|
0
|
1 <?xml version="1.0"?>
|
|
|
2 <tool id="edu.tamu.cpt.gff3.export_seq" name="GFF3 Feature Sequence Export" version="19.1.0.0">
|
|
|
3 <description>Export corresponding sequence in genome from GFF3</description>
|
|
|
4 <macros>
|
|
|
5 <import>macros.xml</import>
|
|
|
6 <import>cpt-macros.xml</import>
|
|
|
7 </macros>
|
|
|
8 <expand macro="requirements"/>
|
|
|
9 <command detect_errors="aggressive"><![CDATA[
|
|
|
10 @GENOME_SELECTOR_PRE@
|
|
|
11
|
|
|
12 $__tool_directory__/gff3_extract_sequence.py
|
|
|
13 @GENOME_SELECTOR@
|
|
|
14
|
|
|
15 @INPUT_GFF@
|
|
|
16
|
|
|
17 #if $feature_filter and $feature_filter is not None:
|
|
|
18 --feature_filter $feature_filter
|
|
|
19 #end if
|
|
|
20 $nodesc
|
|
|
21 > $default]]></command>
|
|
|
22 <inputs>
|
|
|
23 <expand macro="genome_selector" />
|
|
|
24 <expand macro="gff3_input" />
|
|
|
25 <param label="Filter for specific feature types" name="feature_filter" type="text"
|
|
|
26 help="Use 'nice_cds' if your features are coming from Apollo, however this will fail on non-Apollo data"/>
|
|
|
27 <param label="Remove description (use if blasting)" name="nodesc" type="boolean" truevalue="--nodesc" falsevalue=""/>
|
|
|
28 </inputs>
|
|
|
29 <outputs>
|
|
|
30 <data format="fasta" hidden="false" name="default"/>
|
|
|
31 </outputs>
|
|
|
32 <tests>
|
|
|
33 <test>
|
|
|
34 <param name="reference_genome_source" value="history" />
|
|
|
35 <param name="genome_fasta" value="T7_ExtSeqIn.fasta" />
|
|
|
36 <param name="gff3_data" value="T7_ExtSeqIn.gff3" />
|
|
|
37 <param name="nodesc" value="" />
|
|
|
38 <param name="feature_filter" value="CDS" />
|
|
|
39 <output name="output" file="T7_ExtSeqOut.fasta" />
|
|
|
40 </test>
|
|
|
41 <test>
|
|
|
42 <param name="reference_genome_source" value="history" />
|
|
|
43 <param name="genome_fasta" value="Miro_ExtSeqIn.fa" />
|
|
|
44 <param name="gff3_data" value="Miro_ExtSeqIn.gff3" />
|
|
|
45 <param name="nodesc" value="" />
|
|
|
46 <param name="feature_filter" value="CDS" />
|
|
|
47 <output name="output" file="Miro_ExtSeqOut1.fa" />
|
|
|
48 </test>
|
|
|
49 <test>
|
|
|
50 <param name="reference_genome_source" value="history" />
|
|
|
51 <param name="genome_fasta" value="Miro_ExtSeqIn.fa" />
|
|
|
52 <param name="gff3_data" value="Miro_ExtSeqIn.gff3" />
|
|
|
53 <param name="feature_filter" value="CDS" />
|
|
|
54 <param name="nodesc" value="--nodesc" />
|
|
|
55 <output name="output" file="Miro_ExtSeqOut2.fa" />
|
|
|
56 </test>
|
|
|
57 </tests>
|
|
|
58 <help><![CDATA[
|
|
|
59 **What it does**
|
|
|
60
|
|
|
61 From the FASTA sequence for a genome, extracts the *nucleotide* sequences for
|
|
|
62 all CDSs in an input GFF3 and outputs them as a multi-FASTA formatted file.
|
|
|
63
|
|
|
64 The filter for specific feature types was designed for data retrieved from Apollo.
|
|
|
65 Using ‘unique_cds’ extracts the sequence for all CDS. Using ‘nice_cds’ will extract
|
|
|
66 the sequence only for CDS features with a start codon (recommended). If a gene from
|
|
|
67 Apollo has multiple CDSs, the tool will append a "_##" to the end of subsequent genes.
|
|
|
68
|
|
|
69 ]]></help>
|
|
|
70 <expand macro="citations" />
|
|
|
71 </tool>
|
