view obiuniq.xml @ 4:d4bea99366f9 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/obitools commit dabf62d438facc62f3e606ff4419092fdcdfaa44

<tool id="obi_uniq" name="obiuniq" version="@TOOL_VERSION@" profile="@PROFILE@">
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements"/>
    <expand macro="stdio"/>
    <command><![CDATA[
    @GUNZIP_INPUT@

    obiuniq
    --without-progress-bar
    #if str( $options_attribute) == "merge"
        -m '$options_uniq'
    #else
        -c '$options_uniq'
    #end if
    ${mid}
    ${prefix}
    @INPUT_FORMAT@
    input
    @GZIP_OUTPUT@
    > '$output'
    @GENERATE_GALAXY_JSON@
    ]]></command>
    <inputs>
        <param name="input" type="data" format="@INPUT_FORMATS@" label="Input sequences file"/>
        <param name="options_uniq" type="select" label="Attribute to merge">
            <expand macro="attributes"/>
        </param>
        <param name="options_attribute" type="select" label="Use specific option">
            <option value="merge" selected="true">merge</option>
            <option value="category_attribute">category_attribute</option>
        </param>
        <param name="mid" type="boolean" checked="false" truevalue="-i" falsevalue="" label="Add a merged attribute containing the list of sequence record ids merged within this group"/>
    	<param name="prefix" type="boolean" checked="false" truevalue="-p" falsevalue="" label="Dereplicate through a prefix matching"/>
        <expand macro="input_format_options_macro"/>
    </inputs>
    <outputs>
        <data format="auto" name="output"/>
    </outputs>
    <tests>
       <test expect_num_outputs="1">
           <param name="input" value="output_ngsfilter_error_3.fastq" ftype="fastqsanger"/>
           <param name="options_uniq" value="sample"/>
           <param name="options_attribute" value="merge"/>
           <param name="mid" value="False"/>
           <param name="prefix" value="False"/>
           <output name="output" file="output_obiuniq.fasta" ftype="fasta"/>
       </test>
       <test expect_num_outputs="1">
           <param name="input" value="output_ngsfilter_error_3.fastq.gz" ftype="fastqsanger.gz"/>
           <param name="options_uniq" value="family"/>
           <param name="options_attribute" value="category_attribute"/>
           <param name="mid" value="True"/>
           <param name="prefix" value="True"/>
           <output name="output" file="output_obiuniq_family.fasta.gz" ftype="fasta.gz" decompress="true"/>
       </test>
    </tests>

    <help><![CDATA[
    
    .. class:: infomark

    **What it does**

    The obiuniq command is in some way analog to the standard Unix uniq -c command.

    Instead of working text line by text line as the standard Unix tool, the processing is done on sequence records.

    A sequence record is a complex object composed of an identifier, a set of attributes (key=value), a definition, and the sequence itself.

    The obiuniq command groups together sequence records. Then, for each group, a sequence record is printed.

    A group is defined by the sequence and optionally by the values of a set of attributes specified with the -c option.

    As the identifier, the set of attributes (key=value) and the definition of the sequence records that are grouped together may be different, two options (-m and -i) allow refining how these parts of the records are reported.

    \* By default, only attributes with identical values within a group of sequence records are kept.

    \*  A count attribute is set to the total number of sequence records for each group.

    \*  For each attribute specified by the -m option, a new attribute whose key is prefixed by merged is created. These new attributes contain the number of times each value occurs within the group of sequence records.


    @OBITOOLS_LINK@
    ]]>
    
    </help>
    <expand macro="citation" />
</tool>