comparison bamCoverage.xml @ 33:6a5dfb2c0c60 draft

planemo upload for repository https://github.com/deeptools/deepTools/tree/master/galaxy/wrapper/ commit b1f975422b307927bbbe245d57609e9464d5d5c8-dirty

32:33d88fda6240

<tool id="deeptools_bam_coverage" name="bamCoverage" version="@WRAPPER_VERSION@.0">
    <description>generates a coverage bigWig file from a given BAM file</description>
    <macros>
        <token name="@BINARY@">bamCoverage</token>
        <import>deepTools_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command>
<![CDATA[
        ln -s '$bamInput' one.bam &&
        ln -s '${bamInput.metadata.bam_index}' one.bam.bai &&

        @BINARY@
            @THREADS@

            --bam one.bam

            --outFileFormat '$outFileFormat'

            --binSize $binSize

            #if $scaling.type=='rpkm':
                --normalizeUsingRPKM
            #elif $scaling.type=='1x':
                #if $scaling.effectiveGenomeSize.effectiveGenomeSize_opt == "specific":
                    --normalizeTo1x $scaling.effectiveGenomeSize.effectiveGenomeSize
                #else:
                    --normalizeTo1x $scaling.effectiveGenomeSize.effectiveGenomeSize_opt
                #end if
            #end if

            #if str($region).strip() != '':
                --region '$region'

            #end if
]]>
    </command>

    <inputs>
        <param name="bamInput" format="bam" type="data" label="BAM file"
            help=""/>

        <param name="binSize" type="integer" value="50" min="1"
            label="Bin size in bases"
            help="The genome will be divided into bins of the specified size. For each bin, the overlaping number of fragments (or reads)  will be reported. If only half a fragment overlaps, this fraction will be reported. "/>

        <conditional name="scaling">
            <param name="type" type="select" label="Scaling/Normalization method" >
                <option value="1x">Normalize coverage to 1x</option>
                <option value="rpkm">Normalize to fragments (reads) per kilobase per million (RPKM)</option>
                <option value="no">Do not normalize or scale</option>
            </param>
            <when value="rpkm"/>
            <when value="no"/>
            <when value="1x">
                <expand macro="effectiveGenomeSize" />
            </when>
        </conditional>

                        offset of 0 is not permitted. If two values (separated by spaces) are specified, then they will be
                        used to specify a range of positions. Note that specifying something like
                        --Offset 5 -1 will result in the 5th through last position being used, which
                        is equivalent to trimming 4 bases from the 5-prime end of alignments." />

                <param argument="filterRNAstrand" type="select" label="Only include reads originating from fragments from the forward or reverse strand." 
                    help="By default (the no option), all reads are processed, regardless of the strand they originated from. For RNAseq, it can be useful to separately create bigWig files for the forward or reverse strands.
                          Note that this tools assumes that a dUTP-based method was used, so fragments will be assigned to the reverse strand if the second read in a pair is reverse complemented.">
                    <option value="no" selected="true">no</option>
                    <option value="forward">forward</option>
                    <option value="reverse">reverse</option>

        </test>
        <test>
            <param name="bamInput" value="bowtie2 test1.bam" ftype="bam" />
            <param name="outFileFormat" value="bigwig" />
            <param name="showAdvancedOpt" value="no" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result2.bw" ftype="bigwig" />
        </test>
        <test>
            <param name="bamInput" value="bowtie2 test1.bam" ftype="bam" />
            <param name="outFileFormat" value="bedgraph" />
            <param name="showAdvancedOpt" value="no" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result3.bg" ftype="bedgraph" />
        </test>
        <test>
            <param name="bamInput" value="phiX.bam" ftype="bam" />
            <param name="outFileFormat" value="bigwig" />
            <param name="showAdvancedOpt" value="no" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result4.bw" ftype="bigwig" />
        </test>
        <test>
            <param name="bamInput" value="phiX.bam" ftype="bam" />
            <param name="outFileFormat" value="bedgraph" />
            <param name="showAdvancedOpt" value="yes" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result4.bg" ftype="bedgraph" />
        </test>
        <test>
            <param name="bamInput" value="phiX.bam" ftype="bam" />
            <param name="outFileFormat" value="bigwig" />
            <param name="showAdvancedOpt" value="yes" />
            <param name="filterRNAstrand" value="reverse" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result5.bw" ftype="bigwig" />
        </test>
        <test>
            <param name="bamInput" value="bowtie2 test1.bam" ftype="bam" />

--------------

Given a BAM file, this tool generates a bigWig or bedGraph file of fragment or
read coverages. The way the method works is by first calculating all the
number of reads (either extended to match the fragment length or not) that
overlap each bin in the genome. The resulting read counts can be normalized
using either a given scaling factor, the RPKM formula or to get a 1x depth of
coverage (RPGC). In the case of paired-end mapping, each read mate is treated
independently to avoid a bias when a mixture of concordant and discordant
pairs is present. This means that *each end* will be extended to match the
fragment length.

See the usage hints below.

33:6a5dfb2c0c60

<tool id="deeptools_bam_coverage" name="bamCoverage" version="@WRAPPER_VERSION@.0">
    <description>generates a coverage bigWig file from a given BAM or CRAM file</description>
    <macros>
        <token name="@BINARY@">bamCoverage</token>
        <import>deepTools_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command>
<![CDATA[
        ln -s '$bamInput' one.bam &&
        #if $bamInput.ext == 'bam':
            ln -s '${bamInput.metadata.bam_index}' one.bam.bai &&
        #else:
            ln -s '${bamInput.metadata.cram_index}' one.bam.crai &&
        #end if

        @BINARY@
            @THREADS@

            --bam one.bam

            --outFileFormat '$outFileFormat'

            --binSize $binSize

            #if $scaling.type=='rpkm':
                --normalizeUsing RPKM
            #elif $scaling.type=='cpm':
                --normalizeUsing CPM
            #elif $scaling.type=='bpm':
                --normalizeUsing BPM
            #elif $scaling.type=='1x':
                --normalizeUsing RPGC
                #if $scaling.effectiveGenomeSize.effectiveGenomeSize_opt == "specific":
                    --effectiveGenomeSize $scaling.effectiveGenomeSize.effectiveGenomeSize
                #else:
                    --effectiveGenomeSize $scaling.effectiveGenomeSize.effectiveGenomeSize_opt
                #end if
            #end if

            #if str($region).strip() != '':
                --region '$region'

            #end if
]]>
    </command>

    <inputs>
        <param name="bamInput" format="bam,cram" type="data" label="BAM/CRAM file"
            help=""/>

        <param name="binSize" type="integer" value="50" min="1"
            label="Bin size in bases"
            help="The genome will be divided into bins of the specified size. For each bin, the overlaping number of fragments (or reads)  will be reported. If only half a fragment overlaps, this fraction will be reported. "/>

        <conditional name="scaling">
            <param name="type" type="select" label="Scaling/Normalization method" >
                <option value="1x">Normalize coverage to 1x</option>
                <option value="rpkm">Normalize to reads per kilobase per million (RPKM)</option>
                <option value="cpm">Normalize to counts per million (CPM), same as CPM in RNA-seq</option>
                <option value="bpm">Normalize to bins per million (BPM), same as TPM in RNA-seq</option>
                <option value="no">Do not normalize or scale</option>
            </param>
            <when value="rpkm"/>
            <when value="cpm"/>
            <when value="bpm"/>
            <when value="no"/>
            <when value="1x">
                <expand macro="effectiveGenomeSize" />
            </when>
        </conditional>

                        offset of 0 is not permitted. If two values (separated by spaces) are specified, then they will be
                        used to specify a range of positions. Note that specifying something like
                        --Offset 5 -1 will result in the 5th through last position being used, which
                        is equivalent to trimming 4 bases from the 5-prime end of alignments." />

                <param argument="filterRNAstrand" type="select" label="Only include reads originating from fragments from the forward or reverse strand."
                    help="By default (the no option), all reads are processed, regardless of the strand they originated from. For RNAseq, it can be useful to separately create bigWig files for the forward or reverse strands.
                          Note that this tools assumes that a dUTP-based method was used, so fragments will be assigned to the reverse strand if the second read in a pair is reverse complemented.">
                    <option value="no" selected="true">no</option>
                    <option value="forward">forward</option>
                    <option value="reverse">reverse</option>

        </test>
        <test>
            <param name="bamInput" value="bowtie2 test1.bam" ftype="bam" />
            <param name="outFileFormat" value="bigwig" />
            <param name="showAdvancedOpt" value="no" />
            <param name="effectiveGenomeSize_opt" value="specific" />
            <param name="effectiveGenomeSize" value="2451960000" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result2.bw" ftype="bigwig" />
        </test>
        <test>
            <param name="bamInput" value="bowtie2 test1.bam" ftype="bam" />
            <param name="outFileFormat" value="bedgraph" />
            <param name="showAdvancedOpt" value="no" />
            <param name="effectiveGenomeSize_opt" value="specific" />
            <param name="effectiveGenomeSize" value="2451960000" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result3.bg" ftype="bedgraph" />
        </test>
        <test>
            <param name="bamInput" value="phiX.bam" ftype="bam" />
            <param name="outFileFormat" value="bigwig" />
            <param name="showAdvancedOpt" value="no" />
            <param name="effectiveGenomeSize_opt" value="specific" />
            <param name="effectiveGenomeSize" value="2451960000" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result4.bw" ftype="bigwig" />
        </test>
        <test>
            <param name="bamInput" value="phiX.bam" ftype="bam" />
            <param name="outFileFormat" value="bedgraph" />
            <param name="showAdvancedOpt" value="yes" />
            <param name="effectiveGenomeSize_opt" value="specific" />
            <param name="effectiveGenomeSize" value="2451960000" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result4.bg" ftype="bedgraph" />
        </test>
        <test>
            <param name="bamInput" value="phiX.bam" ftype="bam" />
            <param name="outFileFormat" value="bigwig" />
            <param name="showAdvancedOpt" value="yes" />
            <param name="filterRNAstrand" value="reverse" />
            <param name="effectiveGenomeSize_opt" value="specific" />
            <param name="effectiveGenomeSize" value="2451960000" />
            <param name="binSize" value="10" />
            <output name="outFileName" file="bamCoverage_result5.bw" ftype="bigwig" />
        </test>
        <test>
            <param name="bamInput" value="bowtie2 test1.bam" ftype="bam" />

--------------

Given a BAM file, this tool generates a bigWig or bedGraph file of fragment or
read coverages. The way the method works is by first calculating all the
number of reads (either extended to match the fragment length or not) that
overlap each bin in the genome. Various options are available to normalize the reads:
1) using a given scaling factor
2) RPKM (reads per kilobase per million) : RPKM (per bin) =  number of reads per bin / ( number of mapped reads (in millions) * bin length (kb) ).
3) CPM (counts per million) : CPM (per bin) =  number of reads per bin / number of mapped reads (in millions).
4) BPM (bins per million) :  BPM (per bin) =  number of reads per bin / sum of all reads per bin (in millions).
5) RPGC (1x sequencing depth ) : number of reads per bin /(total number of mapped reads * fragment length / effective genome size)

In the case of paired-end mapping, each read mate is treated
independently to avoid a bias when a mixture of concordant and discordant
pairs is present. This means that *each end* will be extended to match the
fragment length.

See the usage hints below.