comparison hicBuildMatrix.xml @ 21:ed2cca6b5de4 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hicexplorer commit 07802a6bd441d9da888cfb8283f8c2135704f7c9

20:29f66c353bcb

            #if $outBam:
                $outBam ./unsorted.bam
            #end if

            $keepSelfCircles
            $removeSelfLigation
            $skipDuplicationCheck

            #if $minMappingQuality and $minMappingQuality is not None:
                --minMappingQuality $minMappingQuality
            #end if

        <param argument="--maxLibraryInsertSize" type="integer" optional="true" value="" label="Maximum library insert size defines different cut offs based on the maximum expected library size" help="*This is not the average fragment size* but the higher end of the fragment size distribution (obtained using for example Fragment Analyzer)
                        which usually is between 800 to 1500 bp. If this value if not known use the default of 1000. The insert value is used to decide if two mates
                        belong to the same fragment (by checking if they are within this max insert size) and to decide if a mate
                        is too far away from the nearest restriction site." />

        <repeat name='binSizes' title='Bin size in bp' min="1" help="If used, the restriction cut places (if given) are used to only consider reads that are in the vicinity of the resctriction sites.
                Otherwise all reads in the interval are considered. Use multiple ones to create a mcool file.">
            <param argument="--binSize" type="integer" optional="true" value="" label="Bin size in bp" />
        </repeat>

        <expand macro="region" />
        <param argument="--keepSelfCircles" type="boolean" truevalue="--keepSelfCircles" falsevalue="" label="Keep self circles" help="If set, outward facing reads without any restriction fragment (self circles) are kept. They will be counted and shown in the QC plots." />
        <param argument="--removeSelfLigation" type="boolean" truevalue="--removeSelfLigation" falsevalue="" label="remove self ligation" help="If set, inward facing reads less than 1000 bp apart and having a restriction site in between are removed. Although this reads do not contribute to any distant contact, they are useful to account for bias in the data" />
        <expand macro="minMappingQuality" />
        <param argument="--skipDuplicationCheck" type="boolean" truevalue="--skipDuplicationCheck" falsevalue="" label="Skip duplication check" help="Identification of duplicated read pairs is memory consuming. Thus, in case of memory errors this check can be skipped." />
        <param argument="--chromosomeSizes" type="data" format="tabular" optional="true" label="Chromosome sizes for your genome" help="File with the chromosome sizes for your genome. A tab-delimited two column layout 'chr_name size' is expected
                    Usually the sizes can be determined from the SAM/BAM input files, however, 
                    for cHi-C or scHi-C it can be that at the start or end no data is present. 
                    Please consider that this option causes that only reads are considered which are on the listed chromosomes.
                    Use this option to guarantee fixed sizes. An example file is available via UCSC: 
                    http://hgdownload.soe.ucsc.edu/goldenPath/dm3/bigZips/dm3.chrom.sizes" />

        <param argument='--outBam' type='boolean' truevalue='--outBam' falsevalue="" checked="false" label="Save valid Hi-C reads in BAM file" help="A bam
                    file containing all valid Hi-C reads can be created
                    using this option. This bam file could be useful to
                    inspect the distribution of valid Hi-C reads pairs or
                    for other downstream analyses, but is not used by any
                    HiCExplorer tool. Computation will be significantly
                    longer if this option is set." />

        <param name='outputFormat' type='select' label="Output file format">
            <option value='h5'>HiCExplorer format</option>
            <option value="cool">cool</option>
        </param>
    </inputs>
    <outputs>
        <data name="outfileBam" from_work_dir="sorted.bam" format="bam" label="${tool.name} BAM file on ${on_string}">

            <change_format>
                <when input="outputFormat" value="cool" format="cool" />
            </change_format>
        </data>
        <data name="qc" format="html" label="${tool.name} QC on ${on_string}" />
        <data name="raw_qc" from_work_dir='raw_qc' format='txt' label="${tool.name} raw QC on ${on_string}" />
    </outputs>
    <tests>
        <test expect_num_outputs="4">
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" />
            </repeat>
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" />
            </repeat>
            <param name='outputFormat' value='h5' />
            <repeat name='binSizes'>
                <param name="binSize" value="5000" />
            </repeat>
            <param name='restrictionCutFile' value='DpnII_10k.bed' />
            <param name='restrictionSequence' value='GATC' />
            <param name='danglingSequence' value='GATC' />
            <param name='outBam' value="True" />
            <output name="outfileBam" file="small_test_matrix_result_sorted.bam" ftype="bam" />
            <output name="outFileName" ftype="h5">
                <assert_contents>
                    <has_h5_keys keys='intervals,matrix' />
                </assert_contents>
            </output>
            <output name="raw_qc" file='raw_qc_report' compare='diff' lines_diff='2' />
        </test>
        <test expect_num_outputs="4">
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" />
            </repeat>
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" />
            </repeat>
            <repeat name='binSizes'>
                <param name="binSize" value="5000" />
            </repeat>
            <param name='restrictionCutFile' value='DpnII_10k.bed' />
            <param name='restrictionSequence' value='GATC' />
            <param name='danglingSequence' value='GATC' />
            <param name='outputFormat' value='cool' />
            <param name='outBam' value="True" />
            <output name="outfileBam" file="small_test_matrix_result_sorted.bam" ftype="bam" />
            <output name="outFileName" ftype="cool">
                <assert_contents>
                    <has_h5_keys keys='bins,chroms,indexes,pixels' />
                </assert_contents>
            </output>
            <output name="raw_qc" file='raw_qc_report' compare='diff' lines_diff='2' />
        </test>
    </tests>
    <help><![CDATA[

Creation of the contact matrix

21:ed2cca6b5de4

            #if $outBam:
                $outBam ./unsorted.bam
            #end if

            $keepSelfCircles
            $keepSelfLigation
            $skipDuplicationCheck

            #if $minMappingQuality and $minMappingQuality is not None:
                --minMappingQuality $minMappingQuality
            #end if

        <param argument="--maxLibraryInsertSize" type="integer" optional="true" value="" label="Maximum library insert size defines different cut offs based on the maximum expected library size" help="*This is not the average fragment size* but the higher end of the fragment size distribution (obtained using for example Fragment Analyzer)
                        which usually is between 800 to 1500 bp. If this value if not known use the default of 1000. The insert value is used to decide if two mates
                        belong to the same fragment (by checking if they are within this max insert size) and to decide if a mate
                        is too far away from the nearest restriction site." />

        <repeat name="binSizes" title="Bin size in bp" min="1" help="If used, the restriction cut places (if given) are used to only consider reads that are in the vicinity of the resctriction sites.
                Otherwise all reads in the interval are considered. Use multiple ones to create a mcool file.">
            <param argument="--binSize" type="integer" optional="true" value="" label="Bin size in bp" />
        </repeat>

        <expand macro="region" />
        <param argument="--keepSelfCircles" type="boolean" truevalue="--keepSelfCircles" falsevalue="" label="Keep self circles" help="If set, outward facing reads without any restriction fragment (self circles) are kept. They will be counted and shown in the QC plots." />
        <param argument="--keepSelfLigation" type="boolean" truevalue="--keepSelfLigation" falsevalue="" label="Keep self ligation" help="If set, inward facing reads less than 1000 bp apart and having a restriction site in between are kept. Although this reads do not contribute to any distant contact, they are useful to account for bias in the data." />
        <expand macro="minMappingQuality" />
        <param argument="--skipDuplicationCheck" type="boolean" truevalue="--skipDuplicationCheck" falsevalue="" label="Skip duplication check" help="Identification of duplicated read pairs is memory consuming. Thus, in case of memory errors this check can be skipped." />
        <param argument="--chromosomeSizes" type="data" format="tabular" optional="true" label="Chromosome sizes for your genome" help="File with the chromosome sizes for your genome. A tab-delimited two column layout 'chr_name size' is expected
                    Usually the sizes can be determined from the SAM/BAM input files, however, 
                    for cHi-C or scHi-C it can be that at the start or end no data is present. 
                    Please consider that this option causes that only reads are considered which are on the listed chromosomes.
                    Use this option to guarantee fixed sizes. An example file is available via UCSC: 
                    http://hgdownload.soe.ucsc.edu/goldenPath/dm3/bigZips/dm3.chrom.sizes" />

        <param argument="--outBam" type="boolean" truevalue="--outBam" falsevalue="" checked="false" label="Save valid Hi-C reads in BAM file" help="A bam
                    file containing all valid Hi-C reads can be created
                    using this option. This bam file could be useful to
                    inspect the distribution of valid Hi-C reads pairs or
                    for other downstream analyses, but is not used by any
                    HiCExplorer tool. Computation will be significantly
                    longer if this option is set." />

        <param name="outputFormat" type="select" label="Output file format">
            <option value="h5">HiCExplorer format</option>
            <option value="cool">cool</option>
        </param>
    </inputs>
    <outputs>
        <data name="outfileBam" from_work_dir="sorted.bam" format="bam" label="${tool.name} BAM file on ${on_string}">

            <change_format>
                <when input="outputFormat" value="cool" format="cool" />
            </change_format>
        </data>
        <data name="qc" format="html" label="${tool.name} QC on ${on_string}" />
        <data name="raw_qc" from_work_dir="raw_qc" format="txt" label="${tool.name} raw QC on ${on_string}" />
    </outputs>
    <tests>
        <test expect_num_outputs="4">
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" />
            </repeat>
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" />
            </repeat>
            <param name="outputFormat" value="h5" />
            <repeat name="binSizes">
                <param name="binSize" value="5000" />
            </repeat>
            <param name="restrictionCutFile" value="DpnII_10k.bed" />
            <param name="restrictionSequence" value="GATC" />
            <param name="danglingSequence" value="GATC" />
            <param name="outBam" value="True" />
            <output name="outfileBam" file="small_test_matrix_result_sorted.bam" ftype="bam" />
            <output name="outFileName" ftype="h5">
                <assert_contents>
                    <has_h5_keys keys="intervals,matrix" />
                </assert_contents>
            </output>
            <output name="raw_qc" file="raw_qc_report" compare="diff" lines_diff="2" />
        </test>
        <test expect_num_outputs="4">
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" />
            </repeat>
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" />
            </repeat>
            <repeat name="binSizes">
                <param name="binSize" value="5000" />
            </repeat>
            <param name="restrictionCutFile" value="DpnII_10k.bed" />
            <param name="restrictionSequence" value="GATC" />
            <param name="danglingSequence" value="GATC" />
            <param name="outputFormat" value="cool" />
            <param name="outBam" value="True" />
            <output name="outfileBam" file="small_test_matrix_result_sorted.bam" ftype="bam" />
            <output name="outFileName" ftype="cool">
                <assert_contents>
                    <has_h5_keys keys="bins,chroms,indexes,pixels" />
                </assert_contents>
            </output>
            <output name="raw_qc" file="raw_qc_report" compare="diff" lines_diff="2" />
        </test>
    </tests>
    <help><![CDATA[

Creation of the contact matrix