|
0
|
1 <?xml version="1.0"?>
|
|
|
2 <tool id="genetrack" name="Genetrack" version="@WRAPPER_VERSION@.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 --chunk_size $chunk_size
|
|
|
26 </command>
|
|
|
27 <inputs>
|
|
|
28 <conditional name="input_format_cond">
|
|
|
29 <param name="input_format" type="select" label="Format of files for conversion">
|
|
6
|
30 <option value="scidx" selected="True">ScIdx</option>
|
|
|
31 <option value="gff">Gff</option>
|
|
0
|
32 </param>
|
|
6
|
33 <when value="scidx">
|
|
|
34 <param name="input_scidx" type="data" format="scidx" multiple="True" label="Predict peaks on" />
|
|
0
|
35 </when>
|
|
|
36 <when value="gff">
|
|
|
37 <param name="input_gff" type="data" format="gff" multiple="True" label="Predict peaks on" />
|
|
|
38 </when>
|
|
|
39 </conditional>
|
|
|
40 <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." />
|
|
|
41 <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." />
|
|
|
42 <param name="up_width" type="integer" value="10" min="0" label="Upstream width of called peaks" />
|
|
|
43 <param name="down_width" type="integer" value="10" min="0" label="Downstream width of called peaks" />
|
|
|
44 <param name="filter" type="integer" value="3" min="0" label="Absolute read filter" help="Removes peaks with lower peak height." />
|
|
|
45 <param name="chunk_size" type="integer" value="10" min="1" label="Chunk each chromosome into" help="Value is millions of base pairs where each size increment uses about 20MB of memory." />
|
|
|
46 </inputs>
|
|
|
47 <outputs>
|
|
|
48 <collection name="genetrack_output" type="list" label="Genetrack results on ${on_string}">
|
|
|
49 <discover_datasets pattern="(?P<designation>.*)" directory="output" ext="gff" visible="false" />
|
|
|
50 </collection>
|
|
|
51 </outputs>
|
|
|
52 <tests>
|
|
|
53 <test>
|
|
|
54 <param name="input_gff" value="genetrack_input2.gff" ftype="gff" />
|
|
|
55 <param name="input_format" value="gff" />
|
|
|
56 <param name="sigma" value="5" />
|
|
|
57 <param name="exclusion" value="20" />
|
|
|
58 <param name="up_width" value="10" />
|
|
|
59 <param name="down_width" value="10" />
|
|
|
60 <param name="filter" value="3" />
|
|
|
61 <param name="chunk_size" value="10" />
|
|
|
62 <output_collection name="genetrack_output" type="list">
|
|
|
63 <element name="s5e20u10d10F3_on_data_1" file="genetrack_output2.gff" ftype="gff" />
|
|
|
64 </output_collection>
|
|
|
65 </test>
|
|
|
66 <test>
|
|
6
|
67 <param name="input_scidx" value="genetrack_input3.scidx" ftype="scidx" />
|
|
|
68 <param name="input_format" value="scidx" />
|
|
0
|
69 <param name="sigma" value="5" />
|
|
|
70 <param name="exclusion" value="20" />
|
|
|
71 <param name="up_width" value="10" />
|
|
|
72 <param name="down_width" value="10" />
|
|
|
73 <param name="filter" value="3" />
|
|
|
74 <param name="chunk_size" value="10" />
|
|
|
75 <output_collection name="genetrack_output" type="list">
|
|
|
76 <element name="s5e20u10d10F3_on_data_1" file="genetrack_output3.gff" ftype="gff" />
|
|
|
77 </output_collection>
|
|
|
78 </test>
|
|
|
79 <test>
|
|
|
80 <param name="input_gff" value="genetrack_input_unsorted4.gff" ftype="gff" />
|
|
|
81 <param name="input_format" value="gff" />
|
|
|
82 <param name="sigma" value="5" />
|
|
|
83 <param name="exclusion" value="20" />
|
|
|
84 <param name="up_width" value="10" />
|
|
|
85 <param name="down_width" value="10" />
|
|
|
86 <param name="filter" value="3" />
|
|
|
87 <param name="chunk_size" value="10" />
|
|
|
88 <output_collection name="genetrack_output" type="list">
|
|
|
89 <element name="s5e20u10d10F3_on_data_1" file="genetrack_output4.gff" ftype="gff" />
|
|
|
90 </output_collection>
|
|
|
91 </test>
|
|
|
92 </tests>
|
|
|
93 <help>
|
|
|
94 **What it does**
|
|
|
95
|
|
|
96 Genetrack takes a standard set of data on both the sense and antisense strands and smooths their relative reads.
|
|
|
97 It then calls the peaks present in the smoothed dataset and uses those peak locations to calculate the final
|
|
|
98 reads from surrounding reads. Finally, it ensures each peak is above a threshold and that two peaks are not
|
|
|
99 too close to each other.
|
|
|
100
|
|
6
|
101 -----
|
|
|
102
|
|
0
|
103 **Options**
|
|
|
104
|
|
|
105 * **Sigma to use when smoothing reads** - Sigma to use when smoothing reads to call peaks.
|
|
|
106 * **Peak exclusion zone** - Exclusion zone around each peak that prevents others from being called.
|
|
|
107 * **Upstream width of called peaks** - Upstream width of called peaks.
|
|
|
108 * **Downstream width of called peaks** - Downstream width of called peaks.
|
|
|
109 * **Filter** - Absolute read filter. Restricts output to only peaks with larger peak height.
|
|
|
110 * **Chunk each chromosome into** - Size, in millions of base pairs, to chunk each chromosome when processing. Each 1 million size uses approximately 20MB of memory.
|
|
|
111 </help>
|
|
|
112 <expand macro="citations" />
|
|
|
113 </tool>
|
