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