comparison picard_CollectRnaSeqMetrics.xml @ 7:08f69add4d06 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92

6:961236c5ec73

    <description> collect metrics about the alignment of RNA to various functional classes of loci in the genome</description>
    <macros>
        <import>picard_macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="3.1.2">R</requirement>
    </expand>
    <command>

      ## Set up input files
      
      ## Reference sequences

      #set $reference_fasta_filename = "localref.fa"
    
      #if str( $reference_source.reference_source_selector ) == "history":
        ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" &amp;&amp;
      #else:
        #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path )
      #end if
      
      ## refFlat data
      ## The awk line below converts a file obtained from UCSC as specified in the tool help to refFlat format
      
      grep -v '^#' ${refFlat} | awk '{print $11"\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10}' > refFlat.tab &amp;&amp;
      
      ## Start picard command
      
      @java_options@
      java -jar \$JAVA_JAR_PATH/picard.jar
      CollectRnaSeqMetrics
      REF_FLAT=refFlat.tab
      
      #if str( $ribosomal_intervals ) != "None":
	 RIBOSOMAL_INTERVALS="${ribosomal_intervals}"

     
      QUIET=true
      VERBOSITY=ERROR
      VALIDATION_STRINGENCY=${validation_stringency}
    
   </command>
   
   <inputs>
      <param format="sam,bam" type="data" name="inputFile" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset" />
      <conditional name="reference_source">
	 <param name="reference_source_selector" type="select" label="Load reference genome from">

	 </when>
      </conditional>        
      <param format="tabular" name="refFlat" type="data" label="Gene annotations in refFlat form" help="See &quot;Obtaining gene annotations in refFlat format&quot; below for help" />
      <param name="ribosomal_intervals" format="picard_interval_list" type="data" optional="True" label="Location of rRNA sequences in genome, in interval_list format" help="RIBOSOMAL_INTERVALS; If not specified no bases will be identified as being ribosomal. The list of intervals can be geberated from BED or Interval datasets using Galaxy BedToIntervalList tool"/>
      <param name="strand_specificity" type="select" label="What is the RNA-seq library strand specificity" help="STRAND_SPECIFICITY; For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND if the reads are expected to be on the transcription strand.">
	 <option value="NONE" select="True">None</option>
	 <option value="FIRST_READ_TRANSCRIPTION_STRAND">First read transcription strand</option>
	 <option value="SECOND_READ_TRANSCRIPTION_STRAND">Second read transcription strand</option>
      </param>
      <param name="minimum_length" type="integer" value="500" label="When calculating coverage based values use only use transcripts of this length or greater" help="MINIMUM_LENGTH; default=500"/>
      <repeat name="ignore_list" title="Sequences to ignore" min="0" help="You can provide multiple sequences by clicking the button below">

  <outputs>
      <data format="pdf" name="pdfFile" label="${tool.name} on ${on_string}: Chart PDF"/>
      <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Summary stats"/>
  </outputs>
  
   <stdio>
    <exit_code range="1:"  level="fatal"/>
  </stdio>
  <tests>
    <test>
      <param name="reference_source_selector" value="history"/>
      <param name="ref_file" value="picard_CollectRnaSeqMetrics_ref.fa" ftype="fasta"/>
      <param name="inputFile" value="picard_CollectRnaSeqMetrics.bam" ftype="bam"/>

7:08f69add4d06

    <description> collect metrics about the alignment of RNA to various functional classes of loci in the genome</description>
    <macros>
        <import>picard_macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="3.3.1">r</requirement>
    </expand>
    <command detect_errors="exit_code"><![CDATA[

      ## Set up input files
      
      ## Reference sequences

      #set $reference_fasta_filename = "localref.fa"
    
      #if str( $reference_source.reference_source_selector ) == "history":
        ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" &&
      #else:
        #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path )
      #end if
      
      ## refFlat data
      ## The awk line below converts a file obtained from UCSC as specified in the tool help to refFlat format
      
      grep -v '^#' ${refFlat} | awk '{print $11"\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10}' > refFlat.tab &&
      
      ## Start picard command
      
      @java_options@
      picard
      CollectRnaSeqMetrics
      REF_FLAT=refFlat.tab
      
      #if str( $ribosomal_intervals ) != "None":
	 RIBOSOMAL_INTERVALS="${ribosomal_intervals}"

     
      QUIET=true
      VERBOSITY=ERROR
      VALIDATION_STRINGENCY=${validation_stringency}
    
   ]]></command>
   
   <inputs>
      <param format="sam,bam" type="data" name="inputFile" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset" />
      <conditional name="reference_source">
	 <param name="reference_source_selector" type="select" label="Load reference genome from">

	 </when>
      </conditional>        
      <param format="tabular" name="refFlat" type="data" label="Gene annotations in refFlat form" help="See &quot;Obtaining gene annotations in refFlat format&quot; below for help" />
      <param name="ribosomal_intervals" format="picard_interval_list" type="data" optional="True" label="Location of rRNA sequences in genome, in interval_list format" help="RIBOSOMAL_INTERVALS; If not specified no bases will be identified as being ribosomal. The list of intervals can be geberated from BED or Interval datasets using Galaxy BedToIntervalList tool"/>
      <param name="strand_specificity" type="select" label="What is the RNA-seq library strand specificity" help="STRAND_SPECIFICITY; For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND if the reads are expected to be on the transcription strand.">
	 <option value="NONE" selected="True">None</option>
	 <option value="FIRST_READ_TRANSCRIPTION_STRAND">First read transcription strand</option>
	 <option value="SECOND_READ_TRANSCRIPTION_STRAND">Second read transcription strand</option>
      </param>
      <param name="minimum_length" type="integer" value="500" label="When calculating coverage based values use only use transcripts of this length or greater" help="MINIMUM_LENGTH; default=500"/>
      <repeat name="ignore_list" title="Sequences to ignore" min="0" help="You can provide multiple sequences by clicking the button below">

  <outputs>
      <data format="pdf" name="pdfFile" label="${tool.name} on ${on_string}: Chart PDF"/>
      <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Summary stats"/>
  </outputs>
  
  <tests>
    <test>
      <param name="reference_source_selector" value="history"/>
      <param name="ref_file" value="picard_CollectRnaSeqMetrics_ref.fa" ftype="fasta"/>
      <param name="inputFile" value="picard_CollectRnaSeqMetrics.bam" ftype="bam"/>