annotate qiime2/qiime_feature-classifier_classify-consensus-vsearch.xml @ 15:276ec629f09a draft

Uploaded

<?xml version="1.0" ?>
<tool id="qiime_feature-classifier_classify-consensus-vsearch" name="qiime feature-classifier classify-consensus-vsearch"
      version="2020.8">
  <description>VSEARCH-based consensus taxonomy classifier</description>
  <requirements>
    <requirement type="package" version="2020.8">qiime2</requirement>
  </requirements>
  <command><![CDATA[
qiime feature-classifier classify-consensus-vsearch

--i-query=$iquery

--i-reference-reads=$ireferencereads

--i-reference-taxonomy=$ireferencetaxonomy

#if str($pmaxaccepts) != 'None':
--p-maxaccepts=$pmaxaccepts
#end if

--p-perc-identity=$ppercidentity

--p-query-cov=$pquerycov

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

--p-min-consensus=$pminconsensus

#if str($punassignablelabel):
  --p-unassignable-label=$punassignablelabel
#end if
#if $psearchexact:
 --p-search-exact
#end if

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

#if str($pmaxhits) != 'None':
--p-maxhits=$pmaxhits
#end if

#if str($pmaxrejects) != 'None':
--p-maxrejects=$pmaxrejects
#end if

#if $pnooutputnohits:
 --p-no-output-no-hits
#end if

--p-weak-id=$pweakid

--p-threads=$pthreads

--o-classification=oclassification

#if str($examples) != 'None':
--examples=$examples
#end if

;
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" />
    <param format="qza,no_unzip.zip" label="--i-reference-taxonomy: ARTIFACT FeatureData[Taxonomy] reference taxonomy labels.                [required]" name="ireferencetaxonomy" optional="False" type="data" />
    <param label="--p-maxaccepts: " name="pmaxaccepts" optional="True" type="select">
      <option selected="True" value="None">Selection is Optional</option>
      <option value="Int % Range(1">Int % Range(1</option>
      <option value="None">None</option>
    </param>
    <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" />
    <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" />
    <param label="--p-strand: " name="pstrand" optional="True" type="select">
      <option selected="True" value="None">Selection is Optional</option>
      <option value="both">both</option>
      <option value="plus">plus</option>
    </param>
    <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" />
    <param label="--p-unassignable-label: TEXT [default: \'Unassigned\']" name="punassignablelabel" optional="False" type="text" value="\'Unassigned\'" />
    <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" />
    <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" />
    <param label="--p-maxhits: " name="pmaxhits" optional="True" type="select">
      <option selected="True" value="None">Selection is Optional</option>
      <option value="Int % Range(1">Int % Range(1</option>
      <option value="None">None</option>
    </param>
    <param label="--p-maxrejects: " name="pmaxrejects" optional="True" type="select">
      <option selected="True" value="None">Selection is Optional</option>
      <option value="Int % Range(1">Int % Range(1</option>
      <option value="None">None</option>
    </param>
    <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" />
    <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" />
    <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
    
  </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. Note that if strand=both, maxaccepts
    will keep N hits for each direction (if searches in the opposite
    direction yield results that exceed the minimum perc_identity). In
    those cases use maxhits to control the total number of hits returned.
    This option works in pair with maxrejects. The search process sorts
    target sequences by decreasing number of k-mers they have in common
    with the query sequence, using that information as a proxy for sequence
    similarity. After pairwise alignments, if the first target sequence
    passes the acceptation criteria, it is accepted as best hit and the
    search process stops for that query. If maxaccepts is set to a higher
    value, more hits are accepted. If maxaccepts and maxrejects are both
    set to "all", the complete database is searched.
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.
maxhits : Int % Range(1, None) | Str % Choices('all'), optional
    Maximum number of hits to show once the search is terminated.
maxrejects : Int % Range(1, None) | Str % Choices('all'), optional
    Maximum number of non-matching target sequences to consider before
    stopping the search. This option works in pair with maxaccepts (see
    maxaccepts description for details).
output_no_hits : Bool, optional
    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.
weak_id : Float % Range(0.0, 1.0, inclusive_end=True), optional
    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.
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>