annotate structure_to_gspan.xml @ 1:133fc317a812 draft

planemo upload for repository https://github.com/mmiladi/galaxytools/blob/graphclust-gspan/tools/GraphClust/Structure_GSPAN commit 746497a64b955f6b9afc1944d1c1d8d877e53267

<tool id="structure_to_gspan" name="Structure to GSPAN" version="0.2">
    <requirements>
        <requirement type="package" version="0.3.1">graphclust-wrappers</requirement>
    </requirements>
    <command detect_errors="exit_code">
    <![CDATA[
        mkdir ./temp/ ./GSPAN_Outputs/ &&
        which structure_2_gspan.pl && 
        structure_2_gspan.pl
            --input-file '$dataFile'
            --input-format '$inputFormat'
            --input-structure-type '$structureType'
            $abstr
            $stack
            $seq_graph_t
            -group $group
            -tmp ./temp
            -o ./GSPAN_Outputs/
    ]]>
    </command>
    <inputs>
        <param type="data" name="dataFile" format="dbn" label="Sequence and Structure input file in the prediction tool format" />
        <param name="inputFormat" type="text" value="vrna-simple"
            label="  Sequence Structure format of the input. Allowed formats: vrna-simple, vrna-mea" help="-input-format"/>
        <param name="structureType" type="text" value="MFE"
            label="  Sequence Structure type from the input to use. Allowed types: MFE, MEA" help="-input-structure-type"/>
        <param argument="-stack" truevalue="-stack" falsevalue="" checked="true"  type="boolean"
            label="Add stacking information to graphs"/>
        <param argument="abstr" truevalue="-abstr" falsevalue="" type="boolean"
            label="Add abstract structure graphs to the single shrep graph instances."/>
        <param argument="-seq-graph-t" name="seq_graph_t" truevalue="-seq-graph-t" falsevalue="" checked="true" type="boolean"
            label="Add for each 't #' a graph which contains no structure"/>
        <param name="group" type="integer" value="10000"
            label="Group size" help="Default is 10000"/>
    </inputs>
    <outputs>
        <collection name="gspan_compressed" type="list" label="GSPAN Groups" >
            <discover_datasets pattern="(?P&lt;name&gt;.*)\.bz2$" directory="GSPAN_Outputs" />
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="dataFile" value="sample_3.struct"/>
            <param name="i_stacks" value="True" />
            <param name="i_abstr" value="False" />
            <param name="seq_graph_t" value="True" />
            <param name="group" value="10000" />
            <output_collection name="gspan_compressed" type="list">
                <element name="1.group.gspan" file="GSPAN_Outputs/sample_3.1.group.gspan.bz2"/>
            </output_collection>
        </test>
    </tests>
    <help>
    <![CDATA[

**What it does**
For each pair of sequence and structure provided in the input file
and convert them into GSPAN format graphs.


**Parameters**

+ **input** : The sequence and structure data, the output of structure prediction tool.

+ **input-format** : Sequence Structure format of the input. Allowed format: "vrna-simple" "vrna-mea"
                        example of input-file for vrna-simple format:
                        >seq1
                        CCGGGCGUGCUG
                        .(((.....))) ( -0.30)
                        >seq2
                        GCGGUUGCCG
                        .(((...))) ( -0.50)

                        example of input-file for vrna-simple format:
                        >seq1
                        CCGGGCGUGCUG
                        .(((.....))) ( -0.30)
                        .{{{.....}}} [ -0.67]
                        .(((.....))) { -0.30 d=1.29}
                        .(((.....))) { -0.30 MEA=9.52}
                         frequency of mfe structure in ensemble 0.550454; ensemble diversity 1.58  
                        >seq2
                        GCGGUUGCCG
                        .(((...))) ( -0.50)
                        .({{...)}, [ -0.99]
                        ..((...)). {  0.60 d=1.89}
                        .(((...))) { -0.50 MEA=6.60}
                         frequency of mfe structure in ensemble 0.452041; ensemble diversity 2.26 

   
+ **stack** : This adds an additional vertex (type P) for each pair of stacked base-pairs and four edges
  (type p) from each of the involved bases to the new vertex.

+ **abstr** : Add abstract structure graphs to the single shrep graph instances.

+ **seq-graph-t** : Add for each 't #' a graph which contains no structure

+ **group** : Combine/group that number of input seqs into 1 gspan file output name is then '<INT>.group.gspan.bz2'

    ]]>
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/bts224</citation>
    </citations>
</tool>