Mercurial > repos > galaxyp > fasta_merge_files_and_filter_unique_sequences

comparison fasta_merge_files_and_filter_unique_sequences.xml @ 4:8462a4e9f86e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/fasta_merge_files_and_filter_unique_sequences commit b4c90f4b5d7e9b233f1150dbc9e5dcbe156809e8
author galaxyp
date Mon, 24 Jul 2017 17:13:10 -0400
parents 9ad0d336e5ed
children 650d553c1fda
comparison
equal deleted inserted replaced
3:9ad0d336e5ed 4:8462a4e9f86e
1 <tool id="fasta_merge_files_and_filter_unique_sequences" name="FASTA Merge Files and Filter Unique Sequences" version="1.1"> 1 <tool id="fasta_merge_files_and_filter_unique_sequences" name="FASTA Merge Files and Filter Unique Sequences" version="1.2.0">
2 <description>Concatenate FASTA database files together</description> 2 <description>Concatenate FASTA database files together</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="2.7.12">python</requirement> 4 <requirement type="package" version="2.7.12">python</requirement>
5 </requirements> 5 </requirements>
6 <command> 6 <command>
7 python '$__tool_directory__/fasta_merge_files_and_filter_unique_sequences.py' 7 python '$__tool_directory__/fasta_merge_files_and_filter_unique_sequences.py'
8 '$output' $uniqueness_criterion '$accession_parser' 8 '$output' $uniqueness_criterion '$accession_parser'
9
10 #if $batchmode.processmode == 'merge':
11 #set $inputs = $batchmode.input_fastas
12 #else:
13 #set $inputs = [ $batchmode.input_fastas ]
14 #end if
9 #for $input in $inputs: 15 #for $input in $inputs:
10 '$input' 16 '$input'
11 #end for 17 #end for
12 </command> 18 </command>
13 <inputs> 19 <inputs>
14 <param name="inputs" format="fasta" multiple="True" type="data" label="Input FASTA files"/> 20 <conditional name="batchmode">
21 <param name="processmode" type="select" label="Run in batch mode?" help="The 'merge all' mode produces one output FASTA for all input FASTA files. The individual mode generates one FASTA file for each set of input FASTAs. For example, if the tool is given 2 collections of 10 FASTAs, it will merge the collections pairwise to create an output collection of 10 FASTAs." display="radio">
22 <option value="individual" selected="True">Merge individual FASTAs (output collection if input is collection)</option>
23 <option value="merge">Merge all FASTAs (always output a single FASTA)</option>
24 </param>
25 <when value="individual">
26 <param name="input_fastas" type="data" format="fasta" label="FASTA file" />
27 </when>
28 <when value="merge">
29 <param name="input_fastas" type="data" format="fasta" multiple="True" label="FASTA file" />
30 </when>
31 </conditional>
15 <param name="uniqueness_criterion" type="select" label="How are sequences judged to be unique?"> 32 <param name="uniqueness_criterion" type="select" label="How are sequences judged to be unique?">
16 <option value="sequence" selected="true">Accession and Sequence</option> 33 <option value="sequence" selected="true">Accession and Sequence</option>
17 <option value="accession">Accession Only</option> 34 <option value="accession">Accession Only</option>
18 </param> 35 </param>
19 <param name="accession_parser" type="text" label="Accession Parsing Regex" value="^&gt;([^ ]+).*$" help="Regular expression with 1 capture group; the capture group is the accession (which must be unique)"> 36 <param name="accession_parser" type="text" label="Accession Parsing Regex" value="^&gt;([^ ]+).*$" help="Regular expression with 1 capture group; the capture group is the accession (which must be unique)">
33 <outputs> 50 <outputs>
34 <data format="fasta" name="output" label="Merged and Filtered FASTA from ${on_string}"/> 51 <data format="fasta" name="output" label="Merged and Filtered FASTA from ${on_string}"/>
35 </outputs> 52 </outputs>
36 <tests> 53 <tests>
37 <test> 54 <test>
38 <param name="inputs" value="1.fa,2.fa" ftype="fasta" /> 55 <param name="input_fastas" value="1.fa,2.fa" ftype="fasta" />
56 <param name="processmode" value="merge" />
39 <param name="uniqueness_criterion" value="sequence" /> 57 <param name="uniqueness_criterion" value="sequence" />
40 <param name="accession_parser" value="^&gt;([^ |]+).*$" /> 58 <param name="accession_parser" value="^&gt;([^ |]+).*$" />
41 <output name="output" file="res-sequence.fa" ftype="fasta" /> 59 <output name="output" file="res-sequence.fa" ftype="fasta" />
42 <assert_stdout> 60 <assert_stdout>
43 <has_line line="Skipping protein '&gt;one_2' with duplicate sequence (first seen as '&gt;one')" /> 61 <has_line line="Skipping protein '&gt;one_2' with duplicate sequence (first seen as '&gt;one')" />
45 <has_line line="Skipping protein '&gt;three_2|456' with duplicate accession" /> 63 <has_line line="Skipping protein '&gt;three_2|456' with duplicate accession" />
46 <has_line line="Skipping protein '&gt;three_2 789' with duplicate accession" /> 64 <has_line line="Skipping protein '&gt;three_2 789' with duplicate accession" />
47 </assert_stdout> 65 </assert_stdout>
48 </test> 66 </test>
49 <test> 67 <test>
50 <param name="inputs" value="1.fa,2.fa" ftype="fasta" /> 68 <param name="input_fastas" value="1.fa,2.fa" ftype="fasta" />
69 <param name="processmode" value="merge" />
51 <param name="uniqueness_criterion" value="accession" /> 70 <param name="uniqueness_criterion" value="accession" />
52 <param name="accession_parser" value="^&gt;([^ |]+).*$" /> 71 <param name="accession_parser" value="^&gt;([^ |]+).*$" />
53 <output name="output" file="res-accession.fa" ftype="fasta" /> 72 <output name="output" file="res-accession.fa" ftype="fasta" />
54 <assert_stdout> 73 <assert_stdout>
55 <has_line line="Skipping protein '&gt;three_2|456' with duplicate accession" /> 74 <has_line line="Skipping protein '&gt;three_2|456' with duplicate accession" />