsevalue=""/>
        <param type="float" name="minimum_identity_to_report" argument="-i" value="0." min="-1." max="1." />
        <param type="float" name="maximum_p_value_to_report" argument="-v" value="1." min="0." max="1."/>
    </inputs>
    <outputs>
        <data name="output" format="tabular" />
    </outputs>
    <tests>
        <test>
            <param name="queries" value="NZ_MYON01000010.1.msh"/>
            <param name="pool_input_selector" value="single"/>
            <param name="pool" value="ERR024951_seqtk_sample_1000_1.fastq"/>
            <output name="output" file="mash_screen_NZ_MYON01000010.1_ERR024951_seqtk_sample_1000_1.tsv"/>
        </test>
        <test>
            <param name="queries" value="NZ_MYON01000010.1.msh"/>
            <param name="pool_input_selector" value="single"/>
            <param name="pool" value="ERR024951_seqtk_sample_1000_2.fastq"/>
            <output name="output" file="mash_screen_NZ_MYON01000010.1_ERR024951_seqtk_sample_1000_2.tsv"/>
        </test>
        <test>
            <param name="queries" value="NZ_MYON01000010.1.msh"/>
            <param name="pool_input_selector" value="paired"/>
            <param name="pool_1" value="ERR024951_seqtk_sample_1000_1.fastq"/>
            <param name="pool_2" value="ERR024951_seqtk_sample_1000_2.fastq"/>
            <output name="output" file="mash_screen_NZ_MYON01000010.1_ERR024951_seqtk_sample_1000_1and2.tsv"/>
        </test>
    </tests>
    <help><![CDATA[
Description:

  Determine how well query sequences are contained within a pool of sequences.
  The queries must be formatted as a single Mash sketch file (.msh), created
  with the `mash sketch` command. The <pool> files can be contigs or reads, in
  fasta or fastq, gzipped or not, and "-" can be given for <pool> to read from
  standard input. The <pool> sequences are assumed to be nucleotides, and will
  be 6-frame translated if the <queries> are amino acids. The output fields are
  [identity, shared-hashes, median-multiplicity, p-value, query-ID,
  query-comment], where median-multiplicity is computed for shared hashes, based
  on the number of observations of those hashes within the pool.
  ]]></help>
    <citations>
        <citation type="bibtex">
@article{ondov2016mash,
  title={Mash: fast genome and metagenome distance estimation using MinHash},
  author={Ondov, Brian D and Treangen, Todd J and Melsted, P{\'a}ll and Mallonee, Adam B and Bergman, Nicholas H and Koren, Sergey and Phillippy, Adam M},
  journal={Genome biology},
  volume={17},
  number={1},
  pages={132},
  year={2016},
  publisher={BioMed Central}
  }
        </citation>
    </citations>
</tool>