|
0
|
1 <?xml version="1.0"?>
|
|
|
2 <tool id="mdust" name="mdust" version="1.0">
|
|
|
3 <description>fast and symmetric DUST implementation to mask low-complexity DNA sequences</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="1.0">mdust</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command interpreter="python">
|
|
|
8 mdust_wrapper.py -i ${input_file} -v ${cutoff} -w ${wsize} -m ${masking_letter.masking_letter_selector} -f ${output_type.output_type_selector}
|
|
|
9
|
|
|
10 #if str( $output_type.output_type_selector) == "default"
|
|
|
11 -o ${output_masked_fasta}
|
|
|
12 #end if
|
|
|
13
|
|
|
14 #if str( $output_type.output_type_selector) == "tab"
|
|
|
15 -o ${output_tab}
|
|
|
16 #end if
|
|
|
17
|
|
|
18 #if str( $output_type.output_type_selector) == "bed"
|
|
|
19 -o ${output_bed}
|
|
|
20 #end if
|
|
|
21 </command>
|
|
|
22 <inputs>
|
|
|
23 <param name="input_file" type="data" format="fasta" label="Input fasta file" help=""/>
|
|
|
24 <param name="cutoff" type="integer" value="28" label="cutt-off" help="cut-off" />
|
|
|
25 <param name="wsize" type="integer" value="3" label="set maximum word size" help="word-size" />
|
|
|
26 <conditional name="masking_letter">
|
|
|
27 <param name="masking_letter_selector" type="select" label="Choose your masking type" help="Select the masking letter (N,X or lowercase)" >
|
|
|
28 <option value="N" selected="True">N (default)</option>
|
|
|
29 <option value="X">X</option>
|
|
|
30 <option value="L">lowercase</option>
|
|
|
31 </param>
|
|
|
32 </conditional>
|
|
|
33 <conditional name="output_type">
|
|
|
34 <param name="output_type_selector" type="select" label="Choose your output type" help="select your output">
|
|
|
35 <option value="default" selected="True">masked file (default)</option>
|
|
|
36 <option value="tab">output masking coordinates only (tab delimited)</option>
|
|
|
37 <option value="bed">output masking coordinates only (bed format)</option>
|
|
|
38 </param>
|
|
|
39 </conditional>
|
|
|
40 </inputs>
|
|
|
41 <outputs>
|
|
|
42 <data format="fasta" name="output_masked_fasta" label="masked.${input_file.name}">
|
|
|
43 <filter>( output_type['output_type_selector'] == 'default' )</filter>
|
|
|
44 </data>
|
|
|
45 <data format="tabular" name="output_tab" label="${input_file.name}.tab">
|
|
|
46 <filter>( output_type['output_type_selector'] == 'tab' )</filter>
|
|
|
47 </data>
|
|
|
48 <data format="bed" name="output_bed" label="${input_file.name}.bed">
|
|
|
49 <filter>( output_type['output_type_selector'] == 'bed' )</filter>
|
|
|
50 </data>
|
|
|
51 </outputs>
|
|
|
52 <tests>
|
|
|
53 <test>
|
|
|
54 <param name="input_file" value="seq-mdust.fsa" />
|
|
|
55 <output name="output_masked_fasta" file="masked-seq-mdust.fsa" ftype="fasta" />
|
|
|
56 </test>
|
|
|
57 </tests>
|
|
|
58 <help><![CDATA[
|
|
|
59 mdust new implementation of the DUST module that uses the same function to assign a complexity score to a sequence, but uses a different rule by which high-scoring sequences are masked.
|
|
|
60
|
|
|
61 -----
|
|
|
62
|
|
|
63 **Usage:** ::
|
|
|
64
|
|
|
65 mdust [<fasta-file>] [-w <wsize>] [-v <cut-off>] [-m N|X|L] [-c]
|
|
|
66 if no <fasta-file> is given, a multi-fasta stream is expected at stdin
|
|
|
67 -v default <cut-off> value is 28 (lower values might mask more,
|
|
|
68 but possibly still useful sequence; > 64 will rarely mask poly-triplets)
|
|
|
69 -w set maximum word size to <wsize> (default 3)
|
|
|
70 -m if fasta output is not disabled by -c, set the masking letter type:
|
|
|
71 N ('N', default), X ('X'), L (make lowercase)
|
|
|
72 -c output masking coordinates only:
|
|
|
73 seq_name, seqlength, mask_start, mask_end (tab delimited)
|
|
|
74
|
|
|
75 -----
|
|
|
76
|
|
|
77 **Reference:** ::
|
|
|
78
|
|
|
79 A fast and symmetric DUST implementation to mask low-complexity DNA sequences.
|
|
|
80 Morgulis A, Gertz EM, Schäffer AA, Agarwala R.
|
|
|
81 J Comput Biol. 2006 Jun;13(5):1028-40.
|
|
|
82 PMID:16796549
|
|
|
83
|
|
|
84
|
|
|
85 ]]>
|
|
|
86 </help>
|
|
|
87 </tool>
|
