annotate summary.shared.xml @ 2:88aa9d575274 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/mothur commit 3418f23b9768f5aafb86488f5ec1cb97530d4fb3

<tool profile="16.07" id="mothur_summary_shared" name="Summary.shared" version="@WRAPPER_VERSION@.0">
    <description>Summary of calculator values for OTUs</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 '$otu' otu.dat &&

echo 'summary.shared(
    shared=otu.dat,
    #if $groups:
        label=${ str($label).replace(",","-") },
    #end if
    #if $label:
        groups=${ str($groups).replace(",","-") },
    #end if
    #if $calc:
        calc=${ str($calc).replace(",","-") },
    #end if
    all=$all,
    distance=$distance,
    #if $subsample.use == "yes":
        #if $subsample.subsample:
            subsample=$subsample.subsample,
        #else
            subsample=T,
        #end if
        #if $subsample.iters:
            iters=$subsample.iters,
        #end if
    #end if
    output=$output,
    processors='\${GALAXY_SLOTS:-8}'
)'
| sed 's/ //g'  ## mothur trips over whitespace
| mothur
| tee mothur.out.log
    ]]></command>
    <inputs>
        <param name="otu" type="data" format="mothur.shared" label="shared - OTU Shared"/>
        <param name="label" type="select" label="label - OTU Labels" multiple="true">
            <expand macro="labeloptions"/>
        </param>
        <param name="groups" type="select" label="groups - Pairwise comparision groups" multiple="true">
            <options>
                <filter type="data_meta" ref="otu" key="groups"/>
            </options>
        </param>
        <param name="calc" type="select" label="calc - Calculators (Uses defaults if none selected)" multiple="true">
            <expand macro="calc-common"/>
            <!-- set default option(s) -->
            <option value="sharedsobs" selected="true">sharedsobs - Shared community richness the observed richness shared between two or more samples</option>
            <option value="sharedchao" selected="true">sharedchao - Shared community richness the two or more sample shared Chao1 richness estimator</option>
            <option value="sharedace" selected="true">sharedace - Shared community richness the two sample shared ACE richness estimator</option>
            <option value="jclass" selected="true">jclass - Community Membership Similarity the traditional Jaccard similarity coefficient based on the observed richness</option>
            <option value="jest" selected="true">jest - Community Membership Similarity the Jaccard similarity coefficient based on the Chao1 estimated richnesses</option>
            <option value="sorclass" selected="true">sorclass - Community Membership Similarity the Sorenson similarity coefficient based on the observed richness</option>
            <option value="sorest" selected="true">sorest - Community Membership Similarity the Sorenson similarity coefficient based on the Chao1 estimated richnesses</option>
            <option value="jabund" selected="true">jabund - Community Structure Similarity the abundance-based Jaccard similarity coefficient</option>
            <option value="sorabund" selected="true">sorabund - Community Structure Similarity the abundance-based Sorenson similarity coefficient</option>
            <option value="thetan" selected="true">thetan - Community Structure Similarity the Smith theta similarity coefficient</option>
            <option value="thetayc" selected="true">thetayc - Community Structure Similarity the Yue &amp; Clayton theta similarity coefficient</option>
        </param>
        <param name="all" type="boolean" truevalue="true" falsevalue="false" checked="false" label="all - Include RAM intensive sharedsobs and sharedchao calculations"/>
        <param name="distance" type="boolean" truevalue="true" falsevalue="false" checked="false" label="distance - Output a distance file for each calculator at each label"/>
        <conditional name="subsample">
            <param name="use" type="select" label="produce subsample distance matrices">
                <option value="no" selected="true">no</option>
                <option value="yes">yes</option>
            </param>
            <when value="yes">
                <param name="subsample" type="integer" value="" optional="true" label="subsample - size pergroup of the sample" help="Leave blank to use the size of your smallest group"/>
                <param name="iters" type="integer" value="" min="1" optional="true" label="iters - Number of times to run the subsample"/>
            </when>
            <when value="no"/>
        </conditional>
        <param name="output" type="select" label="output - Distance Matrix Output Format" help="">
            <option value="lt" selected="true">Phylip formatted Lower Triangle Matrix</option>
            <option value="square">Phylip formatted Square Matrix</option>
        </param>
        <expand macro="param-savelog"/>
    </inputs>
    <outputs>
        <expand macro="logfile-output"/>
        <data name="summary" format="tabular" from_work_dir="otu*.summary" label="${tool.name} on ${on_string}: shared.summary"/>
        <collection name="distfiles" type="list" label="${tool.name} on ${on_string}: dist">
            <filter>distance</filter>
            <discover_datasets pattern=".*?\.(?P&lt;designation&gt;.*)\.dist" format="mothur.dist" />
            <!-- doesn't seem to work for collection elements yet
            <change_format>
                <when input="output" value="lt" format="mothur.lower.dist"/>
                <when input="output" value="square" format="mothur.square.dist"/>
            </change_format>
            -->
        </collection>
    </outputs>
    <tests>
        <test><!-- test with defaults -->
            <param name="otu" value="amazon.an.shared"/>
            <output name="summary" md5="29384359e341721b3519fba35b9301e4" ftype="tabular"/>
            <param name="savelog" value="true"/>
            <expand macro="logfile-test"/>
        </test>
        <test><!-- test with subsample -->
            <param name="otu" value="amazon.mothur.shared"/>
            <param name="use" value="yes"/>
            <param name="subsample" value="10"/>
            <param name="iters" value="42"/>
            <output name="summary" ftype="tabular">
                <assert_contents>
                    <has_text text="forest"/>
                    <has_text text="pasture"/>
                </assert_contents>
            </output>
            <param name="savelog" value="true"/>
            <expand macro="logfile-test"/>
        </test>
        <test><!-- test with label and groups select and all calculators -->
            <param name="otu" value="amazon.an.shared"/>
            <param name="label" value="0.05,0.22,0.32"/>
            <param name="groups" value="forest,pasture"/>
            <param name="calc" value="sharedsobs,sharedchao,sharedace,anderberg,jclass,jest,kulczynski,kulczynskicody,kstest,lennon,ochiai,sorclass,sorest,whittaker,hamming,memchi2,memchord,memeuclidean,mempearson,braycurtis,jabund,morisitahorn,sorabund,thetan,thetayc,canberra,gower,hellinger,manhattan,odum,soergel,spearman,speciesprofile,structchi2,structchord,structeuclidean,structkulczynski,structpearson,sharednseqs,sharedobserved"/>
            <output name="summary" md5="acd56d4ab09ec1c2117f5e4840a875a1" ftype="tabular"/>
            <param name="savelog" value="true"/>
            <expand macro="logfile-test"/>
        </test>
        <test><!-- test with distance output collection -->
            <param name="otu" value="amazon.an.shared"/>
            <param name="distance" value="true"/>
            <output name="summary" ftype="tabular">
                <assert_contents>
                    <has_text text="forest"/>
                    <has_text text="pasture"/>
                </assert_contents>
            </output>
            <param name="calc" value="sorclass"/>
            <output_collection name="distfiles" count="36">
                <element name="sorclass.0.29.lt" ftype="mothur.dist">
                    <assert_contents>
                        <has_text text="forest"/>
                        <has_text text="pasture"/>
                    </assert_contents>
                </element>
            </output_collection>
            <param name="savelog" value="true"/>
            <expand macro="logfile-test"/>
        </test>
    </tests>
    <help><![CDATA[

@MOTHUR_OVERVIEW@

**Command Documentation**

The summary.shared_ command produce a summary file that has the calculator value for each line in the OTU data of the shared_ file and for all possible comparisons between the different groups in the group_ file.  This can be useful if you aren't interested in generating collector's or rarefaction curves for your multi-sample data analysis. It would be worth your while, however, to look at the collector's curves for the calculators you are interested in to determine how sensitive the values are to sampling. If the values are not sensitive to sampling, then you can trust the values. Otherwise, you need to keep sampling.  For calc parameter choices see: https://www.mothur.org/wiki/Calculators

.. _shared: https://www.mothur.org/wiki/Shared_file
.. _group: https://www.mothur.org/wiki/Group_file
.. _summary.shared: https://www.mothur.org/wiki/Summary.shared

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