view siRNA_pipeline.xml @ 0:87fe81de0931 draft default tip

Uploaded

<tool id="plant_sirna_pipeline_v1" name="siRNA_pipeline" veision="1.0.0">
  <description>Program for plant siRNA analysis (rawdata preprocess -> genome alignment -> non-coding annotate ->  siRNA analysis)</description>

  <requirements>
    <requirement type="set_environment">SCRIPT_PATH</requirement>
    <requirement type="package" version="0.12.7">bowtie</requirement>
    <requirement type="package" version="3.0.1">R</requirement>
	<requirement type="package" version="0.0.13">fastx_toolkit </requirement>
	<requirement type="package" version="1.96">threads</requirement>
	<requirement type="package" version="1.06">Parallel-ForkManager</requirement>
	<requirement type="package" version="2.59">SVG</requirement>
	<requirement type="package" version="1.4_001">Boost-Graph</requirement>
  </requirements>

  <command interpreter="perl">siRNA_pipeline.pl 
   ## Change this to accommodate the number of threads you have available.
        -t \${GALAXY_SLOTS:-4}

	-path \$SCRIPT_PATH

    #for $j, $s in enumerate( $series )
    ##rank_of_series=$j
    -i ${s.input}
    -tag ${s.tag}
    #end for

      ## prepare bowtie index
      #set index_path = ''
      #if str($reference_genome.source) == "history":
          #set index_path = $reference_genome.own_file
		-g  $index_path 
	  #else:
          #set index_path = $reference_genome.index.fields.path
		-g ${index_path}.fa -idx $index_path 
	  #end if


	  ## prepare Rfam bowtie index
	  #set rfam_index_path = ''
	  #if str($reference_rfam.source) == "history":
		  #set rfam_index_path = $reference_rfam.own_file
		-rfam $rfam_index_path -v $v 
	  #else:
		  #set rfam_index_path = $reference_rfam.index.fields.path
		-rfam ${rfam_index_path}.fa -idx2 $rfam_index_path -v $v 
	  #end if



   ## Do or not annotate siRNAs by function
    #if $params.function_anno == "yes":

      ## prepare bowtie index
      #set nat_path = ''
      #if str($params.nat_file.source) == "history":
          #set nat_path = $params.nat_file.nat

	  #else:
          #set nat_path = $params.nat_file.index.fields.path
	  #end if

      ## prepare bowtie index
      #set repeat_path = ''
      #if str($params.repeat_file.source) == "history":
          #set repeat_path = $params.repeat_file.repeat

	  #else:
          #set repeat_path = $params.repeat_file.index.fields.path
	  #end if


	 -nat $nat_path -repeat $repeat_path
	#end if
   
   ## Do or not DEG
    #if $degseq.degseq_analysis == "yes" :
    -deg $degseq.deg
    #end if

  -format $format -phred $phred -f $gff -mis $mis -a $a -n $mapnt -d $d -p $p -l $l  -cen $cen -span $span > run.log

  </command>

  <inputs>

   <repeat name="series" title="Raw sequence data file">
     <param name="input" type="data" label="Raw data file"/>
     <param name="tag" type="text" data_ref="input" label="Sample name of raw data"/>
   </repeat>

	<param name="format" type="select" label="raw data format" multiple="false">
	  <option value="fastq">Raw data is fastq. format</option>
	  <option value="fasta">Raw data is fasta. format</option>
	</param>
	
	<param name="phred" type="select" label="input quals are Phred+64 or Phred+33" multiple="false">
	  <option value="64">Phred+64</option>
	  <option value="33" selected="true">Phred+33</option>
	</param>

        <conditional name="reference_genome">
          <param name="source" 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 reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
              <options from_data_table="bowtie_indexes">
                <filter type="sort_by" column="2"/>
                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
              </options>
            </param>
          </when>
          <when value="history">
            <param name="own_file" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" />
          </when>
        </conditional>	<!--param type="data" name="index" label="genome sequence bowtie index"/-->

	        <conditional name="reference_rfam">
          <param name="source" type="select" label="Will you select a rfam reference  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 non-coding reference " help="If your rfam of interest is not listed, contact the Galaxy team">
              <options from_data_table="rfam_bowtie_indexes">
                <filter type="sort_by" column="2"/>
                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
              </options>
            </param>
          </when>
          <when value="history">
            <param name="own_file" type="data" format="fasta" metadata_name="dbkey" label="Select the reference" />
          </when>
        </conditional>

	<param name="gff" type="data" label="gff file" />
	<param name="mis" type="integer" value="0" label="number of allowed mismatches when mapping reads to genome" />
	<param name="v" type="integer" value="0" label="report end-to-end hits less than v mismatches for non-coding alignment"/>
	<param name="a" type="text" value="TGGAATTCTCGGGTGCCAAGG" label="3' adapter sequence" />
	<param name="mapnt" type="integer" value="25" label="a read is allowed to map up to this number of positions in the genome" />
	<param name="d" type="integer" value="100" label="distance of tag to merged a cluster" />

	<param name="p" type="select" label="siRNA cluster identify method" multiple="false">
	  <option value="F">conventional</option>
	  <option value="T">NIBLES</option>
	</param>
	<param name="l" type="integer" value="1000" label="the length of the upstream and downstream,used in position annotate" />


	<conditional name="params">
		<param name="function_anno" type="select" label="Do or not annotate siRNAs by function">
		  <option value="no" selected="true">no</option>
		  <option value="yes">yes</option>
		 </param>
		 <when value="yes">


        <conditional name="nat_file">
          <param name="source" type="select" label="Will you select a atural antisense transcripts file from your history ?" help="down load from ***">
            <option value="indexed">Use a built-in file</option>
            <option value="history">Use one from the history</option>
          </param>
          <when value="indexed">
            <param name="index" type="select" label="Select a atural antisense transcripts file" help="If your species of interest is not listed, contact the Galaxy team">
              <options from_data_table="nat_annotate">
                <filter type="sort_by" column="2"/>
                <validator type="no_options" message="No files are available for the selected input dataset"/>
              </options>
            </param>
          </when>
          <when value="history">
            <param name="nat" type="data" format="txt" metadata_name="dbkey" label="atural antisense transcripts file" />
		  </when>
        </conditional>	<!--param type="data" name="index" label="genome sequence bowtie index"/-->

        <conditional name="repeat_file">
          <param name="source" type="select" label="Will you select a repeat information file from your history ?" help="down load from ***">
            <option value="indexed">Use a built-in file</option>
            <option value="history">Use one from the history</option>
          </param>
          <when value="indexed">
            <param name="index" type="select" label="Select a repeat information file" help="If your species of interest is not listed, contact the Galaxy team">
              <options from_data_table="repeat_annotate">
                <filter type="sort_by" column="2"/>
                <validator type="no_options" message="No files are available for the selected input dataset"/>
              </options>
            </param>
          </when>
          <when value="history">
			<param name="repeat" type="data" metadata_name="dbkey" label="repeat information file out of Repeatmasker" />
		  </when>
        </conditional>	<!--param type="data" name="index" label="genome sequence bowtie index"/-->
		 </when>
    </conditional> <!-- params -->
	
	<param name="cen" type="data" label="centromere file input" />
	<param name="span" type="integer" value="50000" label="plot span" />
	
    <conditional name="degseq">
       <param name="degseq_analysis" type="select" label="Do or not identify Difference Expression Clusters">
		  <option value="no" selected="true">no</option>
		  <option value="yes">yes</option>
       </param>
       <when value="yes">
			<param name="deg" type="data" label="file config of de sample" />
        </when>
    </conditional>
    
  </inputs>

  <outputs>
   <data format="txt" name="siRNA cluster" from_work_dir="cluster_runs/total.result" label="${tool.name} on ${on_string}: siRNA cluster"/>
   <data format="html" name="analysis result" from_work_dir="cluster_runs/result.html" label="${tool.name} on ${on_string}: analysis result"/>

  </outputs>

 <help>

 </help>
 </tool>