annotate fasta2shrep_gspan.xml @ 6:fcb1bb6dc0f9 draft

planemo upload for repository https://github.com/eteriSokhoyan/galaxytools/tree/branchForIterations/tools/GraphClust/GSPAN commit 4dd7269185f6fb9bdc007028007d6540f4cf057d

<tool id="gspan" name="fasta_to_gspan" version="0.1">
    <requirements>
        <requirement type="package" version="0.1.12">graphclust-wrappers</requirement>
        <requirement type="package" version="2.1.6">rnashapes</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command>
    <![CDATA[
      fasta2shrep_gspan.pl
            --fasta '$dataFasta'
            $i_crop_unpaired_ends
            $i_abstr
            $i_stacks
            -t '3=0,5=80'
            -M $M
            -c $rel_energy_range
            -win $wins
            -shift $shift
            $u
            $seq_graph_t
            -group $group

    ]]>
    </command>
    <inputs>
        <param type="data" name="dataFasta" format="fasta" label="Input file in FASTA format" />
        <param name="i_stacks" truevalue="-stack" falsevalue="" checked="True"  type="boolean"
            label="Add stacking information to graphs." help="-stack"/>
        <param name="i_abstr" truevalue="-abstr" falsevalue=""  type="boolean"
            label="Add abstract structure graphs to the single shrep graph instances." help="-abstr"/>
        <param name="i_crop_unpaired_ends" truevalue="-cue" falsevalue=""  type="boolean"
            label="Add abstract structure graphs to the single shrep graph instances." help="-cue"/>
        <param name="M" type="integer" value="5" label="Max number of shreps that should be taken per window." help="-M"/>
        <param name="rel_energy_range" type="integer" value="20"
            label=" Relative energy range, i.e. percentage (%) of MFE energy (RNAshapes)" help="-c"/>
        <param name="wins" type="text" value="40,150"
            label=" A list of window sizes to use" help="comma separated integers"/>
        <param name="shift" type="integer" value="30"
            label="The shift of the window, relative to the window size given inpercent." help="by default 30"/>
        <param name="u" truevalue="-u" falsevalue="" checked="True" type="boolean"
            label="Ignore unstable structures (RNAshapes)" help="-u"/>
        <param name="seq_graph_t" truevalue="-seq-graph-t" falsevalue="" checked="True"  type="boolean"
            label="Add for each 't #' a graph which contains no structure" help="--seq-graph-t"/>
        <param name="group" type="integer" value="10000"
            label="Group size" help="by default 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="dataFasta" value="data.fasta"/>
            <param name="i_stacks" value="True" />
            <param name="i_abstr" value="False" />
            <param name="i_crop_unpaired_ends" value="False" />
            <param name="M" value="5" />
            <param name="rel_energy_range" value="20" />
            <param name="wins" value="40,150" />
            <param name="shift" value="30" />
            <param name="u" value="True" />
            <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/1.group.gspan.bz2"/>
            </output_collection>
        </test>
    </tests>
    <help>
    <![CDATA[

**What it does**

For each fragment of input sequence we use RNAshapes to create a set of structures.
The default parameters for example consider for each input fragment again a
window of size 40nt and 150nt with a window shift of 30%. This allows to
consider local structures as well as global structures for a fragment.
From each such RNAshape window we take the top 5 shreps (suboptimal
structures for the top 5 shapes) within 20% of the mfe energy of that window
and convert them into graphs.
As shape level (abstraction level) we use 3 for short sequences and 5 for
sequences >= 80nt. Please see also RNAshapes documentation for all these
terms.


**Parameters**

+ **input** : Sequences in Fasta format.

+ **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.

+ **cue** : Crop unpaired ends. If you give this flag, then the unpaired ends of each single structure are ignored. E.g. the structure
  ...(((...))).. becomes just (((...)))

+ **M** : Max number of shreps that should be taken per window.

+ **c** : Relative energy range, i.e. percentage (%) of MFE energy (RNAshapes) Use only one of -e and -c!

+ **wins** : A list of window sizes to use. If none are given (empty string ''), then the entire sequence is taken with no windows. Each window > 1 required!

+ **shift** : The shift of the window, relative to the window size given in percent. So you give which percent of the window size shall be
  used for the shift. Of course the shift is rounded down to the
  nearest whole number.
  Example 20 % of a window 150 would result in a step size of 30 nt.
  It is a relative parameter, as you can give different window sizes.
  If you do not give this parameter there is a default shift of 1 nt.

+ **u** : Ignore unstable structures (RNAshapes). This option filters out closed structures with positive free energy.

+ **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>
        <citation type="doi">10.1093/bioinformatics/btu649</citation>
    </citations>
</tool>