<tool name="EstimateLibraryComplexity" id="picard_EstimateLibraryComplexity" version="@TOOL_VERSION@.@WRAPPER_VERSION@">
  <description>assess sequence library complexity from read sequences</description>
  <macros>
    <import>picard_macros.xml</import>
    <token name="@WRAPPER_VERSION@">1</token>
  </macros>
  <expand macro="requirements" />
  <command detect_errors="exit_code"><![CDATA[
    @java_options@
    @symlink_element_identifier@
    picard
    EstimateLibraryComplexity

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

    MIN_IDENTICAL_BASES="${min_identical_bases}"
    MAX_DIFF_RATE="${max_diff_rate}"
    MIN_MEAN_QUALITY="${min_mean_quality}"
    MAX_GROUP_RATIO="${max_group_ratio}"
    READ_NAME_REGEX='${ str( $read_name_regex ) }'
    OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"

    VALIDATION_STRINGENCY="${validation_stringency}"
    QUIET=true
    VERBOSITY=ERROR
    @TMPDIR_OPTION@

  ]]></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="min_identical_bases" type="integer" value="5" label="The minimum number of bases at the starts of reads that must be identical for reads to be grouped together for duplicate detection" help="MIN_IDENTICAL_BASES; In effect total_reads / 4^max_id_bases reads will be compared at a time, so lower numbers will produce more accurate results but consume exponentially more memory and CPU; default=5"/>
    <param name="max_diff_rate" type="float" value="0.03" label="The maximum rate of differences between two reads to call them identical" help="MAX_DIFF_RATE; default=0.03"/>
    <param name="min_mean_quality" type="integer" min="0" max="93" value="20" label="The minimum mean quality of the bases in a read pair for the read to be analyzed" help="MIN_MEAN_QUALITY; Reads with lower average quality are filtered out and not considered in any calculations; default=20"/>
    <param name="max_group_ratio" type="integer" value="500" label="Do not process self-similar groups that are this many times over the mean expected group size" help="MAX_GROUP_RATIO; I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then the mean expected group size would be approximately 10 reads; default-500"/>

    <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="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="tabular" name="outFile" label="${tool.name} on ${on_string}: Library complexity report"/>
  </outputs>

  <tests>
    <test>
      <param name="inputFile" value="picard_EstimateLibraryComplexity.bam" ftype="bam"/>
      <param name="min_identical_bases" value="5"/>
      <param name="max_diff_rate" value="0.03"/>
      <param name="min_mean_quality" value="20"/>
      <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="max_group_ratio" value="500"/>
      <param name="validation_stringency" value="LENIENT"/>
      <output name="outFile" file="picard_EstimateLibraryComplexity_test1.tab" ftype="tabular" lines_diff="4"/>
    </test>
  </tests>


  <help>

**Purpose**

Attempts to estimate library complexity from sequence of read pairs alone. Does so by sorting all reads by the first N bases (5 by default)
of each read and then comparing reads with the first N bases identical to each other for duplicates. Reads are considered to be duplicates
if they match each other with no gaps and an overall mismatch rate less than or equal to MAX_DIFF_RATE (0.03 by default).

Reads of poor quality are filtered out so as to provide a more accurate estimate. The filtering removes reads with any no-calls in the first
N bases or with a mean base quality lower than MIN_MEAN_QUALITY across either the first or second read.

Unpaired reads are ignored in this computation.
The algorithm attempts to detect optical duplicates separately from PCR duplicates and excludes these in the calculation of library size.

Also, since there is no alignment to screen out technical reads one further filter is applied on the data. After examining all reads a Histogram
is built of [#reads in duplicate set -> #of duplicate sets]; all bins that contain exactly one duplicate set are then removed from the Histogram
as outliers before library size is estimated.

@dataset_collections@

@description@

  MIN_IDENTICAL_BASES=Integer   The minimum number of bases at the starts of reads that must be identical for reads to be
                                grouped together for duplicate detection.  In effect total_reads / 4^max_id_bases reads
                                will be compared at a time, so lower numbers will produce more accurate results but
                                consume exponentially more memory and CPU.  Default value: 5.

  MAX_DIFF_RATE=Double          The maximum rate of differences between two reads to call them identical.  Default value:
                                0.03.

  MIN_MEAN_QUALITY=Integer      The minimum mean quality of the bases in a read pair for the read to be analyzed. Reads
                                with lower average quality are filtered out and not considered in any calculations.
                                Default value: 20.

  MAX_GROUP_RATIO=Integer       Do not process self-similar groups that are this many times over the mean expected group
                                size. I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then
                                the mean expected group size would be approximately 10 reads.  Default value: 500.

  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]+).*.

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