|
0
|
1 <?xml version="1.0"?>
|
|
11
|
2 <tool id="genetrack" name="GeneTrack" version="@WRAPPER_VERSION@.0">
|
|
0
|
3 <description>peak predictor</description>
|
|
|
4 <macros>
|
|
|
5 <import>genetrack_macros.xml</import>
|
|
|
6 </macros>
|
|
|
7 <expand macro="requirements" />
|
|
|
8 <command>
|
|
|
9 python $__tool_directory__/genetrack.py
|
|
|
10 --input_format $input_format_cond.input_format
|
|
6
|
11 #if str($input_format_cond.input_format) == "scidx":
|
|
|
12 #for $i in $input_format_cond.input_scidx:
|
|
0
|
13 --input "${i}" "${i.hid}"
|
|
|
14 #end for
|
|
|
15 #elif str($input_format_cond.input_format) == "gff":
|
|
|
16 #for $i in $input_format_cond.input_gff:
|
|
|
17 --input "${i}" "${i.hid}"
|
|
|
18 #end for
|
|
|
19 #end if
|
|
|
20 --sigma $sigma
|
|
|
21 --exclusion $exclusion
|
|
|
22 --up_width $up_width
|
|
|
23 --down_width $down_width
|
|
|
24 --filter $filter
|
|
|
25 </command>
|
|
|
26 <inputs>
|
|
|
27 <conditional name="input_format_cond">
|
|
|
28 <param name="input_format" type="select" label="Format of files for conversion">
|
|
6
|
29 <option value="scidx" selected="True">ScIdx</option>
|
|
|
30 <option value="gff">Gff</option>
|
|
0
|
31 </param>
|
|
6
|
32 <when value="scidx">
|
|
|
33 <param name="input_scidx" type="data" format="scidx" multiple="True" label="Predict peaks on" />
|
|
0
|
34 </when>
|
|
|
35 <when value="gff">
|
|
|
36 <param name="input_gff" type="data" format="gff" multiple="True" label="Predict peaks on" />
|
|
|
37 </when>
|
|
|
38 </conditional>
|
|
|
39 <param name="sigma" type="integer" value="5" min="1" label="Sigma to use when smoothing reads" help="Higher values increase computation but produce more smoothing." />
|
|
|
40 <param name="exclusion" type="integer" value="20" min="1" label="Peak exclusion zone" help="Exclusion zone around each peak that prevents others from being called." />
|
|
12
|
41 <param name="up_width" type="integer" value="10" min="0" label="Exclusion zone of upstream called peaks" />
|
|
|
42 <param name="down_width" type="integer" value="10" min="0" label="Exclusion zone of downstream called peaks" />
|
|
0
|
43 <param name="filter" type="integer" value="3" min="0" label="Absolute read filter" help="Removes peaks with lower peak height." />
|
|
|
44 </inputs>
|
|
|
45 <outputs>
|
|
|
46 <collection name="genetrack_output" type="list" label="Genetrack results on ${on_string}">
|
|
|
47 <discover_datasets pattern="(?P<designation>.*)" directory="output" ext="gff" visible="false" />
|
|
|
48 </collection>
|
|
|
49 </outputs>
|
|
|
50 <tests>
|
|
|
51 <test>
|
|
|
52 <param name="input_gff" value="genetrack_input2.gff" ftype="gff" />
|
|
|
53 <param name="input_format" value="gff" />
|
|
|
54 <param name="sigma" value="5" />
|
|
|
55 <param name="exclusion" value="20" />
|
|
|
56 <param name="up_width" value="10" />
|
|
|
57 <param name="down_width" value="10" />
|
|
|
58 <param name="filter" value="3" />
|
|
|
59 <output_collection name="genetrack_output" type="list">
|
|
|
60 <element name="s5e20u10d10F3_on_data_1" file="genetrack_output2.gff" ftype="gff" />
|
|
|
61 </output_collection>
|
|
|
62 </test>
|
|
|
63 <test>
|
|
6
|
64 <param name="input_scidx" value="genetrack_input3.scidx" ftype="scidx" />
|
|
|
65 <param name="input_format" value="scidx" />
|
|
0
|
66 <param name="sigma" value="5" />
|
|
|
67 <param name="exclusion" value="20" />
|
|
|
68 <param name="up_width" value="10" />
|
|
|
69 <param name="down_width" value="10" />
|
|
|
70 <param name="filter" value="3" />
|
|
|
71 <output_collection name="genetrack_output" type="list">
|
|
|
72 <element name="s5e20u10d10F3_on_data_1" file="genetrack_output3.gff" ftype="gff" />
|
|
|
73 </output_collection>
|
|
|
74 </test>
|
|
|
75 <test>
|
|
|
76 <param name="input_gff" value="genetrack_input_unsorted4.gff" ftype="gff" />
|
|
|
77 <param name="input_format" value="gff" />
|
|
|
78 <param name="sigma" value="5" />
|
|
|
79 <param name="exclusion" value="20" />
|
|
|
80 <param name="up_width" value="10" />
|
|
|
81 <param name="down_width" value="10" />
|
|
|
82 <param name="filter" value="3" />
|
|
|
83 <output_collection name="genetrack_output" type="list">
|
|
|
84 <element name="s5e20u10d10F3_on_data_1" file="genetrack_output4.gff" ftype="gff" />
|
|
|
85 </output_collection>
|
|
|
86 </test>
|
|
|
87 </tests>
|
|
|
88 <help>
|
|
|
89 **What it does**
|
|
|
90
|
|
12
|
91 <![CDATA[
|
|
|
92
|
|
|
93 GeneTrack separately identifies peaks on the forward "+” and reverse “-” strand. The way that GeneTrack works
|
|
|
94 is to replace each tag with a probabilistic distribution of occurrences for that tag at and around its mapped
|
|
|
95 genomic coordinate. The distance decay of the probabilistic distribution is set by adjusting the value of the
|
|
|
96 tool's **Sigma to use when smoothing reads** parameter. GeneTrack then sums the distribution over all mapped
|
|
|
97 tags. This results in a smooth continuous trace that can be globally broadened or tightened by adjusting the
|
|
|
98 sigma value. GeneTrack starts with the highest smoothed peak first, treating each strand separately if indicated
|
|
|
99 by the data, then sets up an exclusion zone (centered over the peak) defined by the value of the **Peak exclusion
|
|
|
100 zone** parameter (see figure). The exclusion zone prevents any secondary peaks from being called on the same strand
|
|
|
101 within that exclusion zone. In rare cases, it may be desirable to set different exclusion zones upstream (more 5’)
|
|
|
102 versus downstream (more 3’) of the peak.
|
|
|
103
|
|
|
104 ]]>
|
|
|
105
|
|
|
106 .. image:: $PATH_TO_IMAGES/genetrack.png
|
|
0
|
107
|
|
6
|
108 -----
|
|
|
109
|
|
0
|
110 **Options**
|
|
|
111
|
|
12
|
112 * **Sigma to use when smoothing reads** - Smooths clusters of tags via a Gaussian distribution.
|
|
|
113 * **Peak exclusion zone** - Exclusion zone around each peak, eliminating all other peaks on the same strand that are within a ± bp distance of the peak.
|
|
|
114 * **Exclusion zone of upstream called peaks** - Defines the exclusion zone centered over peaks upstream of a peak.
|
|
|
115 * **Exclusion zone of downstream called peaks** - Defines the exclusion zone centered over peaks downstream of a peak.
|
|
|
116 * **Filter** - Absolute read filter, restricts output to only peaks with larger peak height.
|
|
0
|
117 </help>
|
|
|
118 <expand macro="citations" />
|
|
|
119 </tool>
|
