annotate computeGCBias.xml @ 2:b5da81864541 draft

Uploaded
author bgruening
date Fri, 15 Nov 2013 11:02:32 -0500
parents d957e25e18a3
children c54d31467be4
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
1 <tool id="deeptools_computeGCBias" name="computeGCBias" version="1.0.1">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
2 <description>to see whether your samples should be normalized for GC bias</description>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
3 <expand macro="requirements" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
4 <stdio>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
5 <exit_code range="0" level="warning" description="Warning" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
6 </stdio>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
7 <macros>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
8 <import>deepTools_macros.xml</import>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
9 </macros>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
10 <command>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
11 #import tempfile
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
12 #set $temp_dir = os.path.abspath(tempfile.mkdtemp())
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
13
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
14 #set $temp_bam_handle = tempfile.NamedTemporaryFile( dir=$temp_dir )
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
15 #set $temp_bam_path = $temp_bam_handle.name + '.bam'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
16 #silent $temp_bam_handle.close()
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
17 #silent os.system("ln -s %s %s" % (str($bamInput), $temp_bam_path))
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
18 #silent os.system("ln -s %s %s.bai" % (str($bamInput.metadata.bam_index), $temp_bam_path))
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
19
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
20 computeGCBias
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
21
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
22 @THREADS@
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
23
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
24 --bamfile '$temp_bam_path'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
25 --GCbiasFrequenciesFile $outFileName
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
26 --fragmentLength $fragmentLength
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
27
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
28 @reference_genome_source@
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
29
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
30
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
31 #if $effectiveGenomeSize.effectiveGenomeSize_opt == "specific":
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
32 --effectiveGenomeSize $effectiveGenomeSize.effectiveGenomeSize
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
33 #else:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
34 --effectiveGenomeSize $effectiveGenomeSize.effectiveGenomeSize_opt
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
35 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
36
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
37
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
38 #if $advancedOpt.showAdvancedOpt == "yes":
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
39 #if str($advancedOpt.region.value) != '':
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
40 --region '$advancedOpt.region'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
41 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
42
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
43 --sampleSize '$advancedOpt.sampleSize'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
44 --regionSize '$advancedOpt.regionSize'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
45
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
46 #if $advancedOpt.filterOut:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
47 --filterOut $advancedOpt.filterOut
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
48 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
49
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
50 #if $advancedOpt.extraSampling:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
51 --extraSampling $advancedOpt.extraSampling
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
52 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
53
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
54 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
55
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
56 #if $saveBiasPlot:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
57 --biasPlot $biasPlot
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
58 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
59
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
60 ## #if $output.showOutputSettings == "yes"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
61 ## #if $output.saveBiasPlot:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
62 ## --biasPlot biasPlot.png ;
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
63 ## mv biasPlot.png $biasPlot
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
64 ## #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
65 ## #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
66
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
67 ; rm $temp_dir -rf
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
68
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
69 </command>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
70 <inputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
71
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
72 <param name="bamInput" format="bam" type="data" label="Input BAM file"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
73 help="The BAM file must be sorted."/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
74
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
75 <expand macro="reference_genome_source" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
76 <expand macro="effectiveGenomeSize" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
77
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
78 <param name="fragmentLength" type="integer" value="300" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
79 label="Fragment length used for the sequencing"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
80 help ="If paired-end reads are used, the fragment length is computed from the BAM file."/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
81
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
82 <conditional name="advancedOpt">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
83 <param name="showAdvancedOpt" type="select" label="Show advanced options" >
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
84 <option value="no" selected="true">no</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
85 <option value="yes">yes</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
86 </param>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
87 <when value="no" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
88 <when value="yes">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
89 <param name="region" type="text" value=""
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
90 label="Region of the genome to limit the operation to"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
91 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;" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
92
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
93 <param name="sampleSize" type="integer" value="50000000" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
94 label="Number of sampling points to be considered" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
95
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
96 <param name="regionSize" type="integer" value="300" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
97 label="Region size"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
98 help ="To plot the reads per GC over a region, the size of the region is required (see below for more details of the mthod). By default, the bin size is set to 300 bp, which is close to the standard fragment size many sequencing applications. However, if the depth of sequencing is low, a larger bin size will be required, otherwise many bins will not overlap with any read."/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
99
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
100 <param name="filterOut" type="data" format="bed" optional="true"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
101 label="BED file containing genomic regions to be excluded from the estimation of the correction"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
102 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." />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
103 <param name="extraSampling" type="data" format="bed" optional="true"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
104 label="BED file containing genomic regions for which extra sampling is required because they are underrepresented in the genome"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
105 help="" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
106 </when>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
107 </conditional>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
108
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
109 <param name="saveBiasPlot" type="boolean" truevalue="--biasPlot" falsevalue="" checked="True" label="Save a diagnostic image summarizing the GC bias found on the sample"/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
110 <!--
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
111 <conditional name="output" >
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
112 <param name="showOutputSettings" type="select" label="Show additional output options" >
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
113 <option value="no" selected="true">no</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
114 <option value="yes">yes</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
115 </param>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
116 <when value="no" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
117 <when value="yes">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
118 <param name="saveBiasPlot" type="boolean" label="Save a diagnostic image summarizing the GC bias found on the sample"/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
119 </when>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
120 </conditional>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
121 -->
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
122 </inputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
123 <outputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
124 <data format="tabular" name="outFileName" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
125 <data format="png" name="biasPlot" label="${tool.name} on ${on_string}: bias plot">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
126 <filter>saveBiasPlot is True</filter>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
127 <!--<filter>(output['showOutputSettings'] == 'yes' and output['saveBiasPlot'] == True)</filter>-->
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
128 </data>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
129 </outputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
130 <help>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
131
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
132 **What it does**
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
133
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
134 This tool computes the GC bias using the method proposed by Benjamini and Speed (2012). Nucleic Acids Res. (see below for more explanations)
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
135 The output is used to plot the bias and can also be used later on to correct the bias with the tool correctGCbias.
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
136 There are two plots produced by the tool: a boxplot showing the absolute read numbers per genomic-GC bin and an x-y plot
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
137 depicting the ratio of observed/expected reads per genomic GC content bin.
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
138
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
139 -----
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
140
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
141 **Summary of the method used**
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
142
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
143 In order to estimate how many reads with what kind of GC content one should have sequenced, we first need to determine how many regions the specific
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
144 reference genome contains for each amount of GC content, i.e. how many regions in the genome have 50% GC (or 10% GC or 90% GC or...).
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
145 We then sample a large number of equally sized genome bins and count how many times we see a bin with 50% GC (or 10% GC or 90% or...). These EXPECTED values are independent of any
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
146 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).
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
147 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.
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
148 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
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
149 usually shows a significant bias towards reads with high GC content (>50%)
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
150
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
151 .. image:: $PATH_TO_IMAGES/QC_GCplots_input.png
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
152
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
153
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
154 **Output files**:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
155
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
156 - Diagnostic plot
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
157
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
158 - box plot of absolute read numbers per genomic GC bin
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
159 - x-y plot of observed/expected read ratios per genomic GC content bin
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
160
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
161 - Data matrix
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
162
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
163 - to be used for GC correction with correctGCbias
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
164
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
165
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
166 -----
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
167
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
168 .. class:: infomark
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
169
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
170 @REFERENCES@
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
171
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
172 </help>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
173 </tool>