0
|
1 <tool name="NormalizeFasta" id="picard_NormalizeFasta" version="1.135">
|
|
2 <description>normalize fasta datasets</description>
|
|
3 <macros>
|
|
4 <import>picard_macros.xml</import>
|
|
5 </macros>
|
|
6 <expand macro="requirements" />
|
|
7 <command>
|
|
8 @java_options@
|
|
9
|
|
10
|
|
11 ## Two lines below are due to the fact that picard likes fasta files to have extension .fa
|
|
12 #set $fasta_file="local_fasta.fa"
|
|
13 ln -s "${inputFile}" "${fasta_file}" &&
|
|
14
|
|
15 java -jar \$JAVA_JAR_PATH/picard.jar
|
|
16 NormalizeFasta
|
|
17
|
|
18 INPUT="${fasta_file}"
|
|
19 OUTPUT="${outFile}"
|
|
20 LINE_LENGTH="${line_length}"
|
|
21 TRUNCATE_SEQUENCE_NAMES_AT_WHITESPACE="${truncate_sequence_names_at_whitespaces}"
|
|
22
|
|
23 QUIET=true
|
|
24 VERBOSITY=ERROR
|
|
25
|
|
26 </command>
|
|
27 <inputs>
|
|
28 <param format="fasta" name="inputFile" type="data" label="FASTA dataset or dataset collection" help="If empty, upload or import a FASTA dataset" />
|
|
29 <param name="line_length" type="integer" value="100" min="1" max="200" label="The line length to be used for the output fasta file" help="LINE_LENGTH; default=100"/>
|
|
30 <param name="truncate_sequence_names_at_whitespaces" type="boolean" label="Truncate sequence names at first whitespace" help="TRUNCATE_SEQUENCE_NAMES_AT_WHITESPACE; default=False"/>
|
|
31 </inputs>
|
|
32
|
|
33 <outputs>
|
|
34 <data format="fasta" name="outFile" label="${tool.name} on ${on_string}: Normalized FASTA dataset"/>
|
|
35 </outputs>
|
|
36
|
|
37 <tests>
|
|
38 <test>
|
|
39 <param name="inputFile" value="picard_NormalizeFasta_ref.fa" ftype="fasta"/>
|
|
40 <param name="line_length" value="40"/>
|
|
41 <param name="truncate_sequence_names_at_whitespaces" value="False"/>
|
|
42 <output name="outFile" file="picard_NormalizeFasta_test1.fa" ftype="fasta"/>
|
|
43 </test>
|
|
44 </tests>
|
|
45
|
|
46 <stdio>
|
|
47 <exit_code range="1:" level="fatal"/>
|
|
48 </stdio>
|
|
49
|
|
50 <help>
|
|
51
|
|
52 **Purpose**
|
|
53
|
|
54 Takes any dataset that conforms to the fasta format and normalizes it so that all lines of sequence except the last line per named sequence are of the same length.
|
|
55
|
|
56 @dataset_collections@
|
|
57
|
|
58 @description@
|
|
59
|
|
60 LINE_LENGTH=Integer The line length to be used for the output fasta file. Default value: 100.
|
|
61
|
|
62 TRUNCATE_SEQUENCE_NAMES_AT_WHITESPACE=Boolean
|
|
63 Truncate sequence names at first whitespace. Default value: false. Possible values: {true, false}
|
|
64
|
|
65 @more_info@
|
|
66
|
|
67 </help>
|
|
68 </tool>
|
|
69
|
|
70
|