annotate sRbowtieCascade.xml @ 0:0528fced93a9 draft default tip

planemo upload for repository https://bitbucket.org/drosofff/gedtools/

<tool id="sRbowtie_cascade" name="Annotate smRNA datasets" version="1.0.1">
  <description>Using iterative sRbowtie Alignments</description>
  <requirements>
        <requirement type="package" version="0.12.7">bowtie</requirement>
  </requirements>
  <command interpreter="python"> sRbowtieCascade.py --output $output
                                                    --num-threads \${GALAXY_SLOTS:-4} ## number of processors to be handled by bowtie
                                                    --mismatch $mismatches
                                                    --input
						    #for $i in $input:
						      $i
						    #end for
                                                   --label
                                                    #for $i in $input:
                                                      "$i.name"
                                                    #end for
                                                   --index
                                                    #if $refGenomeSource1.genomeSource == "history":
                                                      $refGenomeSource1.ownFile
                                                    #else:
                                                      $refGenomeSource1.index.fields.path
                                                    #end if
                                                    #for $i in $AdditionalQueries:
						      #if $i.refGenomeSource.genomeSource == "history":
						        $i.refGenomeSource.ownFile
                                                      #else:
                                                        $i.refGenomeSource.index.fields.path
                                                      #end if
                                                    #end for
                                                   --indexing-flags
						    $refGenomeSource1.genomeSource
                                                    #for $i in $AdditionalQueries:
						      $i.refGenomeSource.genomeSource
                                                    #end for
                                                   --indexName
                                                    #if $refGenomeSource1.genomeSource == "history":
                                                      "$refGenomeSource1.ownFile.name"
                                                    #else:
                                                      "$refGenomeSource1.index.fields.name"
                                                    #end if
                                                    #for $i in $AdditionalQueries:
                                                      #if $i.refGenomeSource.genomeSource == "history":
                                                        "$i.refGenomeSource.ownFile.name"
                                                      #else:
                                                        "$i.refGenomeSource.index.fields.name"
                                                      #end if
                                                    #end for
  </command>
  <inputs>
      <param name="input" type="data" format="fasta" label="Input fasta file: reads clipped from their adapter" help="Only with clipped, raw fasta files" multiple="true"/>
    <param name="mismatches" type="select" label="Number of mismatches allowed" help="specify the number of mismatches allowed during alignments">
        <option value="0">0</option>
        <option value="1" selected="true">1</option>
        <option value="2">2</option>
        <option value="3">3</option>
    </param>
<!-- First bowtie index selection -->
    <conditional name="refGenomeSource1">
      <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
        <option value="indexed">Use a built-in index</option>
        <option value="history">Use one from the history</option>
      </param>
      <when value="indexed">
        <param name="index" type="select" label="Select a DNA reference index" help="if your genome of interest is not listed - contact instance administrator">
          <options from_data_table="bowtie_indexes"/>
        </param>
      </when>
      <when value="history">
        <param name="ownFile" type="data" format="fasta" label="Select a fasta file, to serve as index reference" />
      </when>
    </conditional>
<!-- End of first bowtie index selection -->
<!-- other  bowtie index selections -->
    <repeat name="AdditionalQueries" title="Additional Alignment Step">
	<conditional name="refGenomeSource">
      		<param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
			<option value="indexed">Use a built-in index</option>
			<option value="history">Use one from the history</option>
		</param>
		<when value="indexed">
			<param name="index" type="select" label="Select a DNA reference index" help="if your genome of interest is not listed - contact instance administrator">
				<options from_data_table="bowtie_indexes"/>
			</param>
		</when>
		<when value="history">
			<param name="ownFile" type="data" format="fasta" label="Select a fasta file, to serve as index reference" />
		</when>
        </conditional>
    </repeat>
<!-- End of other bowtie index selections -->
   </inputs>
   <outputs>
   <data format="tabular" name="output" label="Cascade Annotation Analysis"/>
   </outputs>


    <tests>
        <test>
      <param name="input" value ="sample1.fa,sample2.fa,sample3.fa" ftype="fasta" />
      <param name="genomeSource" value="history" />
      <param name="ownFile" value ="dmel-2L-r6.04.fasta" ftype="fasta" />
      <param name="AdditionalQueries_0|refGenomeSource|genomeSource" value="history"/>
      <param name="AdditionalQueries_0|refGenomeSource|ownFile" value="dme_miR21_hairpin.fa" ftype="fasta" />
      <param name="AdditionalQueries_1|refGenomeSource|genomeSource" value="history"/>
      <param name="AdditionalQueries_1|refGenomeSource|ownFile" value="Ensembl_transposon_set.fa" ftype="fasta" />
      <output name="output" ftype="tabular" file="Cascade_Annotation_Analysis.tab" />
        </test>
    </tests>
  <help>

**Intro**

Bowtie_ is a short read aligner designed to be ultrafast and memory-efficient.
A generic "Map with Bowtie for Illumina" Galaxy tool is available in the main Galaxy distribution.
However, this Bowtie wrapper tool only takes FASTQ files as inputs.

Here The sRbowtie wrapper specifically works with short reads FASTA inputs (-v bowtie mode, with -k 1)

.. _Bowtie: http://bowtie-bio.sourceforge.net/index.shtml


------

**What it does**

.. class:: infomark

This script uses the sRbowtie wrapper to iteratively match reads on a reference indexes.

Reads are Matched on DNA references as fast as possible, without taking care of mapping issues

*-v [0,1,2,3] -k 1 --best -p 12 --suppress 6,7,8*

unaligned reads at step N are used as input for sRbowtie at step N+1

-----

**Input formats**

.. class:: warningmark

*The only accepted format for the script is a raw fasta list of reads, clipped from their adapter*

-----

**OUTPUTS**

**Annotation table**

  </help>
</tool>