annotate qiime2/qiime_vsearch_cluster-features-open-reference.xml @ 14:a0a8d77a991c draft

Uploaded
author florianbegusch
date Thu, 03 Sep 2020 09:51:29 +0000
parents f190567fe3f6
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
1 <?xml version="1.0" ?>
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
2 <tool id="qiime_vsearch_cluster-features-open-reference" name="qiime vsearch cluster-features-open-reference"
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
3 version="2020.8">
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
4 <description> Open-reference clustering of features.</description>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
5 <requirements>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
6 <requirement type="package" version="2020.8">qiime2</requirement>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
7 </requirements>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
8 <command><![CDATA[
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
9 qiime vsearch cluster-features-open-reference
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
10
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
11 --i-sequences=$isequences
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
12
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
13 --i-table=$itable
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
14
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
15 --i-reference-sequences=$ireferencesequences
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
16
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
17 --p-perc-identity=$ppercidentity
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
18
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
19 #if str($pstrand) != 'None':
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
20 --p-strand=$pstrand
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
21 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
22
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
23 --p-threads=$pthreads
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
24
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
25 --o-clustered-table=oclusteredtable
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
26
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
27 --o-clustered-sequences=oclusteredsequences
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
28
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
29 --o-new-reference-sequences=onewreferencesequences
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
30
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
31 #if str($examples) != 'None':
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
32 --examples=$examples
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
33 #end if
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
34
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
35 ;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
36 cp onewreferencesequences.qza $onewreferencesequences
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
37
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
38 ]]></command>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
39 <inputs>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
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" />
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
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" />
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
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" />
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
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" />
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
44 <param label="--p-strand: " name="pstrand" optional="True" type="select">
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
45 <option selected="True" value="None">Selection is Optional</option>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
46 <option value="plus">plus</option>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
47 <option value="both">both</option>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
48 </param>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
49 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
50
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
51 </inputs>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
52
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
53 <outputs>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
54 <data format="qza" label="${tool.name} on ${on_string}: clusteredtable.qza" name="oclusteredtable" />
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
55 <data format="qza" label="${tool.name} on ${on_string}: clusteredsequences.qza" name="oclusteredsequences" />
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
56 <data format="qza" label="${tool.name} on ${on_string}: newreferencesequences.qza" name="onewreferencesequences" />
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
57
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
58 </outputs>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
59
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
60 <help><![CDATA[
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
61 Open-reference clustering of features.
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
62 ###############################################################
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
63
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
64 Given a feature table and the associated feature sequences, cluster the
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
65 features against a reference database based on user-specified percent
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
66 identity threshold of their sequences. Any sequences that don't match are
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
67 then clustered de novo. This is not a general-purpose clustering method,
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
68 but rather is intended to be used for clustering the results of quality-
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
69 filtering/dereplication methods, such as DADA2, or for re-clustering a
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
70 FeatureTable at a lower percent identity than it was originally clustered
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
71 at. When a group of features in the input table are clustered into a single
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
72 feature, the frequency of that single feature in a given sample is the sum
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
73 of the frequencies of the features that were clustered in that sample.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
74 Feature identifiers will be inherited from the centroid feature of each
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
75 cluster. For features that match a reference sequence, the centroid feature
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
76 is that reference sequence, so its identifier will become the feature
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
77 identifier. The clustered_sequences result will contain feature
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
78 representative sequences that are derived from the sequences input for all
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
79 features in clustered_table. This will always be the most abundant sequence
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
80 in the cluster. The new_reference_sequences result will contain the entire
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
81 reference database, plus feature representative sequences for any de novo
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
82 features. This is intended to be used as a reference database in subsequent
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
83 iterations of cluster_features_open_reference, if applicable. See the
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
84 vsearch documentation for details on how sequence clustering is performed.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
85
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
86 Parameters
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
87 ----------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
88 sequences : FeatureData[Sequence]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
89 The sequences corresponding to the features in table.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
90 table : FeatureTable[Frequency]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
91 The feature table to be clustered.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
92 reference_sequences : FeatureData[Sequence]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
93 The sequences to use as cluster centroids.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
94 perc_identity : Float % Range(0, 1, inclusive_start=False, inclusive_end=True)
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
95 The percent identity at which clustering should be performed. This
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
96 parameter maps to vsearch's --id parameter.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
97 strand : Str % Choices('plus', 'both'), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
98 Search plus (i.e., forward) or both (i.e., forward and reverse
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
99 complement) strands.
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
100 threads : Int % Range(0, 256, inclusive_end=True), optional
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
101 The number of threads to use for computation. Passing 0 will launch one
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
102 thread per CPU core.
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
103
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
104 Returns
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
105 -------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
106 clustered_table : FeatureTable[Frequency]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
107 The table following clustering of features.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
108 clustered_sequences : FeatureData[Sequence]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
109 Sequences representing clustered features.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
110 new_reference_sequences : FeatureData[Sequence]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
111 The new reference sequences. This can be used for subsequent runs of
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
112 open-reference clustering for consistent definitions of features across
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
113 open-reference feature tables.
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
114 ]]></help>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
115 <macros>
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
116 <import>qiime_citation.xml</import>
14
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
117 </macros>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
118 <expand macro="qiime_citation"/>
a0a8d77a991c Uploaded
florianbegusch
parents: 9
diff changeset
119 </tool>