|
29
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_vsearch_cluster-features-closed-reference" name="qiime vsearch cluster-features-closed-reference"
|
|
|
3 version="2020.8">
|
|
|
4 <description> Closed-reference clustering of features.</description>
|
|
|
5 <requirements>
|
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command><![CDATA[
|
|
|
9 qiime vsearch cluster-features-closed-reference
|
|
|
10
|
|
|
11 --i-sequences=$isequences
|
|
|
12
|
|
|
13 --i-table=$itable
|
|
|
14
|
|
|
15 --i-reference-sequences=$ireferencesequences
|
|
|
16
|
|
|
17 --p-perc-identity=$ppercidentity
|
|
|
18
|
|
|
19 #if str($pstrand) != 'None':
|
|
|
20 --p-strand=$pstrand
|
|
|
21 #end if
|
|
|
22
|
|
|
23 --p-threads=$pthreads
|
|
|
24
|
|
|
25 --o-clustered-table=oclusteredtable
|
|
|
26
|
|
|
27 --o-clustered-sequences=oclusteredsequences
|
|
|
28
|
|
|
29 --o-unmatched-sequences=ounmatchedsequences
|
|
|
30
|
|
|
31 #if str($examples) != 'None':
|
|
|
32 --examples=$examples
|
|
|
33 #end if
|
|
|
34
|
|
|
35 ;
|
|
|
36 cp ounmatchedsequences.qza $ounmatchedsequences
|
|
|
37
|
|
|
38 ]]></command>
|
|
|
39 <inputs>
|
|
|
40 <param format="qza,no_unzip.zip" label="--i-sequences: ARTIFACT FeatureData[Sequence] The sequences corresponding to the features in table. [required]" name="isequences" optional="False" type="data" />
|
|
|
41 <param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency] The feature table to be clustered. [required]" name="itable" optional="False" type="data" />
|
|
|
42 <param format="qza,no_unzip.zip" label="--i-reference-sequences: ARTIFACT FeatureData[Sequence] The sequences to use as cluster centroids. [required]" name="ireferencesequences" optional="False" type="data" />
|
|
|
43 <param label="--p-perc-identity: PROPORTION Range(0, 1, inclusive_start=False, inclusive_end=True) The percent identity at which clustering should be performed. This parameter maps to vsearch\'s --id parameter. [required]" name="ppercidentity" optional="False" type="text" />
|
|
|
44 <param label="--p-strand: " name="pstrand" optional="True" type="select">
|
|
|
45 <option selected="True" value="None">Selection is Optional</option>
|
|
|
46 <option value="plus">plus</option>
|
|
|
47 <option value="both">both</option>
|
|
|
48 </param>
|
|
|
49 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
|
50
|
|
|
51 </inputs>
|
|
|
52
|
|
|
53 <outputs>
|
|
|
54 <data format="qza" label="${tool.name} on ${on_string}: clusteredtable.qza" name="oclusteredtable" />
|
|
|
55 <data format="qza" label="${tool.name} on ${on_string}: clusteredsequences.qza" name="oclusteredsequences" />
|
|
|
56 <data format="qza" label="${tool.name} on ${on_string}: unmatchedsequences.qza" name="ounmatchedsequences" />
|
|
|
57
|
|
|
58 </outputs>
|
|
|
59
|
|
|
60 <help><![CDATA[
|
|
|
61 Closed-reference clustering of features.
|
|
|
62 ###############################################################
|
|
|
63
|
|
|
64 Given a feature table and the associated feature sequences, cluster the
|
|
|
65 features against a reference database based on user-specified percent
|
|
|
66 identity threshold of their sequences. This is not a general-purpose
|
|
|
67 closed-reference clustering method, but rather is intended to be used for
|
|
|
68 clustering the results of quality-filtering/dereplication methods, such as
|
|
|
69 DADA2, or for re-clustering a FeatureTable at a lower percent identity than
|
|
|
70 it was originally clustered at. When a group of features in the input table
|
|
|
71 are clustered into a single feature, the frequency of that single feature
|
|
|
72 in a given sample is the sum of the frequencies of the features that were
|
|
|
73 clustered in that sample. Feature identifiers will be inherited from the
|
|
|
74 centroid feature of each cluster. See the vsearch documentation for details
|
|
|
75 on how sequence clustering is performed.
|
|
|
76
|
|
|
77 Parameters
|
|
|
78 ----------
|
|
|
79 sequences : FeatureData[Sequence]
|
|
|
80 The sequences corresponding to the features in table.
|
|
|
81 table : FeatureTable[Frequency]
|
|
|
82 The feature table to be clustered.
|
|
|
83 reference_sequences : FeatureData[Sequence]
|
|
|
84 The sequences to use as cluster centroids.
|
|
|
85 perc_identity : Float % Range(0, 1, inclusive_start=False, inclusive_end=True)
|
|
|
86 The percent identity at which clustering should be performed. This
|
|
|
87 parameter maps to vsearch's --id parameter.
|
|
|
88 strand : Str % Choices('plus', 'both'), optional
|
|
|
89 Search plus (i.e., forward) or both (i.e., forward and reverse
|
|
|
90 complement) strands.
|
|
|
91 threads : Int % Range(0, 256, inclusive_end=True), optional
|
|
|
92 The number of threads to use for computation. Passing 0 will launch one
|
|
|
93 thread per CPU core.
|
|
|
94
|
|
|
95 Returns
|
|
|
96 -------
|
|
|
97 clustered_table : FeatureTable[Frequency]
|
|
|
98 The table following clustering of features.
|
|
|
99 clustered_sequences : FeatureData[Sequence]
|
|
|
100 The sequences representing clustered features, relabeled by the
|
|
|
101 reference IDs.
|
|
|
102 unmatched_sequences : FeatureData[Sequence]
|
|
|
103 The sequences which failed to match any reference sequences. This
|
|
|
104 output maps to vsearch's --notmatched parameter.
|
|
|
105 ]]></help>
|
|
|
106 <macros>
|
|
|
107 <import>qiime_citation.xml</import>
|
|
|
108 </macros>
|
|
|
109 <expand macro="qiime_citation"/>
|
|
|
110 </tool> |
