annotate picard_CollectGcBiasMetrics.xml @ 0:4419e9980172 draft

Uploaded

<tool name="CollectGcBiasMetrics" id="picard_CollectGcBiasMetrics" version="1.122.0">
  <description>charts the GC bias metrics</description>
  <requirements>
    <requirement type="package" version="1.122.0">picard</requirement>
  </requirements>
  
  <macros>
    <import>picard_macros.xml</import>
  </macros>
  
  <command>
    @java_options@
    ##set up input files

    #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
    
    java -jar \$JAVA_JAR_PATH/CollectGcBiasMetrics.jar
    INPUT="${inputFile}"
    OUTPUT="${outFile}"
    CHART_OUTPUT="${pdfFile}"
    SUMMARY_OUTPUT="${summaryFile}"
    WINDOW_SIZE="${window_size}"
    MINIMUM_GENOME_FRACTION="${minimum_genome_fraction}"
    IS_BISULFITE_SEQUENCED="${is_bisulfite_sequenced}"
    REFERENCE_SEQUENCE="${reference_fasta_filename}"
    ASSUME_SORTED="${assume_sorted}"
    
    VALIDATION_STRINGENCY="${validation_stringency}"
    QUIET=true
    VERBOSITY=ERROR
  
  </command>
  <inputs>
    <param format="sam,bam" name="inputFile" type="data" 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 name="window_size" type="integer" value="100" label="The size of windows on the genome that are used to bin reads" help="WINDOW_SIZE; default=100"/>
    <param name="minimum_genome_fraction" type="float" value="0.00005" label="For summary metrics, exclude GC windows that include less than this fraction of the genome" help="MINIMUM_GENOME_FRACTION; default=0.0005"/>
    <param name="is_bisulfite_sequenced" type="boolean" label="Calculate the base distribution over PF (passing filtering) reads only" checked="true" truevalue="true" falsevalue="false" help="PF_READS_ONLY"/> 
    <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="tabular" name="summaryFile" label="${tool.name} on ${on_string}: Summary stats"/>
    <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Summary data"/>
    <data format="pdf" name="pdfFile" label="${tool.name} on ${on_string}: Chart PDF"/>
  </outputs>
  
  <tests>
    <test>
      <param name="window_size" value="100" />
      <param name="minimum_genome_fraction" value="0.00005" />
      <param name="assume_sorted" value="true" />
      <param name="is_bisulfite_sequenced" value="true" />
      <param name="reference_source_selector" value="history" />
      <param name="ref_file" value="picard_CollectGcBiasMetrics_ref.fa" />
      <param name="inputFile" value="picard_CollectGcBiasMetrics.bam" ftype="bam" />
      <output name="outFile" file="picard_CollectGcBiasMetrics_test1.tab" ftype="tabular" lines_diff="4"/>
    </test> 
  </tests>
  
  <stdio>
    <exit_code range="1:"  level="fatal"/>
  </stdio>
  
  <help>

.. class:: infomark

**Purpose**

Program to chart the nucleotide distribution per cycle in a SAM or BAM file.

@dataset_collections@

@description@

  ALIGNED_READS_ONLY=Boolean    If set to true, calculate the base distribution over aligned reads only.  Default value: 
                                false. Possible values: {true, false} 

  PF_READS_ONLY=Boolean         If set to true calculate the base distribution over PF reads only.  Default value: false. 
                                This option can be set to 'null' to clear the default value. Possible values: {true, 
                                false} 

  ASSUME_SORTED=Boolean
  AS=Boolean                    If true (default), then the sort order in the header file will be ignored.  Default: True 

@more_info@

  </help>
</tool>