annotate bamFingerprint.xml @ 4:ac935c35437a draft

Uploaded
author bgruening
date Sat, 16 Nov 2013 07:54:13 -0500
parents d957e25e18a3
children 135f3bae5c56
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
1 <tool id="deeptools_bamFingerprint" name="bamFingerprint" version="1.0">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
2 <description>plots profiles of BAM files; useful for assesing ChIP signal strength</description>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
3 <expand macro="requirements" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
4 <macros>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
5 <import>deepTools_macros.xml</import>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
6 </macros>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
7 <command>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
8 #import tempfile
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
9 #set $temp_dir = os.path.abspath(tempfile.mkdtemp())
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
10
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
11 #set files=[]
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
12 #set labels=[]
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
13
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
14 @multiple_input_bams@
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
15
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
16 bamFingerprint
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
17
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
18 @THREADS@
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
19
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
20 --bamfiles #echo " ".join($files)
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
21 --labels #echo " ".join($labels)
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
22
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
23 --fragmentLength $fragmentLength
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
24
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
25 #set newoutFileName=str($outFileName)+".png"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
26 --plotFile $newoutFileName
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
27
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
28 #if $outputOpt.showOutputOpt == "yes"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
29 #if $outputOpt.saveRawCounts:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
30 --outRawCounts '$outFileRawCounts'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
31 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
32 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
33
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
34 #if $advancedOpt.showAdvancedOpt == "yes":
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
35
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
36 #if str($advancedOpt.region.value) != '':
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
37 --region '$advancedOpt.region'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
38 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
39
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
40 --binSize '$advancedOpt.binSize'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
41 --numberOfSamples '$advancedOpt.numberOfSamples'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
42
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
43 $advancedOpt.doNotExtendPairedEnds
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
44 $advancedOpt.ignoreDuplicates
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
45 $advancedOpt.skipZeros
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
46
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
47 #if $advancedOpt.minMappingQuality:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
48 --minMappingQuality '$advancedOpt.minMappingQuality'
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
49 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
50 #end if
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
51 ; mv $newoutFileName $outFileName
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
52 ; rm $temp_dir -rf
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
53 </command>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
54
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
55 <inputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
56 <expand macro="multiple_input_bams" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
57
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
58 <param name="fragmentLength" type="integer" value="200" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
59 label="Length of the average fragment size"/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
60 <conditional name="advancedOpt">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
61 <param name="showAdvancedOpt" type="select" label="Show advanced options" >
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
62 <option value="no" selected="true">no</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
63 <option value="yes">yes</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
64 </param>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
65 <when value="no" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
66 <when value="yes">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
67 <param name="region" type="text" value=""
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
68 label="Region of the genome to limit the operation to"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
69 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
70
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
71 <param name="binSize" type="integer" value="10000" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
72 label="Bin size in bp"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
73 help="Length in base pairs for a window used to sample the genome."/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
74
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
75 <param name="numberOfSamples" type="integer" value="100000" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
76 label="Number of samples"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
77 help="Number of samples taken from the genome to compute the scaling factors"/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
78
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
79 <param name="doNotExtendPairedEnds" type="boolean" truevalue="--doNotExtendPairedEnds" falsevalue=""
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
80 label="Do not extend paired ends"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
81 help="If set, reads are not extended to match the fragment length reported in the BAM file, instead they will be extended to match the fragment length. Default is to extend the reads if paired end information is available."/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
82
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
83 <param name="ignoreDuplicates" type="boolean" truevalue="--ignoreDuplicates" falsevalue=""
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
84 label="Ignore duplicates"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
85 help="If set, reads that have the same orientation and start position will be considered only once. If reads are paired, the mate position also has to coincide to ignore a read." />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
86
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
87 <param name="minMappingQuality" type="integer" optional="true" value="1" min="1"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
88 label="Minimum mapping quality"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
89 help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
90
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
91 <param name="skipZeros" type="boolean" truevalue="--skipZeros" falsevalue=""
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
92 label ="Include zeros"
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
93 help ="If set, then zero counts that happen for *all* BAM files given are ignored. This might have the effect that fewer regions are considered than indicated in the option where the number of samples is defined." />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
94 </when>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
95 </conditional>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
96
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
97 <conditional name="outputOpt">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
98 <param name="showOutputOpt" type="select" label="Show additional output options" >
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
99 <option value="no" selected="true">no</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
100 <option value="yes">yes</option>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
101 </param>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
102 <when value="no" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
103 <when value="yes">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
104 <param name="saveRawCounts" type="boolean" label="Save the bin counts"/>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
105 </when>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
106 </conditional>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
107
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
108 </inputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
109 <outputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
110 <data format="png" name="outFileName" />
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
111 <data format="tabular" name="outFileRawCounts" label="${tool.name} on ${on_string}: bin counts">
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
112 <filter>(outputOpt['showOutputOpt'] == 'yes' and outputOpt['saveRawCounts'] == True)</filter>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
113 </data>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
114 </outputs>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
115 <help>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
116
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
117 **What it does**
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
118
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
119 This tool is based on a method developed by Diaz et al. (2012). Stat Appl Genet Mol Biol 11(3).
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
120 The resulting plot can be used to assess the strength of a ChIP (for factors that bind to narrow regions).
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
121 The tool first samples indexed BAM files and counts all reads overlapping a window (bin) of specified length.
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
122 These counts are then sorted according to their rank and the cumulative sum of read counts are plotted. An ideal input
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
123 with perfect uniform distribution of reads along the genome (i.e. without enrichments in open chromatin etc.) should
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
124 generate a straight diagonal line. A very specific and strong ChIP enrichment will be indicated by a prominent and steep
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
125 rise of the cumulative sum towards the highest rank. This means that a big chunk of reads from the ChIP sample is located in
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
126 few bins which corresponds to high, narrow enrichments seen for transcription factors.
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
127
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
128
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
129 .. image:: $PATH_TO_IMAGES/QC_fingerprint.png
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
130
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
131
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
132 **Output files**:
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
133
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
134 - Diagnostic plot
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
135 - Data matrix of raw counts
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
136
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
137 -----
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
138
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
139 .. class:: infomark
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
140
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
141 @REFERENCES@
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
142
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
143 </help>
d957e25e18a3 Uploaded
bgruening
parents:
diff changeset
144 </tool>