|
0
|
1 <tool id="bedtools_getfastabed" name="GetFastaBed" version="@WRAPPER_VERSION@.0">
|
|
|
2 <description></description>
|
|
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements" />
|
|
|
7 <expand macro="stdio" />
|
|
|
8 <command>
|
|
1
|
9 <![CDATA[
|
|
0
|
10 bedtools getfasta
|
|
|
11 $name
|
|
|
12 $tab
|
|
|
13 $strand
|
|
|
14 $split
|
|
|
15 -fi $fasta
|
|
1
|
16 -bed $input
|
|
0
|
17 -fo $output
|
|
1
|
18 ]]>
|
|
0
|
19 </command>
|
|
|
20 <inputs>
|
|
1
|
21 <param format="bed,vcf,gff,gff3" name="input" type="data" label="BED/VCF/GFF file" />
|
|
0
|
22 <param format="fasta" name="fasta" type="data" label="Fasta file" />
|
|
1
|
23 <param name="name" type="boolean" checked="false" truevalue="-name" falsevalue=""
|
|
|
24 label="Use the 'name' column in the BED file for the FASTA headers in the output FASTA file"
|
|
|
25 help="(-name)" />
|
|
|
26 <param name="tab" type="boolean" checked="false" truevalue="-tab" falsevalue=""
|
|
|
27 label="Report extract sequences in a tab-delimited format instead of in FASTA format"
|
|
|
28 help="(-tab)" />
|
|
|
29 <param name="strand" type="boolean" checked="false" truevalue="-s" falsevalue=""
|
|
|
30 label="Force strandedness"
|
|
|
31 help="If the feature occupies the antisense strand, the sequence will be reverse complemented. (-s)" />
|
|
|
32 <expand macro="split" />
|
|
0
|
33 </inputs>
|
|
|
34 <outputs>
|
|
1
|
35 <data format="fasta" name="output">
|
|
|
36 <change_format>
|
|
|
37 <when input="tab" value="-tab" format="tabular" />
|
|
|
38 </change_format>
|
|
|
39 </data>
|
|
0
|
40 </outputs>
|
|
1
|
41 <tests>
|
|
|
42 <test>
|
|
|
43 <param name="input" value="nucBed1.bed" ftype="bed" />
|
|
|
44 <param name="fasta" value="nucBed1.fasta" ftype="fasta" />
|
|
|
45 <param name="tab" value="False" />
|
|
|
46 <param name="split" value="False" />
|
|
|
47 <output name="output" file="getfastaBed_result1.bed" ftype="fasta" />
|
|
|
48 </test>
|
|
|
49 <test>
|
|
|
50 <param name="input" value="nucBed1.bed" ftype="bed" />
|
|
|
51 <param name="fasta" value="nucBed1.fasta" ftype="fasta" />
|
|
|
52 <param name="tab" value="True" />
|
|
|
53 <param name="split" value="False" />
|
|
|
54 <output name="output" file="getfastaBed_result2.tabular" ftype="tabular" />
|
|
|
55 </test>
|
|
|
56 </tests>
|
|
0
|
57 <help>
|
|
1
|
58 <![CDATA[
|
|
0
|
59 **What it does**
|
|
|
60
|
|
1
|
61 bedtools getfasta will extract the sequence defined by the coordinates in a BED interval and create a new FASTA entry in the output file for each extracted sequence. By default, the FASTA header for each extracted sequence will be formatted as follows: “>chrom>:<start>-<end>”.
|
|
0
|
62
|
|
|
63 .. image:: $PATH_TO_IMAGES/getfasta-glyph.png
|
|
|
64
|
|
|
65 .. class:: warningmark
|
|
|
66
|
|
|
67 1. The headers in the input FASTA file must exactly match the chromosome column in the BED file.
|
|
|
68
|
|
|
69 2. You can use the UNIX fold command to set the line width of the FASTA output. For example, fold -w 60 will make each line of the FASTA file have at most 60 nucleotides for easy viewing.
|
|
|
70
|
|
|
71 @REFERENCES@
|
|
1
|
72 ]]>
|
|
0
|
73 </help>
|
|
|
74 <expand macro="citations" />
|
|
|
75 </tool>
|
