<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="stdio"/>
    <expand macro="version_command"/>
    <command><![CDATA[
@SHELL_OPTIONS@

## create symlinks to input datasets
ln -s '$fasta' fasta.dat &&
ln -s '$name' name.dat &&
ln -s '$group' group.dat &&

echo 'pre.cluster(
    fasta=fasta.dat,
    #if $name.is_of_type("mothur.names"):
        name=name.dat,
    #elif $name.is_of_type("mothur.count_table"):
        count=name.dat,
    #end if
    #if $group:
        group=group.dat,
    #end if
    diffs=$diffs,
    match=$match,
    mismatch=$mismatch,
    gapopen=$gapopen,
    gapextend=$gapextend,
    topdown=$topdown,
    processors='\${GALAXY_SLOTS:-8}'
)'
| sed 's/ //g'  ## mothur trips over whitespace
| mothur
| tee mothur.out.log &&

cat fasta* &&

if [ -f fasta.precluster.map ]; then mv fasta.precluster.map fasta.precluster.fasta.map; fi
    ]]></command>
    <inputs>
        <param argument="fasta" type="data" format="fasta" label="fasta - Sequence Fasta"/>
        <param argument="name" type="data" format="mothur.names,mothur.count_table" optional="true" label="name file or count table - Sequences Name reference"/>
        <param argument="group" type="data" format="mothur.groups" optional="true" label="group - Sequences Name reference"/>
        <param argument="diffs" type="integer" value="1" min="0" label="diffs - Number of mismatched bases to allow between sequences in a group (default 1)"/>
        <param argument="match" type="integer" value="1" label="match - reward for a match (default 1)"/>
        <param argument="mismatch" type="integer" value="-1" label="mismatch - penalty for a mismatch (default -1)"/>
        <param argument="gapopen" type="integer" value="-2" label="gapopen - penalty for opening a gap (default -2)"/>
        <param argument="gapextend" type="integer" value="-1" label="gapextend - penalty for extending a gap (default -1)"/>
        <param argument="topdown" type="boolean" truevalue="true" falsevalue="false" checked="true" label="topdown"
            help="cluster from largest abundance to smallest or vice versa. Default=Yes, meaning largest to smallest"/>
        <expand macro="param-savelog"/>
    </inputs>
    <outputs>
        <expand macro="logfile-output"/>
        <data name="fasta_out" format_source="fasta" from_work_dir="fasta*.precluster.dat" label="${tool.name} on ${on_string}: precluster.fasta"/>
        <data name="names_out" format="mothur.names" from_work_dir="fasta*.precluster.names" label="${tool.name} on ${on_string}: precluster.names">
            <filter>name.ext != "mothur.count_table"</filter>
        </data>
        <data name="count_out" format="mothur.count_table" from_work_dir="fasta*.precluster.count_table" label="${tool.name} on ${on_string}: precluster.count_table">
            <filter>name.ext == "mothur.count_table"</filter>
        </data>
        <collection name="map_out" type="list" label="${tool.name} on ${on_string}: precluster.map">
            <discover_datasets pattern="fasta\.precluster\.(?P&lt;designation&gt;.*)\.map" format="tabular"/>
        </collection>
    </outputs>
    <tests>
        <test><!-- test with fasta and names file -->
            <param name="fasta" value="amazon.fasta_head" ftype="fasta"/>
            <param name="name" value="amazon.head.names" ftype="mothur.names"/>
            <output name="fasta_out" ftype="fasta">
                <assert_contents>
                    <expand macro="test-fasta-format"/>
                    <has_text text="U68589"/>
                </assert_contents>
            </output>
            <output name="names_out" ftype="mothur.names">
                <assert_contents>
                    <expand macro="test-names-format"/>
                    <has_line_matching expression="^U68589\tU68589$"/>
                </assert_contents>
            </output>
            <output_collection name="map_out" count="1">
                <element name="fasta" ftype="tabular">
                    <assert_contents>
                        <has_text text="ideal_seq_1"/>
                        <has_text text="U68589"/>
                    </assert_contents>
                </element>
            </output_collection>
            <param name="savelog" value="true"/>
            <expand macro="logfile-test"/>
        </test>
        <test><!-- test with fasta and count table -->
            <param name="fasta" value="amazon.fasta_head" ftype="fasta"/>
            <param name="name" value="amazon.count_table" ftype="mothur.count_table"/>
            <output name="fasta_out" ftype="fasta">
                <assert_contents>
                    <expand macro="test-fasta-format"/>
                    <has_text text="U68589"/>
                </assert_contents>
            </output>
            <output name="count_out" ftype="mothur.count_table">
                <assert_contents>
                    <expand macro="test-count-format"/>
                    <has_text text="U68589"/>
                </assert_contents>
            </output>
            <output_collection name="map_out" count="1">
                <element name="fasta" ftype="tabular">
                    <assert_contents>
                        <has_text text="ideal_seq_1"/>
                        <has_text text="U68589"/>
                    </assert_contents>
                </element>
            </output_collection>
            <param name="savelog" value="true"/>
            <expand macro="logfile-test"/>
        </test>
    </tests>
    <help><![CDATA[

@MOTHUR_OVERVIEW@

**Command Documentation**

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: https://www.mothur.org/wiki/Pre.cluster

v1.24.0: Updated to mothur 1.33, added count and topdown parameter

    ]]></help>
    <expand macro="citations"/>
</tool>