Mercurial > repos > florianbegusch > qiime2_suite

comparison qiime2/qiime_vsearch_cluster-features-closed-reference.xml @ 14:a0a8d77a991c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author florianbegusch
date Thu, 03 Sep 2020 09:51:29 +0000
parents f190567fe3f6
children
comparison
equal deleted inserted replaced
13:887cd4ad8e16 14:a0a8d77a991c
1 <?xml version="1.0" ?> 1 <?xml version="1.0" ?>
2 <tool id="qiime_vsearch_cluster-features-closed-reference" name="qiime vsearch cluster-features-closed-reference" version="2019.7"> 2 <tool id="qiime_vsearch_cluster-features-closed-reference" name="qiime vsearch cluster-features-closed-reference"
3 <description> - Closed-reference clustering of features.</description> 3 version="2020.8">
4 <requirements> 4 <description> Closed-reference clustering of features.</description>
5 <requirement type="package" version="2019.7">qiime2</requirement> 5 <requirements>
6 </requirements> 6 <requirement type="package" version="2020.8">qiime2</requirement>
7 <command><![CDATA[ 7 </requirements>
8 <command><![CDATA[
8 qiime vsearch cluster-features-closed-reference 9 qiime vsearch cluster-features-closed-reference
10
9 --i-sequences=$isequences 11 --i-sequences=$isequences
12
10 --i-table=$itable 13 --i-table=$itable
14
11 --i-reference-sequences=$ireferencesequences 15 --i-reference-sequences=$ireferencesequences
12 16
13 #if str($ppercidentity): 17 --p-perc-identity=$ppercidentity
14 --p-perc-identity="$ppercidentity" 18
19 #if str($pstrand) != 'None':
20 --p-strand=$pstrand
15 #end if 21 #end if
16 22
17 #if str($pstrand) != 'None': 23 --p-threads=$pthreads
18 --p-strand=$pstrand 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
19 #end if 33 #end if
20 34
21 #set $pthreads = '${GALAXY_SLOTS:-4}' 35 ;
36 cp ounmatchedsequences.qza $ounmatchedsequences
22 37
23 #if str($pthreads): 38 ]]></command>
24 --p-threads="$pthreads" 39 <inputs>
25 #end if 40 <param format="qza,no_unzip.zip" label="--i-sequences: ARTIFACT FeatureData[Sequence] The sequences corresponding to the features in table. [required]" name="isequences" optional="False" type="data" />
41 <param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency] The feature table to be clustered. [required]" name="itable" optional="False" type="data" />
42 <param format="qza,no_unzip.zip" label="--i-reference-sequences: ARTIFACT FeatureData[Sequence] The sequences to use as cluster centroids. [required]" name="ireferencesequences" optional="False" type="data" />
43 <param label="--p-perc-identity: PROPORTION Range(0, 1, inclusive_start=False, inclusive_end=True) The percent identity at which clustering should be performed. This parameter maps to vsearch\'s --id parameter. [required]" name="ppercidentity" optional="False" type="text" />
44 <param label="--p-strand: " name="pstrand" optional="True" type="select">
45 <option selected="True" value="None">Selection is Optional</option>
46 <option value="plus">plus</option>
47 <option value="both">both</option>
48 </param>
49 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
50
51 </inputs>
26 52
27 --o-clustered-table=oclusteredtable 53 <outputs>
28 --o-clustered-sequences=oclusteredsequences 54 <data format="qza" label="${tool.name} on ${on_string}: clusteredtable.qza" name="oclusteredtable" />
29 --o-unmatched-sequences=ounmatchedsequences 55 <data format="qza" label="${tool.name} on ${on_string}: clusteredsequences.qza" name="oclusteredsequences" />
30 ; 56 <data format="qza" label="${tool.name} on ${on_string}: unmatchedsequences.qza" name="ounmatchedsequences" />
31 cp oclusteredtable.qza $oclusteredtable; 57
32 cp oclusteredsequences.qza $oclusteredsequences; 58 </outputs>
33 cp ounmatchedsequences.qza $ounmatchedsequences 59
34 ]]></command> 60 <help><![CDATA[
35 <inputs> 61 Closed-reference clustering of features.
36 <param format="qza,no_unzip.zip" label="--i-sequences: ARTIFACT FeatureData[Sequence] The sequences corresponding to the features in table. [required]" name="isequences" optional="False" type="data"/> 62 ###############################################################
37 <param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency] The feature table to be clustered. [required]" name="itable" optional="False" type="data"/>
38 <param format="qza,no_unzip.zip" label="--i-reference-sequences: ARTIFACT FeatureData[Sequence] The sequences to use as cluster centroids. [required]" name="ireferencesequences" optional="False" type="data"/>
39 <param label="--p-perc-identity: PROPORTION Range(0, 1, inclusive_start=False, inclusive_end=True) The percent identity at which clustering should be performed. This parameter maps to vsearch's --id parameter. [required]" name="ppercidentity" optional="False" type="float" value="" min="0" max="1" exclude_max="False" />
40 <param label="--p-strand: " name="pstrand" optional="True" type="select">
41 <option selected="True" value="None">Selection is Optional</option>
42 <option value="plus">plus</option>
43 <option value="both">both</option>
44 </param>
45 </inputs>
46 <outputs>
47 <data format="qza" label="${tool.name} on ${on_string}: clusteredtable.qza" name="oclusteredtable"/>
48 <data format="qza" label="${tool.name} on ${on_string}: clusteredsequences.qza" name="oclusteredsequences"/>
49 <data format="qza" label="${tool.name} on ${on_string}: unmatchedsequences.qza" name="ounmatchedsequences"/>
50 </outputs>
51 <help><![CDATA[
52 Open-reference clustering of features.
53 ######################################
54 63
55 Given a feature table and the associated feature sequences, cluster the 64 Given a feature table and the associated feature sequences, cluster the
56 features against a reference database based on user-specified percent 65 features against a reference database based on user-specified percent
57 identity threshold of their sequences. Any sequences that don't match are 66 identity threshold of their sequences. This is not a general-purpose
58 then clustered de novo. This is not a general-purpose clustering method, 67 closed-reference clustering method, but rather is intended to be used for
59 but rather is intended to be used for clustering the results of quality- 68 clustering the results of quality-filtering/dereplication methods, such as
60 filtering/dereplication methods, such as DADA2, or for re-clustering a 69 DADA2, or for re-clustering a FeatureTable at a lower percent identity than
61 FeatureTable at a lower percent identity than it was originally clustered 70 it was originally clustered at. When a group of features in the input table
62 at. When a group of features in the input table are clustered into a single 71 are clustered into a single feature, the frequency of that single feature
63 feature, the frequency of that single feature in a given sample is the sum 72 in a given sample is the sum of the frequencies of the features that were
64 of the frequencies of the features that were clustered in that sample. 73 clustered in that sample. Feature identifiers will be inherited from the
65 Feature identifiers will be inherited from the centroid feature of each 74 centroid feature of each cluster. See the vsearch documentation for details
66 cluster. For features that match a reference sequence, the centroid feature 75 on how sequence clustering is performed.
67 is that reference sequence, so its identifier will become the feature
68 identifier. The clustered_sequences result will contain feature
69 representative sequences that are derived from the sequences input for all
70 features in clustered_table. This will always be the most abundant sequence
71 in the cluster. The new_reference_sequences result will contain the entire
72 reference database, plus feature representative sequences for any de novo
73 features. This is intended to be used as a reference database in subsequent
74 iterations of cluster_features_open_reference, if applicable. See the
75 vsearch documentation for details on how sequence clustering is performed.
76 76
77 Parameters 77 Parameters
78 ---------- 78 ----------
79 sequences : FeatureData[Sequence] 79 sequences : FeatureData[Sequence]
80 The sequences corresponding to the features in table. 80 The sequences corresponding to the features in table.
86 The percent identity at which clustering should be performed. This 86 The percent identity at which clustering should be performed. This
87 parameter maps to vsearch's --id parameter. 87 parameter maps to vsearch's --id parameter.
88 strand : Str % Choices('plus', 'both'), optional 88 strand : Str % Choices('plus', 'both'), optional
89 Search plus (i.e., forward) or both (i.e., forward and reverse 89 Search plus (i.e., forward) or both (i.e., forward and reverse
90 complement) strands. 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.
91 94
92 Returns 95 Returns
93 ------- 96 -------
94 clustered_table : FeatureTable[Frequency] 97 clustered_table : FeatureTable[Frequency]
95 The table following clustering of features. 98 The table following clustering of features.
96 clustered_sequences : FeatureData[Sequence] 99 clustered_sequences : FeatureData[Sequence]
97 Sequences representing clustered features. 100 The sequences representing clustered features, relabeled by the
98 new_reference_sequences : FeatureData[Sequence] 101 reference IDs.
99 The new reference sequences. This can be used for subsequent runs of 102 unmatched_sequences : FeatureData[Sequence]
100 open-reference clustering for consistent definitions of features across 103 The sequences which failed to match any reference sequences. This
101 open-reference feature tables. 104 output maps to vsearch's --notmatched parameter.
102 ]]></help> 105 ]]></help>
103 <macros> 106 <macros>
104 <import>qiime_citation.xml</import> 107 <import>qiime_citation.xml</import>
105 </macros> 108 </macros>
106 <expand macro="qiime_citation"/> 109 <expand macro="qiime_citation"/>
107 </tool> 110 </tool>