comparison picard_MarkDuplicatesWithMateCigar.xml @ 12:05087b27692a draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92

11:efc56ee1ade4

  <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
  <macros>
    <import>picard_macros.xml</import>
  </macros>
  <expand macro="requirements" />
  <command>
    @java_options@
    
    java -jar \$JAVA_JAR_PATH/picard.jar
    MarkDuplicatesWithMateCigar
    
    INPUT="${inputFile}"
    OUTPUT="${outFile}"
    

    BLOCK_SIZE=100000
    VALIDATION_STRINGENCY="${validation_stringency}"
    QUIET=true
    VERBOSITY=ERROR
  
  </command>
  <inputs>
    <param format="bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/>
      <param name="comment" type="text" label="Add this comment to BAM dataset"/>
    
    <param name="minimum_distance" type="integer" value="-1" label="The minimum distance to buffer records to account for clipping on the 5' end of the records" help="MINIMUM_DISTANCE; Set this number to -1 to use twice the first read's read length (or 100, whichever is smaller); default=-1"/>
    <param name="skip_pairs_with_no_mate_cigar" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Skip record pairs with no mate cigar and include them in the output" help="SKIP_PAIRS_WITH_NO_MATE_CIGAR; default=True"/>
    <param name="remove_duplicates" type="boolean" label="If true do not write duplicates to the output file instead of writing them with appropriate flags set" help="REMOVE_DUPLICATES; default=False"/>
    <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED; default=True"/>

    <param name="duplicate_scoring_strategy" type="select" label="The scoring strategy for choosing the non-duplicate among candidates" help="DUPLICATE_SCORING_STRATEGY; default=TOTAL_MAPPED_REFERENCE_LENGTH">
      <option value="TOTAL_MAPPED_REFERENCE_LENGTH" select="True">TOTAL_MAPPED_REFERENCE_LENGTH</option>
      <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
    </param>


    <param name="read_name_regex" type="text" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*." label="Regular expression that can be used to parse read names in the incoming SAM/BAM dataset" help="READ_NAME_REGEX; Read names are parsed to extract three variables: tile/region, x coordinate and y coordinate. These values are used to estimate the rate of optical duplication in order to give a more accurate estimated library size. See help below for more info; default=[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.">

      <param name="validation_stringency" value="LENIENT"/>
      <output name="outFile" file="picard_MarkDuplicatesWithMateCigar_test1.bam" ftype="bam" lines_diff="4"/>
    </test>
  </tests>
  
  <stdio>
    <exit_code range="1:"  level="fatal"/>
  </stdio>
  
  <help>

**Purpose**

12:05087b27692a

  <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
  <macros>
    <import>picard_macros.xml</import>
  </macros>
  <expand macro="requirements" />
  <command detect_errors="exit_code"><![CDATA[
    @java_options@
    
    picard
    MarkDuplicatesWithMateCigar
    
    INPUT="${inputFile}"
    OUTPUT="${outFile}"
    

    BLOCK_SIZE=100000
    VALIDATION_STRINGENCY="${validation_stringency}"
    QUIET=true
    VERBOSITY=ERROR
  
  ]]></command>
  <inputs>
    <param format="bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/>
      <param name="comment" type="text" label="Add this comment to BAM dataset"/>
    
    <param name="minimum_distance" type="integer" value="-1" label="The minimum distance to buffer records to account for clipping on the 5' end of the records" help="MINIMUM_DISTANCE; Set this number to -1 to use twice the first read's read length (or 100, whichever is smaller); default=-1"/>
    <param name="skip_pairs_with_no_mate_cigar" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Skip record pairs with no mate cigar and include them in the output" help="SKIP_PAIRS_WITH_NO_MATE_CIGAR; default=True"/>
    <param name="remove_duplicates" type="boolean" label="If true do not write duplicates to the output file instead of writing them with appropriate flags set" help="REMOVE_DUPLICATES; default=False"/>
    <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED; default=True"/>

    <param name="duplicate_scoring_strategy" type="select" label="The scoring strategy for choosing the non-duplicate among candidates" help="DUPLICATE_SCORING_STRATEGY; default=TOTAL_MAPPED_REFERENCE_LENGTH">
      <option value="TOTAL_MAPPED_REFERENCE_LENGTH" selected="True">TOTAL_MAPPED_REFERENCE_LENGTH</option>
      <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
    </param>


    <param name="read_name_regex" type="text" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*." label="Regular expression that can be used to parse read names in the incoming SAM/BAM dataset" help="READ_NAME_REGEX; Read names are parsed to extract three variables: tile/region, x coordinate and y coordinate. These values are used to estimate the rate of optical duplication in order to give a more accurate estimated library size. See help below for more info; default=[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.">

      <param name="validation_stringency" value="LENIENT"/>
      <output name="outFile" file="picard_MarkDuplicatesWithMateCigar_test1.bam" ftype="bam" lines_diff="4"/>
    </test>
  </tests>
  
  
  <help>

**Purpose**