Mercurial > repos > florianbegusch > qiime2_suite

comparison qiime2/qiime_feature-classifier_classify-consensus-vsearch.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_feature-classifier_classify-consensus-vsearch" name="qiime feature-classifier classify-consensus-vsearch" version="2019.7"> 2 <tool id="qiime_feature-classifier_classify-consensus-vsearch" name="qiime feature-classifier classify-consensus-vsearch"
3 <description> - VSEARCH consensus taxonomy classifier</description> 3 version="2020.8">
4 <requirements> 4 <description>VSEARCH-based consensus taxonomy classifier</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 feature-classifier classify-consensus-vsearch 9 qiime feature-classifier classify-consensus-vsearch
9 10
10 --i-query=$iquery 11 --i-query=$iquery
12
11 --i-reference-reads=$ireferencereads 13 --i-reference-reads=$ireferencereads
12 14
15 --i-reference-taxonomy=$ireferencetaxonomy
13 16
14 #if str( $id_to_taxonomy_fp.selector ) == 'history' 17 #if str($pmaxaccepts) != 'None':
15 #set $tax = $id_to_taxonomy_fp.taxonomy_fp 18 --p-maxaccepts=$pmaxaccepts
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 19 #end if
21 20
21 --p-perc-identity=$ppercidentity
22 22
23 #if $psearchexact: 23 --p-query-cov=$pquerycov
24 --p-search-exact 24
25 #if str($pstrand) != 'None':
26 --p-strand=$pstrand
25 #end if 27 #end if
26 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
27 37
28 #if $ptophitsonly: 38 #if $ptophitsonly:
29 --p-top-hits-only 39 --p-top-hits-only
30 #end if 40 #end if
31 41
32 42 #if str($pmaxhits) != 'None':
33 43 --p-maxhits=$pmaxhits
34 #if str($pmaxaccepts):
35 --p-maxaccepts=$pmaxaccepts
36 #end if 44 #end if
37 45
38 #if str($ppercidentity): 46 #if str($pmaxrejects) != 'None':
39 --p-perc-identity=$ppercidentity 47 --p-maxrejects=$pmaxrejects
40 #end if 48 #end if
41 49
42 #if str($pquerycov): 50 #if $pnooutputnohits:
43 --p-query-cov=$pquerycov 51 --p-no-output-no-hits
44 #end if 52 #end if
45 53
46 #if str($pstrand) != 'None': 54 --p-weak-id=$pweakid
47 --p-strand=$pstrand
48 #end if
49 55
50 #if str($pminconsensus): 56 --p-threads=$pthreads
51 --p-min-consensus=$pminconsensus
52 #end if
53
54
55
56
57
58 #if '__sq__' in str($punassignablelabel):
59 #set $punassignablelabel_temp = $punassignablelabel.replace('__sq__', "'")
60 #set $punassignablelabel = $punassignablelabel_temp
61 #end if
62
63 #if str($punassignablelabel):
64 --p-unassignable-label="$punassignablelabel"
65 #end if
66
67
68
69
70 #set $pthreads = '${GALAXY_SLOTS:-4}'
71 #if str($pthreads):
72 --p-threads="$pthreads"
73 #end if
74 57
75 --o-classification=oclassification 58 --o-classification=oclassification
76 59
60 #if str($examples) != 'None':
61 --examples=$examples
62 #end if
63
77 ; 64 ;
78 cp oclassification.qza $oclassification 65 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 66
84 <conditional name="id_to_taxonomy_fp" optional="True"> 67 ]]></command>
85 <param name="selector" type="select" label="Reference taxonomy to query"> 68 <inputs>
86 <option value="cached">Public databases</option> 69 <param format="qza,no_unzip.zip" label="--i-query: ARTIFACT FeatureData[Sequence] Sequences to classify taxonomically. [required]" name="iquery" optional="False" type="data" />
87 <option value="history">Databases from your history</option> 70 <param format="qza,no_unzip.zip" label="--i-reference-reads: ARTIFACT FeatureData[Sequence] reference sequences. [required]" name="ireferencereads" optional="False" type="data" />
88 </param> 71 <param format="qza,no_unzip.zip" label="--i-reference-taxonomy: ARTIFACT FeatureData[Taxonomy] reference taxonomy labels. [required]" name="ireferencetaxonomy" optional="False" type="data" />
89 <when value="cached"> 72 <param label="--p-maxaccepts: " name="pmaxaccepts" optional="True" type="select">
90 <param argument="--taxonomy_fp" label="Reference taxonomy" type="select" optional="True"> 73 <option selected="True" value="None">Selection is Optional</option>
91 <options from_data_table="qiime_taxonomy" /> 74 <option value="Int % Range(1">Int % Range(1</option>
92 </param> 75 <option value="None">None</option>
93 </when> 76 </param>
94 <when value="history"> 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" />
95 <param argument="--taxonomy_fp" type="data" format="qza,no_unzip.zip" label="Reference databases" optional="True" /> 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" />
96 </when> 79 <param label="--p-strand: " name="pstrand" optional="True" type="select">
97 </conditional> 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>
98 103
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"/> 104 <outputs>
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"/> 105 <data format="qza" label="${tool.name} on ${on_string}: classification.qza" name="oclassification" />
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"/> 106
102 <param label="--p-strand: Align against reference sequences in forward ('plus') or both directions ('both'). [default: 'both']" name="pstrand" optional="True" type="select"> 107 </outputs>
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"/>
108 <param label="--p-unassignable-label: TEXT [default: 'Unassigned']" name="punassignablelabel" optional="True" type="text" value="Unassigned"/>
109 108
110 109 <help><![CDATA[
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
114 </inputs>
115 <outputs>
116 <data format="qza" label="${tool.name} on ${on_string}: classification.qza" name="oclassification"/>
117 </outputs>
118 <help><![CDATA[
119 VSEARCH-based consensus taxonomy classifier 110 VSEARCH-based consensus taxonomy classifier
111 ###############################################################
120 112
121 Assign taxonomy to query sequences using VSEARCH. Performs VSEARCH global 113 Assign taxonomy to query sequences using VSEARCH. Performs VSEARCH global
122 alignment between query and reference_reads, then assigns consensus 114 alignment between query and reference_reads, then assigns consensus
123 taxonomy to each query sequence from among maxaccepts top hits, 115 taxonomy to each query sequence from among maxaccepts top hits,
124 min_consensus of which share that taxonomic assignment. Unlike classify- 116 min_consensus of which share that taxonomic assignment. Unlike classify-
133 reference sequences. 125 reference sequences.
134 reference_taxonomy : FeatureData[Taxonomy] 126 reference_taxonomy : FeatureData[Taxonomy]
135 reference taxonomy labels. 127 reference taxonomy labels.
136 maxaccepts : Int % Range(1, None) | Str % Choices('all'), optional 128 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 129 Maximum number of hits to keep for each query. Set to "all" to keep all
138 hits > perc_identity similarity. 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.
139 perc_identity : Float % Range(0.0, 1.0, inclusive_end=True), optional 142 perc_identity : Float % Range(0.0, 1.0, inclusive_end=True), optional
140 Reject match if percent identity to query is lower. 143 Reject match if percent identity to query is lower.
141 query_cov : Float % Range(0.0, 1.0, inclusive_end=True), optional 144 query_cov : Float % Range(0.0, 1.0, inclusive_end=True), optional
142 Reject match if query alignment coverage per high-scoring pair is 145 Reject match if query alignment coverage per high-scoring pair is
143 lower. 146 lower.
157 top_hits_only : Bool, optional 160 top_hits_only : Bool, optional
158 Only the top hits between the query and reference sequence sets are 161 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 162 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 163 percentage of identity. Multiple equally scored top hits will be used
161 for consensus taxonomic assignment if maxaccepts is greater than 1. 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.
162 threads : Int % Range(1, None), optional 185 threads : Int % Range(1, None), optional
163 Number of threads to use for job parallelization. 186 Number of threads to use for job parallelization.
164 187
165 Returns 188 Returns
166 ------- 189 -------
167 classification : FeatureData[Taxonomy] 190 classification : FeatureData[Taxonomy]
168 The resulting taxonomy classifications. 191 The resulting taxonomy classifications.
169 ]]></help> 192 ]]></help>
170 <macros> 193 <macros>
171 <import>qiime_citation.xml</import> 194 <import>qiime_citation.xml</import>
172 </macros> 195 </macros>
173 <expand macro="qiime_citation"/> 196 <expand macro="qiime_citation"/>
174 </tool> 197 </tool>