view qiime2/qiime_feature-classifier_classify-consensus-vsearch.xml @ 9:f190567fe3f6 draft

Uploaded
author florianbegusch
date Wed, 14 Aug 2019 15:12:48 -0400
parents de4c22a52df4
children a0a8d77a991c
line wrap: on
line source

<?xml version="1.0" ?>
<tool id="qiime_feature-classifier_classify-consensus-vsearch" name="qiime feature-classifier classify-consensus-vsearch" version="2019.7">
	<description> - VSEARCH consensus taxonomy classifier</description>
	<requirements>
		<requirement type="package" version="2019.7">qiime2</requirement>
	</requirements>
	<command><![CDATA[
qiime feature-classifier classify-consensus-vsearch

--i-query=$iquery
--i-reference-reads=$ireferencereads


#if str( $id_to_taxonomy_fp.selector ) == 'history'
#set $tax = $id_to_taxonomy_fp.taxonomy_fp
--i-reference-taxonomy '$tax'
#else:
#set $tax = $id_to_taxonomy_fp.taxonomy_fp.fields.path
--i-reference-taxonomy '$tax'
#end if


#if $psearchexact:
  --p-search-exact
#end if


#if $ptophitsonly:
  --p-top-hits-only
#end if



#if str($pmaxaccepts):
 --p-maxaccepts=$pmaxaccepts
#end if

#if str($ppercidentity):
 --p-perc-identity=$ppercidentity
#end if

#if str($pquerycov):
 --p-query-cov=$pquerycov
#end if

#if str($pstrand) != 'None':
 --p-strand=$pstrand
#end if

#if str($pminconsensus):
 --p-min-consensus=$pminconsensus
#end if





#if '__sq__' in str($punassignablelabel):
  #set $punassignablelabel_temp = $punassignablelabel.replace('__sq__', "'")
  #set $punassignablelabel = $punassignablelabel_temp
#end if

#if str($punassignablelabel):
 --p-unassignable-label="$punassignablelabel"
#end if




#set $pthreads = '${GALAXY_SLOTS:-4}'
#if str($pthreads):
 --p-threads="$pthreads"
#end if

--o-classification=oclassification

;
cp oclassification.qza $oclassification
	]]></command>
	<inputs>
		<param format="qza,no_unzip.zip" label="--i-query: ARTIFACT FeatureData[Sequence] Sequences to classify taxonomically.      [required]" name="iquery" optional="False" type="data"/>
		<param format="qza,no_unzip.zip" label="--i-reference-reads: ARTIFACT FeatureData[Sequence] reference sequences.                      [required]" name="ireferencereads" optional="False" type="data"/>

		<conditional name="id_to_taxonomy_fp" optional="True">
		   <param name="selector" type="select" label="Reference taxonomy to query">
			  <option value="cached">Public databases</option>
			  <option value="history">Databases from your history</option>
		   </param>
		   <when value="cached">
			  <param argument="--taxonomy_fp" label="Reference taxonomy" type="select" optional="True">
				 <options from_data_table="qiime_taxonomy" />
			  </param>
		   </when>
		   <when value="history">
			  <param argument="--taxonomy_fp" type="data" format="qza,no_unzip.zip" label="Reference databases" optional="True" />
		   </when>
		</conditional>

		<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"/>
		<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"/>
		<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"/>
		<param label="--p-strand: Align against reference sequences in forward   ('plus') or both directions ('both').  [default: 'both']" name="pstrand" optional="True" type="select">
			<option value="None">Selection is Optional</option>
			<option selected="True" value="both">both</option>
			<option value="plus">plus</option>
		</param>
		<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"/>
		<param label="--p-unassignable-label: TEXT [default: 'Unassigned']" name="punassignablelabel" optional="True" type="text" value="Unassigned"/>


		<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"/>
		<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"/>

	</inputs>
	<outputs>
		<data format="qza" label="${tool.name} on ${on_string}: classification.qza" name="oclassification"/>
	</outputs>
	<help><![CDATA[
VSEARCH-based consensus taxonomy classifier

Assign taxonomy to query sequences using VSEARCH. Performs VSEARCH global
alignment between query and reference_reads, then assigns consensus
taxonomy to each query sequence from among maxaccepts top hits,
min_consensus of which share that taxonomic assignment. Unlike classify-
consensus-blast, this method searches the entire reference database before
choosing the top N hits, not the first N hits.

Parameters
----------
query : FeatureData[Sequence]
    Sequences to classify taxonomically.
reference_reads : FeatureData[Sequence]
    reference sequences.
reference_taxonomy : FeatureData[Taxonomy]
    reference taxonomy labels.
maxaccepts : Int % Range(1, None) | Str % Choices('all'), optional
    Maximum number of hits to keep for each query. Set to "all" to keep all
    hits > perc_identity similarity.
perc_identity : Float % Range(0.0, 1.0, inclusive_end=True), optional
    Reject match if percent identity to query is lower.
query_cov : Float % Range(0.0, 1.0, inclusive_end=True), optional
    Reject match if query alignment coverage per high-scoring pair is
    lower.
strand : Str % Choices('both', 'plus'), optional
    Align against reference sequences in forward ("plus") or both
    directions ("both").
min_consensus : Float % Range(0.5, 1.0, inclusive_start=False, inclusive_end=True), optional
    Minimum fraction of assignments must match top hit to be accepted as
    consensus assignment.
unassignable_label : Str, optional
search_exact : Bool, optional
    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.
top_hits_only : Bool, optional
    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.
threads : Int % Range(1, None), optional
    Number of threads to use for job parallelization.

Returns
-------
classification : FeatureData[Taxonomy]
    The resulting taxonomy classifications.
	]]></help>
<macros>
    <import>qiime_citation.xml</import>
</macros>
<expand macro="qiime_citation"/>
</tool>