<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@
    picard
    MarkDuplicates

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

    METRICS_FILE='${metrics_file}'
    #for $element in $comments:
      COMMENT='${element.comment}'
    #end for

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

    DUPLICATE_SCORING_STRATEGY='${duplicate_scoring_strategy}'

    #import pipes
    #if $read_name_regex:
      READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) }
    #end if
    OPTICAL_DUPLICATE_PIXEL_DISTANCE='${optical_duplicate_pixel_distance}'

    # Optional arguments
    #if $barcode_tag:
      BARCODE_TAG='${barcode_tag}'
    #end if

    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"/>
    <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments">
      <param name="comment" type="text" label="Add this comment to BAM dataset"/>
    </repeat>
    <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=SUM_OF_BASE_QUALITIES">
      <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>
    <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"/>

    <param name="barcode_tag" type="text" optional="True" label="Barcode Tag" help="Barcode SAM tag. This tag can be utilized when you have data from an assay that includes Unique Molecular Indices."/>

   <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_MarkDuplicates.bam" ftype="bam"/>
      <param name="comment" value="test-run"/>
      <param name="assume_sorted" value="True"/>
      <param name="remove_duplicates" value="True"/>
      <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="SUM_OF_BASE_QUALITIES"/>
      <param name="validation_stringency" value="LENIENT"/>
      <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/>
    </test>
    <test>
      <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
      <param name="comment" value="test-run"/>
      <param name="assume_sorted" value="True"/>
      <param name="remove_duplicates" value="False"/>
      <param name="read_name_regex" value=""/>
      <param name="optical_duplicate_pixel_distance" value="100"/>
      <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
      <param name="validation_stringency" value="LENIENT"/>
      <output name="outFile" file="picard_MarkDuplicates_test2.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.

@dataset_collections@

@description@

  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        This option is only needed if your read names do not follow a standard illumina convention
                                of colon separation but do contain tile, x, and y coordinates (unusual).
                                A 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: ''
                                

  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>