annotate bamCorrelate.xml @ 0:03e5e7b2cedd draft default tip

Uploaded
author devteam
date Thu, 14 Nov 2013 15:58:04 -0500
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
1 <tool id="deeptools_bamCorrelate" name="bamCorrelate" version="1.0.1">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
2 <description>correlates pairs of BAM files</description>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
3 <expand macro="requirements" />
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
4 <macros>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
5 <import>deepTools_macros.xml</import>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
6 </macros>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
7 <command>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
8 #import tempfile
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
9 #set $temp_dir = os.path.abspath(tempfile.mkdtemp())
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
10
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
11 #set files=[]
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
12 #set labels=[]
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
13
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
14 @multiple_input_bams@
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
15
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
16 bamCorrelate
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
17
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
18 @THREADS@
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
19
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
20 --bamfiles #echo " ".join($files)
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
21 --labels #echo " ".join($labels)
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
22
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
23 --fragmentLength $fragmentLength
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
24 --corMethod $corMethod
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
25
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
26 #set newoutFileName=str($outFileName)+".png"
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
27 --plotFile $newoutFileName
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
28
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
29 #if $outputOpt.showOutputOpt == "yes"
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
30 --outRawCounts '$outFileRawCounts'
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
31 --outFileCorMatrix '$outFileCorMatrix'
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
32 #end if
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
33
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
34 #if $mode.modeOpt == "bins":
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
35 --binSize '$mode.binSize'
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
36 --numberOfSamples '$modenumberOfSamples'
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
37 #else:
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
38 --BED $mode.region_file
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
39 #end if
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
40
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
41 ## options available in both modes
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
42 #if $mode.advancedOpt.showAdvancedOpt == "yes":
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
43
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
44 #if str($mode.advancedOpt.region.value) != '':
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
45 --region '$mode.advancedOpt.region'
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
46 #end if
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
47
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
48 $mode.advancedOpt.doNotExtendPairedEnds
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
49 $mode.advancedOpt.ignoreDuplicates
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
50 $mode.advancedOpt.includeZeros
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
51
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
52 #if $mode.advancedOpt.minMappingQuality:
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
53 --minMappingQuality '$mode.advancedOpt.minMappingQuality'
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
54 #end if
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
55
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
56 #if $mode.advancedOpt.zMin:
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
57 --zMin $mode.advancedOpt.zMin
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
58 #end if
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
59 #if $mode.advancedOpt.zMax:
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
60 --zMax $mode.advancedOpt.zMax
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
61 #end if
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
62 --colorMap '$mode.advancedOpt.colorMap'
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
63
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
64 #end if
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
65
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
66 ; mv $newoutFileName $outFileName
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
67 ; rm $temp_dir -rf
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
68 </command>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
69
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
70 <inputs>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
71 <expand macro="multiple_input_bams" />
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
72
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
73 <param name="fragmentLength" type="integer" value="300" min="1"
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
74 label="Length of the average fragment size"
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
75 help ="Reads will be extended to match this length unless they are paired-end, in which case they will be extended to match the fragment length. *NOTE*: If the BAM files contain mated and unmated paired-end reads, unmated reads will be extended to match the fragment length."/>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
76
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
77 <param name="corMethod" type="select" label="Correlation method">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
78 <option value="pearson">Pearson</option>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
79 <option value="spearman">Spearman</option>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
80 </param>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
81
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
82 <conditional name="mode">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
83 <param name="modeOpt" type="select" label="Choose computation mode"
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
84 help="In the bins mode, the correlation is computed based on equal length bins. In the BED file mode, as list of genomic regions in BED format has to be given. For each region in the BED file the number of overlapping reads is counted in each of the BAM files. Then the correlation is computed.">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
85 <option value="bins" selected="true">Bins</option>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
86 <option value="BED-file">Limit correlation to certain regions (BED file)</option>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
87 </param>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
88 <when value="bins">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
89 <param name="binSize" type="integer" value="10000" min="1"
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
90 label="Bin size in bp"
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
91 help="Length in base pairs for a window used to sample the genome."/>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
92
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
93 <param name="numberOfSamples" type="integer" value="100000" min="1"
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
94 label="Number of samples"
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
95 help="Number of samples taken from the genome to compute the scaling factors"/>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
96 <expand macro="bamCorrelate_mode_actions" />
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
97 </when>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
98 <when value="BED-file">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
99 <param name="region_file" type="data" format="bed" label="Region file in BED format" help="Correlation is computed for the number of reads that overlap such regions."/>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
100 <expand macro="bamCorrelate_mode_actions" />
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
101 </when>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
102
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
103 </conditional>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
104
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
105 <conditional name="outputOpt">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
106 <param name="showOutputOpt" type="select" label="Show additional output options" >
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
107 <option value="no" selected="true">no</option>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
108 <option value="yes">yes</option>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
109 </param>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
110 <when value="no" />
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
111 <when value="yes">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
112 <param name="saveRawCounts" type="boolean" label="Save the bin counts"/>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
113 <param name="saveCorMatrix" type="boolean" label="Save the correlation matrix"/>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
114 </when>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
115 </conditional>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
116
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
117 </inputs>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
118 <outputs>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
119 <data format="png" name="outFileName" />
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
120 <data format="tabular" name="outFileRawCounts" label="${tool.name} on ${on_string}: bin counts">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
121 <filter>(outputOpt['showOutputOpt'] == 'yes' and outputOpt['saveRawCounts'] == True)</filter>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
122 </data>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
123 <data format="tabular" name="outFileCorMatrix" label="${tool.name} on ${on_string}: correlation matrix">
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
124 <filter>(outputOpt['showOutputOpt'] == 'yes' and outputOpt['saveCorMatrix'] == True)</filter>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
125 </data>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
126 </outputs>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
127 <help>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
128
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
129 **What it does**
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
130
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
131 This tool is useful to assess the overall similarity of different BAM files. A typical application
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
132 is to check the correlation between replicates or published data sets.
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
133
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
134 The tool splits the genomes into bins of given length. For each bin, the number of reads
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
135 found in each BAM file is counted and a correlation is computed for all
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
136 pairs of BAM files.
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
137
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
138
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
139 .. image:: $PATH_TO_IMAGES/QC_bamCorrelate_humanSamples.png
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
140 :alt: Heatmap of RNA Polymerase II ChIP-seq
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
141
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
142
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
143 **Output files**:
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
144
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
145 - diagnostic plot produced by bamCorrelate is a clustered heatmap displaying the values for each pair-wise correlation, see below for an example
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
146 - data matrix (optional) in case you want to plot the correlation values using a different program, e.g. R, this matrix can be used
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
147
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
148
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
149
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
150
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
151 -----
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
152
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
153 .. class:: infomark
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
154
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
155 @REFERENCES@
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
156
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
157 </help>
03e5e7b2cedd Uploaded
devteam
parents:
diff changeset
158 </tool>