|
0
|
1 <tool id="protxml_to_gff" name="Proteomics to GFF" version="1.1.0">
|
|
|
2 <description>Export Proteomics Data to GFF</description>
|
|
|
3
|
|
|
4 <requirements>
|
|
|
5 <container type="docker">iracooke/protk-1.4.1</container>
|
|
|
6 <requirement type="package" version="1.4">protk</requirement>
|
|
|
7 <requirement type="package" version="2.2.29">blast+</requirement>
|
|
|
8 </requirements>
|
|
|
9
|
|
|
10 <command>
|
|
|
11 protxml_to_gff.rb $protxml_file
|
|
|
12
|
|
|
13 #if $database.source_select=="built_in":
|
|
|
14 -d $database.dbkey
|
|
|
15 #else
|
|
|
16 -d $database.fasta_file
|
|
|
17 #end if
|
|
|
18
|
|
|
19 -c $gene_file
|
|
|
20
|
|
|
21 --gff-idregex='$gffidpattern'
|
|
|
22
|
|
|
23 -o $output
|
|
|
24
|
|
|
25
|
|
|
26 </command>
|
|
|
27
|
|
|
28 <stdio>
|
|
|
29 <exit_code range="1:" level="fatal" description="Failure" />
|
|
|
30 </stdio>
|
|
|
31
|
|
|
32 <inputs>
|
|
|
33 <conditional name="database">
|
|
|
34 <param name="source_select" type="select" label="Database source used for Proteomics Searches" help="Database should be an amino acid fasta file with entry id's that can be parsed to obtain contig or scaffold ids referenced in your gff file">
|
|
|
35 <option value="input_ref">Your Upload File</option>
|
|
|
36 <option value="built_in">Built-In</option>
|
|
|
37 </param>
|
|
|
38 <when value="built_in">
|
|
|
39 <param name="dbkey" type="select" format="text" >
|
|
|
40 <label>Database</label>
|
|
|
41 <options from_file="pepxml_databases.loc">
|
|
|
42 <column name="name" index="0" />
|
|
|
43 <column name="value" index="2" />
|
|
|
44 </options>
|
|
|
45 </param>
|
|
|
46 </when>
|
|
|
47 <when value="input_ref">
|
|
|
48 <param name="fasta_file" type="data" format="fasta" label="Uploaded FASTA file" />
|
|
|
49 </when>
|
|
|
50 </conditional>
|
|
|
51
|
|
|
52 <param name="protxml_file" type="data" format="protxml" multiple="false" label="Proteomics Search Results" help="A ProtXML file produced by Protein Prophet"/>
|
|
|
53
|
|
|
54 <param name="gene_file" type="data" format="gff3" multiple="false" label="Protein coordinates" help="A gff3 file with coordinates for all protein entries used for proteomics searches. Coordinates should correspond to entries in the genome fasta file"/>
|
|
|
55
|
|
|
56 <param name="gffidpattern" size="40" type="text" value="lcl\|([^ ]*)" label="gff id regex" help="Regex with capture group for parsing gff ids from protein ids">
|
|
|
57 <sanitizer>
|
|
|
58 <valid initial="string.printable">
|
|
|
59 <remove value="'"/>
|
|
|
60 </valid>
|
|
|
61 <mapping initial="none">
|
|
|
62 <add source="'" target="__sq__"/>
|
|
|
63 </mapping>
|
|
|
64 </sanitizer>
|
|
|
65 </param>
|
|
|
66
|
|
|
67 </inputs>
|
|
|
68
|
|
|
69 <outputs>
|
|
|
70 <data format="gff3" name="output" />
|
|
|
71 </outputs>
|
|
|
72
|
|
|
73
|
|
|
74 <tests>
|
|
|
75 <test>
|
|
|
76 <param name="source_select" value="input_ref"/>
|
|
|
77 <param name="fasta_file" value="small_prot.fasta" format="fasta"/>
|
|
|
78
|
|
|
79 <param name="protxml_file" value="small.prot.xml" format="protxml"/>
|
|
|
80 <param name="gene_file" value="small_combined.gff" format="gff3"/>
|
|
|
81 <output name="output" format="gff3">
|
|
|
82 <assert_contents>
|
|
|
83 <has_text text="polypeptide" />
|
|
|
84 </assert_contents>
|
|
|
85 </output>
|
|
|
86 </test>
|
|
|
87 </tests>
|
|
|
88
|
|
|
89 <help>
|
|
|
90
|
|
|
91 **What it does**
|
|
|
92
|
|
|
93 Exports peptides and proteins to gff
|
|
|
94
|
|
|
95 ----
|
|
|
96
|
|
|
97 **References**
|
|
|
98
|
|
|
99
|
|
|
100 </help>
|
|
|
101
|
|
|
102 </tool>
|
