|
0
|
1 <tool name="Two wiggle file correlation in union regions" id="correlation_intervals" version="0.1.0">
|
|
|
2 <description>Calculate the correlation coefficient of two wiggle / bigwig files in the union regions from two bed files</description>
|
|
|
3 <macros>
|
|
|
4 <import>corr_macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements_union" />
|
|
|
7 <command>
|
|
|
8 #if $wfile1.extension == "wig"
|
|
|
9 qc_chIP_peak.py -s $step -m $method -f bed
|
|
|
10 #elif $wfile1.extension == "bigwig"
|
|
|
11 qc_chIP_peakBW.py
|
|
|
12 #end if
|
|
|
13 -x $wfile1 -y $wfile2 -p $bfile1 -q $bfile2 -r qc_chIP-output.txt &> $log &&
|
|
|
14 Rscript qc_chIP-output.txt
|
|
|
15 </command>
|
|
|
16 <inputs>
|
|
|
17 <!-- need pybedtools for qc_chIP_peakBW.py
|
|
|
18 <param format="wig,bigwig" name="wfile1" type="data" label="WIGGLE / bigwig file 1"/>
|
|
|
19 -->
|
|
|
20 <param format="wig" name="wfile1" type="data" label="WIGGLE / bigwig file 1"/>
|
|
|
21 <param format="bed" name="bfile1" type="data" label="BED file 1(100,000 lines max)"/>
|
|
|
22 <!-- need pybedtools for qc_chIP_peakBW.py
|
|
|
23 <param format="wig,bigwig" name="wfile2" type="data" label="WIGGLE / bigwig file 2"/>
|
|
|
24 -->
|
|
|
25 <param format="wig" name="wfile2" type="data" label="WIGGLE / bigwig file 2"/>
|
|
|
26 <param format="bed" name="bfile2" type="data" label="BED file 2(100,000 lines max)"/>
|
|
|
27 <param name="step" type="integer" label="Step" value="5" help="step in points. This option is only used for wig file.">
|
|
|
28 <validator type="in_range" max="100" min="1" message="Step is out of range, Step has to be between 1 to 100" />
|
|
|
29 </param>
|
|
|
30 <param name="method" type="select" label="method:" help="method to process the paired two sets of data in the sampling step." >
|
|
|
31 <option value="mean" selected="true">mean</option>
|
|
|
32 <option value="median">median</option>
|
|
|
33 <option value="sum">sum</option>
|
|
|
34 <option value="sample">sample</option>
|
|
|
35 </param>
|
|
|
36 <param name="method" type="hidden" label="method:" help="method to process the paired two sets of data in the sampling step." >
|
|
|
37 <option value="mean">mean</option>
|
|
|
38 </param>
|
|
|
39 </inputs>
|
|
|
40 <outputs>
|
|
|
41 <data format="pdf" name="output" from_work_dir="qc_chIP-output.txt.pdf"/>
|
|
|
42 <data format="txt" name="log" label="job log" />
|
|
|
43 <data format="txt" name="rscript" label="job rscript" from_work_dir="qc_chIP-output.txt"/>
|
|
|
44 </outputs>
|
|
|
45 <expand macro="stdio"/>
|
|
|
46 <tests>
|
|
|
47 <test>
|
|
|
48 <param name="wfile1" value="control.wig" />
|
|
|
49 <param name="bfile1" value="peaks.bed" />
|
|
|
50 <param name="wfile2" value="treatment.wig" />
|
|
|
51 <param name="bfile2" value="peaks.bed" />
|
|
|
52 <param name="step" value="5" />
|
|
|
53 <output name="log">
|
|
|
54 <assert_contents>
|
|
|
55 <has_text_matching expression="centering pscore2" />
|
|
|
56 </assert_contents>
|
|
|
57 </output>
|
|
|
58 </test>
|
|
|
59 </tests>
|
|
|
60
|
|
|
61
|
|
|
62 <help>
|
|
|
63 This tool calculates the correlation coefficient on two sets where the
|
|
|
64 two sets intersect The tool is written by Tao Liu. It calls R for
|
|
|
65 plotting.
|
|
|
66
|
|
|
67 .. class:: infomark
|
|
|
68
|
|
|
69 **TIP:** This can be used to evaluate the correlation between
|
|
|
70 two biological replicates.
|
|
|
71
|
|
|
72 .. class:: warningmark
|
|
|
73
|
|
|
74 **NEED IMPROVEMENT**
|
|
|
75
|
|
|
76 -----
|
|
|
77
|
|
|
78 **Parameters**
|
|
|
79
|
|
|
80 - **WIGGLE file 1 and 2** are the two wiggle files to be
|
|
|
81 included. These two are required.
|
|
|
82 - **BED file 1 and 2** are the two BED files to be used to
|
|
|
83 extract scores from wiggle files.
|
|
|
84 - **wiggle files** click *Add new wiggle file* to add more wiggle
|
|
|
85 files and labels.
|
|
|
86 - **Genome/Assembly** Genome assembly to be used. The tool will
|
|
|
87 download the chromosome information from UCSC database.
|
|
|
88 - **Method** When scores are extracted for a region in BED file, a
|
|
|
89 method will be applied to calculate a value to represent this
|
|
|
90 region. Options are *median* to use the median value or *mean* to
|
|
|
91 use the average value.
|
|
|
92 - **Step** Step in data points. The step is a window to extract the
|
|
|
93 scores from wiggle files along the whole genome. So that every step
|
|
|
94 number of points will have a value to represent it by using certain **Method**
|
|
|
95 - **Method** When scores are extracted for a step long window, a
|
|
|
96 method will be applied to calculate a value to represent this
|
|
|
97 window. Options are *median* to use the median value or *mean* to
|
|
|
98 use the average value, or *sample* to sample 1 point to represent
|
|
|
99 the region, or *sum* to use the sum of values in the region.
|
|
|
100
|
|
|
101 -----
|
|
|
102
|
|
|
103 **Outputs**
|
|
|
104
|
|
|
105 - **PNG file** is the correlation plot
|
|
|
106
|
|
|
107 </help>
|
|
|
108
|
|
|
109 </tool>
|
