comparison computeGCBias.xml @ 10:a68a771625d2 draft

Uploaded

9:73761f33f198

<tool id="deeptools_computeGCBias" name="computeGCBias" version="1.0.1">
  <description>to see whether your samples should be normalized for GC bias</description>
  
  <requirements>
    <requirement type="package" version="1.5.1_3e13687c89e951476776b15afb4bbbc3b906f761">deepTools</requirement>
    <requirement type="package" >deepTools</requirement>
  </requirements>
  <stdio>
    <exit_code range="0" level="warning" description="Warning" />
  </stdio>
  <command>
    #import tempfile
    #set $temp_dir = os.path.abspath(tempfile.mkdtemp())

    #set $temp_bam_handle = tempfile.NamedTemporaryFile( dir=$temp_dir )
    #set $temp_bam_path = $temp_bam_handle.name + '.bam'
    #silent $temp_bam_handle.close()
    #silent os.system("ln -s %s %s" % (str($bamInput), $temp_bam_path))
    #silent os.system("ln -s %s %s.bai" % (str($bamInput.metadata.bam_index), $temp_bam_path))

  computeGCBias

  ##ToDo
  --numberOfProcessors 4

  --bamfile '$temp_bam_path'
  --species '$species'
  --GCbiasFrequenciesFile $outFileName
  --fragmentLength $fragmentLength

  #if $source.ref_source=="history":
    --genome $source.input1
  #else:
    --genome "${source.input1_2bit.fields.path}"
  #end if

  #if $advancedOpt.showAdvancedOpt == "yes":
    #if str($advancedOpt.region.value) != '':
      --region '$advancedOpt.region'
    #end if
    
    --binSize '$advancedOpt.binSize'
    --sampleSize '$advancedOpt.sampleSize'
    --regionSize '$advancedOpt.regionSize'

    #if $advancedOpt.filterOut:
      --filterOut $advancedOpt.filterOut

##      #end if
##  #end if

  ; rm $temp_dir -rf

  </command>
  <inputs>

      <param name="bamInput" format="bam" type="data" label="Input BAM file"
        help="The BAM file must be sorted."/>
      <!--<param name="species" type="text" value="" label="Species name abbreviation" />-->

        <param name="species" type="select" label="Species name abbreviation">
            <option value="hg19">hg19</option>
            <option value="ce10">ce10</option>
            <option value="dm3">dm3</option>
            <option value="mm9">mm9</option>
        </param>

      <conditional name="source">
        <param name="ref_source" type="select" label="Reference genome">
            <option value="cached">locally cached</option>
            <option value="history">in your history</option>
        </param>
        <when value="cached">
            <param name="input1_2bit" type="select" label="Using reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
                <options from_data_table="deepTools_seqs" />
            </param>
        </when>
        <when value="history">
            <param name="input1" type="data" format="twobit" label="Select a reference dataset in 2bit format" />
        </when>
      </conditional>
      <param name="fragmentLength" type="integer" value="300" min="1"
        label="Fragment length used for the sequencing"
        help ="If paired-end reads are used, the fragment length is computed from the BAM file."/>

    <conditional name="advancedOpt">

        <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="50" min="1" 
             label="Bin size in bp"
             help="Size of the bins in bp for the ouput of the bigwig/bedgraph file."/>
             
           <param name="sampleSize" type="integer" value="50000000" min="1"
             label="Number of sampling points to be considered" />
           
           <param name="regionSize" type="integer" value="300" min="1"

sequencing as it only depends on the respective reference genome (i.e. it will most likely vary between mouse and fruit fly due to their genome's different GC contents).
The OBSERVED values are based on the reads from the sequenced sample. Instead of noting how many genomic regions there are per GC content, we now count the reads per GC content.
In an ideal sample without GC bias, the ratio of OBSERVED/EXPECTED values should be close to 1 regardless of the GC content. Due to PCR (over)amplifications, the majority of ChIP samples
usually shows a significant bias towards reads with high GC content (>50%)

-----

.. class:: infomark

If you would like to give us feedback or you run into any trouble, please send an email to [e-mail]

This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.

.. _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>
</tool>

10:a68a771625d2

<tool id="deeptools_computeGCBias" name="computeGCBias" version="1.0.1">
    <description>to see whether your samples should be normalized for GC bias</description>
    <expand macro="requirements" />
    <stdio>
        <exit_code range="0" level="warning" description="Warning" />
    </stdio>
    <macros>
        <import>deepTools_macros.xml</import>
    </macros>
    <command>
        #import tempfile
        #set $temp_dir = os.path.abspath(tempfile.mkdtemp())

    #set $temp_bam_handle = tempfile.NamedTemporaryFile( dir=$temp_dir )
    #set $temp_bam_path = $temp_bam_handle.name + '.bam'
    #silent $temp_bam_handle.close()
    #silent os.system("ln -s %s %s" % (str($bamInput), $temp_bam_path))
    #silent os.system("ln -s %s %s.bai" % (str($bamInput.metadata.bam_index), $temp_bam_path))

  computeGCBias

    @THREADS@

  --bamfile '$temp_bam_path'
  --GCbiasFrequenciesFile $outFileName
  --fragmentLength $fragmentLength

    @reference_genome_source@


  #if $effectiveGenomeSize.effectiveGenomeSize_opt == "specific":
    --effectiveGenomeSize $effectiveGenomeSize.effectiveGenomeSize
  #else:
    --effectiveGenomeSize $effectiveGenomeSize.effectiveGenomeSize_opt
  #end if


  #if $advancedOpt.showAdvancedOpt == "yes":
    #if str($advancedOpt.region.value) != '':
      --region '$advancedOpt.region'
    #end if
    
    --sampleSize '$advancedOpt.sampleSize'
    --regionSize '$advancedOpt.regionSize'

    #if $advancedOpt.filterOut:
      --filterOut $advancedOpt.filterOut

##      #end if
##  #end if

  ; rm $temp_dir -rf

    </command>
    <inputs>

        <param name="bamInput" format="bam" type="data" label="Input BAM file"
            help="The BAM file must be sorted."/>

        <expand macro="reference_genome_source" />
        <expand macro="effectiveGenomeSize" />

      <param name="fragmentLength" type="integer" value="300" min="1"
        label="Fragment length used for the sequencing"
        help ="If paired-end reads are used, the fragment length is computed from the BAM file."/>

    <conditional name="advancedOpt">

        <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="sampleSize" type="integer" value="50000000" min="1"
             label="Number of sampling points to be considered" />
           
           <param name="regionSize" type="integer" value="300" min="1"

sequencing as it only depends on the respective reference genome (i.e. it will most likely vary between mouse and fruit fly due to their genome's different GC contents).
The OBSERVED values are based on the reads from the sequenced sample. Instead of noting how many genomic regions there are per GC content, we now count the reads per GC content.
In an ideal sample without GC bias, the ratio of OBSERVED/EXPECTED values should be close to 1 regardless of the GC content. Due to PCR (over)amplifications, the majority of ChIP samples
usually shows a significant bias towards reads with high GC content (>50%)

.. image:: $PATH_TO_IMAGES/QC_GCplots_input.png


**Output files**:

- Diagnostic plot

  - box plot of absolute read numbers per genomic GC bin
  - x-y plot of observed/expected read ratios per genomic GC content bin

- Data matrix

  - to be used for GC correction with correctGCbias


-----

.. class:: infomark

@REFERENCES@

    </help>
</tool>