annotate bamCorrelate.xml @ 52:c0a054f2eff8 draft

Uploaded
author bgruening
date Mon, 22 Dec 2014 18:56:27 -0500
parents 72d1d7c68bd3
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
45
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
1 <tool id="deeptools_bamCorrelate" name="bamCorrelate" version="@WRAPPER_VERSION@.0">
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
2 <description>correlates pairs of BAM files</description>
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
3 <expand macro="requirements" />
22
8710187d1eb5 Uploaded
bgruening
parents: 16
diff changeset
4 <expand macro="stdio" />
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
5 <macros>
34
934b9fccabd4 Uploaded
bgruening
parents: 33
diff changeset
6 <token name="@BINARY@">bamCorrelate</token>
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
7 <import>deepTools_macros.xml</import>
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
8 </macros>
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
9 <command>
52
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
10 <![CDATA[
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
11 #set files=[]
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
12 #set labels=[]
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
13
14
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
14 @multiple_input_bams@
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
15
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
16 bamCorrelate
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
17
16
d0667be9cb0c Uploaded
bgruening
parents: 15
diff changeset
18 $mode.modeOpt
15
351cd1f8791b Uploaded
bgruening
parents: 14
diff changeset
19
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
20 @THREADS@
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
21
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
22 --bamfiles #echo " ".join($files)
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
23 --labels #echo " ".join($labels)
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
24 --fragmentLength $fragmentLength
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
25 --corMethod $corMethod
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
26
24
e43b4015b4cc Uploaded
bgruening
parents: 22
diff changeset
27 --plotFile $outFileName
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
28
29
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
29 #if $output.showOutputSettings == "yes"
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
30 --outRawCounts '$outFileRawCounts'
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
31 --outFileCorMatrix '$outFileCorMatrix'
24
e43b4015b4cc Uploaded
bgruening
parents: 22
diff changeset
32 --plotFileFormat $output.outFileFormat
e43b4015b4cc Uploaded
bgruening
parents: 22
diff changeset
33 #else:
e43b4015b4cc Uploaded
bgruening
parents: 22
diff changeset
34 --plotFileFormat 'png'
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
35 #end if
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
36
16
d0667be9cb0c Uploaded
bgruening
parents: 15
diff changeset
37 #if $mode.modeOpt == "bins":
d0667be9cb0c Uploaded
bgruening
parents: 15
diff changeset
38 --binSize '$mode.binSize'
45
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
39 --distanceBetweenBins '$mode.distanceBetweenBins'
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
40 $mode.doNotRemoveOutliers
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
41
16
d0667be9cb0c Uploaded
bgruening
parents: 15
diff changeset
42 #else:
d0667be9cb0c Uploaded
bgruening
parents: 15
diff changeset
43 --BED $mode.region_file
d0667be9cb0c Uploaded
bgruening
parents: 15
diff changeset
44 #end if
d0667be9cb0c Uploaded
bgruening
parents: 15
diff changeset
45
30
2e5b92e7f3cb Uploaded
bgruening
parents: 29
diff changeset
46 #### options available in both modes
2e5b92e7f3cb Uploaded
bgruening
parents: 29
diff changeset
47 #if str($mode.region.value) != '':
2e5b92e7f3cb Uploaded
bgruening
parents: 29
diff changeset
48 --region '$mode.region'
2e5b92e7f3cb Uploaded
bgruening
parents: 29
diff changeset
49 #end if
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
50
30
2e5b92e7f3cb Uploaded
bgruening
parents: 29
diff changeset
51 #if $mode.advancedOpt.showAdvancedOpt == "yes":
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
52
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
53 $mode.advancedOpt.doNotExtendPairedEnds
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
54 $mode.advancedOpt.ignoreDuplicates
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
55 $mode.advancedOpt.includeZeros
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
56
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
57 #if $mode.advancedOpt.minMappingQuality:
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
58 --minMappingQuality '$mode.advancedOpt.minMappingQuality'
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
59 #end if
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
60
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
61 #if $mode.advancedOpt.zMin:
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
62 --zMin $mode.advancedOpt.zMin
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
63 #end if
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
64 #if $mode.advancedOpt.zMax:
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
65 --zMax $mode.advancedOpt.zMax
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
66 #end if
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
67 --colorMap '$mode.advancedOpt.colorMap'
1
21d563d5f2b2 Uploaded
bgruening
parents: 0
diff changeset
68
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
69 #end if
52
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
70 ]]>
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
71 </command>
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
72
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
73 <inputs>
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
74 <expand macro="multiple_input_bams" />
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
75
52
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
76 <param name="fragmentLength" type="integer" value="200" min="1"
14
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
77 label="Length of the average fragment size"
52
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
78 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. (--fragmentLength)"/>
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
79
14
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
80 <param name="corMethod" type="select" label="Correlation method">
45
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
81 <option value="spearman" selected="True">Spearman</option>
14
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
82 <option value="pearson">Pearson</option>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
83 </param>
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
84
14
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
85 <conditional name="mode">
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
86 <param name="modeOpt" type="select" label="Choose computation mode"
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
87 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.">
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
88 <option value="bins" selected="true">Bins</option>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
89 <option value="BED-file">Limit correlation to certain regions (BED file)</option>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
90 </param>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
91 <when value="bins">
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
92 <param name="binSize" type="integer" value="10000" min="1"
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
93 label="Bin size in bp"
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
94 help="Length in base pairs for a window used to sample the genome."/>
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
95
45
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
96 <param name="distanceBetweenBins" type="integer" value="0" min="0"
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
97 label="Distance between bins"
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
98 help="By default, bamCorrelate considers consecutive bins of
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
99 the specified 'Bin size'. However, to reduce the
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
100 computation time, a larger distance between bins can
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
101 by given. Larger distances result in less bins being
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
102 considered"/>
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
103
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
104 <param name="doNotRemoveOutliers" type="boolean"
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
105 truevalue="--doNotRemoveOutliers" falsevalue="" label="Do not filter outliers"
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
106 help="By default, bins with very large counts are removed.
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
107 By setting this option, outliers will not be
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
108 removed. Bins with unusually large counts normally
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
109 correspond to regions in the genome that accumulate
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
110 lot of reads like satellite regions. If outliers are not
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
111 removed the pearson correlation will wrongly report a
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
112 very high correlation; that's why, by default,
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
113 bamCorrelate tries to remove outliers using
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
114 the median absolute deviation (MAD) method applying a
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
115 threshold of 200 to only consider extremely large
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
116 deviations from the median."/>
b9feca1f07f0 Uploaded
bgruening
parents: 43
diff changeset
117
14
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
118 <expand macro="bamCorrelate_mode_actions" />
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
119 </when>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
120 <when value="BED-file">
52
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
121 <param name="region_file" type="data" format="bed"
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
122 label="Region file in BED format"
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
123 help="Correlation is computed for the number of reads that overlap such regions."/>
14
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
124 <expand macro="bamCorrelate_mode_actions" />
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
125 </when>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
126 </conditional>
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
127
29
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
128 <conditional name="output">
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
129 <param name="showOutputSettings" type="select" label="Show advanced output settings" >
14
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
130 <option value="no" selected="true">no</option>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
131 <option value="yes">yes</option>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
132 </param>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
133 <when value="no" />
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
134 <when value="yes">
25
df9f0dbb1d2a Uploaded
bgruening
parents: 24
diff changeset
135 <expand macro="input_image_file_format"/>
14
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
136 <param name="saveRawCounts" type="boolean" label="Save the bin counts"/>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
137 <param name="saveCorMatrix" type="boolean" label="Save the correlation matrix"/>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
138 </when>
b0d64a9930d6 Uploaded
bgruening
parents: 10
diff changeset
139 </conditional>
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
140
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
141 </inputs>
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
142 <outputs>
25
df9f0dbb1d2a Uploaded
bgruening
parents: 24
diff changeset
143 <expand macro="output_image_file_format" />
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
144 <data format="tabular" name="outFileRawCounts" label="${tool.name} on ${on_string}: bin counts">
29
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
145 <filter>
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
146 ((
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
147 output['showOutputSettings'] == 'yes' and
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
148 output['saveRawCounts'] is True
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
149 ))
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
150 </filter>
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
151 </data>
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
152 <data format="tabular" name="outFileCorMatrix" label="${tool.name} on ${on_string}: correlation matrix">
29
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
153 <filter>
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
154 ((
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
155 output['showOutputSettings'] == 'yes' and
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
156 output['saveCorMatrix'] is True
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
157 ))
60788be7b346 Uploaded
bgruening
parents: 25
diff changeset
158 </filter>
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
159 </data>
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
160 </outputs>
52
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
161 <tests>
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
162 <test>
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
163 <repeat name="input_files">
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
164 <param name="bamfile" value="bowtie2-test1.bam" ftype="bam" />
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
165 </repeat>
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
166 <repeat name="input_files">
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
167 <param name="bamfile" value="bowtie2-test1.bam" ftype="bam" />
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
168 </repeat>
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
169 <param name="modeOpt" value="bins" />
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
170 <param name="binSize" value="10" />
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
171 <param name="showOutputSettings" value="no" />
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
172 <output name="outFileName" file="bamCorrelate_result1.png" ftype="png" compare="sim_size" />
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
173 </test>
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
174 </tests>
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
175 <help>
52
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
176 <![CDATA[
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
177 **What it does**
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
178
5
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
179 This tool is useful to assess the overall similarity of different BAM files. A typical application
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
180 is to check the correlation between replicates or published data sets.
1f312af2f8db Uploaded
bgruening
parents: 1
diff changeset
181
6
c5847db0cb41 Uploaded
bgruening
parents: 5
diff changeset
182 The tool splits the genomes into bins of given length. For each bin, the number of reads
43
c5787c91cab8 Uploaded
bgruening
parents: 37
diff changeset
183 found in each BAM file is counted and a correlation (either Pearson or Spearman) is computed for all
c5787c91cab8 Uploaded
bgruening
parents: 37
diff changeset
184 pairs of BAM files. Finally, a heatmap is drawn based on the similarity of the samples.
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
185
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
186
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
187 .. image:: $PATH_TO_IMAGES/QC_bamCorrelate_humanSamples.png
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
188 :alt: Heatmap of RNA Polymerase II ChIP-seq
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
189
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
190
43
c5787c91cab8 Uploaded
bgruening
parents: 37
diff changeset
191 You can find more details on the bamCorrelate wiki page: https://github.com/fidelram/deepTools/wiki/QC#wiki-bamCorrelate
37
2f7edf06a5da Uploaded
bgruening
parents: 34
diff changeset
192
2f7edf06a5da Uploaded
bgruening
parents: 34
diff changeset
193
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
194 **Output files**:
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
195
43
c5787c91cab8 Uploaded
bgruening
parents: 37
diff changeset
196 - **diagnostic plot**: clustered heatmap displaying the values for each pair-wise correlation, see below for an example
c5787c91cab8 Uploaded
bgruening
parents: 37
diff changeset
197 - data matrix (optional): if you want to plot the correlation values using a different program, e.g. R, this matrix can be used
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
198
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
199
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
200 -----
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
201
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
202 @REFERENCES@
52
c0a054f2eff8 Uploaded
bgruening
parents: 48
diff changeset
203 ]]>
10
a68a771625d2 Uploaded
bgruening
parents: 9
diff changeset
204 </help>
48
72d1d7c68bd3 Uploaded
bgruening
parents: 45
diff changeset
205 <expand macro="citations" />
0
09b65c12a75a Uploaded
bgruening
parents:
diff changeset
206 </tool>