Mercurial > repos > yating-l > bigbed_to_fa_340

comparison bigbed_to_fa.xml @ 0:512ed6da2367 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload
author yating-l
date Wed, 17 May 2017 16:49:32 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:512ed6da2367
1 <?xml version="1.0"?>
2 <tool id="bigbed_to_fa" name="bigBedToFa" version="1.0">
3 <description>Retrieve sequences associated with bigBed features</description>
4
5 <macros>
6 <import>ucsc_macros.xml</import>
7 </macros>
8
9 <expand macro="requirements_twobit">
10 <requirement type="package" version="340">ucsc_bigbed</requirement>
11 </expand>
12
13 <command detect_errors="exit_code">
14 <![CDATA[
15 #set no_mask = ""
16 #if str($masking_option) == "upper":
17 #set no_mask = "-noMask"
18 #end if
19
20 ${__tool_directory__}/bigbed_to_standard_bed.pl -i "${bigbed_input}" |
21 twoBitToFa ${no_mask} -bed=stdin "${twobit_input}" stdout
22
23 ## Add extra option to change soft masked bases to N's
24 #if str($masking_option) == "hard":
25 | awk '{ if (/^>/) { print } else { gsub(/[acgt]/, "N"); print } }'
26 #end if
27
28 > "${fasta_output}"
29 ]]>
30 </command>
31 <inputs>
32 <param name="twobit_input" type="data" format="twobit" label="twoBit input file" />
33
34 <param name="bigbed_input" type="data" format="bigbed" label="bigBed input file" />
35
36 <param name="masking_option" type="select"
37 label="Repeat masking option"
38 help="Specify how repeats within the twoBit file should be represented">
39
40 <option value="upper">Show repeats in uppercase (no masking)</option>
41
42 <option value="lower" selected="true">Show repeats in lowercase (soft masking)</option>
43
44 <option value="hard">Show repeats as N's (hard masking)</option>
45 </param>
46
47 </inputs>
48 <outputs>
49 <data name="fasta_output" format="fasta" />
50 </outputs>
51 <tests>
52 <test>
53 <!-- Test bigBedToFa with bed4 and default (soft) masking -->
54 <param name="twobit_input" value="contigs.out.2bit" ftype="twobit" />
55 <param name="bigbed_input" value="contigs.trf_4.bb" ftype="bigbed" />
56 <output name="fasta_output" file="contigs.trf_4.soft.fa" />
57 </test>
58 <test>
59 <!-- Test bigBedToFa with bed4 and no masking -->
60 <param name="twobit_input" value="contigs.out.2bit" ftype="twobit" />
61 <param name="bigbed_input" value="contigs.trf_4.bb" ftype="bigbed" />
62 <param name="masking_option" value="upper" />
63 <output name="fasta_output" file="contigs.trf_4.nomask.fa" />
64 </test>
65 <test>
66 <!-- Test bigBedToFa with bed4 and hard masking -->
67 <param name="twobit_input" value="contigs.out.2bit" ftype="twobit" />
68 <param name="bigbed_input" value="contigs.trf_4.bb" ftype="bigbed" />
69 <param name="masking_option" value="hard" />
70 <output name="fasta_output" file="contigs.trf_4.hard.fa" />
71 </test>
72 <test>
73 <!-- Test bigBedToFa with bed4+12 with default masking -->
74 <param name="twobit_input" value="contigs.out.2bit" ftype="twobit" />
75 <param name="bigbed_input" value="contigs.trf_4_12.bb" ftype="bigbed" />
76 <output name="fasta_output" file="contigs.trf_4_12.fa" />
77 </test>
78 <test>
79 <!-- Test bigBedToFa with bed6+2 with default masking -->
80 <param name="twobit_input" value="contigs.out.2bit" ftype="twobit" />
81 <param name="bigbed_input" value="contigs.models_6_2.bb" ftype="bigbed" />
82 <output name="fasta_output" file="contigs.models_6_2.fa" />
83 </test>
84 <test>
85 <!-- Test bigBedToFa with bed12+2 with default masking -->
86 <param name="twobit_input" value="contigs.out.2bit" ftype="twobit" />
87 <param name="bigbed_input" value="contigs.models_12_2.bb" ftype="bigbed" />
88 <output name="fasta_output" file="contigs.models_12_2.fa" />
89 </test>
90 </tests>
91 <help>
92 <![CDATA[
93 **What it does**
94
95 bigBedToFa retrieves sequences associated with the features in a
96 `bigBed <https://genome.ucsc.edu/goldenpath/help/bigBed.html>`_ file
97 from a `twoBit Sequence Archive <https://genome.ucsc.edu/goldenpath/help/twoBit.html>`_.
98
99 .. class:: infomark
100
101 **Extracted sequences:**
102
103 For files with `12 standard BED columns <https://genome.ucsc.edu/FAQ/FAQformat.html#format1>`_,
104 this program will concatenate the sequences associated with each block (e.g., exons), and
105 exclude the sequences between adjacent blocks (e.g., introns).
106
107 ]]></help>
108
109 <expand macro="citations" />
110 </tool>