annotate picard_MarkDuplicatesWithMateCigar.xml @ 14:465cbb0cf2eb draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 74ee0f0b594075fab7f707aaffb4a7f9dac35f2f

<tool name="MarkDuplicatesWithMateCigar" id="picard_MarkDuplicatesWithMateCigar" version="@TOOL_VERSION@.0">
  <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@
    picard
    MarkDuplicatesWithMateCigar

    INPUT='$escaped_element_identifier'
    OUTPUT="${outFile}"

    METRICS_FILE="${metrics_file}"
    COMMENT="${comment}"

    MINIMUM_DISTANCE="${minimum_distance}"
    SKIP_PAIRS_WITH_NO_MATE_CIGAR="${skip_pairs_with_no_mate_cigar}"


    REMOVE_DUPLICATES="${remove_duplicates}"
    ASSUME_SORTED="${assume_sorted}"

    DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}"

    #import pipes
    READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" }
    OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"


    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]+).*.">
      <sanitizer>
        <valid initial="string.printable">
        </valid>
      </sanitizer>
    </param>
    <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="500" label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/>

   <expand macro="VS" />

  </inputs>

  <outputs>
    <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/>
    <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/>
  </outputs>

  <tests>
    <test>
      <param name="inputFile" value="picard_MarkDuplicatesWithMateCigar.bam" ftype="bam"/>
      <param name="minimum_distance" value="-1"/>
      <param name="skip_pairs_with_no_mate_cigar" value="True"/>
      <param name="comment" value="test-run"/>
      <param name="assume_sorted" value="True"/>
      <param name="remove_duplicates" value="False"/>
      <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
      <param name="optical_duplicate_pixel_distance" value="100"/>
      <param name="duplicate_scoring_strategy" value="TOTAL_MAPPED_REFERENCE_LENGTH"/>
      <param name="validation_stringency" value="LENIENT"/>
      <output name="outFile" file="picard_MarkDuplicatesWithMateCigar_test1.bam" ftype="bam" lines_diff="4"/>
    </test>
  </tests>


  <help>

**Purpose**

Examines aligned records in the supplied SAM or BAM dataset to locate duplicate molecules. All records are then written to the output file with the duplicate records flagged.

------

.. class:: warningmark

On the difference between **MarkDuplicates** and **picard_MarkDuplicatesWithMateCigar**

From Samtools Announce MailingList_:

This tool can replace MarkDuplicates if the input SAM/BAM has Mate CIGAR (MC) optional tags pre-computed
(see the tools RevertOriginalBaseQualitiesAndAddMateCigar and FixMateInformation).  This allows the new tool
to perform a streaming duplicate marking routine (i.e. a single-pass).  This tool cannot be used with
alignments that have large gaps or reference skips, which happens frequently in RNA-seq data.

.. _MailingList: http://sourceforge.net/p/samtools/mailman/message/32910359/

@dataset_collections@

@description@

  MINIMUM_DISTANCE=Integer      The minimum distance to buffer records to account for clipping on the 5' end of the
                                records.Set this number to -1 to use twice the first read's read length (or 100,
                                whichever is smaller).  Default value: -1. This option can be set to 'null' to clear the
                                default value.

  SKIP_PAIRS_WITH_NO_MATE_CIGAR=Boolean
                                Skip record pairs with no mate cigar and include them in the output.  Default value:
                                true. This option can be set to 'null' to clear the default value. Possible values:
                                {true, false}

  COMMENT=String
  CO=String                     Comment(s) to include in the output file's header.  This option may be specified 0 or
                                more times.

  REMOVE_DUPLICATES=Boolean     If true do not write duplicates to the output file instead of writing them with
                                appropriate flags set.  Default value: false.

  READ_NAME_REGEX=String        Regular expression that can be used to parse read names in the incoming SAM file. 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. Set this option to null to disable optical duplicate
                                detection. The regular expression should contain three capture groups for the three
                                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:
                                [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.

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

  OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
                                The maximum offset between two duplicte clusters in order to consider them optical
                                duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
                                unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
                                which case 50-100 is more normal.  Default value: 100.

@more_info@

  </help>
</tool>