view preProcess.xml @ 52:8b8c356e6db5 draft

Uploaded
author big-tiandm
date Fri, 05 Dec 2014 01:28:46 -0500
parents 7b5a48b972e9
children
line wrap: on
line source

<tool id="preprocess" name="preProcess" veision="1.0.0">
  <description>tool for Raw data preprocess analisis, including 3' adapter triming, reads collaping, genome mapping and  rfam non-miRNA analysis </description>

  <requirements>
	<requirement type="package" version="0.0.13">fastx_toolkit </requirement>
    <requirement type="package" version="0.12.7">bowtie</requirement>
    <requirement type="set_environment">SCRIPT_PATH</requirement>
    <!--requirement type="package" version="3.0.1">R</requirement!-->
	<requirement type="package" version="2.59">SVG</requirement>
	<requirement type="package" version="2.1.8">ViennaRNA</requirement>
  </requirements>

  <!--command interpreter="perl">miPlant.pl -i $input -format $format -gfa $gfa -idx $index -pre $pre -mat $mat -rfam $rfam -idx2 $idx2 -D $D -a $a -M $M -min $min -max $max -mis $mis -e $e -f $f -v $v -r $r -dis $dis -flank $flank -mfe $mfe -t $t -o $output</command-->

  <command interpreter="perl">preProcess.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

   ## Do or not annotate rfam non-miRNA RNAs
    #if $params.annotate_rfam == "yes":
		  ## prepare Rfam bowtie index
		  #set rfam_index_path = ''
		  #if str($params.annotate_rfam.reference_rfam.source) == "history":
			  bowtie-build "$params.annotate_rfam.reference_rfam.own_file" rfam; ln -s "$params.annotate_rfam.reference_rfam.own_file" rfam.fa;
			  #set rfam_index_path = 'rfam'
		  #else:
			  #set rfam_index_path = $params.annotate_rfam.reference_rfam.index.fields.path
		  #end if

		-rfam ${rfam_index_path}.fa -idx2 $rfam_index_path -v $v 
	#end if

        ## prepare bowtie index
        #set index_path = ''
        #if str($reference_genome.source) == "history":
            bowtie-build "$reference_genome.own_file" genome; ln -s "$reference_genome.own_file" genome.fa;
            #set index_path = 'genome'
        #else:
            #set index_path = $reference_genome.index.fields.path
		#end if

    -format $format -gfa ${index_path}.fa -idx $index_path -phred $phred -a $a -M $mapnt -min $min -max $max -mis $mismatch  > run.log
  </command>

  <inputs>

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

	<!--param name="input" format="tabular"  type="data" label="input config file" /-->
	
	<param name="format" type="select" lable="raw data format" multiple="false">
	  <option value="fastq">Raw data is fastq. format</option>
	  <option value="fasta">Raw data is fasta. format</option>
	</param>

	        <!-- reference genome -->
        <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 name="gfa"  type="data" label="genome sequence fasta file"/-->
	<!--param type="data" name="index" label="genome sequence bowtie index"/-->
	<param name="phred" type="select" lable="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>
	<param name="a" type="text" value="ATCTCGTATG" label="3' adapter sequence" />
	<param name="mapnt" type="integer" value="8" label="minimum adapter map nts" />
	<param name="min" type="integer" value="19" label="minimum microRNA length" />
	<param name="max" type="integer" value="28" label="maximum microRNA length" />
	<param name="mismatch" type="integer" value="0" label="number of allowed mismatches when mapping reads to genome" />

	<conditional name="params">
		<param name="annotate_rfam" type="select" label="annotate rfam nocoding RNAs(excluding miRNA)">
		  <option value="yes" selected="true">yes</option>
		  <option value="no">no</option>
		 </param>
		 <when value="yes">
			<!--param name="rfam" type="data" label="rfam sequence file" /-->
			<conditional name="reference_rfam">
			  <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" help="If your reference 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="v" type="integer" value="0" label="report end-to-end hits less than v mismatches for rfam mapping"/>
		 </when>
    </conditional> 



  </inputs>

  <outputs>
   <data format="html" name="preprocess result" from_work_dir="preProcess/preprocessResult.html" label="${tool.name} on ${on_string}: preprocess result"/>

   <data format="txt" name="clean FASTA data" from_work_dir="preProcess/preProcess_clean/collapse_reads_$min_$max.fa" label="${tool.name} on ${on_string}: clean FASTA data"/>

   <data format="txt" name="genome mapping result" from_work_dir="preProcess/genome_match/genome_mapped.bwt" label="${tool.name} on ${on_string}: genome mapping result"/>
   <data format="txt" name="genome mapped FASTA reads" from_work_dir="preProcess/genome_match/genome_mapped.fa" label="${tool.name} on ${on_string}: genome mapped FASTA reads"/>

   <data format="txt" name="Rfam mapping result" from_work_dir="preProcess/rfam_match/rfam_mapped.bwt" label="${tool.name} on ${on_string}: Rfam mapping result">
   <filter>(params['annotate_rfam'] == 'Yes')</filter>
   </data>
   <data format="txt" name="Rfam mapped FASTA file" from_work_dir="preProcess/rfam_match/rfam_mapped.fa" label="${tool.name} on ${on_string}: Rfam mapped FASTA file">
   <filter>(params['annotate_rfam'] == 'Yes')</filter>
   </data>
   <data format="txt" name="Rfam not mapped FASTA file" from_work_dir="preProcess/rfam_match/rfam_not_mapped.fa" label="${tool.name} on ${on_string}: Rfam not mapped FASTA file">
   <filter>(params['annotate_rfam'] == 'Yes')</filter>
   </data>
   <data format="html" name="input config" from_work_dir="preProcess/input_config" label="${tool.name} on ${on_string}: input config"/>

  </outputs>

 <help>

 </help>
 </tool>