<?xml version="1.0" ?>
<tool id="qiime_vsearch_cluster-features-de-novo" name="qiime vsearch cluster-features-de-novo"
      version="2020.8">
  <description>De novo clustering of features.</description>
  <requirements>
    <requirement type="package" version="2020.8">qiime2</requirement>
  </requirements>
  <command><![CDATA[
qiime vsearch cluster-features-de-novo

--i-sequences=$isequences

--i-table=$itable

--p-perc-identity=$ppercidentity

--p-threads=$pthreads

--o-clustered-table=oclusteredtable

--o-clustered-sequences=oclusteredsequences

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

;
cp oclusteredsequences.qza $oclusteredsequences

  ]]></command>
  <inputs>
    <param format="qza,no_unzip.zip" label="--i-sequences: ARTIFACT FeatureData[Sequence] The sequences corresponding to the features in table.                                    [required]" name="isequences" optional="False" type="data" />
    <param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency] The feature table to be clustered.        [required]" name="itable" optional="False" type="data" />
    <param label="--p-perc-identity: PROPORTION Range(0, 1, inclusive_start=False, inclusive_end=True)   The percent identity at which clustering should be performed. This parameter maps to vsearch\'s --id parameter.                                [required]" name="ppercidentity" optional="False" type="text" />
    <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
    
  </inputs>

  <outputs>
    <data format="qza" label="${tool.name} on ${on_string}: clusteredtable.qza" name="oclusteredtable" />
    <data format="qza" label="${tool.name} on ${on_string}: clusteredsequences.qza" name="oclusteredsequences" />
    
  </outputs>

  <help><![CDATA[
De novo clustering of features.
###############################################################

Given a feature table and the associated feature sequences, cluster the
features based on user-specified percent identity threshold of their
sequences. This is not a general-purpose de novo clustering method, but
rather is intended to be used for clustering the results of quality-
filtering/dereplication methods, such as DADA2, or for re-clustering a
FeatureTable at a lower percent identity than it was originally clustered
at. When a group of features in the input table are clustered into a single
feature, the frequency of that single feature in a given sample is the sum
of the frequencies of the features that were clustered in that sample.
Feature identifiers and sequences will be inherited from the centroid
feature of each cluster. See the vsearch documentation for details on how
sequence clustering is performed.

Parameters
----------
sequences : FeatureData[Sequence]
    The sequences corresponding to the features in table.
table : FeatureTable[Frequency]
    The feature table to be clustered.
perc_identity : Float % Range(0, 1, inclusive_start=False, inclusive_end=True)
    The percent identity at which clustering should be performed. This
    parameter maps to vsearch's --id parameter.
threads : Int % Range(0, 256, inclusive_end=True), optional
    The number of threads to use for computation. Passing 0 will launch one
    thread per CPU core.

Returns
-------
clustered_table : FeatureTable[Frequency]
    The table following clustering of features.
clustered_sequences : FeatureData[Sequence]
    Sequences representing clustered features.
  ]]></help>
  <macros>
    <import>qiime_citation.xml</import>
  </macros>
  <expand macro="qiime_citation"/>
</tool>