|
0
|
1 <tool id="bg_find_subsequences" name="Subsequence search" version="0.1">
|
|
|
2 <description>providing regions in BED format</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="1.6.5">biopyhon</requirement>
|
|
|
5 </requirements>
|
|
|
6 <command interpreter="python">
|
|
|
7 <![CDATA[
|
|
|
8 find_subsequences.py
|
|
|
9 --input $input
|
|
|
10 --output $output
|
|
|
11 --pattern "$pattern"
|
|
|
12 #if $input.ext == 'fasta':
|
|
|
13 --format 'fasta'
|
|
|
14 #else:
|
|
|
15 --format 'fastq'
|
|
|
16 #end if
|
|
|
17 ]]>
|
|
|
18 </command>
|
|
|
19 <inputs>
|
|
|
20 <param format="fasta,fastq" name="input" type="data" label="Sequence to be searched"
|
|
|
21 help="This can be in FASTA or FASTQ format." />
|
|
|
22 <param name="pattern" type="text" value="" label="Search pattern" help="For example GGATCC for BamH1.">
|
|
|
23 <validator type="regex" message="Only letters are allowed.">^[a-zA-Z]+$</validator>
|
|
|
24 </param>
|
|
|
25 </inputs>
|
|
|
26 <outputs>
|
|
|
27 <data format="bed" name="output" />
|
|
|
28 </outputs>
|
|
|
29 <tests>
|
|
|
30 <test>
|
|
|
31 <param name="input" value="find_subsequences_input1.fasta" ftype="fasta"/>
|
|
|
32 <param name="pattern" value="atcg"/>
|
|
|
33 <output name="output" file="find_subsequences_simple_result1.bed" ftype="bed"/>
|
|
|
34 </test>
|
|
|
35 <test>
|
|
|
36 <param name="input" value="find_subsequences_input1.fasta" ftype="fasta"/>
|
|
|
37 <param name="pattern" value="atnncg"/>
|
|
|
38 <output name="output" file="find_subsequences_advanced_result1.bed" ftype="bed"/>
|
|
|
39 </test>
|
|
|
40 </tests>
|
|
|
41 <help>
|
|
|
42 <![CDATA[
|
|
|
43
|
|
|
44 **What it does**
|
|
|
45
|
|
|
46 Searches for a subsequence in a larger sequence. For example to get all restriction enzymes for BamH1.
|
|
|
47
|
|
|
48 If you are searching in a DNA sequence you can use ambiguous values using the standard
|
|
|
49 `nucleotide ambiguity code <http://www.dnabaser.com/articles/IUPAC%20ambiguity%20codes.html>`_.
|
|
|
50
|
|
|
51 This tool is searching on both strands.
|
|
|
52
|
|
|
53 ]]>
|
|
|
54 </help>
|
|
|
55 <citations>
|
|
|
56 <citation type="doi">10.1093/bioinformatics/btp163</citation>
|
|
|
57 </citations>
|
|
|
58 </tool>
|
