annotate computeGCBias.xml @ 5:1f312af2f8db draft

Uploaded
author bgruening
date Tue, 06 Aug 2013 08:20:47 -0400
parents 21d563d5f2b2
children c5847db0cb41
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
1 <tool id="computeGCBias" name="computeGCBias" version="1.0.1">
5
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
2 <description>to see whether your samples should be normalized for GC bias</description>
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
3
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
4 <requirements>
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
5 <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement>
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
6 </requirements>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
7 <stdio>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
8 <exit_code range="0" level="warning" description="Warning" />
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
9 </stdio>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
10 <command>
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
11 #import tempfile
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
12 #set $temp_dir = os.path.abspath(tempfile.mkdtemp())
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
13
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
14 #set $temp_bam_handle = tempfile.NamedTemporaryFile( dir=$temp_dir )
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
15 #set $temp_bam_path = $temp_bam_handle.name + '.bam'
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
16 #silent $temp_bam_handle.close()
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
17 #silent os.system("ln -s %s %s" % (str($bamInput), $temp_bam_path))
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
18 #silent os.system("ln -s %s %s.bai" % (str($bamInput.metadata.bam_index), $temp_bam_path))
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
19
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
20 computeGCBias
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
21
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
22 ##ToDo
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
23 --numberOfProcessors 4
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
24
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
25 --bamfile '$temp_bam_path'
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
26 --species '$species'
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
27 --GCbiasFrequenciesFile $outFileName
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
28 --fragmentLength $fragmentLength
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
29
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
30 #if $source.ref_source=="history":
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
31 --genome $source.input1
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
32 #else:
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
33 --genome "${source.input1_2bit.fields.path}"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
34 #end if
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
35
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
36 #if $advancedOpt.showAdvancedOpt == "yes":
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
37 #if str($advancedOpt.region.value) != '':
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
38 --region '$advancedOpt.region'
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
39 #end if
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
40
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
41 --binSize '$advancedOpt.binSize'
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
42 --sampleSize '$advancedOpt.sampleSize'
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
43 --regionSize '$advancedOpt.regionSize'
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
44
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
45 #if $advancedOpt.filterOut:
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
46 --filterOut $advancedOpt.filterOut
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
47 #end if
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
48
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
49 #if $advancedOpt.extraSampling:
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
50 --extraSampling $advancedOpt.extraSampling
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
51 #end if
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
52
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
53 #end if
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
54
5
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
55 #if $saveBiasPlot:
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
56 --biasPlot $biasPlot
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
57 #end if
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
58
5
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
59 ## #if $output.showOutputSettings == "yes"
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
60 ## #if $output.saveBiasPlot:
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
61 ## --biasPlot biasPlot.png ;
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
62 ## mv biasPlot.png $biasPlot
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
63 ## #end if
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
64 ## #end if
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
65
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
66 ; rm $temp_dir -rf
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
67
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
68 </command>
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
69 <inputs>
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
70
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
71 <param name="bamInput" format="bam" type="data" label="Input BAM file"
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
72 help="The BAM file must be sorted and indexed."/>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
73 <!--<param name="species" type="text" value="" label="Species name abbreviation" />-->
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
74
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
75 <param name="species" type="select" label="Species name abbreviation">
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
76 <option value="hg19">hg19</option>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
77 <option value="ce10">ce10</option>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
78 <option value="dm3">dm3</option>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
79 <option value="mm9">mm9</option>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
80 </param>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
81
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
82 <conditional name="source">
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
83 <param name="ref_source" type="select" label="Reference genome">
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
84 <option value="cached">locally cached</option>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
85 <option value="history">in your history</option>
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
86 </param>
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
87 <when value="cached">
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
88 <param name="input1_2bit" type="select" label="Using reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
89 <options from_data_table="deepTools_seqs" />
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
90 </param>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
91 </when>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
92 <when value="history">
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
93 <param name="input1" type="data" format="twobit" label="Select a reference dataset in 2bit format" />
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
94 </when>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
95 </conditional>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
96 <param name="fragmentLength" type="integer" value="300" min="1"
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
97 label="Fragment length used for the sequencing"
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
98 help ="If paired-end reads are used the fragment length is computed based from the bam file."/>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
99
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
100 <conditional name="advancedOpt">
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
101 <param name="showAdvancedOpt" type="select" label="Show advanced options" >
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
102 <option value="no" selected="true">no</option>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
103 <option value="yes">yes</option>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
104 </param>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
105 <when value="no" />
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
106 <when value="yes">
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
107 <param name="region" type="text" value=""
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
108 label="Region of the genome to limit the operation to"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
109 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;" />
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
110
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
111 <param name="binSize" type="integer" value="50" min="1"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
112 label="Bin size in bp"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
113 help="Size of the bins in bp for the ouput of the bigwig/bedgraph file."/>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
114
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
115 <param name="sampleSize" type="integer" value="50000000" min="1"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
116 label="Number of sampling points to be considered" />
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
117
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
118 <param name="regionSize" type="integer" value="300" min="1"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
119 label="Region size"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
120 help ="To plot the reads per GC over a region the size of the region is required. By default, the bin size is set to 300bp, which is close to the standard fragment size for Illumina machines. However, if the depth of sequencing is low a larger bin size will be required, otherwise many bins will not overlap with any read."/>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
121
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
122 <param name="filterOut" type="data" format="bed" optional="true"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
123 label="BED file containing genomic regions to be excluded from the estimation of the correction"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
124 help="Such regions usually contain repetitive regions and peaks that if included will bias the correction. It is recommended to filter out known repetitive regions if multi-reads (reads that map to more than one genomic position) were excluded. In the case of ChIP-seq data, it is recommended to first use a peak caller to identify and filter out the identified peaks." />
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
125 <param name="extraSampling" type="data" format="bed" optional="true"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
126 label="BED file containing genomic regions for which extra sampling is required because they are underrepresented in the genome"
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
127 help="" />
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
128 </when>
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
129 </conditional>
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
130
5
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
131 <param name="saveBiasPlot" type="boolean" truevalue="--biasPlot" falsevalue="" checked="True" label="Save a diagnostic image summarizing the GC bias found on the sample"/>
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
132 <!--
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
133 <conditional name="output" >
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
134 <param name="showOutputSettings" type="select" label="Show additional output options" >
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
135 <option value="no" selected="true">no</option>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
136 <option value="yes">yes</option>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
137 </param>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
138 <when value="no" />
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
139 <when value="yes">
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
140 <param name="saveBiasPlot" type="boolean" label="Save a diagnostic image summarizing the GC bias found on the sample"/>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
141 </when>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
142 </conditional>
5
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
143 -->
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
144 </inputs>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
145 <outputs>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
146 <data format="tabular" name="outFileName" />
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
147 <data format="png" name="biasPlot" label="${tool.name} on ${on_string}: bias plot">
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
148 <filter>(output['showOutputSettings'] == 'yes' and output['saveBiasPlot'] == True)</filter>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
149 </data>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
150 </outputs>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
151 <help>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
152
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
153 **What it does**
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
154
5
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
155 This tool computes the GC bias ussing the method proposed by Benjamini and Speed (2012). Nucleic Acids Res.
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
156 The output is used to plot the bias and can also be used later on to correct the bias with the tool correctGCbias.
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
157
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
158 -----
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
159
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
160 .. class:: infomark
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
161
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
162 Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_.
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
163
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
164 This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
165
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
166
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
167 .. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
168 .. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
169 .. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
170
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
171 </help>
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
172 </tool>