Mercurial > repos > iuc > proteinortho_grab_proteins

comparison proteinortho_grab_proteins.xml @ 0:d348c3a151d9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://gitlab.com/paulklemm_PHD/proteinortho commit 889335c0a31f156c3f90d4c2048cb4df155a53b2"
author iuc
date Tue, 18 Feb 2020 17:57:53 -0500
parents
children fa2d1e652ec1
comparison
equal deleted inserted replaced
-1:000000000000 0:d348c3a151d9
1 <tool id="proteinortho_grab_proteins" name="Proteinortho grab proteins" version="@TOOL_VERSION@+galaxy@WRAPPER_VERSION@">
2 <description>finds genes/proteins in a given fasta file</description>
3 <macros>
4 <import>proteinortho_macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="version_command"/>
8 <command detect_errors="exit_code"><![CDATA[
9 ## the following ln-action is necessary, since the file names are used by proteinortho (output contains filenames => species names)
10 #import re
11 #for $f in $input_files#
12 ln -sf '$f' '${re.sub('[^\w\-_.]', '_', f.element_identifier)}' &&
13 #end for#
14 #if $query.querytype == "file":
15 ln -sf '$query.queryfile' 'query' &&
16 #end if
17 mkdir output && cd output &&
18 proteinortho_grab_proteins.pl
19 --tofiles
20 #if $regex:
21 $regex
22 #end if
23 #if $source:
24 $source
25 #end if
26 #if $query.querytype == "string":
27 '$query.querystring'
28 #else:
29 ../query
30 #end if
31 #for $f in $input_files#
32 ../${re.sub('[^\w\-_.]', '_', f.element_identifier)}
33 #end for#
34 ]]></command>
35 <inputs>
36 <param name="input_files" type="data" format="fasta" multiple="true" min="1" label="Select the input fasta files"/>
37 <conditional name="query">
38 <param name="querytype" type="select" label="Query type">
39 <option value="string" selected="true">String</option>
40 <option value="file">orthology-groups output file</option>
41 </param>
42 <when value="string">
43 <param name="querystring" type="text" label="A string of the protein/gene name/identifier that you want to search">
44 <sanitizer invalid_char="">
45 <valid initial="string.letters,string.digits">
46 <add value="!"/>
47 <add value="="/>
48 <add value="-"/>
49 <add value="."/>
50 <add value="*"/>
51 <add value="?"/>
52 <add value="+"/>
53 <add value="\\"/>
54 <add value="_"/>
55 <add value="|"/>
56 <add value="&#91;"/> <!-- left square bracket, e.g subselecting from vec[1] -->
57 <add value="&#93;"/> <!-- right square bracket -->
58 <add value="&#40;"/> <!-- left parenthesis -->
59 <add value="&#41;"/> <!-- right parenthesis -->
60 </valid>
61 </sanitizer>
62 </param>
63 </when>
64 <when value="file">
65 <param name="queryfile" type="data" format="tabular" label="A orthology-groups file" help="For each group a fasta file is generated containing all proteins/genes of that group."/>
66 </when>
67 </conditional>
68 <param argument="--regex" type="boolean" checked="false" truevalue="-E" falsevalue="" label="Enable regular expressions (perl)" help="If not: the string is escaped (e.g. | -> \|) [-E]"/>
69 <param argument="--source" type="boolean" checked="false" truevalue="-source" falsevalue="" label="Add the filename to the gene/protein-name [--source]"/>
70 </inputs>
71 <outputs>
72 <collection name="listproteinorthograbproteins" type="list" label="${tool.name} on ${on_string}: list of fasta">
73 <discover_datasets pattern="__designation__" format="fasta" directory="output" visible="false"/>
74 </collection>
75 </outputs>
76 <tests>
77 <test>
78 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
79 <param name="querytype" value="string"/>
80 <param name="querystring" value="E_1"/>
81 <output_collection name="listproteinorthograbproteins" count="1"/>
82 </test>
83 <test>
84 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
85 <param name="querytype" value="string"/>
86 <param name="regex" value="true"/>
87 <param name="source" value="true"/>
88 <param name="querystring" value="M..2"/>
89 <output_collection name="listproteinorthograbproteins" count="1"/>
90 </test>
91 <test>
92 <param name="input_files" value="L.fasta,C.fasta,C2.fasta,E.fasta,M.fasta"/>
93 <param name="querytype" value="file"/>
94 <param name="queryfile" value="result.proteinortho.tsv"/>
95 <output_collection name="listproteinorthograbproteins" count="34"/>
96 </test>
97 </tests>
98 <help><![CDATA[proteinortho grab proteins
99
100 **What it does**
101
102 proteinortho_grab_proteins : find gene(s)/protein(s) in a given fasta file and retrieve their sequence(s). You can also use a orthology-groups file, then all sequences for each group (one line of the file) is outputted. This can result in many files!
103
104 **Other Proteinortho-Tools for downstream analysis**
105
106 * `proteinortho summary` : Summaries the orthology-pairs/RBH files to determine how the species are connected to each other.
107
108 More information can be found on github https://gitlab.com/paulklemm_PHD/proteinortho
109 ]]>
110 </help>
111 <expand macro="citations"/>
112 </tool>