<tool id="deeptools_bam_pe_fragmentsize" name="bamPEFragmentSize" version="@WRAPPER_VERSION@.0">
    <description>Estimate the predominant cDNA fragment length from paired-end sequenced BAM/CRAM files</description>
    <macros>
        <token name="@BINARY@">bamPEFragmentSize</token>
        <import>deepTools_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command>
<![CDATA[
        @multiple_input_bams@
        @BINARY@
            @THREADS@
            --bamfiles #echo " ".join($files)
            #if $samplesLabel:
                --samplesLabel #echo " ".join($samplesLabel)
            #else:
                --samplesLabel #echo " ".join($labels)
            #end if
            #if $histogram:
                --histogram '$histogram_outfile'
                --plotFileFormat '$outFileFormat'
            #end if
            --plotTitle "$plotTitle"
            #if $advancedOpt.showAdvancedOpt == 'yes'
                --binSize '$advancedOpt.binSize'
                --distanceBetweenBins '$advancedOpt.distanceBetweenBins'
                $advancedOpt.logScale
                --maxFragmentLength '$advancedOpt.maxFragmentLength'
                @blacklist@
                #if $advancedOpt.table
                    --table '$table'
                #end if
                #if $advancedOpt.outRawFragmentLengths
                    --outRawFragmentLengths '$fragLengths'
                #end if
            #end if
            > '$outfile'
]]>
    </command>
    <inputs>
        <expand macro="multiple_input_bams" MIN="1" />
        <param argument="--histogram" type="boolean" truevalue="--histogram" falsevalue=""
            label="Get the distribution of read/fragment lengths as a histogram"
            help=""/>
        <expand macro="input_image_file_format" />
        <param argument="--samplesLabel" type="text" size="30"
            label="Labels for the samples (each BAM file) plotted"
            help="The default is to use the file name of the sample. The sample labels should be separated by
            spaces and quoted if a label itself contains a space E.g. label-1 &quot;label 2&quot;">
            <sanitizer>
               <valid initial="string.printable">
               </valid>
            </sanitizer>
        </param>
        <expand macro="plotTitle" />
        <conditional name="advancedOpt">
            <param name="showAdvancedOpt" type="select" label="Show advanced options" >
                <option value="no" selected="true">no</option>
                <option value="yes">yes</option>
            </param>
            <when value="no" />
            <when value="yes">
                <param argument="--binSize" type="integer" value="1000" min="1" optional="true"
                    label="bin size, in bases" help="Length in bases of the window used to sample the genome. (--binSize)"/>
                <param argument="--distanceBetweenBins" type="integer" value="1000000" min="0" optional="true"
                    label="bin spacing, in bases"
                    help="To reduce the computation time, not every possible genomic bin is sampled. This option allows you to set the distance between bins actually sampled from. Larger numbers are sufficient for high coverage samples, while smaller values are useful for lower coverage samples. Note that if you specify a value that results in too few (&lt;1000) reads sampled, the value will be decreased. (--distanceBetweenBins)"/>
                <param argument="--table" type="boolean" truevalue="--table" falsevalue=""
                    label="Write metrics to a tab-separated file?"
                    help="Write the read/fragment metrics to a tab-separated file, which is primarily useful for more automated downstream processing." />
                <param argument="--outRawFragmentLengths" type="boolean" truevalue="--outRawFragmentLengths" falsevalue=""
                    label="Write a file containing the read/fragment length information?"
                    help="Write the read/fragment length distribution underlying the (optional) plot to a file. This can then be processed in R or other downstream applications." />
                <param argument="--logScale" type="boolean" truevalue="--logScale" falsevalue=""
                    label="Plot log frequencies"
                    help="Plot the frequencies on the log10 scale" />

                <param argument="--maxFragmentLength" type="integer" min="0" value="0"
                    label="Maximum fragment length"
                    help="Maximum fragment length included in the histogram. A value of 0 (the default) denotes twice the mean fragment length" />
                <expand macro="blacklist" />
            </when>
        </conditional>

    </inputs>
    <outputs>
        <data name="outfile" format="txt" label="${tool.name} on ${on_string}: Read/Fragment metrics"/>
        <data name="histogram_outfile" format="png" label="${tool.name} on ${on_string}: Read/Fragment histogram">
            <filter>histogram is True</filter>
            <change_format>
                <when input="outFileFormat" value="pdf" format="pdf" />
                <when input="outFileFormat" value="svg" format="svg" />
                <when input="outFileFormat" value="eps" format="eps" />
                <when input="outFileFormat" value="plotly" format="html" />
            </change_format>
        </data>
        <data name="table" format="tabular" label="${tool.name} on ${on_string}: Read/Fragment metrics in tabular format">
            <filter>table is True</filter>
        </data>
        <data name="fragLengths" format="tabular" label="${tool.name} on ${on_string}: Raw Read/Fragment lengths occurrences">
            <filter>outRawFragmentLengths is True</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="bamfiles" value="bowtie2 test1.bam" ftype="bam" />
            <param name="histogram" value="True" />
            <param name="plotTitle" value="Test Plot" />
            <output name="outfile" file="bamPEFragmentSize_result1.txt" ftype="txt" />
            <output name="histogram_outfile" file="bamPEFragmentSize_histogram_result1.png" ftype="png" compare="sim_size" />
        </test>
        <test>
            <param name="bamfiles" value="bowtie2 test1.bam" ftype="bam" />
            <param name="showAdvancedOpt" value="yes" />
            <param name="table" value="True" />
            <param name="outRawFragmentLengths" value="yes" />
            <output name="table" file="bamPEFragmentSize_table1.txt" ftype="tabular" />
            <output name="fragLengths" file="bamPEFragmentSize_lengths1.txt" ftype="tabular" />
        </test>
    </tests>
    <help>
<![CDATA[

What it does
------------

This tool samples the given BAM files with paired-end data to estimate the fragment length distribution.
Properly paired reads are preferred for computation, i.e., unless a region does not contain any concordant pairs, discordant pairs are ignored.

Output
------

The **default** output is a simple summary statistic for the observed fragment lengths.

Optionally, you can obtain a histogram of fragment sizes, which will give you a better idea of the distribution of fragment lengths.

.. image:: $PATH_TO_IMAGES/bamPEFragmentSize_output.png
   :width: 600
   :height: 520

If the ``--table`` option is specified, the summary statistics are additionally printed in a tabular format::

    	Frag. Len. Min.	Frag. Len. 1st. Qu.	Frag. Len. Mean	Frag. Len. Median	Frag. Len. 3rd Qu.	Frag. Len. Max	Frag. Len. Std.	Read Len. Min.	Read Len. 1st. Qu.	Read Len. Mean	Read Len. Median	Read Len. 3rd Qu.	Read Len. Max	Read Len. Std.
    bowtie2 test1.bam	241.0	241.5	244.666666667	242.0	246.5	251.0	4.49691252108	251.0	251.0	251.0	251.0	251.0	251.0	0.0

If the ``--outRawFragmentLengths`` option is provided, another history item will be produced, containing the raw data underlying the histogram. It has the following format::

    #bamPEFragmentSize
    Size	Occurrences	Sample
    241	1	bowtie2 test1.bam
    242	1	bowtie2 test1.bam
    251	1	bowtie2 test1.bam

The "Size" is the fragment (or read, for single-end datasets) size and "Occurrences" are the number of times reads/fragments with that length were observed. For easing downstream processing, the sample name is also included on each row.


-----

@REFERENCES@
]]>
    </help>
    <expand macro="citations" />
</tool>