comparison picard_MarkDuplicates.xml @ 19:5053a18d9bc8 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 7036343b9ac0a0ffc2ce4f6db465b9298ef05e73

18:7615ac66c6e5

<tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.2">
  <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@
    @symlink_element_identifier@

      <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
      <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option>
    </param>

    <param name="read_name_regex" type="text" value="" label="Regular expression that can be used in unusual situations to parse non-standard 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='' (uses : separation)">
 
      <sanitizer>
        <valid initial="string.printable">
        </valid>
      </sanitizer>
    </param>

                                variables, in order. It must match the entire read name. Note that if the default regex
                                is specified, a regex match is not actually done, but instead the read name  is split on
                                colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
                                tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
                                are assumed to be tile, x and y values.  Default value: ''
                                

  DUPLICATE_SCORING_STRATEGY=ScoringStrategy
  DS=ScoringStrategy            The scoring strategy for choosing the non-duplicate among candidates.  Default value:
                                SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}

  OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
                                The maximum offset between two duplicate clusters in order to consider them optical
                                duplicates. This should be set to 100 for (circa 2011+) read names and typical flowcells.
                                Structured flow cells (NovaSeq, HiSeq 4000, X) should use ~2500. 
                                For older conventions, distances could be to some fairly small number (e.g. 5-10 pixels)
                                Default value: 100.

  BARCODE_TAG=String            Barcode SAM tag (ex. BC for 10X Genomics)  Default value: null.

@more_info@

  </help>
</tool>

19:5053a18d9bc8

<tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.@WRAPPER_VERSION@">
  <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
  <macros>
    <import>picard_macros.xml</import>
    <token name="@WRAPPER_VERSION@">0</token>
  </macros>
  <expand macro="requirements" />
  <command detect_errors="exit_code"><![CDATA[
    @java_options@
    @symlink_element_identifier@

      <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
      <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option>
    </param>

    <param name="read_name_regex" type="text" value="" label="Regular expression that can be used in unusual situations to parse non-standard 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='' (uses : separation)">

      <sanitizer>
        <valid initial="string.printable">
        </valid>
      </sanitizer>
    </param>

                                variables, in order. It must match the entire read name. Note that if the default regex
                                is specified, a regex match is not actually done, but instead the read name  is split on
                                colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
                                tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
                                are assumed to be tile, x and y values.  Default value: ''


  DUPLICATE_SCORING_STRATEGY=ScoringStrategy
  DS=ScoringStrategy            The scoring strategy for choosing the non-duplicate among candidates.  Default value:
                                SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}

  OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
                                The maximum offset between two duplicate clusters in order to consider them optical
                                duplicates. This should be set to 100 for (circa 2011+) read names and typical flowcells.
                                Structured flow cells (NovaSeq, HiSeq 4000, X) should use ~2500.
                                For older conventions, distances could be to some fairly small number (e.g. 5-10 pixels)
                                Default value: 100.

  BARCODE_TAG=String            Barcode SAM tag (ex. BC for 10X Genomics)  Default value: null.

@more_info@

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