annotate picard_CollectRnaSeqMetrics.xml @ 27:a1f0b3f4b781 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 11b94d7cd69b919f16feb10bd4b830a963334ab8"

<tool name="CollectRnaSeqMetrics" id="picard_CollectRnaSeqMetrics" version="@TOOL_VERSION@.@WRAPPER_VERSION@">
    <description> collect metrics about the alignment of RNA to various functional classes of loci in the genome</description>
    <macros>
        <import>picard_macros.xml</import>
    <token name="@WRAPPER_VERSION@">2</token>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="3.4.1">r-base</requirement>
        <requirement type="package" version="357">ucsc-gff3togenepred</requirement>
        <requirement type="package" version="357">ucsc-gtftogenepred</requirement>
    </expand>
    <command detect_errors="exit_code"><![CDATA[
      ## Set up input files
      @symlink_element_identifier@
      ## Reference sequences

      #set $reference_fasta_filename = "localref.fa"

      @handle_reference_source@

      ## refFlat data
      ## The awk line below converts a file obtained from UCSC as specified in the tool help to refFlat format

      #if str($gene_reference_source.gene_reference_source_selector) == "gtf"
        #if $gene_reference_source.refFlat.ext == 'gff3'
            gff3ToGenePred '${gene_reference_source.refFlat}' refFlat.tab.raw &&
        #else
            gtfToGenePred -genePredExt '${gene_reference_source.refFlat}' refFlat.tab.raw &&
        #end if
        grep -v '^#' refFlat.tab.raw | awk '{print $12"\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10}' > refFlat.tab &&
      #else
        grep -v '^#' ${refFlat} | awk '{if ($3 == "+" || $3 == "-") print $11"\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10; else print}' > refFlat.tab &&
      #end if

      ## 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='$escaped_element_identifier'
      OUTPUT="${outFile}"
      REFERENCE_SEQUENCE="${reference_fasta_filename}"
      ASSUME_SORTED="${assume_sorted}"
      @TMPDIR_OPTION@
      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>

      <conditional name="gene_reference_source">
         <param name="gene_reference_source_selector" type="select" label="Load gene annotation from">
            <option value="gtf">GTF/GFF3</option>
            <option value="refflat">refFlat</option>
         </param>
         <when value="gtf">
              <param name="refFlat"
                     format="gtf,gff3"
                     type="data"
                     label="Gene annotation (GTF/GFF3)"/>
         </when>
         <when value="refflat">
              <param name="refFlat"
                     format="tabular"
                     type="data"
                     label="Gene annotations in refFlat form"
                     help="See &quot;Obtaining gene annotations in refFlat format&quot; below for help"/>
         </when>
      </conditional>


      <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">
          <param name="sequence" type="text" 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>

  <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="gene_reference_source_selector" value="refflat" />
      <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>
   <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="gene_reference_source_selector" value="refflat" />
      <param name="refFlat" value="picard_CollectRnaSeqMetrics.ucsc_output" />
      <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>

    <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="gene_reference_source_selector" value="gtf" />
      <param name="refFlat" value="picard_CollectRnaSeqMetrics.gtf" ftype="gtf" />
      <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_test2.tab" ftype="tabular" lines_diff="4"/>
    </test>

    <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="gene_reference_source_selector" value="gtf" />
      <param name="refFlat" value="picard_CollectRnaSeqMetrics.gff3" ftype="gff3" />
      <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_test3.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: https://genome.ucsc.edu/FAQ/FAQformat.html#format9

@description@

   REF_FLAT=File                 Gene annotations in refFlat form.  Format described here:
                                 https://genome.ucsc.edu/FAQ/FAQformat.html#format9  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:
                                 https://samtools.github.io/htsjdk/javadoc/htsjdk/htsjdk/samtools/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>
  <expand macro="citations" />
</tool>