Mercurial > repos > florianbegusch > qiime2_suite

comparison qiime2/qiime_vsearch_cluster-features-closed-reference.xml @ 0:370e0b6e9826 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author florianbegusch
date Wed, 17 Jul 2019 03:05:17 -0400
parents
children a025a4a89e07
comparison
equal deleted inserted replaced
-1:000000000000 0:370e0b6e9826
1 <?xml version="1.0" ?>
2 <tool id="qiime_vsearch_cluster-features-closed-reference" name="qiime vsearch cluster-features-closed-reference" version="2019.4">
3 <description> - Closed-reference clustering of features.</description>
4 <requirements>
5 <requirement type="package" version="2019.4">qiime2</requirement>
6 </requirements>
7 <command><![CDATA[
8 qiime vsearch cluster-features-closed-reference
9 --i-sequences=$isequences
10 --i-table=$itable
11 --i-reference-sequences=$ireferencesequences
12 --p-perc-identity="$ppercidentity"
13
14 #if str($pstrand) != 'None':
15 --p-strand=$pstrand
16 #end if
17
18 #set $pthreads = '${GALAXY_SLOTS:-4}'
19
20 #if str($pthreads):
21 --p-threads="$pthreads"
22 #end if
23
24 --o-clustered-table=oclusteredtable
25 --o-clustered-sequences=oclusteredsequences
26 --o-unmatched-sequences=ounmatchedsequences
27 ;
28 cp oclusteredtable.qza $oclusteredtable;
29 cp oclusteredsequences.qza $oclusteredsequences;
30 cp ounmatchedsequences.qza $ounmatchedsequences
31 ]]></command>
32 <inputs>
33 <param format="qza,no_unzip.zip" label="--i-sequences: ARTIFACT FeatureData[Sequence] The sequences corresponding to the features in table. [required]" name="isequences" optional="False" type="data"/>
34 <param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency] The feature table to be clustered. [required]" name="itable" optional="False" type="data"/>
35 <param format="qza,no_unzip.zip" label="--i-reference-sequences: ARTIFACT FeatureData[Sequence] The sequences to use as cluster centroids. [required]" name="ireferencesequences" optional="False" type="data"/>
36 <param label="--p-perc-identity: PROPORTION Range(0, 1, inclusive_start=False, inclusive_end=True) The percent identity at which clustering should be performed. This parameter maps to vsearch's --id parameter. [required]" name="ppercidentity" optional="False" type="float" value="" min="0" max="1" exclude_max="False" />
37 <param label="--p-strand: " name="pstrand" optional="True" type="select">
38 <option selected="True" value="None">Selection is Optional</option>
39 <option value="plus">plus</option>
40 <option value="both">both</option>
41 </param>
42 </inputs>
43 <outputs>
44 <data format="qza" label="${tool.name} on ${on_string}: clusteredtable.qza" name="oclusteredtable"/>
45 <data format="qza" label="${tool.name} on ${on_string}: clusteredsequences.qza" name="oclusteredsequences"/>
46 <data format="qza" label="${tool.name} on ${on_string}: unmatchedsequences.qza" name="ounmatchedsequences"/>
47 </outputs>
48 <help><![CDATA[
49 Open-reference clustering of features.
50 ######################################
51
52 Given a feature table and the associated feature sequences, cluster the
53 features against a reference database based on user-specified percent
54 identity threshold of their sequences. Any sequences that don't match are
55 then clustered de novo. This is not a general-purpose clustering method,
56 but rather is intended to be used for clustering the results of quality-
57 filtering/dereplication methods, such as DADA2, or for re-clustering a
58 FeatureTable at a lower percent identity than it was originally clustered
59 at. When a group of features in the input table are clustered into a single
60 feature, the frequency of that single feature in a given sample is the sum
61 of the frequencies of the features that were clustered in that sample.
62 Feature identifiers will be inherited from the centroid feature of each
63 cluster. For features that match a reference sequence, the centroid feature
64 is that reference sequence, so its identifier will become the feature
65 identifier. The clustered_sequences result will contain feature
66 representative sequences that are derived from the sequences input for all
67 features in clustered_table. This will always be the most abundant sequence
68 in the cluster. The new_reference_sequences result will contain the entire
69 reference database, plus feature representative sequences for any de novo
70 features. This is intended to be used as a reference database in subsequent
71 iterations of cluster_features_open_reference, if applicable. See the
72 vsearch documentation for details on how sequence clustering is performed.
73
74 Parameters
75 ----------
76 sequences : FeatureData[Sequence]
77 The sequences corresponding to the features in table.
78 table : FeatureTable[Frequency]
79 The feature table to be clustered.
80 reference_sequences : FeatureData[Sequence]
81 The sequences to use as cluster centroids.
82 perc_identity : Float % Range(0, 1, inclusive_start=False, inclusive_end=True)
83 The percent identity at which clustering should be performed. This
84 parameter maps to vsearch's --id parameter.
85 strand : Str % Choices('plus', 'both'), optional
86 Search plus (i.e., forward) or both (i.e., forward and reverse
87 complement) strands.
88
89 Returns
90 -------
91 clustered_table : FeatureTable[Frequency]
92 The table following clustering of features.
93 clustered_sequences : FeatureData[Sequence]
94 Sequences representing clustered features.
95 new_reference_sequences : FeatureData[Sequence]
96 The new reference sequences. This can be used for subsequent runs of
97 open-reference clustering for consistent definitions of features across
98 open-reference feature tables.
99 ]]></help>
100 <macros>
101 <import>qiime_citation.xml</import>
102 </macros>
103 <expand macro="qiime_citation"/>
104 </tool>