diff bamFingerprint.xml @ 10:a68a771625d2 draft

Uploaded
author bgruening
date Tue, 29 Oct 2013 17:26:28 -0400
parents 73761f33f198
children b0d64a9930d6
line wrap: on
line diff
--- a/bamFingerprint.xml	Tue Sep 17 10:27:29 2013 -0400
+++ b/bamFingerprint.xml	Tue Oct 29 17:26:28 2013 -0400
@@ -1,138 +1,131 @@
 <tool id="deeptools_bamFingerprint" name="bamFingerprint" version="1.0">
-  <description>plots profiles of BAM files; useful for assesing ChIP signal strength</description>
-  <requirements>
-    <requirement type="package" version="1.5.1_3e13687c89e951476776b15afb4bbbc3b906f761">deepTools</requirement>
-    <requirement type="package" >deepTools</requirement>
-  </requirements>
-  <command>
-    #import tempfile
-    #set $temp_dir = os.path.abspath(tempfile.mkdtemp())
+    <description>plots profiles of BAM files; useful for assesing ChIP signal strength</description>
+    <expand macro="requirements" />
+    <macros>
+        <import>deepTools_macros.xml</import>
+    </macros>
+    <command>
+        #import tempfile
+        #set $temp_dir = os.path.abspath(tempfile.mkdtemp())
 
-    #set files=[]
-    #set labels=[]
-    #for $i in $inputs
-        #set $temp_input_handle = tempfile.NamedTemporaryFile( dir=$temp_dir )
-        #set $temp_input_path = $temp_input_handle.name
-        #silent $temp_input_handle.close()
-        #silent os.system("ln -s %s %s.bam" % (str($i.bamfile), $temp_input_path))
-        #silent os.system("ln -s %s %s.bam.bai" % (str($i.bamfile.metadata.bam_index), $temp_input_path))
-        #silent $files.append('%s.bam' % $temp_input_path)
+        #set files=[]
+        #set labels=[]
+        #for $i in $inputs
+            #set $temp_input_handle = tempfile.NamedTemporaryFile( dir=$temp_dir )
+            #set $temp_input_path = $temp_input_handle.name
+            #silent $temp_input_handle.close()
+            #silent os.system("ln -s %s %s.bam" % (str($i.bamfile), $temp_input_path))
+            #silent os.system("ln -s %s %s.bam.bai" % (str($i.bamfile.metadata.bam_index), $temp_input_path))
+            #silent $files.append('%s.bam' % $temp_input_path)
 
-        ##set $files += [str($i.bamfile)]
-        #if str($i.label.value) != "":
-            #set $labels += ["\"%s\"" % ($i.label.value)]
-        #else
-            #set $labels += ["\"%s\"" % ($i.bamfile.name)]
-        #end if
-    #end for
-
-  bamFingerprint
-
-  ##ToDo
-  --numberOfProcessors 4
+            ##set $files += [str($i.bamfile)]
+            #if str($i.label.value) != "":
+                #set $labels += ["\"%s\"" % ($i.label.value)]
+            #else
+                #set $labels += ["\"%s\"" % ($i.bamfile.name)]
+            #end if
+        #end for
 
-  --bamfiles #echo " ".join($files)
-  --labels #echo " ".join($labels)
+    bamFingerprint
 
-  --fragmentLength $fragmentLength
+        @THREADS@
 
-  #set newoutFileName=str($outFileName)+".png"
-  --plotFile $newoutFileName
+      --bamfiles #echo " ".join($files)
+      --labels #echo " ".join($labels)
 
-  #if $outputOpt.showOutputOpt == "yes"
-      #if $outputOpt.saveRawCounts:
-        --outRawCounts '$outFileRawCounts' 
-      #end if
-  #end if
+      --fragmentLength $fragmentLength
+
+      #set newoutFileName=str($outFileName)+".png"
+      --plotFile $newoutFileName
 
-  #if $advancedOpt.showAdvancedOpt == "yes":
-    
-    #if str($advancedOpt.region.value) != '':
-      --region '$advancedOpt.region'
-    #end if
-
-    --binSize '$advancedOpt.binSize'
-    --numberOfSamples '$advancedOpt.numberOfSamples'
+      #if $outputOpt.showOutputOpt == "yes"
+          #if $outputOpt.saveRawCounts:
+            --outRawCounts '$outFileRawCounts' 
+          #end if
+      #end if
 
-    $advancedOpt.doNotExtendPairedEnds
-    $advancedOpt.ignoreDuplicates
-    $advancedOpt.skipZeros
+      #if $advancedOpt.showAdvancedOpt == "yes":
+        
+        #if str($advancedOpt.region.value) != '':
+          --region '$advancedOpt.region'
+        #end if
 
-    #if $advancedOpt.minMappingQuality:
-      --minMappingQuality '$advancedOpt.minMappingQuality'
-    #end if
-  #end if
-  ; mv $newoutFileName $outFileName
-  ; rm $temp_dir -rf
-  </command>
+        --binSize '$advancedOpt.binSize'
+        --numberOfSamples '$advancedOpt.numberOfSamples'
+
+        $advancedOpt.doNotExtendPairedEnds
+        $advancedOpt.ignoreDuplicates
+        $advancedOpt.skipZeros
 
-  <inputs>
-  <repeat name="inputs" title="Input files" min="2">
-    <param name="bamfile" type="data" format="bam" 
-        label="Bam file" 
-        help="The BAM file must be sorted."/>
-    <param name="label" type="text" size="30" optional="true" value=""
-        label="Label"
-        help="Label to use in the output. If not given the dataset name will be used instead."/>
-  </repeat>
-  <param name="fragmentLength" type="integer" value="200" min="1"
-       label="Length of the average fragment size"/>
-  <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="region" type="text" value=""
-       label="Region of the genome to limit the operation to"
-       help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example &quot;chr10&quot; or &quot;chr10:456700:891000&quot;" />
-    
-    <param name="binSize" type="integer" value="10000" min="1" 
-       label="Bin size in bp"
-       help="Length in base pairs for a window used to sample the genome."/>
-    
-    <param name="numberOfSamples" type="integer" value="100000" min="1" 
-       label="Number of samples"
-       help="Number of samples taken from the genome to compute the scaling factors"/>
-    
-    <param name="doNotExtendPairedEnds" type="boolean" truevalue="--doNotExtendPairedEnds" falsevalue=""
-        label="Do not extend paired ends"
-        help="If set, reads are not extended to match the fragment length reported in the BAM file, instead they will be extended to match the fragment length. Default is to extend the reads if paired end information is available."/>
-      
-    <param name="ignoreDuplicates" type="boolean" truevalue="--ignoreDuplicates" falsevalue=""
-        label="Ignore duplicates"
-        help="If set, reads that have the same orientation and start position will be considered only once. If reads are paired, the mate position also has to coincide to ignore a read." /> 
-      
-    <param name="minMappingQuality" type="integer" optional="true" value="1" min="1"
-        label="Minimum mapping quality"
-        help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/>
-        
-    <param name="skipZeros" type="boolean" truevalue="--skipZeros" falsevalue=""
-       label ="Include zeros"
-       help  ="If set, then zero counts that happen for *all* BAM files given are ignored. This might have the effect that fewer regions are considered than indicated in the option where the number of samples is defined." />
-    </when>
-  </conditional>
+        #if $advancedOpt.minMappingQuality:
+          --minMappingQuality '$advancedOpt.minMappingQuality'
+        #end if
+      #end if
+      ; mv $newoutFileName $outFileName
+      ; rm $temp_dir -rf
+    </command>
+
+    <inputs>
+        <expand macro="multiple_input_bams" />
 
-  <conditional name="outputOpt">
-    <param name="showOutputOpt" type="select" label="Show additional output options" >
-      <option value="no" selected="true">no</option>
-      <option value="yes">yes</option>
-    </param>
-    <when value="no" />
-    <when value="yes">
-    <param name="saveRawCounts" type="boolean" label="Save the bin counts"/>
-    </when>
-  </conditional>
-  </inputs>
-  <outputs>
-    <data format="png" name="outFileName" />
-    <data format="tabular" name="outFileRawCounts" label="${tool.name} on ${on_string}: bin counts">
-      <filter>(outputOpt['showOutputOpt'] == 'yes' and outputOpt['saveRawCounts'] == True)</filter>
-    </data>
-  </outputs>
-  <help>
+        <param name="fragmentLength" type="integer" value="200" min="1"
+           label="Length of the average fragment size"/>
+        <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="region" type="text" value=""
+                   label="Region of the genome to limit the operation to"
+                   help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example &quot;chr10&quot; or &quot;chr10:456700:891000&quot;" />
+                
+                <param name="binSize" type="integer" value="10000" min="1" 
+                   label="Bin size in bp"
+                   help="Length in base pairs for a window used to sample the genome."/>
+                
+                <param name="numberOfSamples" type="integer" value="100000" min="1" 
+                   label="Number of samples"
+                   help="Number of samples taken from the genome to compute the scaling factors"/>
+                
+                <param name="doNotExtendPairedEnds" type="boolean" truevalue="--doNotExtendPairedEnds" falsevalue=""
+                    label="Do not extend paired ends"
+                    help="If set, reads are not extended to match the fragment length reported in the BAM file, instead they will be extended to match the fragment length. Default is to extend the reads if paired end information is available."/>
+                  
+                <param name="ignoreDuplicates" type="boolean" truevalue="--ignoreDuplicates" falsevalue=""
+                    label="Ignore duplicates"
+                    help="If set, reads that have the same orientation and start position will be considered only once. If reads are paired, the mate position also has to coincide to ignore a read." /> 
+                  
+                <param name="minMappingQuality" type="integer" optional="true" value="1" min="1"
+                    label="Minimum mapping quality"
+                    help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/>
+                    
+                <param name="skipZeros" type="boolean" truevalue="--skipZeros" falsevalue=""
+                   label ="Include zeros"
+                   help  ="If set, then zero counts that happen for *all* BAM files given are ignored. This might have the effect that fewer regions are considered than indicated in the option where the number of samples is defined." />
+            </when>
+        </conditional>
+
+        <conditional name="outputOpt">
+            <param name="showOutputOpt" type="select" label="Show additional output options" >
+                <option value="no" selected="true">no</option>
+                <option value="yes">yes</option>
+            </param>
+            <when value="no" />
+            <when value="yes">
+                <param name="saveRawCounts" type="boolean" label="Save the bin counts"/>
+            </when>
+        </conditional>
+
+    </inputs>
+    <outputs>
+        <data format="png" name="outFileName" />
+        <data format="tabular" name="outFileRawCounts" label="${tool.name} on ${on_string}: bin counts">
+            <filter>(outputOpt['showOutputOpt'] == 'yes' and outputOpt['saveRawCounts'] == True)</filter>
+        </data>
+    </outputs>
+    <help>
 
 **What it does**
 
@@ -145,18 +138,20 @@
 rise of the cumulative sum towards the highest rank. This means that a big chunk of reads from the ChIP sample is located in
 few bins which corresponds to high, narrow enrichments seen for transcription factors.
 
+
+.. image:: $PATH_TO_IMAGES/QC_fingerprint.png
+
+
+**Output files**:
+
+- Diagnostic plot
+- Data matrix of raw counts
+
 -----
 
 .. class:: infomark
 
-If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com
-
-This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
-
+@REFERENCES@
 
-.. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
-.. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
-
-  </help>
-  
+    </help>
 </tool>