view qiime2/qiime_quality-control_exclude-seqs.xml @ 15:276ec629f09a draft

Uploaded
author florianbegusch
date Thu, 03 Sep 2020 09:56:05 +0000
parents a0a8d77a991c
children
line wrap: on
line source

<?xml version="1.0" ?>
<tool id="qiime_quality-control_exclude-seqs" name="qiime quality-control exclude-seqs"
      version="2020.8">
  <description>Exclude sequences by alignment</description>
  <requirements>
    <requirement type="package" version="2020.8">qiime2</requirement>
  </requirements>
  <command><![CDATA[
qiime quality-control exclude-seqs

--i-query-sequences=$iquerysequences

--i-reference-sequences=$ireferencesequences

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

--p-perc-identity=$ppercidentity

#if str($pevalue):
  --p-evalue=$pevalue
#end if
--p-perc-query-aligned=$ppercqueryaligned

--p-threads=$pthreads

#if str($pleftjustify) != 'None':
--p-left-justify=$pleftjustify
#end if

--o-sequence-hits=osequencehits

--o-sequence-misses=osequencemisses

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

;
cp osequencemisses.qza $osequencemisses

  ]]></command>
  <inputs>
    <param format="qza,no_unzip.zip" label="--i-query-sequences: ARTIFACT FeatureData[Sequence] Sequences to test for exclusion           [required]" name="iquerysequences" optional="False" type="data" />
    <param format="qza,no_unzip.zip" label="--i-reference-sequences: ARTIFACT FeatureData[Sequence] Reference sequences to align against feature sequences                                 [required]" name="ireferencesequences" optional="False" type="data" />
    <param label="--p-method: " name="pmethod" optional="True" type="select">
      <option selected="True" value="None">Selection is Optional</option>
      <option value="blast">blast</option>
      <option value="blastn-short">blastn-short</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 reference is lower. Must be in range [0.0, 1.0]   [default: 0.97]" max="1.0" min="0.0" name="ppercidentity" optional="True" type="float" value="0.97" />
    <param label="--p-evalue: NUMBER       BLAST expectation (E) value threshold for saving hits. Reject if E value is higher than threshold. This threshold is disabled by default.    [optional]" name="pevalue" optional="False" type="text" />
    <param label="--p-perc-query-aligned: NUMBER Percent of query sequence that must align to reference in order to be accepted as a hit. [default: 0.97]" name="ppercqueryaligned" optional="True" type="float" value="0.97" />
    <param label="--p-left-justify: " name="pleftjustify" optional="True" type="select">
      <option selected="True" value="None">Selection is Optional</option>
      <option value="False">False</option>
    </param>
    <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
    
  </inputs>

  <outputs>
    <data format="qza" label="${tool.name} on ${on_string}: sequencehits.qza" name="osequencehits" />
    <data format="qza" label="${tool.name} on ${on_string}: sequencemisses.qza" name="osequencemisses" />
    
  </outputs>

  <help><![CDATA[
Exclude sequences by alignment
###############################################################

This method aligns feature sequences to a set of reference sequences to
identify sequences that hit/miss the reference within a specified
perc_identity, evalue, and perc_query_aligned. This method could be used to
define a positive filter, e.g., extract only feature sequences that align
to a certain clade of bacteria; or to define a negative filter, e.g.,
identify sequences that align to contaminant or human DNA sequences that
should be excluded from subsequent analyses. Note that filtering is
performed based on the perc_identity, perc_query_aligned, and evalue
thresholds (the latter only if method==BLAST and an evalue is set). Set
perc_identity==0 and/or perc_query_aligned==0 to disable these filtering
thresholds as necessary.

Parameters
----------
query_sequences : FeatureData[Sequence]
    Sequences to test for exclusion
reference_sequences : FeatureData[Sequence]
    Reference sequences to align against feature sequences
method : Str % Choices('blast', 'blastn-short')¹ | Str % Choices('vsearch')², optional
    Alignment method to use for matching feature sequences against
    reference sequences
perc_identity : Float % Range(0.0, 1.0, inclusive_end=True), optional
    Reject match if percent identity to reference is lower. Must be in
    range [0.0, 1.0]
evalue : Float, optional
    BLAST expectation (E) value threshold for saving hits. Reject if E
    value is higher than threshold. This threshold is disabled by default.
perc_query_aligned : Float, optional
    Percent of query sequence that must align to reference in order to be
    accepted as a hit.
threads : Int % Range(1, None), optional
    Number of jobs to execute. Only applies to vsearch method.
left_justify : Bool % Choices(False)¹ | Bool², optional
    Reject match if the pairwise alignment begins with gaps

Returns
-------
sequence_hits : FeatureData[Sequence]
    Subset of feature sequences that align to reference sequences
sequence_misses : FeatureData[Sequence]
    Subset of feature sequences that do not align to reference sequences
  ]]></help>
  <macros>
    <import>qiime_citation.xml</import>
  </macros>
  <expand macro="qiime_citation"/>
</tool>