<tool id="je_markdupes" name="Je-MarkDuplicates" version="1.0">
    <description>to filter BAM files for read duplicates taking UMIs into account</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <stdio>
        <exit_code range="1:" level="fatal" description="Tool exception" />
    </stdio>
    <version_command>echo '1.0'</version_command>
    <command interpreter="bash">
<![CDATA[
    je markdupes

    ## picard MarkDuplicates defaults
    INPUT="${inputFile}"
    OUTPUT="${outFile}"

    METRICS_FILE="${metrics_file}"

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

    #for $element in $adv_options.comments:
        COMMENT="${element.comment}"
    #end for

    DUPLICATE_SCORING_STRATEGY="${adv_options.duplicate_scoring_strategy}"

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

    VALIDATION_STRINGENCY="${adv_options.validation_stringency}"
    QUIET=true
    VERBOSITY=ERROR

    ## Je Markdupes Specific
    MM=${MM}
    #if str($MAX_N) != "":
        MAX_N=${MAX_N}
    #end if
    @barcode_option_cmd@

    #for $i, $option in enumerate( $repeat_slots )
        #if str($option.SLOTS) != "":
            SLOTS=${option.SLOTS}
        #end if
    #end for

    #if str($trim_conditional.T) == "true":
        T=${trim_conditional.T}
        #for $i, $option in enumerate( $trim_conditional.repeat_tslots )
            #if str($option.TSLOTS) != "":
                TSLOTS=${option.TSLOTS}
            #end if
        #end for
    #end if
]]>
    </command>
    <configfiles>
        <expand macro="barcode_config_file"></expand>
    </configfiles>

    <inputs>
        <param format="bam,sam" name="inputFile" type="data" label="Select SAM/BAM dataset"
            help="If empty, upload or import a SAM/BAM dataset"/>
        <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"/>
        <conditional name="barcodes">
            <param name="barcode_list_type_con" type="select" label="Do you have a predefined list of UMIs">
                <option value="file" selected="true">A one column txt file from the history</option>
                <option value="text">Paste the UMI list in a text field</option>
                <option value="no_barcodes">No predefined list</option>
            </param>

            <when value="file">
                <param name="BARCODE_FILE" type="data" format="tabular,txt" label="UMI file"
                    help="BARCODE_FILE. Pre-defined list of Unique Molecular Identifiers that can be expected.
                    Format: one column text file, one UMI per line. All UMIs MUST have the same length."/>
            </when>

            <when value="text">
                <param name="barcode_text" type="text" area="True" size="10x30"
                    value="barcode\n" label="Barcode file"
                    help="BARCODE_FILE. Pre-defined list of Unique Molecular Identifiers that can be expected.
                    Format: one column text file, one UMI per line. All UMIs MUST have the same length.">
                    <sanitizer>
                        <valid initial="string.printable"></valid>
                        <mapping initial="none"/>
                    </sanitizer>
                </param>
            </when>
            <when value="no_barcodes"/>
        </conditional>
        <repeat name="repeat_slots" min="1" title="Unique Molecular Identifier location">
            <param name="SLOTS" type="text" value="-1" label="Where to find the UMIs in the read name"
                help="SLOTS. The last position is considered by default (-1). See help below."/>
        </repeat>
        <param name="MM" type="integer" value="1" min="0"
            label="Number of maximum mismatches to consider two Unique Molecular Identifiers (UMIs) similar"
            help="MISMATCHES"/>
        <param name="MAX_N" type="text" value="" label="Maximum number of Ns a UMI can contain"
              help="MAX_NUMBER_OF_N. Above this value, reads are placed in a 'undefined' group.
              Default value is the MISMATCHES number."/>
        <param name="SPLIT" type="text" value=":" label="Character to split up the header" help="SPLIT"/>
        <conditional name="trim_conditional">
            <param name="T" type="select"
                label="Should barcode information be removed from read names in the output BAM" help="TRIM_HEADERS">
                <option value="true">Yes</option>
                <option value="false" selected="true">No</option>
            </param>
            <when value="true">
                <repeat name="repeat_tslots" min="1" title="Unique Molecular Identifier location for trimming">
                    <param name="TSLOTS" type="text" value="-1"
                        label="Where to find the UMIs in the read name that should be removed from the header"
                        help="TSLOTS. Value for SLOTS is considered by default. See help below"/>
                </repeat>
            </when>
            <when value="false"/>
        </conditional>
        <section name="adv_options" title="Advanced Options" expanded="False">
            <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="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="[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"/>

            <param name="validation_stringency" type="select" label="Select validation stringency"
                help="Setting stringency to SILENT can improve performance when processing a BAM file in which
                variable-length data (read, qualities, tags) do not otherwise need to be decoded.">
              <option value="LENIENT" selected="True">Lenient</option>
              <option value="SILENT">Silent</option>
              <option value="STRICT">Strict</option>
            </param>
        </section>
    </inputs>
    <outputs>
        <data format="bam" name="outFile" label="${tool.name} on ${on_string}: Je-MarkDuplicates BAM output"/>
        <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: Je-MarkDuplicate metrics"/>
    </outputs>

    <tests>
        <test>
          <!-- picard markduplicates default test -->
          <param name="inputFile" value="markdupes_DNase_sorted.bam" ftype="bam"/>
          <param name="barcode_list_type_con" value="file"/>
          <param name="BARCODE_FILE" value="markdupes_umis.txt" ftype="txt"/>
          <param name="repeat_slots_0|SLOTS" value="-1"/>
          <param name="repeat_slots_1|SLOTS" value="-2"/>
          <param name="MM" value="2"/>
          <param name="MAX_N" value="1"/>
          <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="markdupes_DNase_sorted_marked.bam" ftype="bam" lines_diff="2"/>
          <output name="metrics_file" file="markdupes_metrics.txt" ftype="txt" lines_diff="4"/>
        </test>
    </tests>


  <help>
<![CDATA[
**What it does**

Je MarkDupes: Examines aligned records in the supplied SAM or BAM file to locate duplicate molecules taking into account
molecular barcodes (Unique Molecular Identifiers or UMIs) found in read header.
All records are then either written to the output file with the duplicate records flagged or trashed.

Input file is a bam file.

Author: Charles Girardot  (charles.girardot@embl.de).

Wrapper by: Jelle Scholtalbers (jelle.scholtalbers@embl.de).

------

**Know what you are doing**

.. class:: warningmark

  You will want to read the `documentation`__.

  .. __: http://gbcs.embl.de/portal/Je

------

**Parameter list**

This is an exhaustive list of options::

  INPUT=String
  I=String

    One or more input SAM or BAM files to analyze. Must be coordinate sorted.

    Default value: null. This option may be specified 0 or more times.

  OUTPUT=File
  O=File

    The output file to write marked records to

    Required.

  MISMATCHES=Integer
  MM=Integer

    Number of MisMatches (inclusive) to still consider two Unique Molecular Identifiers
    (UMIs) the same i.e. this option buffers for sequencing errors.
    Indeed, in case of a sequencing error, 2 duplicate reads would not be considered
    duplicates anymore.
    Note that N are not considered mismatches during comparison ie ATTNGG and NTTANG are seen
    as the same barcode and these two reads would be flagged duplicates.
    This option takes a single value even when several barcodes are present (see SLOTS).
    Note that when declaring several barcodes (see SLOTS) AND providing a predefined set
    of barcodes (see BC option), the MM value is applicable in each lookup. When a predefined
    set of barcodes is NOT given, the different barcodes (SLOTS) are concatenated first and
    the MM value is therefore considered *overall* as the concatenated code is seen as a
    unique code.
    MM=null is like MM=0
    Use the minimum Hamming distance of the original barcode set (if applicable).

    Required.

  MAX_NUMBER_OF_N=Integer
  MAX_N=Integer

    Maximum number of Ns a molecular code can contain (inclusive). Above this value, reads
    are placed in a UNDEF group.
    More precisely, these 'too degenarate' codes will not :
    	 * be compared to the list of predefined codes [predefined code list situation ie BC
    option given] nor
    	 * be considered as a potential independent code [no predefined code list situation ie
    BC option not given]
    Default value is the MISMATCHES number.
    Note that when declaring several barcodes (see SLOTS) AND providing a predefined set
    of barcodes (see BC option), the MAX_N value is applicable to each barcode. When a
    predefined set
    of barcodes is NOT given, the different barcodes (SLOTS) are concatenated first and the
    MAX_N value
    is therefore considered *overall*.

    Default value: null.


  SLOTS=Integer
  SLOTS=Integer

    Where to find the UMIs (and only the UMIs) in the read name once read name has been
    tokenized using the SPLIT character (e.g. ':').
    By default, the UMI is considered to be found at the end of the read header i.e. after
    the last ':'. Use this option to indicate other or additional UMI positions (e.g.
    multiple UMIs present in read header.
    IMPORTANT: counting starts at 1 and negative numbers can be used to start counting from
    the end.
    For example, consider the following read name that lists 3 different barcodes in the end:
      HISEQ:44:C6KC0ANXX:8:2112:20670:79594:CGATGTTT:GATCCTAG:AAGGTACG
    to indicate that the three barcodes are molecular codes, use
      SLOTS=-1 SLOTS=-2 SLOTS=-3
    if only the 2 last ones should be considered (the third one being a sample encoding
    barcode), use
      SLOTS=-1 SLOTS=-2

    Default value: null. This option may be specified 0 or more times.

  BARCODE_FILE=File
  BC=File

    Pre-defined list of UMIs that can be expected. Format: one column text file, one barcode
    per line. All UMIs MUST have the same length.

    Default value: null.

  TRIM_HEADERS=Boolean
  T=Boolean

    Should barcode information be removed from read names in the output BAM?

    Default value: false. This option can be set to 'null' to clear the default value.
    Possible values: {true, false}

  TSLOTS=Integer
  TSLOTS=Integer

    Where to find *all* barcode(s) (i.e. sample encoding and UMIs) in the read name once has
    been tokenized using the SPLIT character (e.g. ':').
    This option is only considered when TRIM_HEADERS=true. When TSLOTS is ommited while
    TRIM_HEADERS=true, the values of SLOTS apply.
    IMPORTANT : counting starts at 1 and negative numbers can be used to start counting from
    the end.
    See SLOT help for examples.

    Default value: null. This option may be specified 0 or more times.

  SPLIT_CHAR=String
  SPLIT=String

    Character to use to split up the read header line, default is ':'.

    Default value: ':'. This option can be set to 'null' to clear the default value.

  INPUT=String
  I=String

    One or more input SAM or BAM files to analyze. Must be coordinate sorted.

    Default value: null. This option may be specified 0 or more times.

  OUTPUT=File
  O=File

    The output file to write marked records to  Required.

  METRICS_FILE=File
  M=File

    File to write duplication metrics to  Required.

  COMMENT=String
  CO=String

    Comment(s) to include in the output file's header.

    Default value: null. 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. This option can be set to 'null' to clear
    the default value.
    Possible values: {true, false}

  ASSUME_SORTED=Boolean
  AS=Boolean

    If true, assume that the input file is coordinate sorted even if the header says
    otherwise.

    Default value: false. This option can be set to 'null' to clear the default
    value.
    Possible values: {true, false}

  DUPLICATE_SCORING_STRATEGY=ScoringStrategy
  DS=ScoringStrategy

    The scoring strategy for choosing the non-duplicate among candidates.

    Default value: SUM_OF_BASE_QUALITIES. This option can be set to 'null' to clear the default value.
    Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}

  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]+).*. This option can be set to 'null' to
    clear the default value.

  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. This option can be set to 'null'
    to clear the default value.

]]>
  </help>

</tool>