view qiime2/qiime_cutadapt_demux-single.xml @ 10:21c7954105a9 draft

Fix
author florianbegusch
date Sun, 25 Aug 2019 10:26:27 -0400
parents f190567fe3f6
children a0a8d77a991c
line wrap: on
line source

<?xml version="1.0" ?>
<tool id="qiime_cutadapt_demux-single" name="qiime cutadapt demux-single" version="2019.7">
	<description> - Demultiplex single-end sequence data with barcodes in- sequence.</description>
	<requirements>
		<requirement type="package" version="2019.7">qiime2</requirement>
	</requirements>
	<command><![CDATA[
qiime cutadapt demux-single

--i-seqs=$iseqs


#if str($pbatchsize):
  --p-batch-size $pbatchsize
#end if

#if str($pminimumlength):
  --p-minimum-length $pminimumlength
#end if





#if $input_files_mbarcodesfile:
#def list_dict_to_string(list_dict):
#set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
#for d in list_dict[1:]:
	#set $file_list = $file_list + ' --m-barcodes-file=' + d['additional_input'].__getattr__('file_name')
#end for
#return $file_list
#end def
--m-barcodes-file=$list_dict_to_string($input_files_mbarcodesfile)
#end if



#if '__sq__' in str($mbarcodescolumn):
  #set $mbarcodescolumn_temp = $mbarcodescolumn.replace('__sq__', "'")
  #set $mbarcodescolumn = $mbarcodescolumn_temp
#end if

--m-barcodes-column="$mbarcodescolumn"



#if str($perrorrate):
 --p-error-rate=$perrorrate
#end if


--o-per-sample-sequences=opersamplesequences
--o-untrimmed-sequences=ountrimmedsequences
;

cp opersamplesequences.qza $opersamplesequences;
cp ountrimmedsequences.qza $ountrimmedsequences
	]]></command>
	<inputs>

		<param label="--p-batch-size:  INTEGER  The number of samples cutadapt demultiplexes Range(0, None) concurrently. Demultiplexing in smaller batches will yield the same result with marginal speed loss, and may solve 'too many files' errors related to sample quantity. Set to '0' to process all samples at once. [default: 0]" name="pbatchsize" optional="True" type="integer" value="0" min="0"/>
		<param label="--p-minimum-length: INTEGER  Range(1, None) Discard reads shorter than specified value. Note, the cutadapt default of 0 has been overridden, because that value produces empty sequence records.  [default: 1]" name="pminimumlength" optional="True" type="integer" value="1" min="1"/>


		<param format="qza,no_unzip.zip" label="--i-seqs: ARTIFACT MultiplexedSingleEndBarcodeInSequence The single-end sequences to be demultiplexed. [required]" name="iseqs" optional="False" type="data"/>
		<repeat name="input_files_mbarcodesfile" optional="False" title="--m-barcodes-file">
			<param label="--m-barcodes-file: Metadata file or artifact viewable as metadata. This option may be supplied multiple times to merge metadata. [required]" name="additional_input" type="data" format="tabular,qza,no_unzip.zip" />
		</repeat>
		<param label="--m-barcodes-column: COLUMN  MetadataColumn[Categorical] The sample metadata column listing the per-sample barcodes.                                 [required]" name="mbarcodescolumn" optional="False" type="text"/>
		<param label="--p-error-rate: PROPORTION Range(0, 1, inclusive_end=True) The level of error tolerance, specified as the maximum allowable error rate. The default value specified by cutadapt is 0.1 (=10%), which is greater than `demux emp-*`, which is 0.0 (=0%). [default: 0.1]" name="perrorrate" optional="True" type="float" min="0" max="1" exclude_max="False" value="0.1"/>
	</inputs>
	<outputs>
		<data format="qza" label="${tool.name} on ${on_string}: persamplesequences.qza" name="opersamplesequences"/>
		<data format="qza" label="${tool.name} on ${on_string}: untrimmedsequences.qza" name="ountrimmedsequences"/>
	</outputs>
	<help><![CDATA[
Demultiplex single-end sequence data with barcodes in-sequence.
###############################################################

Demultiplex sequence data (i.e., map barcode reads to sample ids). Barcodes
are expected to be located within the sequence data (versus the header, or
a separate barcode file).

Parameters
----------
seqs : MultiplexedSingleEndBarcodeInSequence
    The single-end sequences to be demultiplexed.
barcodes : MetadataColumn[Categorical]
    The sample metadata column listing the per-sample barcodes.
error_rate : Float % Range(0, 1, inclusive_end=True), optional
    The level of error tolerance, specified as the maximum allowable error
    rate. The default value specified by cutadapt is 0.1 (=10%), which is
    greater than `demux emp-*`, which is 0.0 (=0%).
batch_size : Int % Range(0, None), optional
    The number of samples cutadapt demultiplexes concurrently.
    Demultiplexing in smaller batches will yield the same result with
    marginal speed loss, and may solve "too many files" errors related to
    sample quantity. Set to "0" to process all samples at once.
minimum_length : Int % Range(1, None), optional
    Discard reads shorter than specified value. Note, the cutadapt default
    of 0 has been overridden, because that value produces empty sequence
    records.

Returns
-------
per_sample_sequences : SampleData[SequencesWithQuality]
    The resulting demultiplexed sequences.
untrimmed_sequences : MultiplexedSingleEndBarcodeInSequence
    The sequences that were unmatched to barcodes.
	]]></help>
<macros>
    <import>qiime_citation.xml</import>
</macros>
<expand macro="qiime_citation"/>
</tool>