annotate segmentation-fold.xml @ 2:22d7b6019372 draft

planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/segmentation_fold_galaxy_wrapper commit 7e54643d9af0065268d5cde2f2fc9872d2de8fa9

<tool id="segmentation_fold" name="segmentation-fold" version="1.6.3-0">
    <description>RNA-Folding including predefined segments including K-turns</description>
    
    <requirements>
        <requirement type="package" version="1.6.3">segmentation-fold</requirement>
    </requirements>
    
    <stdio></stdio>
    
    <version_command>segmentation-fold --version | head -n 2 | tail -n 1 | sed -e 's/^[[:space:]]*//' -e 's/[[:space:]]*$//'</version_command>
    
    <command><![CDATA[
        segmentation-fold
            
            #if $input.method == "fasta"
                -f $input.input_fasta
            #else
                -s $input.input_sequence
            #end if
            
            -p $predict_segments
            -h $min_hairpin_size
            
            #if $parameters.settings == "default"
                -x "\$SEGMENTATION_FOLD_DEFAULT_XML"
            #else
                -x "${parameters.input_xml}"
            #end if
            
            -t \${GALAXY_SLOTS:-4}
            > $output_dbn
    ]]></command>
    
    <inputs>
        <conditional name="input">
            <param name="method" type="select" label="Energy parameters">
                <option value="fasta" selected="true">As FASTA-file</option>
                <option value="text">As text</option>
            </param>
            <when value="fasta">
                <param name="input_fasta" type="data" format="fasta" label="Fasta file with RNA-sequece (-f)" />
            </when>
            <when value="text"> 
                <param name="input_sequence" type="text" label="RNA-sequece (-s)" />
            </when>
        </conditional>
        
        <param name="predict_segments" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Enable segment prediction functionality (-p)" />
        <param name="min_hairpin_size" type="integer" min="1" value="3" label="Minimum hairpin size (-h)" />
        
        <conditional name="parameters">
            <param name="settings" type="select" label="Energy parameters">
                <option value="default" selected="true">Default</option>
                <option value="custom">Custom</option>
            </param>
            <when value="default" />
            <when value="custom"> 
                <param name="input_xml" type="data" format="xml" multiple="false" label="Use custom 'segments.xml'-syntaxed file (-x)" />
            </when>
        </conditional>
    </inputs>
    
    <outputs>
        <data format="dbn" name="output_dbn" label="segmentation-fold" />
        <!--<data format="dot-bracket" name="output_dbn" label="${tool.name} on ${str(input.input_fasta.hid) + ': ' + input.input_fasta.name if $input.method == 'fasta' else $input.input_sequence.upper() }" />-->
    </outputs>
    
    <tests>
        <test>
            <param  name="input_fasta" value="test_01.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_01.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_02.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_02.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_03.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_03.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_04.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_04.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_05.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_05.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_06.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_06.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_07.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_07.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_08.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_08.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_09.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_09.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_10.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_10.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_11.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_11.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_12.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_12.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_13.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_13.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_14.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_14.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_15.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_15.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_16.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_16.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_17.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_17.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_18.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_18.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_19.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_19.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_20.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_20.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_21.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_21.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_22.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_22.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_23.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_23.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_24.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_24.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_25.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_25.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_26.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_26.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_27.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_27.dbn" />
        </test>
        <test>
            <param  name="input_fasta" value="test_28.fa" ftype="fasta" />
            <output name="output_dbn"   file="test_28.dbn" />
        </test>
    </tests>
    
    <help><![CDATA[
**What it does**:

Segmentation-fold is a application in the field of bioinformatics that
predicts RNA 2D-structures. The model has an extension with respect to
the classical Zuker algorithm, to allow new "structure elements" named
segments and segmentloops. This makes it capable of folding a
pre-defined substructure with multiple canonical or non-canonical base
pairs, like K-turns and loop-E-motifs. Some of such sturcture elements
are present in the corresponding energy table, although custom tables
can be provided as well.


**Running segmentation-fold**

Segmentation-fold has to be provided with a sequence of which it has to
predict the 2D structure. This can be done using a plain text sequence
(allowed charset: ACTUG) or a FASTA file. A FASTA file has the following
syntax:

    >Sequence name and other details
    
    AGUGUAGCUGUGUCGAUCGUAAGUCAG

As the database of free energy parameters will most likely be updated
over time we have added the possiblity to include this XML file as
additional parameter. The most up to date version of this file can be
found at the following url:

https://github.com/yhoogstrate/segmentation-fold/blob/master/share/segmentation-fold/segments.xml

If you would like to compare the results with a prediction as if the
segment and segmentloop extension were disabled, you can disable it with
the given parameter.

**Output**

The output is in DotBracket format (dbn) and can be visualized with e.g.
DrawRNAjs or VaRNA.

DrawRNAjs can be installed in galaxy by following the instructions at
the following link:

https://github.com/bgruening/galaxytools/tree/master/visualisations/drawrnajs

Details on the dbn-format can be found here:

https://wiki.galaxyproject.org/Learn/Datatypes#Dbn

**Authors**

Youri Hoogstrate (yhoogstrate @ github)
    ]]></help>
    
    <citations>
        <citation type="bibtex">
           @mastersthesis{mastersthesis,
              author       = {Youri Hoogstrate}, 
              title        = {An algorithm for predicting RNA 2D structures including K-turns},
              school       = {University of Technology Delft, Leiden University},
              year         = 2012,
              address      = {},
              month        = 11,
              note         = {Research assignment for Master Computer-science},
              url          = { https://yh-kt-fold.googlecode.com/files/Report.pdf }
            }
        </citation>
    </citations>
</tool>