comparison picard_CollectRnaSeqMetrics.xml @ 33:3f254c5ced1d draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 9ecbbb878d68a980ba35a90865e524c723ca3ed8

32:f9242e01365a

<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

      #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}"
      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**

                                 value: true. Possible values: {true, false}

@more_info@

  </help>
  <expand macro="citations" />
</tool>

33:3f254c5ced1d

<tool name="CollectRnaSeqMetrics" id="picard_CollectRnaSeqMetrics" version="@TOOL_VERSION@.@WRAPPER_VERSION@" profile="@PROFILE@">
    <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@">0</token>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="447">ucsc-gff3togenepred</requirement>
        <requirement type="package" version="447">ucsc-gtftogenepred</requirement>
    </expand>
    <command detect_errors="exit_code"><![CDATA[
      ## Set up input files
      @symlink_element_identifier@
      ## Reference sequences

      #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}'
      --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"/>
                    <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**

                                 value: true. Possible values: {true, false}

@more_info@

  </help>
    <expand macro="citations"/>
</tool>