<?xml version="1.0" ?>
<tool id="qiime_dada2_denoise-pyro" name="qiime dada2 denoise-pyro"
      version="2020.8">
  <description>Denoise and dereplicate single-end pyrosequences</description>
  <requirements>
    <requirement type="package" version="2020.8">qiime2</requirement>
  </requirements>
  <command><![CDATA[
qiime dada2 denoise-pyro

--i-demultiplexed-seqs=$idemultiplexedseqs

--p-trunc-len=$ptrunclen

--p-trim-left=$ptrimleft

--p-max-ee=$pmaxee

--p-trunc-q=$ptruncq

--p-max-len=$pmaxlen

#if str($ppoolingmethod) != 'None':
--p-pooling-method=$ppoolingmethod
#end if

#if str($pchimeramethod) != 'None':
--p-chimera-method=$pchimeramethod
#end if

--p-min-fold-parent-over-abundance=$pminfoldparentoverabundance

--p-n-threads=$pnthreads

--p-n-reads-learn=$pnreadslearn

#if $pnohashedfeatureids:
 --p-no-hashed-feature-ids
#end if

--o-table=otable

--o-representative-sequences=orepresentativesequences

--o-denoising-stats=odenoisingstats

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

;
cp odenoisingstats.qza $odenoisingstats

  ]]></command>
  <inputs>
    <param format="qza,no_unzip.zip" label="--i-demultiplexed-seqs: ARTIFACT SampleData[SequencesWithQuality] The single-end demultiplexed pyrosequencing sequences (e.g. 454, IonTorrent) to be denoised. [required]" name="idemultiplexedseqs" optional="False" type="data" />
    <param label="--p-trunc-len: INTEGER  Position at which sequences should be truncated due to decrease in quality. This truncates the 3\' end of the of the input sequences, which will be the bases that were sequenced in the last cycles. Reads that are shorter than this value will be discarded. If 0 is provided, no truncation or length filtering will be performed                               [required]" name="ptrunclen" optional="False" type="text" />
    <param label="--p-trim-left: INTEGER  Position at which sequences should be trimmed due to low quality. This trims the 5\' end of the of the input sequences, which will be the bases that were sequenced in the first cycles.           [default: 0]" name="ptrimleft" optional="True" type="integer" value="0" />
    <param label="--p-max-ee: NUMBER      Reads with number of expected errors higher than this value will be discarded.          [default: 2.0]" name="pmaxee" optional="True" type="float" value="2.0" />
    <param label="--p-trunc-q: INTEGER    Reads are truncated at the first instance of a quality score less than or equal to this value. If the resulting read is then shorter than `trunc-len`, it is discarded.                         [default: 2]" name="ptruncq" optional="True" type="integer" value="2" />
    <param label="--p-max-len: INTEGER    Remove reads prior to trimming or truncation which are longer than this value. If 0 is provided no reads will be removed based on length.         [default: 0]" name="pmaxlen" optional="True" type="integer" value="0" />
    <param label="--p-pooling-method: " name="ppoolingmethod" optional="True" type="select">
      <option selected="True" value="None">Selection is Optional</option>
      <option value="independent">independent</option>
      <option value="pseudo">pseudo</option>
    </param>
    <param label="--p-chimera-method: " name="pchimeramethod" optional="True" type="select">
      <option selected="True" value="None">Selection is Optional</option>
      <option value="none">none</option>
      <option value="consensus">consensus</option>
      <option value="pooled">pooled</option>
    </param>
    <param label="--p-min-fold-parent-over-abundance: NUMBER The minimum abundance of potential parents of a sequence being tested as chimeric, expressed as a fold-change versus the abundance of the sequence being tested. Values should be greater than or equal to 1 (i.e. parents should be more abundant than the sequence being tested). This parameter has no effect if chimera-method is \'none\'.           [default: 1.0]" name="pminfoldparentoverabundance" optional="True" type="float" value="1.0" />
    <param label="--p-n-reads-learn: INTEGER The number of reads to use when training the error model. Smaller numbers will result in a shorter run time but a less reliable error model. [default: 250000]" name="pnreadslearn" optional="True" type="integer" value="250000" />
    <param label="--p-no-hashed-feature-ids: Do not if true, the feature ids in the resulting table will be presented as hashes of the sequences defining each feature. The hash will always be the same for the same sequence so this allows feature tables to be merged across runs of this method. You should only merge tables if the exact same parameters are used for each run.                         [default: True]" name="pnohashedfeatureids" selected="False" type="boolean" />
    <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
    
  </inputs>

  <outputs>
    <data format="qza" label="${tool.name} on ${on_string}: table.qza" name="otable" />
    <data format="qza" label="${tool.name} on ${on_string}: representativesequences.qza" name="orepresentativesequences" />
    <data format="qza" label="${tool.name} on ${on_string}: denoisingstats.qza" name="odenoisingstats" />
    
  </outputs>

  <help><![CDATA[
Denoise and dereplicate single-end pyrosequences
###############################################################

This method denoises single-end pyrosequencing sequences, dereplicates
them, and filters chimeras.

Parameters
----------
demultiplexed_seqs : SampleData[SequencesWithQuality]
    The single-end demultiplexed pyrosequencing sequences (e.g. 454,
    IonTorrent) to be denoised.
trunc_len : Int
    Position at which sequences should be truncated due to decrease in
    quality. This truncates the 3' end of the of the input sequences, which
    will be the bases that were sequenced in the last cycles. Reads that
    are shorter than this value will be discarded. If 0 is provided, no
    truncation or length filtering will be performed
trim_left : Int, optional
    Position at which sequences should be trimmed due to low quality. This
    trims the 5' end of the of the input sequences, which will be the bases
    that were sequenced in the first cycles.
max_ee : Float, optional
    Reads with number of expected errors higher than this value will be
    discarded.
trunc_q : Int, optional
    Reads are truncated at the first instance of a quality score less than
    or equal to this value. If the resulting read is then shorter than
    `trunc_len`, it is discarded.
max_len : Int, optional
    Remove reads prior to trimming or truncation which are longer than this
    value. If 0 is provided no reads will be removed based on length.
pooling_method : Str % Choices('independent', 'pseudo'), optional
    The method used to pool samples for denoising. "independent": Samples
    are denoised indpendently. "pseudo": The pseudo-pooling method is used
    to approximate pooling of samples. In short, samples are denoised
    independently once, ASVs detected in at least 2 samples are recorded,
    and samples are denoised independently a second time, but this time
    with prior knowledge of the recorded ASVs and thus higher sensitivity
    to those ASVs.
chimera_method : Str % Choices('consensus', 'none', 'pooled'), optional
    The method used to remove chimeras. "none": No chimera removal is
    performed. "pooled": All reads are pooled prior to chimera detection.
    "consensus": Chimeras are detected in samples individually, and
    sequences found chimeric in a sufficient fraction of samples are
    removed.
min_fold_parent_over_abundance : Float, optional
    The minimum abundance of potential parents of a sequence being tested
    as chimeric, expressed as a fold-change versus the abundance of the
    sequence being tested. Values should be greater than or equal to 1
    (i.e. parents should be more abundant than the sequence being tested).
    This parameter has no effect if chimera_method is "none".
n_threads : Int, optional
    The number of threads to use for multithreaded processing. If 0 is
    provided, all available cores will be used.
n_reads_learn : Int, optional
    The number of reads to use when training the error model. Smaller
    numbers will result in a shorter run time but a less reliable error
    model.
hashed_feature_ids : Bool, optional
    If true, the feature ids in the resulting table will be presented as
    hashes of the sequences defining each feature. The hash will always be
    the same for the same sequence so this allows feature tables to be
    merged across runs of this method. You should only merge tables if the
    exact same parameters are used for each run.

Returns
-------
table : FeatureTable[Frequency]
    The resulting feature table.
representative_sequences : FeatureData[Sequence]
    The resulting feature sequences. Each feature in the feature table will
    be represented by exactly one sequence.
denoising_stats : SampleData[DADA2Stats]
  ]]></help>
  <macros>
    <import>qiime_citation.xml</import>
  </macros>
  <expand macro="qiime_citation"/>
</tool>