annotate hicDetectLoops.xml @ 1:5759cd7db0d1 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hicexplorer commit 5744259254d4254a29cb7a6687fbbfd103301064"

<tool id="hicexplorer_hicdetectloops" name="@BINARY@" version="@WRAPPER_VERSION@.0">
    <description>searches for enriched regions</description>
    <macros>
        <token name="@BINARY@">hicDetectLoops</token>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
        ln -s '$matrix_h5_cooler' 'matrix.$matrix_h5_cooler.ext' &&
        @BINARY@

            --matrix  'matrix.$matrix_h5_cooler.ext'

            #if $peakWidth:
                --peakWidth $peakWidth
            #end if

            #if $windowSize:
                --windowSize $windowSize
            #end if

            #if $pValuePreselection:
                --pValuePreselection $pValuePreselection
            #end if

            #if $peakInteractionsThreshold:
                --peakInteractionsThreshold $peakInteractionsThreshold
            #end if

            #if $maximumInteractionPercentageThreshold:
                --maximumInteractionPercentageThreshold $maximumInteractionPercentageThreshold
            #end if
            #if $pValue:
                --pValue $pValue
            #end if
            #if $maxLoopDistance:
                --maxLoopDistance $maxLoopDistance
            #end if

            #if $region:
                --region '$region'
            #end if

            #if $chromosomes:
                #set $chromosome = ' '.join([ '\'%s\'' % $chrom for $chrom in str($chromosomes).split(' ') ])
                --chromosomes $chromosome
            #end if

            --statisticalTest $statisticalTest_selector
            
            --outFileName output_loop.bedgraph

            --threads @THREADS@
]]>
    </command>
    <inputs>
        <expand macro="matrix_h5_cooler_macro" />
        <param argument="--peakWidth" type="integer" optional='true' label="Peak width" help= "The width of the peak region in bins. The square around the peak will include (2 * peakWidth)^2 bins." />
        <param argument="--windowSize" type="integer" optional='true' label="Window size" help= "The window size for the neighborhood region the peak is located in. All values from this region (exclude the values from the peak
                           region) are tested against the peak region for significant difference. The square will have the size of (2 * windowSize)^2 bins" />
        <param argument="--pValuePreselection" type="float" label="P-value preselection" help= "Only candidates with p-values less the given threshold will be considered as candidates. 
                                For each genomic distance a negative binomial distribution is fitted and for each pixel a p-value given by the cumulative density function is given. 
                                This does NOT influence the p-value for the neighborhood testing." value='0.05'/>
        <param argument="--peakInteractionsThreshold" type="integer" label="Minimum interaction number" help= "The minimum number of interactions a detected peaks needs to have to be considered." value='5' />
        <param argument="--maximumInteractionPercentageThreshold" type="float" value='0.1' label="Maximum interaction share" help= "For each genomic distance the maximum value is considered and all candidates need to have at least \'max_value * maximumInteractionPercentageThreshold\' interactions." />
        <param argument="--pValue" type="float" label="P-value" help= "Rejection level for the statistical test for H0. H0 is peak region and background have the same distribution." value='0.05'/>
        <param argument="--maxLoopDistance" optional='true'  type="integer" label="Maximal loop distance" help= "Maximum genomic distance of a loop, usually loops are within a distance of ~2MB." value='2000000'/>
        <param argument="--minLoopDistance" optional='true'  type="integer" label="Maximal loop distance" help= "Minimum genomic distance of a loop to be considered." value='100000'/>
        <param argument="--chromosomes" optional='true'  type="text" label="Chromosomes to include" help= "Chromosomes to include in the analysis. If not set, all chromosomes are included." />
        <param argument="--region" optional='true'  type="text" label="Chromosomes to include" help= "The format is chr:start-end." />
        <param name="statisticalTest_selector" type="select" label="Stistical test">
            <option value="wilcoxon-rank-sum" selected="True">Wilcoxon rank-sum'</option>
            <option value="anderson-darling">Anderson-Darling</option>
        </param>
    </inputs>
    <outputs> 
        <data name='output_loops' from_work_dir='output_loop.bedgraph' format='bedgraph' label='Computed loops'/>
    </outputs>
    <tests>
        <test>
            <param name="matrix_h5_cooler" value="small_test_matrix.cool"/>
            <param name="maxLoopDistance" value="30000000"/>
            <param name="windowSize" value="5"/>
            <param name="peakWidth" value="2"/>
            <param name="pValue" value="0.5"/>
            <param name="pValuePreselection" value="0.55"/>
            <!-- <param name="chromosomes" value="X"/> -->
            <output name="output_loops" file="hicDetectLoops/loops.bedgraph" ftype="bedgraph" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[

Loop detection
==============

Computes enriched regions (peaks) or long range contacts on the given contact matrix.

For more information about HiCExplorer please consider our documentation on readthedocs.io_.

.. _readthedocs.io: http://hicexplorer.readthedocs.io/en/latest/index.html

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