comparison picard_CollectRnaSeqMetrics.xml @ 8:e417b1d6288d draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e

7:08f69add4d06

        <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}"
      #end if
      
      STRAND_SPECIFICITY="${strand_specificity}"
      MINIMUM_LENGTH="${minimum_length}"
      CHART_OUTPUT="${pdfFile}"

      #for $sequence_to_ignore in $ignore_list:
	 IGNORE_SEQUENCE="${sequence_to_ignore.sequence}"
      #end for
      
      RRNA_FRAGMENT_PERCENTAGE="${rrna_fragment_percentage}"
      METRIC_ACCUMULATION_LEVEL="${metric_accumulation_level}"
      INPUT="${inputFile}"
      OUTPUT="${outFile}"
      REFERENCE_SEQUENCE="${reference_fasta_filename}"
      ASSUME_SORTED="${assume_sorted}"
     
      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">
	    <option value="cached">Local cache</option>

	    </param>
	 </when>
	 <when value="history">
	    <param name="ref_file" type="data" format="fasta" label="Use the folloing dataset as the reference sequence" help="REFERENCE_SEQUENCE; You can upload a FASTA sequence to the history and use it as reference" />
	 </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="SAMPLE">Sample</option>
	 <option value="LIBRARY">Library</option>
	 <option value="READ_GROUP">Read group</option>
      </param>
      <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED"/>
      
      <expand macro="VS" />

  </inputs>
  <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"/>

      proteinId
   7. Click **done with selection**
   8. Click **Send query to Galaxy**
   9. A new dataset will appear in the current Galaxy history
   10. Use this dataset as the input for **Gene annotations in refFlat form** dropdown of this tool
   
.. _refFlat: http://genome.ucsc.edu/goldenPath/gbdDescriptionsOld.html#RefFlat

@description@

   REF_FLAT=File                 Gene annotations in refFlat form.  Format described here: 
                                 http://genome.ucsc.edu/goldenPath/gbdDescriptionsOld.html#RefFlat  Required. 

   RIBOSOMAL_INTERVALS=File      Location of rRNA sequences in genome, in interval_list format.  If not specified no bases 
                                 will be identified as being ribosomal. Format described here: 
                                 http://picard.sourceforge.net/javadoc/net/sf/picard/util/IntervalList.html  and can be
				 generated from BED datasetes using Galaxy's wrapper for picard_BedToIntervalList tool

   STRAND_SPECIFICITY=StrandSpecificity
   STRAND=StrandSpecificity      For strand-specific library prep. For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND 
                                 if the reads are expected to be on the transcription strand.  Required. Possible values: 
                                 {NONE, FIRST_READ_TRANSCRIPTION_STRAND, SECOND_READ_TRANSCRIPTION_STRAND} 

   MINIMUM_LENGTH=Integer        When calculating coverage based values (e.g. CV of coverage) only use transcripts of this 
                                 length or greater.  Default value: 500.

   IGNORE_SEQUENCE=String        If a read maps to a sequence specified with this option, all the bases in the read are 
                                 counted as ignored bases.  

   RRNA_FRAGMENT_PERCENTAGE=Double
                                 This percentage of the length of a fragment must overlap one of the ribosomal intervals 
                                 for a read or read pair by this must in order to be considered rRNA.  Default value: 0.8. 

   METRIC_ACCUMULATION_LEVEL=MetricAccumulationLevel
   LEVEL=MetricAccumulationLevel The level(s) at which to accumulate metrics.    Possible values: {ALL_READS, SAMPLE, 
                                 LIBRARY, READ_GROUP} This option may be specified 0 or more times.
				 
   ASSUME_SORTED=Boolean
   AS=Boolean                    If true (default), then the sort order in the header file will be ignored.  Default 
                                 value: true. Possible values: {true, false} 

@more_info@

  </help>
</tool>

8:e417b1d6288d

        <requirement type="package" version="3.3.1">r</requirement>
    </expand>
    <command detect_errors="exit_code"><![CDATA[

      ## Set up input files
      @symlink_element_identifier@
      ## 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}"
      #end if

      STRAND_SPECIFICITY="${strand_specificity}"
      MINIMUM_LENGTH="${minimum_length}"
      CHART_OUTPUT="${pdfFile}"

      #for $sequence_to_ignore in $ignore_list:
	 IGNORE_SEQUENCE="${sequence_to_ignore.sequence}"
      #end for

      RRNA_FRAGMENT_PERCENTAGE="${rrna_fragment_percentage}"
      METRIC_ACCUMULATION_LEVEL="${metric_accumulation_level}"
      INPUT='$inputFile.element_identifier'
      OUTPUT="${outFile}"
      REFERENCE_SEQUENCE="${reference_fasta_filename}"
      ASSUME_SORTED="${assume_sorted}"

      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">
	    <option value="cached">Local cache</option>

	    </param>
	 </when>
	 <when value="history">
	    <param name="ref_file" type="data" format="fasta" label="Use the folloing dataset as the reference sequence" help="REFERENCE_SEQUENCE; You can upload a FASTA sequence to the history and use it as reference" />
	 </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="SAMPLE">Sample</option>
	 <option value="LIBRARY">Library</option>
	 <option value="READ_GROUP">Read group</option>
      </param>
      <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED"/>

      <expand macro="VS" />

  </inputs>
  <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"/>

      proteinId
   7. Click **done with selection**
   8. Click **Send query to Galaxy**
   9. A new dataset will appear in the current Galaxy history
   10. Use this dataset as the input for **Gene annotations in refFlat form** dropdown of this tool

.. _refFlat: http://genome.ucsc.edu/goldenPath/gbdDescriptionsOld.html#RefFlat

@description@

   REF_FLAT=File                 Gene annotations in refFlat form.  Format described here:
                                 http://genome.ucsc.edu/goldenPath/gbdDescriptionsOld.html#RefFlat  Required.

   RIBOSOMAL_INTERVALS=File      Location of rRNA sequences in genome, in interval_list format.  If not specified no bases
                                 will be identified as being ribosomal. Format described here:
                                 http://picard.sourceforge.net/javadoc/net/sf/picard/util/IntervalList.html  and can be
				 generated from BED datasetes using Galaxy's wrapper for picard_BedToIntervalList tool

   STRAND_SPECIFICITY=StrandSpecificity
   STRAND=StrandSpecificity      For strand-specific library prep. For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND
                                 if the reads are expected to be on the transcription strand.  Required. Possible values:
                                 {NONE, FIRST_READ_TRANSCRIPTION_STRAND, SECOND_READ_TRANSCRIPTION_STRAND}

   MINIMUM_LENGTH=Integer        When calculating coverage based values (e.g. CV of coverage) only use transcripts of this
                                 length or greater.  Default value: 500.

   IGNORE_SEQUENCE=String        If a read maps to a sequence specified with this option, all the bases in the read are
                                 counted as ignored bases.

   RRNA_FRAGMENT_PERCENTAGE=Double
                                 This percentage of the length of a fragment must overlap one of the ribosomal intervals
                                 for a read or read pair by this must in order to be considered rRNA.  Default value: 0.8.

   METRIC_ACCUMULATION_LEVEL=MetricAccumulationLevel
   LEVEL=MetricAccumulationLevel The level(s) at which to accumulate metrics.    Possible values: {ALL_READS, SAMPLE,
                                 LIBRARY, READ_GROUP} This option may be specified 0 or more times.

   ASSUME_SORTED=Boolean
   AS=Boolean                    If true (default), then the sort order in the header file will be ignored.  Default
                                 value: true. Possible values: {true, false}

@more_info@

  </help>
</tool>