|
0
|
1 <tool id="trf" name="Tandem Repeats Finder" version="4.04">
|
|
|
2 <description>Detect tandem repeats that have undergone extensive mutational change</description>
|
|
|
3 <command interpreter="python">trf_wrapper.py
|
|
|
4 $input1 $match $mismatch $delta $mprobability $iprobability $minscore
|
|
|
5 $maxperiod $masked $flanking $noredundancy -o $outputdat -k $outputmask -t
|
|
|
6 $report -i $indices
|
|
|
7 </command>
|
|
|
8 <inputs>
|
|
|
9 <param format="fasta" name="input1" type="data">
|
|
|
10 <label>Sequence</label>
|
|
|
11 </param>
|
|
|
12 <param name="match" size="4" type="text" value="2">
|
|
|
13 <label>Match</label>
|
|
|
14 </param>
|
|
|
15 <param name="mismatch" size="4" type="text" value="7">
|
|
|
16 <label>Mismatch</label>
|
|
|
17 </param>
|
|
|
18 <param name="delta" size="4" type="text" value="7">
|
|
|
19 <label>Indels</label>
|
|
|
20 </param>
|
|
|
21 <param name="mprobability" size="4" type="integer" value="80" label="Matching probability, %">
|
|
|
22 <validator type="in_range" message="(10-100)" min="10" max="100"/>
|
|
|
23 </param>
|
|
|
24 <param name="iprobability" size="4" type="integer" value="10" label="Indel probability, %">
|
|
|
25 <validator type="in_range" message="(10-100)" min="10" max="100"/>
|
|
|
26 </param>
|
|
|
27 <param name="minscore" size="3" type="integer" value="50">
|
|
|
28 <label>Minimum alignment score for repeat reporting</label>
|
|
|
29 <validator type="in_range" message="(30-150)" min="30" max="150"/>
|
|
|
30 </param>
|
|
|
31 <param name="maxperiod" size="4" type="integer" value="500">
|
|
|
32 <label>Maximum period size for repeat reporting</label>
|
|
|
33 <validator type="in_range" message="(1-2000)" min="1" max="2000"/>
|
|
|
34 </param>
|
|
|
35 <param name="flanking" type="boolean" checked="no" truevalue="-f" falsevalue="" display="checkboxes">
|
|
|
36 <label>Flanking sequence</label>
|
|
|
37 </param>
|
|
|
38 <param name="masked" type="boolean" checked="no" truevalue="-m" falsevalue="" display="checkboxes">
|
|
|
39 <label>Masked Sequence File</label>
|
|
|
40 </param>
|
|
|
41 <param name="noredundancy" type="boolean" checked="no" truevalue="-r" falsevalue="" display="checkboxes">
|
|
|
42 <label>No redundancy elimination</label>
|
|
|
43 </param>
|
|
|
44 </inputs>
|
|
|
45 <outputs>
|
|
|
46 <data format="html" name="report" label="${tool.name} on ${on_string}: Report"/>
|
|
|
47 <data format="html" name="indices" label="${tool.name} on ${on_string}: Indices"/>
|
|
|
48 <data format="tabular" name="outputdat" label="${tool.name} on ${on_string}: Data"/>
|
|
|
49 <data format="txt" name="outputmask" label="${tool.name} on ${on_string}: Masked Sequence">
|
|
|
50 <filter>masked is True</filter>
|
|
|
51 </data>
|
|
|
52 </outputs>
|
|
|
53 <tests>
|
|
|
54 <test>
|
|
|
55 <param name="input1" value="trf_input.fasta"/>
|
|
|
56 <param name="match" value="2"/>
|
|
|
57 <param name="mismatch" value="7"/>
|
|
|
58 <param name="delta" value="7"/>
|
|
|
59 <param name="mprobability" value="80"/>
|
|
|
60 <param name="iprobability" value="10"/>
|
|
|
61 <param name="minscore" value="50"/>
|
|
|
62 <param name="maxperiod" value="500"/>
|
|
|
63 <param name="masked" value="-m"/>
|
|
|
64 <param name="flanking" value=""/>
|
|
|
65 <param name="noredundancy" value=""/>
|
|
|
66 <output name="outputdat" file="trf_out.dat"/>
|
|
|
67 <output name="outputmask" file="trf_out.mask"/>
|
|
|
68 </test>
|
|
|
69 </tests>
|
|
|
70 <help>
|
|
|
71 .. class:: warningmark
|
|
|
72
|
|
|
73 The input dataset needs to be in FASTA format.
|
|
|
74
|
|
|
75 -----
|
|
|
76
|
|
|
77 Tandem Repeats Finder, Version 4.04
|
|
|
78
|
|
|
79 Copyright (C) Dr. Gary Benson 1999-2004. All rights reserved.
|
|
|
80
|
|
|
81
|
|
|
82 Please cite:
|
|
|
83
|
|
|
84 G. Benson, "Tandem repeats finder: a program to analyze DNA sequences" Nucleic Acids Research (1999) Vol. 27, No. 2, pp. 573-580.
|
|
|
85
|
|
|
86
|
|
|
87 A tandem repeat in DNA is two or more adjacent, approximate copies of a pattern
|
|
|
88 of nucleotides. Tandem Repeats Finder is a program to locate and display tandem
|
|
|
89 repeats in DNA sequences. In order to use the program, the user submits a
|
|
|
90 sequence in FASTA format. There is no need to specify the pattern, the size of
|
|
|
91 the pattern or any other parameter. The output consists of two files: a repeat
|
|
|
92 table file and an alignment file. The repeat table contains information about
|
|
|
93 each repeat, including its location, size, number of copies and nucleotide
|
|
|
94 content. Clicking on the location indices for one of the table entries opens a
|
|
|
95 second web browser that shows an alignment of the copies against a consensus
|
|
|
96 pattern. The program is very fast, analyzing sequences on the order of .5Mb in
|
|
|
97 just a few seconds. Submitted sequences may be of arbitrary length. Repeats
|
|
|
98 with pattern size in the range from 1 to 2000 bases are detected.
|
|
|
99 </help>
|
|
|
100 </tool>
|
|
|
101 <!--
|
|
|
102 Please use: trf File Match Mismatch Delta PM PI Minscore MaxPeriod [options]
|
|
|
103 Where: (all weights, penalties, and scores are positive)
|
|
|
104 File = sequences input file
|
|
|
105 Match = matching weight
|
|
|
106 Mismatch = mismatching penalty
|
|
|
107 Delta = indel penalty
|
|
|
108 PM = match probability (whole number)
|
|
|
109 PI = indel probability (whole number)
|
|
|
110 Minscore = minimum alignment score to report
|
|
|
111 MaxPeriod = maximum period size to report
|
|
|
112 [options] = one or more of the following :
|
|
|
113 -m masked sequence file
|
|
|
114 -f flanking sequence
|
|
|
115 -d data file
|
|
|
116 -h suppress html output
|
|
|
117 -r no redundancy elimination
|
|
|
118 Note the sequence file should be in FASTA format:
|
|
|
119 -->
|
