comparison picard_MarkDuplicatesWithMateCigar.xml @ 33:3f254c5ced1d draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 9ecbbb878d68a980ba35a90865e524c723ca3ed8

32:f9242e01365a

<tool name="MarkDuplicatesWithMateCigar" id="picard_MarkDuplicatesWithMateCigar" 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@">3</token>
  </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}"

    READ_NAME_REGEX='${ str( $read_name_regex ) }'
    OPTICAL_DUPLICATE_PIXEL_DISTANCE="${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]+).*.">
      <expand macro="sanitize_query" />
    </param>
    <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="5000" 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 ${on_string}: metrics"/>
    <data format="bam" name="outFile" label="${tool.name} on ${on_string}: BAM"/>
  </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.

                                which case 50-100 is more normal.  Default value: 100.

@more_info@

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

33:3f254c5ced1d

<tool name="MarkDuplicatesWithMateCigar" id="picard_MarkDuplicatesWithMateCigar" version="@TOOL_VERSION@.@WRAPPER_VERSION@" profile="@PROFILE@">
    <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@
    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}

    --READ_NAME_REGEX '${ str( $read_name_regex ) }'
    --OPTICAL_DUPLICATE_PIXEL_DISTANCE '${optical_duplicate_pixel_distance}'

    --BLOCK_SIZE 100000
    --VALIDATION_STRINGENCY '${validation_stringency}'
    --QUIET true
    --VERBOSITY ERROR

  ]]></command>
    <inputs>
        <param name="inputFile" type="data" format="bam" 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>
            <option value="RANDOM">RANDOM</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]+).*.">
            <expand macro="sanitize_query"/>
        </param>
        <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="5000" 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 ${on_string}: metrics"/>
        <data format="bam" name="outFile" label="${tool.name} on ${on_string}: BAM"/>
    </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.

                                which case 50-100 is more normal.  Default value: 100.

@more_info@

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