Mercurial > repos > iuc > mothur_filter_seqs
comparison filter.seqs.xml @ 0:870f2a438139 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/mothur commit a9d1e0debcd357d8080a1c6c5f1d206dd45a7a4d
author | iuc |
---|---|
date | Fri, 19 May 2017 05:26:45 -0400 |
parents | |
children | c799faca02a1 |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:870f2a438139 |
---|---|
1 <tool profile="16.07" id="mothur_filter_seqs" name="Filter.seqs" version="@WRAPPER_VERSION@.0"> | |
2 <description>removes columns from alignments</description> | |
3 <macros> | |
4 <import>macros.xml</import> | |
5 </macros> | |
6 <expand macro="requirements"/> | |
7 <expand macro="stdio"/> | |
8 <expand macro="version_command"/> | |
9 <command><![CDATA[ | |
10 @SHELL_OPTIONS@ | |
11 | |
12 ## create symlinks to input datasets | |
13 ln -s "$fasta" fasta.dat && | |
14 #for $i in $inputs: | |
15 ln -s "$i.fasta" fasta${inputs.index($i)}.dat && | |
16 #end for | |
17 ln -s "$hard" hard.dat && | |
18 | |
19 echo 'filter.seqs( | |
20 fasta=fasta.dat#for $i in $inputs#-fasta${inputs.index($i)}.dat#end for#, | |
21 vertical=$vertical, | |
22 #if $trump: | |
23 trump=$trump, | |
24 #end if | |
25 soft=$soft, | |
26 #if $hard: | |
27 hard=hard.dat, | |
28 #end if | |
29 processors='\${GALAXY_SLOTS:-8}' | |
30 )' | |
31 | sed 's/ //g' ## mothur trips over whitespace | |
32 | mothur | |
33 | tee mothur.out.log && | |
34 | |
35 ## rename collection files for more transparent element naming | |
36 mv fasta.filter.fasta "${fasta.element_identifier}".filter.fasta | |
37 #for i in $inputs: | |
38 && mv fasta${inputs.index($i)}.filter.fasta "${i.fasta.element_identifier}".filter.fasta | |
39 #end for | |
40 ]]></command> | |
41 <inputs> | |
42 <param name="fasta" type="data" format="mothur.align" label="fasta - Alignment Fasta"/> | |
43 <repeat name="inputs" title="Additional Alignment File"> | |
44 <param name="fasta" type="data" format="mothur.align" label="fasta - Alignment Fasta"/> | |
45 </repeat> | |
46 <param name="vertical" type="boolean" checked="true" truevalue="true" falsevalue="false" label="vertical - Vertical column" help="Ignore any column that only contains gap characters (i.e. '-' or '.')"/> | |
47 <param name="trump" type="select" label="trump - Trump character" help="Remove a column if the trump character is found at that position in any sequence of the alignment"> | |
48 <option value="">Off</option> | |
49 <option value=".">.</option> | |
50 <option value="-">-</option> | |
51 <option value="N">N</option> | |
52 </param> | |
53 <param name="soft" type="integer" value="0" min="0" max="100" label="soft - percentage required to retain column. (0-100)" help="Removes any column where the dominant base (i.e. A, T, G, C, or U) does not occur in at least a designated percentage of sequences"/> | |
54 <param name="hard" type="data" format="mothur.filter" optional="True" label="hard - Hard Column Filter" help="A file should only contain one line consisting of 0's and 1's"/> | |
55 </inputs> | |
56 <outputs> | |
57 <expand macro="logfile-output"/> | |
58 <data name="out_filter" format="mothur.filter" from_work_dir="fasta*.filter" label="${tool.name} on ${on_string}: filter"/> | |
59 <collection name="filteredfastas" type="list" label="${tool.name} on ${on_string}: filtered fastas"> | |
60 <discover_datasets pattern="(?P<designation>.*)\.filter\.fasta" format="fasta"/> | |
61 <filter>inputs</filter> <!-- only output collection if multiple outputs--> | |
62 </collection> | |
63 <data name="filteredfasta" format="fasta" from_work_dir="*.filter.fasta" label="${tool.name} on ${on_string}: filtered fasta"> | |
64 <filter>not inputs</filter> | |
65 </data> | |
66 </outputs> | |
67 <tests> | |
68 <test><!-- test with multiple inputs and collection output --> | |
69 <param name="fasta" value="HMP_MOCK.v35.align" ftype="mothur.align"/> | |
70 <repeat name="inputs"> | |
71 <param name="fasta" value="Mock_S280_L001_R1_001_small.trim.contigs.good.align_head" ftype="mothur.align"/> | |
72 </repeat> | |
73 <output name="out_filter" md5="3e6c2cfef46baf35d2a8b5cafe53e3a4"/> | |
74 <output_collection name="filteredfastas" count="2"> | |
75 <element name="HMP_MOCK.v35.align" md5="ef4c6c2d9a882f7a22e5fa3c814af7cc" ftype="fasta"/> | |
76 </output_collection> | |
77 <expand macro="logfile-test"/> | |
78 </test> | |
79 <test><!-- test with single input and non-collection output --> | |
80 <param name="fasta" value="HMP_MOCK.v35.align" ftype="mothur.align"/> | |
81 <output name="out_filter" md5="3e6c2cfef46baf35d2a8b5cafe53e3a4"/> | |
82 <output name="filteredfasta" md5="ef4c6c2d9a882f7a22e5fa3c814af7cc"/> | |
83 <expand macro="logfile-test"/> | |
84 </test> | |
85 </tests> | |
86 <help> | |
87 <![CDATA[ | |
88 | |
89 @MOTHUR_OVERVIEW@ | |
90 | |
91 **Command Documentation** | |
92 | |
93 The filter.seqs_ command removes columns from alignments based on a criteria defined by the user. For example, alignments generated against reference alignments (e.g. from RDP, SILVA, or greengenes) often have columns where every character is either a '.' or a '-'. These columns are not included in calculating distances because they have no information in them. By removing these columns, the calculation of a large number of distances is accelerated. Also, people also like to mask their sequences to remove variable regions using a soft or hard mask (e.g. Lane's mask). This type of masking is only encouraged for deep-level phylogenetic analysis, not fine level analysis such as that needed with calculating OTUs. | |
94 | |
95 .. _filter.seqs: https://www.mothur.org/wiki/Filter.seqs | |
96 | |
97 v.1.20.0: Updated to Mothur 1.33 | |
98 | |
99 ]]> | |
100 </help> | |
101 <expand macro="citations"/> | |
102 </tool> |