annotate picard_CollectRnaSeqMetrics.xml @ 2:801f5e934011 draft default tip

Uploaded

<tool name="CollectRnaSeqMetrics" id="picard_CollectRnaSeqMetrics" version="1.122.0">
<description> collect metrics about the alignment of RNA to various functional classes of loci in the genome</description>
<requirements>
   <requirement type="package" version="1.122.0">picard</requirement>
</requirements>

<macros>
    <import>picard_macros.xml</import>
</macros>
  

   <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/CollectRnaSeqMetrics.jar
      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>
	    <option value="history">History</option>
	 </param>
	 <when value="cached">
	    <param name="ref_file" type="select" label="Using reference genome" help="REFERENCE_SEQUENCE">
	       <options from_data_table="all_fasta"></options>
	       <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
	    </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" 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">
          <param name="sequence" type="text" size="80" label="Ignore reads matching this sequence"/>
      </repeat>
      <param name="rrna_fragment_percentage" type="float" value="0.8" label="This percentage of the length of a fragment must overlap one of the ribosomal intervals for a read or read pair to be considered rRNA." help="RRNA_FRAGMENT_PERCENTAGE; default=0.8"/>
      <param name="metric_accumulation_level" type="select" label="The level(s) at which to accumulate metrics" multiple="true" help="METRIC_ACCUMULATION_LEVEL">
	 <option value="ALL_READS" selected="True">All reads</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>
  
   <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"/>
      <param name="assume_sorted" value="true" />
      <param name="refFlat" value="picard_CollectRnaSeqMetrics.refFlat" />
      <param name="metric_accumulation_level" value="ALL_READS" />
      <param name="minimum_length" value="500" />
      <param name="strand_specificity" value="NONE" />
      <param name="rrna_fragment_percentage" value="0.8" />
      <output name="outFile" file="picard_CollectRnaSeqMetrics_test1.tab" ftype="tabular" lines_diff="4"/>
    </test>

  </tests>
  <help>

.. class:: infomark

**Purpose**

Collects metrics about the alignment of RNA to various functional classes of loci in the genome: coding, intronic, UTR, intergenic, ribosomal.

@dataset_collections@

-----

.. class:: warningmark

**Obtaining gene annotations in refFlat format**

This tool requires gene annotations in refFlat_ format. These data can be obtained from UCSC table browser directly through Galaxy by following these steps:

   1. Click on **Get Data** in the upper part of left pane of Galaxy interface
   2. Click on **UCSC Main** link
   3. Set your genome and dataset of interest. It **must** be the same genome build against which you have mapped the reads contained in the BAM file you are analyzing
   4. In the **output format** field choose **selected fields from primary and related tables**
   5. Click **get output** button
   6. In the first table presented at the top of the page select (using checkboxes) first 11 fields:
      name
      chrom
      strand
      txStart
      txEnd
      cdsStart
      cdsEnd
      exonCount
      exonStarts
      exonEnds
      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>