annotate computeGCBias.xml @ 6:1ee0b1ecf500 draft

Uploaded
author bgruening
date Mon, 02 Dec 2013 07:49:06 -0500
parents c54d31467be4
children c53a73b8eef9
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>
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
11 ln -s $bamInput local_bamInput.bam;
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
12 ln -s $bamInput.metadata.bam_index local_bamInput.bam.bai;
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
13
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
14 computeGCBias
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
15
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
16 @THREADS@
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
17
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
18 --bamfile 'local_bamInput.bam'
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
19 --GCbiasFrequenciesFile $outFileName
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
20 --fragmentLength $fragmentLength
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
21
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
22 @reference_genome_source@
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
23
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
24 #if $effectiveGenomeSize.effectiveGenomeSize_opt == "specific":
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
25 --effectiveGenomeSize $effectiveGenomeSize.effectiveGenomeSize
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
26 #else:
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
27 --effectiveGenomeSize $effectiveGenomeSize.effectiveGenomeSize_opt
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
28 #end if
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
29
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
30 #if $advancedOpt.showAdvancedOpt == "yes":
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
31 #if str($advancedOpt.region.value) != '':
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
32 --region '$advancedOpt.region'
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
33 #end if
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
34
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
35 --sampleSize '$advancedOpt.sampleSize'
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
36 --regionSize '$advancedOpt.regionSize'
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
37
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
38 #if $advancedOpt.filterOut:
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
39 --filterOut $advancedOpt.filterOut
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
40 #end if
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
41
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
42 #if $advancedOpt.extraSampling:
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
43 --extraSampling $advancedOpt.extraSampling
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
44 #end if
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
45 #end if
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
46
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
47 #if $saveBiasPlot:
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
48 --biasPlot $biasPlot
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
49 #end if
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
50
5
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
51 ## #if $output.showOutputSettings == "yes"
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
52 ## #if $output.saveBiasPlot:
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
53 ## --biasPlot biasPlot.png ;
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
54 ## mv biasPlot.png $biasPlot
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
55 ## #end if
c54d31467be4 Uploaded
bgruening
parents: 0
diff changeset
56 ## #end if
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
57
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
58 </command>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
59 <inputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
60
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
61 <param name="bamInput" format="bam" type="data" label="Input BAM file"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
62 help="The BAM file must be sorted."/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
63
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
64 <expand macro="reference_genome_source" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
65 <expand macro="effectiveGenomeSize" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
66
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
67 <param name="fragmentLength" type="integer" value="300" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
68 label="Fragment length used for the sequencing"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
69 help ="If paired-end reads are used, the fragment length is computed from the BAM file."/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
70
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
71 <conditional name="advancedOpt">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
72 <param name="showAdvancedOpt" type="select" label="Show advanced options" >
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
73 <option value="no" selected="true">no</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
74 <option value="yes">yes</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
75 </param>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
76 <when value="no" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
77 <when value="yes">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
78 <param name="region" type="text" value=""
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
79 label="Region of the genome to limit the operation to"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
80 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
81
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
82 <param name="sampleSize" type="integer" value="50000000" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
83 label="Number of sampling points to be considered" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
84
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
85 <param name="regionSize" type="integer" value="300" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
86 label="Region size"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
87 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
88
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
89 <param name="filterOut" type="data" format="bed" optional="true"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
90 label="BED file containing genomic regions to be excluded from the estimation of the correction"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
91 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
92 <param name="extraSampling" type="data" format="bed" optional="true"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
93 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
94 help="" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
95 </when>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
96 </conditional>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
97
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
98 <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
99 <!--
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
100 <conditional name="output" >
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
101 <param name="showOutputSettings" type="select" label="Show additional output options" >
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
102 <option value="no" selected="true">no</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
103 <option value="yes">yes</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
104 </param>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
105 <when value="no" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
106 <when value="yes">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
107 <param name="saveBiasPlot" type="boolean" label="Save a diagnostic image summarizing the GC bias found on the sample"/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
108 </when>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
109 </conditional>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
110 -->
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
111 </inputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
112 <outputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
113 <data format="tabular" name="outFileName" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
114 <data format="png" name="biasPlot" label="${tool.name} on ${on_string}: bias plot">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
115 <filter>saveBiasPlot is True</filter>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
116 <!--<filter>(output['showOutputSettings'] == 'yes' and output['saveBiasPlot'] == True)</filter>-->
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
117 </data>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
118 </outputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
119 <help>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
120
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
121 **What it does**
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
122
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
123 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
124 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
125 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
126 depicting the ratio of observed/expected reads per genomic GC content bin.
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
127
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
128 -----
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
129
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
130 **Summary of the method used**
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
131
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
132 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
133 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
134 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
135 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
136 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
137 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
138 usually shows a significant bias towards reads with high GC content (>50%)
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
139
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
140 .. image:: $PATH_TO_IMAGES/QC_GCplots_input.png
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
141
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
142
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
143 **Output files**:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
144
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
145 - Diagnostic plot
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
146
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
147 - box plot of absolute read numbers per genomic GC bin
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
148 - x-y plot of observed/expected read ratios per genomic GC content bin
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
149
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
150 - Data matrix
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
151
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
152 - to be used for GC correction with correctGCbias
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
153
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
154
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
155 -----
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
156
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
157 .. class:: infomark
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
158
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
159 @REFERENCES@
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
160
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
161 </help>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
162 </tool>