annotate qiime2/qiime_vsearch_cluster-features-open-reference.xml @ 0:370e0b6e9826 draft

Uploaded
author florianbegusch
date Wed, 17 Jul 2019 03:05:17 -0400
parents
children f190567fe3f6
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" ?>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
2 <tool id="qiime_vsearch_cluster-features-open-reference" name="qiime vsearch cluster-features-open-reference" version="2019.4">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
3 <description> - Open-reference clustering of features.</description>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
4 <requirements>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
5 <requirement type="package" version="2019.4">qiime2</requirement>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
6 </requirements>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
7 <command><![CDATA[
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
8 qiime vsearch cluster-features-open-reference
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
9
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
10 --i-sequences=$isequences
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
11 --i-table=$itable
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
12 --i-reference-sequences=$ireferencesequences
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
13 --p-perc-identity="$ppercidentity"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
14
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
15 #if str($pstrand) != 'None':
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
16 --p-strand=$pstrand
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
17 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
18
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
19 #set $pthreads = '${GALAXY_SLOTS:-4}'
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
20 #if str($pthreads):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
21 --p-threads="$pthreads"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
22 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
23
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
24 --o-clustered-table=oclusteredtable
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
25 --o-clustered-sequences=oclusteredsequences
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
26 --o-new-reference-sequences=onewreferencesequences
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
27 ;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
28 cp oclusteredtable.qza $oclusteredtable;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
29 cp oclusteredsequences.qza $oclusteredsequences;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
30 cp onewreferencesequences.qza $onewreferencesequences
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
31 ]]></command>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
32 <inputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
36
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
38 <param label="--p-strand: " name="pstrand" optional="True" type="select">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
39 <option selected="True" value="None">Selection is Optional</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
40 <option value="plus">plus</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
41 <option value="both">both</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
42 </param>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
43 </inputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
44 <outputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
45 <data format="qza" label="${tool.name} on ${on_string}: clusteredtable.qza" name="oclusteredtable"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
46 <data format="qza" label="${tool.name} on ${on_string}: clusteredsequences.qza" name="oclusteredsequences"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
47 <data format="qza" label="${tool.name} on ${on_string}: newreferencesequences.qza" name="onewreferencesequences"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
48 </outputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
49 <help><![CDATA[
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
50 Open-reference clustering of features.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
51 ######################################
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
52
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
53 Given a feature table and the associated feature sequences, cluster the
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
54 features against a reference database based on user-specified percent
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
55 identity threshold of their sequences. Any sequences that don't match are
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
56 then clustered de novo. This is not a general-purpose clustering method,
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
57 but rather is intended to be used for clustering the results of quality-
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
58 filtering/dereplication methods, such as DADA2, or for re-clustering a
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
59 FeatureTable at a lower percent identity than it was originally clustered
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
60 at. When a group of features in the input table are clustered into a single
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
61 feature, the frequency of that single feature in a given sample is the sum
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
62 of the frequencies of the features that were clustered in that sample.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
63 Feature identifiers will be inherited from the centroid feature of each
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
64 cluster. For features that match a reference sequence, the centroid feature
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
65 is that reference sequence, so its identifier will become the feature
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
66 identifier. The clustered_sequences result will contain feature
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
67 representative sequences that are derived from the sequences input for all
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
68 features in clustered_table. This will always be the most abundant sequence
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
69 in the cluster. The new_reference_sequences result will contain the entire
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
70 reference database, plus feature representative sequences for any de novo
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
71 features. This is intended to be used as a reference database in subsequent
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
72 iterations of cluster_features_open_reference, if applicable. See the
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
73 vsearch documentation for details on how sequence clustering is performed.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
74
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
75 Parameters
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
76 ----------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
77 sequences : FeatureData[Sequence]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
78 The sequences corresponding to the features in table.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
79 table : FeatureTable[Frequency]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
80 The feature table to be clustered.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
81 reference_sequences : FeatureData[Sequence]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
82 The sequences to use as cluster centroids.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
83 perc_identity : Float % Range(0, 1, inclusive_start=False, inclusive_end=True)
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
84 The percent identity at which clustering should be performed. This
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
85 parameter maps to vsearch's --id parameter.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
86 strand : Str % Choices('plus', 'both'), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
87 Search plus (i.e., forward) or both (i.e., forward and reverse
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
88 complement) strands.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
89
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
90 Returns
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
91 -------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
92 clustered_table : FeatureTable[Frequency]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
93 The table following clustering of features.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
94 clustered_sequences : FeatureData[Sequence]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
95 Sequences representing clustered features.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
96 new_reference_sequences : FeatureData[Sequence]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
97 The new reference sequences. This can be used for subsequent runs of
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
98 open-reference clustering for consistent definitions of features across
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
99 open-reference feature tables.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
100 ]]></help>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
101 <macros>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
102 <import>qiime_citation.xml</import>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
103 </macros>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
104 <expand macro="qiime_citation"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
105 </tool>