29
|
1 <?xml version="1.0" ?>
|
|
2 <tool id="qiime_feature-classifier_classify-consensus-vsearch" name="qiime feature-classifier classify-consensus-vsearch"
|
|
3 version="2020.8">
|
|
4 <description>VSEARCH-based consensus taxonomy classifier</description>
|
|
5 <requirements>
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
7 </requirements>
|
|
8 <command><![CDATA[
|
|
9 qiime feature-classifier classify-consensus-vsearch
|
|
10
|
|
11 --i-query=$iquery
|
|
12
|
|
13 --i-reference-reads=$ireferencereads
|
|
14
|
|
15 --i-reference-taxonomy=$ireferencetaxonomy
|
|
16
|
|
17 #if str($pmaxaccepts) != 'None':
|
|
18 --p-maxaccepts=$pmaxaccepts
|
|
19 #end if
|
|
20
|
|
21 --p-perc-identity=$ppercidentity
|
|
22
|
|
23 --p-query-cov=$pquerycov
|
|
24
|
|
25 #if str($pstrand) != 'None':
|
|
26 --p-strand=$pstrand
|
|
27 #end if
|
|
28
|
|
29 --p-min-consensus=$pminconsensus
|
|
30
|
|
31 #if str($punassignablelabel):
|
|
32 --p-unassignable-label=$punassignablelabel
|
|
33 #end if
|
|
34 #if $psearchexact:
|
|
35 --p-search-exact
|
|
36 #end if
|
|
37
|
|
38 #if $ptophitsonly:
|
|
39 --p-top-hits-only
|
|
40 #end if
|
|
41
|
|
42 #if str($pmaxhits) != 'None':
|
|
43 --p-maxhits=$pmaxhits
|
|
44 #end if
|
|
45
|
|
46 #if str($pmaxrejects) != 'None':
|
|
47 --p-maxrejects=$pmaxrejects
|
|
48 #end if
|
|
49
|
|
50 #if $pnooutputnohits:
|
|
51 --p-no-output-no-hits
|
|
52 #end if
|
|
53
|
|
54 --p-weak-id=$pweakid
|
|
55
|
|
56 --p-threads=$pthreads
|
|
57
|
|
58 --o-classification=oclassification
|
|
59
|
|
60 #if str($examples) != 'None':
|
|
61 --examples=$examples
|
|
62 #end if
|
|
63
|
|
64 ;
|
|
65 cp oclassification.qza $oclassification
|
|
66
|
|
67 ]]></command>
|
|
68 <inputs>
|
|
69 <param format="qza,no_unzip.zip" label="--i-query: ARTIFACT FeatureData[Sequence] Sequences to classify taxonomically. [required]" name="iquery" optional="False" type="data" />
|
|
70 <param format="qza,no_unzip.zip" label="--i-reference-reads: ARTIFACT FeatureData[Sequence] reference sequences. [required]" name="ireferencereads" optional="False" type="data" />
|
|
71 <param format="qza,no_unzip.zip" label="--i-reference-taxonomy: ARTIFACT FeatureData[Taxonomy] reference taxonomy labels. [required]" name="ireferencetaxonomy" optional="False" type="data" />
|
|
72 <param label="--p-maxaccepts: " name="pmaxaccepts" optional="True" type="select">
|
|
73 <option selected="True" value="None">Selection is Optional</option>
|
|
74 <option value="Int % Range(1">Int % Range(1</option>
|
|
75 <option value="None">None</option>
|
|
76 </param>
|
|
77 <param exclude_max="False" label="--p-perc-identity: PROPORTION Range(0.0, 1.0, inclusive_end=True) Reject match if percent identity to query is lower. [default: 0.8]" max="1.0" min="0.0" name="ppercidentity" optional="True" type="float" value="0.8" />
|
|
78 <param exclude_max="False" 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. [default: 0.8]" max="1.0" min="0.0" name="pquerycov" optional="True" type="float" value="0.8" />
|
|
79 <param label="--p-strand: " name="pstrand" optional="True" type="select">
|
|
80 <option selected="True" value="None">Selection is Optional</option>
|
|
81 <option value="both">both</option>
|
|
82 <option value="plus">plus</option>
|
|
83 </param>
|
|
84 <param exclude_max="False" exclude_min="True" 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. [default: 0.51]" max="1.0" min="0.5" name="pminconsensus" optional="True" type="float" value="0.51" />
|
|
85 <param label="--p-unassignable-label: TEXT [default: \'Unassigned\']" name="punassignablelabel" optional="False" type="text" value="\'Unassigned\'" />
|
|
86 <param label="--p-search-exact: --p-search-exact: / --p-no-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" />
|
|
87 <param label="--p-top-hits-only: --p-top-hits-only: / --p-no-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" />
|
|
88 <param label="--p-maxhits: " name="pmaxhits" optional="True" type="select">
|
|
89 <option selected="True" value="None">Selection is Optional</option>
|
|
90 <option value="Int % Range(1">Int % Range(1</option>
|
|
91 <option value="None">None</option>
|
|
92 </param>
|
|
93 <param label="--p-maxrejects: " name="pmaxrejects" optional="True" type="select">
|
|
94 <option selected="True" value="None">Selection is Optional</option>
|
|
95 <option value="Int % Range(1">Int % Range(1</option>
|
|
96 <option value="None">None</option>
|
|
97 </param>
|
|
98 <param label="--p-no-output-no-hits: Do not report both matching and non-matching queries. WARNING: always use the default setting for this option unless if you know what you are doing! If you set this option to False, your sequences and feature table will need to be filtered to exclude unclassified sequences, otherwise you may run into errors downstream from missing feature IDs. [default: True]" name="pnooutputnohits" selected="False" type="boolean" />
|
|
99 <param exclude_max="False" label="--p-weak-id: PROPORTION Range(0.0, 1.0, inclusive_end=True) Show hits with percentage of identity of at least N, without terminating the search. A normal search stops as soon as enough hits are found (as defined by maxaccepts, maxrejects, and perc-identity). As weak-id reports weak hits that are not deduced from maxaccepts, high perc-identity values can be used, hence preserving both speed and sensitivity. Logically, weak-id must be smaller than the value indicated by perc-identity, otherwise this option will be ignored. [default: 0.0]" max="1.0" min="0.0" name="pweakid" optional="True" type="float" value="0.0" />
|
|
100 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
101
|
|
102 </inputs>
|
|
103
|
|
104 <outputs>
|
|
105 <data format="qza" label="${tool.name} on ${on_string}: classification.qza" name="oclassification" />
|
|
106
|
|
107 </outputs>
|
|
108
|
|
109 <help><![CDATA[
|
|
110 VSEARCH-based consensus taxonomy classifier
|
|
111 ###############################################################
|
|
112
|
|
113 Assign taxonomy to query sequences using VSEARCH. Performs VSEARCH global
|
|
114 alignment between query and reference_reads, then assigns consensus
|
|
115 taxonomy to each query sequence from among maxaccepts top hits,
|
|
116 min_consensus of which share that taxonomic assignment. Unlike classify-
|
|
117 consensus-blast, this method searches the entire reference database before
|
|
118 choosing the top N hits, not the first N hits.
|
|
119
|
|
120 Parameters
|
|
121 ----------
|
|
122 query : FeatureData[Sequence]
|
|
123 Sequences to classify taxonomically.
|
|
124 reference_reads : FeatureData[Sequence]
|
|
125 reference sequences.
|
|
126 reference_taxonomy : FeatureData[Taxonomy]
|
|
127 reference taxonomy labels.
|
|
128 maxaccepts : Int % Range(1, None) | Str % Choices('all'), optional
|
|
129 Maximum number of hits to keep for each query. Set to "all" to keep all
|
|
130 hits > perc_identity similarity. Note that if strand=both, maxaccepts
|
|
131 will keep N hits for each direction (if searches in the opposite
|
|
132 direction yield results that exceed the minimum perc_identity). In
|
|
133 those cases use maxhits to control the total number of hits returned.
|
|
134 This option works in pair with maxrejects. The search process sorts
|
|
135 target sequences by decreasing number of k-mers they have in common
|
|
136 with the query sequence, using that information as a proxy for sequence
|
|
137 similarity. After pairwise alignments, if the first target sequence
|
|
138 passes the acceptation criteria, it is accepted as best hit and the
|
|
139 search process stops for that query. If maxaccepts is set to a higher
|
|
140 value, more hits are accepted. If maxaccepts and maxrejects are both
|
|
141 set to "all", the complete database is searched.
|
|
142 perc_identity : Float % Range(0.0, 1.0, inclusive_end=True), optional
|
|
143 Reject match if percent identity to query is lower.
|
|
144 query_cov : Float % Range(0.0, 1.0, inclusive_end=True), optional
|
|
145 Reject match if query alignment coverage per high-scoring pair is
|
|
146 lower.
|
|
147 strand : Str % Choices('both', 'plus'), optional
|
|
148 Align against reference sequences in forward ("plus") or both
|
|
149 directions ("both").
|
|
150 min_consensus : Float % Range(0.5, 1.0, inclusive_start=False, inclusive_end=True), optional
|
|
151 Minimum fraction of assignments must match top hit to be accepted as
|
|
152 consensus assignment.
|
|
153 unassignable_label : Str, optional
|
|
154 search_exact : Bool, optional
|
|
155 Search for exact full-length matches to the query sequences. Only 100%
|
|
156 exact matches are reported and this command is much faster than the
|
|
157 default. If True, the perc_identity and query_cov settings are ignored.
|
|
158 Note: query and reference reads must be trimmed to the exact same DNA
|
|
159 locus (e.g., primer site) because only exact matches will be reported.
|
|
160 top_hits_only : Bool, optional
|
|
161 Only the top hits between the query and reference sequence sets are
|
|
162 reported. For each query, the top hit is the one presenting the highest
|
|
163 percentage of identity. Multiple equally scored top hits will be used
|
|
164 for consensus taxonomic assignment if maxaccepts is greater than 1.
|
|
165 maxhits : Int % Range(1, None) | Str % Choices('all'), optional
|
|
166 Maximum number of hits to show once the search is terminated.
|
|
167 maxrejects : Int % Range(1, None) | Str % Choices('all'), optional
|
|
168 Maximum number of non-matching target sequences to consider before
|
|
169 stopping the search. This option works in pair with maxaccepts (see
|
|
170 maxaccepts description for details).
|
|
171 output_no_hits : Bool, optional
|
|
172 Report both matching and non-matching queries. WARNING: always use the
|
|
173 default setting for this option unless if you know what you are doing!
|
|
174 If you set this option to False, your sequences and feature table will
|
|
175 need to be filtered to exclude unclassified sequences, otherwise you
|
|
176 may run into errors downstream from missing feature IDs.
|
|
177 weak_id : Float % Range(0.0, 1.0, inclusive_end=True), optional
|
|
178 Show hits with percentage of identity of at least N, without
|
|
179 terminating the search. A normal search stops as soon as enough hits
|
|
180 are found (as defined by maxaccepts, maxrejects, and perc_identity). As
|
|
181 weak_id reports weak hits that are not deduced from maxaccepts, high
|
|
182 perc_identity values can be used, hence preserving both speed and
|
|
183 sensitivity. Logically, weak_id must be smaller than the value
|
|
184 indicated by perc_identity, otherwise this option will be ignored.
|
|
185 threads : Int % Range(1, None), optional
|
|
186 Number of threads to use for job parallelization.
|
|
187
|
|
188 Returns
|
|
189 -------
|
|
190 classification : FeatureData[Taxonomy]
|
|
191 The resulting taxonomy classifications.
|
|
192 ]]></help>
|
|
193 <macros>
|
|
194 <import>qiime_citation.xml</import>
|
|
195 </macros>
|
|
196 <expand macro="qiime_citation"/>
|
|
197 </tool> |