diff computeMatrix.xml @ 0:14cb57237e46 draft

planemo upload for repository https://github.com/fidelram/deepTools/tree/master/galaxy/wrapper/ commit 0a9265a12a303b54cdaa974e82e87c2ac60962ee-dirty
author bgruening
date Mon, 25 Jan 2016 20:26:32 -0500
parents
children 275ed3e83de0
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/computeMatrix.xml	Mon Jan 25 20:26:32 2016 -0500
@@ -0,0 +1,264 @@
+<tool id="deeptools_compute_matrix" name="computeMatrix" version="@WRAPPER_VERSION@.0">
+    <description>prepares data for plotting a heatmap or a profile of given regions</description>
+    <macros>
+        <token name="@BINARY@">computeMatrix</token>
+        <import>deepTools_macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <command>
+<![CDATA[
+        #import tempfile
+
+        @BINARY@
+
+            $mode.mode_select
+            --regionsFileName
+            #for $rf in $regionsFiles:
+                '$rf.regionsFile' 
+            #end for
+            --scoreFileName
+            #for $bw in $scoreFileName:
+                '$bw' 
+            #end for
+            --outFileName '$outFileName'
+
+            @THREADS@
+
+            #if $output.showOutputSettings == "yes"
+                #if $output.saveMatrix:
+                --outFileNameMatrix '$outFileNameMatrix'
+                #end if
+
+                #if $output.saveSortedRegions:
+                    --outFileSortedRegions '$outFileSortedRegions'
+                #end if
+            #end if
+
+            #if $mode.mode_select == "reference-point":
+                --referencePoint $mode.referencePoint
+                $mode.nanAfterEnd
+                --beforeRegionStartLength $mode.beforeRegionStartLength
+                --afterRegionStartLength $mode.afterRegionStartLength
+            #else
+                --regionBodyLength $mode.regionBodyLength
+                #if $mode.regionStartLength.regionStartLength_select == "yes":
+                    --beforeRegionStartLength $mode.regionStartLength.beforeRegionStartLength
+                    --afterRegionStartLength $mode.regionStartLength.afterRegionStartLength
+                #end if
+            #end if
+
+            #if $advancedOpt.showAdvancedOpt == "yes":
+                --sortRegions '$advancedOpt.sortRegions'
+                --sortUsing '$advancedOpt.sortUsing'
+                --averageTypeBins '$advancedOpt.averageTypeBins'
+                $advancedOpt.skipNAs
+                $advancedOpt.skipZeros
+                --binSize $advancedOpt.binSize
+
+                #if $advancedOpt.minThreshold is not None and str($advancedOpt.minThreshold) != '':
+                    --minThreshold $advancedOpt.minThreshold
+                #end if
+                #if $advancedOpt.maxThreshold is not None and str($advancedOpt.maxThreshold) != '':
+                    --maxThreshold $advancedOpt.maxThreshold
+                #end if
+                #if $advancedOpt.scale is not None and str($advancedOpt.scale) != '':
+                    --scale $advancedOpt.scale
+                #end if
+
+            #end if
+]]>
+    </command>
+    <inputs>
+
+        <repeat name="regionsFiles" title="Select regions" min="1">
+            <param name="regionsFile" format="bed" type="data" label="Regions to plot"
+                help="File, in BED format, containing the regions to plot."/>
+        </repeat>
+
+        <param name="scoreFileName" format="bigwig" type="data"
+            label="Score file" multiple="True"
+            help="You can generate a bigWig file from either a
+            bedGraph or WIG file using UCSC tools or from a BAM file using the
+            bamCoverage tool. (--scoreFileName)"/>
+
+        <conditional name="mode" >
+            <param name="mode_select" type="select"
+                label="computeMatrix has two main output options"
+                help="In the scale-regions mode, all regions in the BED file are
+                stretched or shrunk to the same length (in bases) that is indicated
+                by the user. Reference-point refers to a position within the BED
+                regions (e.g start of region). In the reference-point mode only
+                those genomic positions before (upstream) and/or after (downstream)
+                the reference point will be considered.">
+                <option value="scale-regions" selected="true">scale-regions</option>
+                <option value="reference-point">reference-point</option>
+            </param>
+
+            <when value="scale-regions" >
+                <param argument="--regionBodyLength" type="integer" value="500"
+                    label="Distance in bases to which all regions are going to be fit" help=""/>
+                <conditional name="regionStartLength">
+                    <param name="regionStartLength_select" type="select" label="Set distance up- and downstream of the given regions">
+                        <option value="no" selected="true">no</option>
+                        <option value="yes">yes</option>
+                    </param>
+                    <when value="no" />
+                    <when value="yes">
+                        <param argument="--beforeRegionStartLength" type="integer" value="1000" min="1"
+                            label="Distance upstream of the region start position"
+                            help="If the regions are genes, this would be the
+                            distance upstream of the transcription start site."/>
+                        <param argument="--afterRegionStartLength" type="integer" value="1000" min="1"
+                            label="Distance downstream of the region end position"
+                            help="If the regions are genes, this would be the
+                            distance downstream of the transcription end site."/>
+                    </when>
+                </conditional>
+            </when>
+            <when value="reference-point">
+                <param name="referencePoint" type="select" label="The reference point for the plotting">
+                    <option value="TSS" selected="true">beginning of region (e.g. TSS)</option>
+                    <option	 value="TES">end of region (e.g. TES)</option>
+                    <option value="center">center of region</option>
+                </param>
+                <param name="nanAfterEnd" type="boolean" truevalue="--nanAfterEnd" falsevalue=""
+                    label="Discard any values after the region end"
+                    help="This is useful to visualize the region end when not using the
+                    scale-regions mode and when the reference-point is set to the TSS. (--nanAfterEnd)"/>
+                <param name="beforeRegionStartLength" type="integer" value="1000" min="1"
+                    label="Distance upstream of the start site of the regions defined in the region file"
+                    help="If the regions are genes, this would be the distance upstream of the transcription start site. (--beforeRegionStartLength)"/>
+                <param name="afterRegionStartLength" type="integer" value="1000" min="1"
+                    label="Distance downstream of the end site of the given regions"
+                    help="If the regions are genes, this would be the distance downstream of the transcription end site. (--afterRegionStartLength)"/>
+            </when>
+        </conditional>
+
+        <expand macro="input_graphic_output_settings">
+            <expand macro="input_save_matrix_values" />
+        </expand>
+
+        <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 name="binSize" type="integer" value="50" min="1"
+                    label="Length, in bases, of non-overlapping bins used for averaging the score over the regions length"
+                    help="(--binSize)"/>
+
+                <expand macro="sortRegions" />
+                <expand macro="sortUsing" />
+
+                <param name="averageTypeBins" type="select"
+                    label="Define the type of statistic that should be displayed."
+                    help="The value is computed for each bin. (--averageTypeBins)">
+                    <option value="mean" selected="true">mean</option>
+                    <option value="median">median</option>
+                    <option value="min">min</option>
+                    <option value="max">max</option>
+                    <option value="sum">sum</option>
+                    <option value="std">std</option>
+                </param>
+
+                <param name="missingDataAsZero" type="boolean" truevalue="--missingDataAsZero" falsevalue="" checked="False"
+                    label="Convert missing values to 0?."
+                    help="If set to 'yes', missing values (NAs) are converted to 0.
+                          The default is to ignore such cases, which will be
+                          depicted as black areas once a heatmap is created." />
+
+                <expand macro="skipZeros" />
+                <expand macro="skipNAs" />
+
+                <param name="minThreshold" type="float" optional="True"
+                    label="Minimum threshold"
+                    help="Any region containing a value that is equal or less than this numeric
+                    value will be skipped. This is useful to skip, for example, genes where the
+                    read count is zero for any of the bins. This could be the result of
+                    unmappable areas and can bias the overall results. (--minThreshold)"/>
+                <param name="maxThreshold" type="float" optional="True"
+                    label="Maximum threshold"
+                    help="Any region containing a value that is equal or higher that this
+                    numeric value will be skipped. The max threshold is useful to skip those
+                    few regions with very high read counts (e.g. major satellites) that may
+                    bias the average values. (--maxThreshold)"/>
+                <param name="scale" type="float" optional="True" label="Scaling factor"
+                    help="If set, all values are multiplied by this number. (--scale)"/>
+            </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <data format="deeptools_compute_matrix_archive" name="outFileName" label="${tool.name} on ${on_string}: Matrix" />
+        <expand macro="output_graphic_outputs" />
+        <expand macro="output_save_matrix_values" />
+    </outputs>
+    <!--
+    computeMatrix -S test.bw -R test2.bed -a 100 -b 100 -bs 1
+    -->
+    <tests>
+        <test>
+            <param name="regionsFile" value="computeMatrix1.bed" ftype="bed" />
+            <param name="scoreFileName" value="bamCoverage_result4.bw" ftype="bigwig" />
+            <param name="showAdvancedOpt" value="yes" />
+            <param name="mode_select" value="reference-point" />
+            <param name="binSize" value="10" />
+            <param name="sortUsing" value="sum" />
+            <param name="averageTypeBins" value="sum" />
+            <param name="skipNAs" value="False" />
+            <param name="beforeRegionStartLength" value="10" />
+            <param name="afterRegionStartLength" value="10" />
+            <output name="outFileName" file="computeMatrix_result1.gz" ftype="deeptools_compute_matrix_archive" compare="sim_size" />
+        </test>
+        <test>
+            <param name="regionsFile" value="computeMatrix2.bed" ftype="bed" />
+            <param name="scoreFileName" value="computeMatrix2.bw" ftype="bigwig" />
+            <param name="showAdvancedOpt" value="yes" />
+            <param name="mode_select" value="reference-point" />
+            <param name="binSize" value="10" />
+            <param name="beforeRegionStartLength" value="10" />
+            <param name="afterRegionStartLength" value="10" />
+            <output name="outFileName" file="computeMatrix_result2.gz" ftype="deeptools_compute_matrix_archive" compare="sim_size" />
+        </test>
+        <test>
+            <param name="regionsFile" value="computeMatrix2.bed" ftype="bed" />
+            <param name="scoreFileName" value="computeMatrix2.bw" ftype="bigwig" />
+            <param name="showAdvancedOpt" value="yes" />
+            <param name="mode_select" value="scale-regions" />
+            <param name="endLabel" value="END" />
+            <param name="regionStartLength" value="yes" />
+            <output name="outFileName" file="computeMatrix_result3.gz" ftype="deeptools_compute_matrix_archive" compare="sim_size" />
+        </test>
+    </tests>
+  <help>
+<![CDATA[
+**What it does**
+
+This tool prepares an intermediate file (a gzipped table of values)
+that contains scores associated with genomic regions and can be used
+afterwards to plot a heatmap or profile.
+
+Genomic regions can really be anything - genes, parts of genes, ChIP-seq
+peaks, favorite genome regions... as long as you provide a proper file
+in BED or INTERVAL format. If you would like to compare different groups of regions
+(i.e. genes from chromosome 2 and 3), you can supply more than 1 BED file, one for each group.
+
+computeMatrix can also be used to filter and sort
+regions according to their score by making use of its advanced output options.
+
+
+.. image:: $PATH_TO_IMAGES/flowChart_computeMatrixetc.png
+   :alt: Relationship between computeMatrix, heatmapper and profiler
+
+
+You can find more details on the computeMatrix doc page: https://deeptools.readthedocs.org/en/master/content/tools/computeMatrix.html
+
+
+-----
+
+@REFERENCES@
+]]>
+    </help>
+    <expand macro="citations" />
+</tool>