view qiime2/qiime_dada2_denoise-paired.xml @ 7:85b520815e85 draft

Uploaded
author florianbegusch
date Tue, 13 Aug 2019 07:53:59 -0400
parents de4c22a52df4
children f190567fe3f6
line wrap: on
line source

<?xml version="1.0" ?>
<tool id="qiime_dada2_denoise-paired" name="qiime dada2 denoise-paired" version="2019.4">
	<description> - Denoise and dereplicate paired-end sequences</description>
	<requirements>
		<requirement type="package" version="2019.4">qiime2</requirement>
	</requirements>
	<command><![CDATA[

#def parse_file(file):
	#import csv
	#set $read = csv.reader(open($file, "r"))
	#set $qc = 0
	#for l in $read:
	#if "50%" in l:
	#set $num = 0.0
	#for i in l[1:]:
	#if float(i) <= 25.0
	#set $num = i
	#set $qc = l.index($num) - 1
	#break
	#end if
	#end for
	#end if
#end for
#return $qc
#end def

#def find_QC(file):
	#set $f_file_path=str(file).split(".dat")[0] + '_files/forward-seven-number-summaries.csv'
	#set $r_file_path=str(file).split(".dat")[0] + '_files/reverse-seven-number-summaries.csv'
	#set $qc_f = $parse_file($f_file_path)
	#set $qc_r = $parse_file($r_file_path)
	#return $qc_f, $qc_r
#end def

#def find_adapters(mapping_fp):
	#import csv
	#set $forward = 0
	#set $reversed = 0
	#set $reader = csv.reader(open(str(mapping_fp)), delimiter='\t')
	#for row in $reader:
	#if "#" not in str(row[0]):
	#set $forward = len(row[2])
	#set $reversed = len(row[3])
	#break
	#end if
	#end for
#return int($forward), int($reversed)
#end def

#if str($mapping_fp) != 'None' and (int($ptrimleftf) == -1 or int($ptrimleftr) == -1):
	#set $both_adapters = $find_adapters($mapping_fp)
	#set $ptrimleftf=$both_adapters[0]
	#set $ptrimleftr=$both_adapters[1]
#end if

#if str($sum_fp) != 'None' and (int($ptrunclenf) == -1 or int($ptrunclenr) == -1):
	#set $both_qc = $find_QC($sum_fp)
	#set $ptrunclenf=$both_qc[0]
	#set $ptrunclenr=$both_qc[1]
#end if


qiime dada2 denoise-paired

--i-demultiplexed-seqs=$idemultiplexedseqs


#if str($ptrunclenf):
 --p-trunc-len-f="$ptrunclenf"
#end if

#if str($ptrunclenf):
 --p-trunc-len-r="$ptrunclenr"
#end if

#if str($ptrimleftf):
 --p-trim-left-f=$ptrimleftf
#end if

#if str($ptrimleftr):
 --p-trim-left-r=$ptrimleftr
#end if

#if str($pmaxee):
 --p-max-ee=$pmaxee
#end if

#if str($ptruncq):
 --p-trunc-q=$ptruncq
#end if

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

#if str($pminfoldparentoverabundance):
 --p-min-fold-parent-over-abundance=$pminfoldparentoverabundance
#end if

#set $pnthreads = '${GALAXY_SLOTS:-4}'

#if str($pnthreads):
 --p-n-threads="$pnthreads"
#end if


#if str($pnreadslearn):
 --p-n-reads-learn=$pnreadslearn
#end if

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

--o-table=otable
--o-representative-sequences=orepresentativesequences
--o-denoising-stats=odenoisingstats
;
cp otable.qza $otable;
cp orepresentativesequences.qza $orepresentativesequences;
cp odenoisingstats.qza $odenoisingstats
	]]></command>
	<inputs>
		<param format="tabular" label="Mapping file where 3rd and 4th columns must be forward and reverse primers respectively" name="mapping_fp" optional="True" type="data"/>
		<param format="html" label="Summary file" name="sum_fp" optional="True" type="data"/>

		<param format="qza,no_unzip.zip" label="--i-demultiplexed-seqs: ARTIFACT SampleData[PairedEndSequencesWithQuality] The paired-end demultiplexed sequences to be denoised.                                  [required]" name="idemultiplexedseqs" optional="False" type="data"/>
		<param label="--p-trunc-len-f: INTEGER Position at which forward read 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. After this parameter is applied there must still be at least a 20 nucleotide overlap between the forward and reverse reads. If 0 is provided, no truncation or length filtering will be performed [required]" name="ptrunclenf" optional="False" value="" type="integer"/>
		<param label="--p-trunc-len-r: INTEGER Position at which reverse read 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. After this parameter is applied there must still be at least a 20 nucleotide overlap between the forward and reverse reads. If 0 is provided, no truncation or length filtering will be performed [required]" name="ptrunclenr" optional="False" value="" type="integer"/>
		<param label="--p-trim-left-f: INTEGER Position at which forward read sequences should be trimmed due to low quality. This trims the 5' end of the input sequences, which will be the bases that were sequenced in the first cycles.      [default: 0]" name="ptrimleftf" optional="True" type="integer" value="0"/>
		<param label="--p-trim-left-r: INTEGER Position at which reverse read sequences should be trimmed due to low quality. This trims the 5' end of the input sequences, which will be the bases that were sequenced in the first cycles.      [default: 0]" name="ptrimleftr" 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-f` or `trunc-len-r` (depending on the direction of the read) it is discarded.                   [default: 2]" name="ptruncq" optional="True" type="integer" value="2"/>
		<param label="--p-chimera-method: " name="pchimeramethod" optional="True" type="select">
			<option selected="True" value="None">Selection is Optional</option>
			<option value="consensus">consensus</option>
			<option value="pooled">pooled</option>
			<option value="none">none</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: 1000000]" name="pnreadslearn" optional="True" type="integer" value="1000000"/>
		<param label="--p-no-hashed-feature-ids: If false, 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: False]" name="pnohashedfeatureids" selected="False" type="boolean"/>
	</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 paired-end sequences
############################################

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

Parameters
----------
demultiplexed_seqs : SampleData[PairedEndSequencesWithQuality]
    The paired-end demultiplexed sequences to be denoised.
trunc_len_f : Int
    Position at which forward read 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. After
    this parameter is applied there must still be at least a 20 nucleotide
    overlap between the forward and reverse reads. If 0 is provided, no
    truncation or length filtering will be performed
trunc_len_r : Int
    Position at which reverse read 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. After
    this parameter is applied there must still be at least a 20 nucleotide
    overlap between the forward and reverse reads. If 0 is provided, no
    truncation or length filtering will be performed
trim_left_f : Int, optional
    Position at which forward read sequences should be trimmed due to low
    quality. This trims the 5' end of the input sequences, which will be
    the bases that were sequenced in the first cycles.
trim_left_r : Int, optional
    Position at which reverse read sequences should be trimmed due to low
    quality. This trims the 5' end 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_f` or `trunc_len_r` (depending on the direction of the read)
    it is discarded.
chimera_method : Str % Choices('consensus', 'pooled', 'none'), 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".
    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, and these sequences will be the
    joined paired-end sequences.
denoising_stats : SampleData[DADA2Stats]
	]]></help>
<macros>
    <import>qiime_citation.xml</import>
</macros>
<expand macro="qiime_citation"/>
</tool>