|
0
|
1 <?xml version="1.0" ?>
|
|
9
|
2 <tool id="qiime_feature-classifier_classify-consensus-vsearch" name="qiime feature-classifier classify-consensus-vsearch" version="2019.7">
|
|
0
|
3 <description> - VSEARCH consensus taxonomy classifier</description>
|
|
|
4 <requirements>
|
|
9
|
5 <requirement type="package" version="2019.7">qiime2</requirement>
|
|
0
|
6 </requirements>
|
|
|
7 <command><![CDATA[
|
|
|
8 qiime feature-classifier classify-consensus-vsearch
|
|
|
9
|
|
|
10 --i-query=$iquery
|
|
|
11 --i-reference-reads=$ireferencereads
|
|
|
12
|
|
|
13
|
|
|
14 #if str( $id_to_taxonomy_fp.selector ) == 'history'
|
|
|
15 #set $tax = $id_to_taxonomy_fp.taxonomy_fp
|
|
|
16 --i-reference-taxonomy '$tax'
|
|
|
17 #else:
|
|
|
18 #set $tax = $id_to_taxonomy_fp.taxonomy_fp.fields.path
|
|
|
19 --i-reference-taxonomy '$tax'
|
|
|
20 #end if
|
|
|
21
|
|
|
22
|
|
9
|
23 #if $psearchexact:
|
|
|
24 --p-search-exact
|
|
|
25 #end if
|
|
|
26
|
|
|
27
|
|
|
28 #if $ptophitsonly:
|
|
|
29 --p-top-hits-only
|
|
|
30 #end if
|
|
|
31
|
|
|
32
|
|
4
|
33
|
|
6
|
34 #if str($pmaxaccepts):
|
|
0
|
35 --p-maxaccepts=$pmaxaccepts
|
|
|
36 #end if
|
|
|
37
|
|
6
|
38 #if str($ppercidentity):
|
|
0
|
39 --p-perc-identity=$ppercidentity
|
|
|
40 #end if
|
|
|
41
|
|
6
|
42 #if str($pquerycov):
|
|
0
|
43 --p-query-cov=$pquerycov
|
|
|
44 #end if
|
|
|
45
|
|
|
46 #if str($pstrand) != 'None':
|
|
|
47 --p-strand=$pstrand
|
|
|
48 #end if
|
|
|
49
|
|
6
|
50 #if str($pminconsensus):
|
|
0
|
51 --p-min-consensus=$pminconsensus
|
|
|
52 #end if
|
|
|
53
|
|
4
|
54
|
|
|
55
|
|
|
56
|
|
|
57
|
|
|
58 #if '__sq__' in str($punassignablelabel):
|
|
|
59 #set $punassignablelabel_temp = $punassignablelabel.replace('__sq__', "'")
|
|
|
60 #set $punassignablelabel = $punassignablelabel_temp
|
|
|
61 #end if
|
|
|
62
|
|
0
|
63 #if str($punassignablelabel):
|
|
|
64 --p-unassignable-label="$punassignablelabel"
|
|
|
65 #end if
|
|
|
66
|
|
4
|
67
|
|
|
68
|
|
|
69
|
|
0
|
70 #set $pthreads = '${GALAXY_SLOTS:-4}'
|
|
|
71 #if str($pthreads):
|
|
|
72 --p-threads="$pthreads"
|
|
|
73 #end if
|
|
|
74
|
|
|
75 --o-classification=oclassification
|
|
9
|
76
|
|
0
|
77 ;
|
|
|
78 cp oclassification.qza $oclassification
|
|
|
79 ]]></command>
|
|
|
80 <inputs>
|
|
|
81 <param format="qza,no_unzip.zip" label="--i-query: ARTIFACT FeatureData[Sequence] Sequences to classify taxonomically. [required]" name="iquery" optional="False" type="data"/>
|
|
|
82 <param format="qza,no_unzip.zip" label="--i-reference-reads: ARTIFACT FeatureData[Sequence] reference sequences. [required]" name="ireferencereads" optional="False" type="data"/>
|
|
|
83
|
|
|
84 <conditional name="id_to_taxonomy_fp" optional="True">
|
|
|
85 <param name="selector" type="select" label="Reference taxonomy to query">
|
|
|
86 <option value="cached">Public databases</option>
|
|
|
87 <option value="history">Databases from your history</option>
|
|
|
88 </param>
|
|
|
89 <when value="cached">
|
|
|
90 <param argument="--taxonomy_fp" label="Reference taxonomy" type="select" optional="True">
|
|
|
91 <options from_data_table="qiime_taxonomy" />
|
|
|
92 </param>
|
|
|
93 </when>
|
|
|
94 <when value="history">
|
|
|
95 <param argument="--taxonomy_fp" type="data" format="qza,no_unzip.zip" label="Reference databases" optional="True" />
|
|
|
96 </when>
|
|
|
97 </conditional>
|
|
|
98
|
|
|
99 <param label="--p-maxaccepts: INTEGER Maximum number of hits to keep for each query. Set Range(0, None) to 0 to keep all hits > perc-identity similarity. Must be in range [0, infinity]. [default: 10]" name="pmaxaccepts" optional="True" type="integer" min="0" value="10"/>
|
|
|
100 <param label="--p-perc-identity: PROPORTION Range(0.0, 1.0, inclusive_end=True) Reject match if percent identity to query is lower. Must be in range [0.0, 1.0]. [default: 0.8]" name="ppercidentity" optional="True" type="float" min="0" max="1" exclude_max="False" value="0.8"/>
|
|
|
101 <param label="--p-query-cov: PROPORTION Range(0.0, 1.0, inclusive_end=True) Reject match if query alignment coverage per high-scoring pair is lower. Must be in range [0.0, 1.0]. [default: 0.8]" name="pquerycov" optional="True" type="float" min="0" max="1" exclude_max="False" value="0.8"/>
|
|
|
102 <param label="--p-strand: Align against reference sequences in forward ('plus') or both directions ('both'). [default: 'both']" name="pstrand" optional="True" type="select">
|
|
|
103 <option value="None">Selection is Optional</option>
|
|
|
104 <option selected="True" value="both">both</option>
|
|
|
105 <option value="plus">plus</option>
|
|
|
106 </param>
|
|
|
107 <param label="--p-min-consensus: NUMBER Range(0.5, 1.0, inclusive_start=False, inclusive_end=True) Minimum fraction of assignments must match top hit to be accepted as consensus assignment. Must be in range (0.5, 1.0]. [default: 0.51]" name="pminconsensus" optional="True" type="float" min="0.5" max="1" exclude_min="True" exclude_max="False" value="0.51"/>
|
|
4
|
108 <param label="--p-unassignable-label: TEXT [default: 'Unassigned']" name="punassignablelabel" optional="True" type="text" value="Unassigned"/>
|
|
9
|
109
|
|
|
110
|
|
|
111 <param label="--p-search-exact: Search for exact full-length matches to the query sequences. Only 100% exact matches are reported and this command is much faster than the default. If True, the perc-identity and query-cov settings are ignored. Note: query and reference reads must be trimmed to the exact same DNA locus (e.g., primer site) because only exact matches will be reported. [default: False]" name="psearchexact" selected="False" type="boolean"/>
|
|
|
112 <param label="--p-top-hits-only: Only the top hits between the query and reference sequence sets are reported. For each query, the top hit is the one presenting the highest percentage of identity. Multiple equally scored top hits will be used for consensus taxonomic assignment if maxaccepts is greater than 1. [default: False]" name="ptophitsonly" selected="False" type="boolean"/>
|
|
|
113
|
|
0
|
114 </inputs>
|
|
|
115 <outputs>
|
|
|
116 <data format="qza" label="${tool.name} on ${on_string}: classification.qza" name="oclassification"/>
|
|
|
117 </outputs>
|
|
|
118 <help><![CDATA[
|
|
9
|
119 VSEARCH-based consensus taxonomy classifier
|
|
0
|
120
|
|
|
121 Assign taxonomy to query sequences using VSEARCH. Performs VSEARCH global
|
|
|
122 alignment between query and reference_reads, then assigns consensus
|
|
|
123 taxonomy to each query sequence from among maxaccepts top hits,
|
|
|
124 min_consensus of which share that taxonomic assignment. Unlike classify-
|
|
|
125 consensus-blast, this method searches the entire reference database before
|
|
|
126 choosing the top N hits, not the first N hits.
|
|
|
127
|
|
|
128 Parameters
|
|
|
129 ----------
|
|
|
130 query : FeatureData[Sequence]
|
|
|
131 Sequences to classify taxonomically.
|
|
|
132 reference_reads : FeatureData[Sequence]
|
|
|
133 reference sequences.
|
|
|
134 reference_taxonomy : FeatureData[Taxonomy]
|
|
|
135 reference taxonomy labels.
|
|
9
|
136 maxaccepts : Int % Range(1, None) | Str % Choices('all'), optional
|
|
|
137 Maximum number of hits to keep for each query. Set to "all" to keep all
|
|
|
138 hits > perc_identity similarity.
|
|
0
|
139 perc_identity : Float % Range(0.0, 1.0, inclusive_end=True), optional
|
|
9
|
140 Reject match if percent identity to query is lower.
|
|
0
|
141 query_cov : Float % Range(0.0, 1.0, inclusive_end=True), optional
|
|
|
142 Reject match if query alignment coverage per high-scoring pair is
|
|
9
|
143 lower.
|
|
0
|
144 strand : Str % Choices('both', 'plus'), optional
|
|
|
145 Align against reference sequences in forward ("plus") or both
|
|
|
146 directions ("both").
|
|
|
147 min_consensus : Float % Range(0.5, 1.0, inclusive_start=False, inclusive_end=True), optional
|
|
|
148 Minimum fraction of assignments must match top hit to be accepted as
|
|
9
|
149 consensus assignment.
|
|
0
|
150 unassignable_label : Str, optional
|
|
9
|
151 search_exact : Bool, optional
|
|
|
152 Search for exact full-length matches to the query sequences. Only 100%
|
|
|
153 exact matches are reported and this command is much faster than the
|
|
|
154 default. If True, the perc_identity and query_cov settings are ignored.
|
|
|
155 Note: query and reference reads must be trimmed to the exact same DNA
|
|
|
156 locus (e.g., primer site) because only exact matches will be reported.
|
|
|
157 top_hits_only : Bool, optional
|
|
|
158 Only the top hits between the query and reference sequence sets are
|
|
|
159 reported. For each query, the top hit is the one presenting the highest
|
|
|
160 percentage of identity. Multiple equally scored top hits will be used
|
|
|
161 for consensus taxonomic assignment if maxaccepts is greater than 1.
|
|
|
162 threads : Int % Range(1, None), optional
|
|
|
163 Number of threads to use for job parallelization.
|
|
0
|
164
|
|
|
165 Returns
|
|
|
166 -------
|
|
|
167 classification : FeatureData[Taxonomy]
|
|
|
168 The resulting taxonomy classifications.
|
|
|
169 ]]></help>
|
|
|
170 <macros>
|
|
|
171 <import>qiime_citation.xml</import>
|
|
|
172 </macros>
|
|
|
173 <expand macro="qiime_citation"/>
|
|
|
174 </tool>
|
