view tools/mothur/pre.cluster.xml @ 0:ee4fee239fe7 draft default tip

planemo upload commit 68a4fd4cc5332c57ac39bef73db224425af0706c-dirty

<tool profile="16.07" id="mothur_pre_cluster" name="Pre.cluster" version="@WRAPPER_VERSION@.0">
    <description>Remove sequences due to pyrosequencing errors</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="version_command"/>
    <command detect_errors="aggressive"><![CDATA[
        echo 'pre.cluster(
            fasta=$fasta,
            #if $name.is_of_type("mothur.names"):
                name=$name,
            #elif $name.is_of_type("mothur.count_table"):
                count=$name,
            #end if
            #if $group:
                group=$group,
            #end if
            diffs=$diffs,
            topdown=$topdown,
            processors='\${GALAXY_SLOTS:-8}'
        )'
        | sed 's/ //g'  ## mothur trips over whitespace
        | mothur &&

        ## move output files to correct destination
        prefix="$fasta" &&
        mv \${prefix%.dat}*.precluster.names "$names_out" &&
        mv \${prefix%.dat}*.precluster.map "$map_out" &&
        mv \${prefix%.dat}*.precluster.dat "$fasta_out" &&
        mv mothur.*.logfile "$logfile"
    ]]></command>
    <inputs>
        <param name="fasta" type="data" format="fasta" label="fasta - Sequence Fasta"/>
        <param name="name" type="data" format="mothur.names,mothur.count_table" optional="true" label="name file or count table- Sequences Name reference"/>
        <param name="group" type="data" format="mothur.groups" optional="true" label="group - Sequences Name reference"/>
        <param name="diffs" type="integer" value="1" min="0" label="diffs - Number of mismatched bases to allow between sequences in a group (default 1)"/>
        <param name="topdown" type="boolean" truevalue="true" falsevalue="false" checked="false" label="allows you to specify whether to cluster from largest abundance to smallest or vice versa. Default =T, which is largest to smallest"/>
    </inputs>
    <outputs>
        <data name="logfile" format="txt" label="${tool.name} on ${on_string}: logfile"/>
        <data name="fasta_out" format_source="fasta" label="${tool.name} on ${on_string}: precluster.fasta"/>
        <data name="names_out" format="mothur.names" label="${tool.name} on ${on_string}: precluster.names"/>
        <data name="map_out" format="tabular" label="${tool.name} on ${on_string}: precluster.map"/>
    </outputs>
    <tests>
        <test><!-- test with fasta and names file -->
            <param name="fasta" value="amazon.fasta_head" ftype="fasta"/>
            <param name="name" value="amazon.head.names" ftype="mothur.names"/>
            <output name="fasta_out" md5="d5d37ace0f2a5c020edd0aa9eb7aca9b" ftype="fasta"/>
            <output name="names_out" md5="51090fe5e111920ec1003c2073532d96" ftype="mothur.names"/>
            <output name="map_out" md5="c2ca7b0d45aa3881c7bd5cb8a44c853b" ftype="tabular"/>
            <expand macro="logfile-test"/>
        </test>
    </tests>
    <help>
<![CDATA[

@MOTHUR_OVERVIEW@

**Command Documenation**

The pre.cluster_ command implements a pseudo-single linkage algorithm with the goal of removing sequences that are likely due to pyrosequencing errors. The basic idea is that abundant sequences are more likely to generate erroneous sequences than rare sequences. With that in mind, the algorithm proceeds by ranking sequences in order of their abundance. Then we walk through the list of sequences looking for rarer sequences that are within some threshold of the original sequence. Those that are within the threshold are merged with the larger sequence. The original Huse method performs this task on a distance matrix, whereas we do it based on the original sequences. The advantage of our approach is that the algorithm works on aligned sequences instead of a distance matrix. This is advantageous because by pre-clustering you remove a large number of sequences making the distance calculation much faster.

.. _pre.cluster: http://www.mothur.org/wiki/Pre.cluster

v1.24.0: Updated to mothur 1.33, added count and topdown parameter
]]>
    </help>
    <expand macro="citations"/>
</tool>