view epicseg.xml @ 0:6260e42c7d49 draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/epicseg commit 560df98ab92af885e9d2e909ee8709885e52cbd3

<tool id="epicseg_segment" name="EpiCSeg - Chromatin segmentation" version="@VERSION_STRING@">
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[

        mkdir -p '${ report.files_path }' &&

        ## Acquire the count matrices
        #for $d, $dataset in enumerate( $datasets ):
            #for $i, $mark in enumerate( $dataset.marks ):
                ln -s -f '${mark.reads}' '${d}_${i}.bam' &&
                ln -s -f '${mark.reads.metadata.bam_index}' '${d}_${i}.bam.bai' &&
            #end for

            Rscript '${__tool_directory__}/epicseg.R' getcounts
                --binsize $binsize --nthreads \${GALAXY_SLOTS:-2}
                --regions '$regions' --target '${d}.tab'

                #for $i, $mark in enumerate( $dataset.marks):
                    --mark '${mark.label}:${d}_${i}.bam' --mapq ${mark.mapq}
                        ${mark.pairedend} --shift ${mark.shift}
                #end for

                &&
        #end for

        ## Normalize the datasets
        #if len( $datasets ) == 1:
            ln -s 0.tab 0_norm.tab
        #else:
            Rscript '${__tool_directory__}/epicseg.R' normalizecounts
                --nthreads \${GALAXY_SLOTS:-2}

                #for $d, $dataset in enumerate( $datasets)
                    --counts '${d}.tab'
                #end for

        #end if

        &&

        ## Segment
        Rscript '${__tool_directory__}/epicseg.R' segment --regions '$regions'
           --nstates $nstates --nthreads \${GALAXY_SLOTS:-2}
           --outdir '${report.files_path}'
           #for $d, $dataset in enumerate( $datasets ):
              --counts '${dataset.name}:${d}_norm.tab'
           #end for

           --maxiter $maxiter

           #for $annot in $annots:
              --annot '${annot.name}:${annot.file}'
           #end for#
         &&
         cp ${report.files_path}/report.html . &&
         cp ${report.files_path}/segmentation*.bed .
    ]]></command>
    <inputs>
        <param type="data" name="regions" format="bed" label="Regions in BED format"
               help="BED file with the genomic regions of interest.
                     These regions will be automatically partitioned into
                     smaller, consecutive bins. Only the first three fields
                     in the file matter.  If the region lengths are not
                     multiples of the given binsize a new bed file will be
                     produced where each coordinate is a multiple of binsize."/>
        <param type="integer" name="binsize" min="0" value="200"
            help="Size of a bin in base pairs. Each given region will
                  be partitioned into bins of this size."/>
        <repeat name="datasets" title="Datasets"
                help="Chromatin segmentation may be performed across one or more
                      datasets (e.g. cell-types or conditions) each
                      of which consisting
                      of a set of chromatin marks (e.g. H3K4me3).
                      If multiple datasets are used,
                      they must share the same set of chromatin marks.">
            <param type="text" name="name" label="Dataset name"
                   value="Treatment" />
            <repeat name="marks" title="Chromatin mark">
                <param type="text" name="label" label="Mark name"
                       value="H3K4me3" />
                <param type="data" name="reads" label="Reads in BAM format"
                       format="bam"
                       help="BAM file containing the read alignments for
                             the corresponding chromatin mark.
                             If the same mark name is used multiple times,
                             the associated reads will be treated as replicates
                             and collapsed into one experiment."/>
                <param type="integer" name="mapq" min="0" value="0"
                       help="Minimum mapping quality for the reads (see the
                             bam format specification for the mapq field).
                             Only reads with the mapq field above or equal
                             to the specified value will be considered."/>
                <param type="boolean" name="pairedend"
                       truevalue="--pairedend TRUE" falsevalue="--pairedend FALSE"
                       help="Set this option to TRUE or FALSE to activate or
                             deactivate the paired-end mode. Only read pairs
                             where both ends are mapped will be considered and
                             assigned to the bin where the midpoint of the
                             read pair is located. If this flag is set, the
                             `shift` option will be ignored."/>
                <param type="integer" name="shift" value="75"
                       help="Shift the reads in the 5' direction by a fixed
                             number of base pairs. The read will be assigned
                             to the bin where the shifted 5' end of the read
                             is located. This option will be ignored in
                             paired-end mode."/>
            </repeat>
        </repeat>


        <param type="integer" name="nstates" label="Number of states"
               min="0" value="5"
               help="Number of chromatin states."/>
        <param type="integer" name="maxiter" value="200"
               help="Maximum number of iterations during training."/>

        <repeat name="annots" title="Annotation"
                help="(Optional) Annotation tracks might be overlayed
                      with the segmentation results.">
            <param type="text" name="name" label="Annotation name"
                   value="genes" />
            <param type="data" name="file" label="Annotation"
                   format="bed"
                   help="BED-file containing the annotation. For example,
                         gene annotation or CpG-islands." />
        </repeat>
    </inputs>
    <outputs>
        <data name="report" format="html" from_work_dir='report.html' >
            <discover_datasets pattern="segmentation" format="bed"
                               visible="true" />
        </data>
    </outputs>
    <tests>
        <test>
            <!-- 1 Dataset w/o annotation -->
            <param name="regions" value="chr1.bed"/>
                <repeat name="datasets">
                    <param name="name" value="DS1" />
                    <repeat name="marks">
                      <param name="label" value="H3K4me3" />
                      <param name="reads" value="chr1_h1hesc_h3k4me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H3K4me1" />
                      <param name="reads" value="chr1_h1hesc_h3k4me1.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H3K4me1" />
                      <param name="reads" value="chr1_h1hesc_h3k4me1_rep2.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H4K27me3" />
                      <param name="reads" value="chr1_h1hesc_h3k27me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                </repeat>
            <param name="binsize" value="200" />
            <param name="nstates" value="5" />
            <output name="report" file="report_1ds.html"/>
        </test>
        <test>
            <!-- 1 Dataset with annotation -->
            <param name="regions" value="chr1.bed"/>
                <repeat name="datasets">
                    <param name="name" value="DS1" />
                    <repeat name="marks">
                      <param name="label" value="H3K4me3" />
                      <param name="reads" value="chr1_h1hesc_h3k4me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H3K4me1" />
                      <param name="reads" value="chr1_h1hesc_h3k4me1.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H3K4me1" />
                      <param name="reads" value="chr1_h1hesc_h3k4me1_rep2.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H4K27me3" />
                      <param name="reads" value="chr1_h1hesc_h3k27me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                </repeat>
            <param name="binsize" value="200" />
            <param name="nstates" value="5" />
            <repeat name="annots">
              <param name="name" value="cpg" />
              <param name="file" value="cpgIslandExt.hg19.bed" />
            </repeat>
            <output name="report" file="report_1ds_w_annot.html"/>
        </test>

        <test>
            <!-- 2 Datasets w/o annotation -->
            <param name="regions" value="chr1.bed"/>
                <repeat name="datasets">
                    <param name="name" value="DS1" />
                    <repeat name="marks">
                      <param name="label" value="H3K4me3" />
                      <param name="reads" value="chr1_h1hesc_h3k4me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H3K4me1" />
                      <param name="reads" value="chr1_h1hesc_h3k4me1.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H4K27me3" />
                      <param name="reads" value="chr1_h1hesc_h3k27me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                </repeat>
                <repeat name="datasets">
                    <param name="name" value="DS2" />
                    <repeat name="marks">
                      <param name="label" value="H3K4me3" />
                      <param name="reads" value="chr1_h1hesc_h3k4me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H3K4me1" />
                      <param name="reads" value="chr1_h1hesc_h3k4me1_rep2.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H4K27me3" />
                      <param name="reads" value="chr1_h1hesc_h3k27me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                </repeat>
            <param name="binsize" value="200" />
            <param name="nstates" value="5" />
            <output name="report" file="report_2ds.html"/>
        </test>

        <test>
            <!-- 2 Datasets with annotation -->
            <param name="regions" value="chr1.bed"/>
                <repeat name="datasets">
                    <param name="name" value="DS1" />
                    <repeat name="marks">
                      <param name="label" value="H3K4me3" />
                      <param name="reads" value="chr1_h1hesc_h3k4me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H3K4me1" />
                      <param name="reads" value="chr1_h1hesc_h3k4me1.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H4K27me3" />
                      <param name="reads" value="chr1_h1hesc_h3k27me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                </repeat>
                <repeat name="datasets">
                    <param name="name" value="DS2" />
                    <repeat name="marks">
                      <param name="label" value="H3K4me3" />
                      <param name="reads" value="chr1_h1hesc_h3k4me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H3K4me1" />
                      <param name="reads" value="chr1_h1hesc_h3k4me1_rep2.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                    <repeat name="marks">
                      <param name="label" value="H4K27me3" />
                      <param name="reads" value="chr1_h1hesc_h3k27me3.bam" />
                      <param name="mapq" value="0"/>
                      <param name="pairedend" value="--pairedend FALSE"/>
                      <param name="shift" value="75"/>
                    </repeat>
                </repeat>
            <param name="binsize" value="200" />
            <param name="nstates" value="5" />
            <repeat name="annots">
              <param name="name" value="cpg" />
              <param name="file" value="cpgIslandExt.hg19.bed" />
            </repeat>
            <output name="report" file="report_2ds_w_annot.html"/>
        </test>
    </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**

**EpiCSeg - Chromatin segmentation** is a tool for performing chromatin segmentation.
It takes as input

  1. one or more datasets (e.g. cell-types or conditions)
     which consist of the next-generation sequencing alignments
     (in bam format) for a common set of chromatin marks (e.g. H3K27me3, H3K4me3, etc.)
  2. a bed file containing the regions of interest
  3. (optional) a set of annotation files (in bed format)
     against which the segmentation results are compared.
     For example, CpG island annotation.

It produces

  1. an html report that summarizes the chromatin segmentation results
  2. a bed file per dataset that contains the chromatin segments.

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