Mercurial > repos > florianbegusch > qiime2_suite
view qiime2/qiime_cutadapt_trim-single.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_cutadapt_trim-single" name="qiime cutadapt trim-single" version="2020.8"> <description>Find and remove adapters in demultiplexed single-end sequences.</description> <requirements> <requirement type="package" version="2020.8">qiime2</requirement> </requirements> <command><![CDATA[ qiime cutadapt trim-single --i-demultiplexed-sequences=$idemultiplexedsequences --p-cores=$pcores #if $padapter: --p-adapter #end if #if str($pfront): --p-front=$pfront #end if #if '__ob__' in str($panywhere): #set $panywhere_temp = $panywhere.replace('__ob__', '[') #set $panywhere = $panywhere_temp #end if #if '__cb__' in str($panywhere): #set $panywhere_temp = $panywhere.replace('__cb__', ']') #set $panywhere = $panywhere_temp #end if #if 'X' in str($panywhere): #set $panywhere_temp = $panywhere.replace('X', '\\') #set $panywhere = $panywhere_temp #end if #if '__sq__' in str($panywhere): #set $panywhere_temp = $panywhere.replace('__sq__', "'") #set $panywhere = $panywhere_temp #end if #if '__db__' in str($panywhere): #set $panywhere_temp = $panywhere.replace('__db__', '"') #set $panywhere = $panywhere_temp #end if #if str($panywhere): --p-anywhere=$panywhere #end if --p-error-rate=$perrorrate #if $pnoindels: --p-no-indels #end if --p-times=$ptimes --p-overlap=$poverlap #if $pmatchreadwildcards: --p-match-read-wildcards #end if #if $pnomatchadapterwildcards: --p-no-match-adapter-wildcards #end if --p-minimum-length=$pminimumlength #if $pdiscarduntrimmed: --p-discard-untrimmed #end if --o-trimmed-sequences=otrimmedsequences #if str($examples) != 'None': --examples=$examples #end if ; cp otrimmedsequences.qza $otrimmedsequences ]]></command> <inputs> <param format="qza,no_unzip.zip" label="--i-demultiplexed-sequences: ARTIFACT SampleData[SequencesWithQuality] The single-end sequences to be trimmed. [required]" name="idemultiplexedsequences" optional="False" type="data" /> <param label="--p-adapter: --p-adapter: TEXT... Sequence of an adapter ligated to the 3\' end. The List[Str] adapter and any subsequent bases are trimmed. If a `$` is appended, the adapter is only found if it is at the end of the read. If your sequence of interest is \'framed\' by a 5\' and a 3\' adapter, use this parameter to define a \'linked\' primer - see https://cutadapt.readthedocs.io for complete details. [optional]" name="padapter" selected="False" type="boolean" /> <param label="--p-front: TEXT... Sequence of an adapter ligated to the 5\' end. The List[Str] adapter and any preceding bases are trimmed. Partial matches at the 5\' end are allowed. If a `^` character is prepended, the adapter is only found if it is at the beginning of the read. [optional]" name="pfront" optional="False" type="text" /> <param label="--p-anywhere: TEXT... Sequence of an adapter that may be ligated to the 5\' List[Str] or 3\' end. Both types of matches as described under `adapter` and `front` are allowed. If the first base of the read is part of the match, the behavior is as with `front`, otherwise as with `adapter`. This option is mostly for rescuing failed library preparations - do not use if you know which end your adapter was ligated to. [optional]" name="panywhere" optional="False" type="text" /> <param exclude_max="False" label="--p-error-rate: PROPORTION Range(0, 1, inclusive_end=True) Maximum allowed error rate. [default: 0.1]" max="1" min="0" name="perrorrate" optional="True" type="float" value="0.1" /> <param label="--p-no-indels: Do not allow insertions or deletions of bases when matching adapters. [default: True]" name="pnoindels" selected="False" type="boolean" /> <param label="--p-times: INTEGER Remove multiple occurrences of an adapter if it is Range(1, None) repeated, up to `times` times. [default: 1]" min="1" name="ptimes" optional="True" type="integer" value="1" /> <param label="--p-overlap: INTEGER Require at least `overlap` bases of overlap between Range(1, None) read and adapter for an adapter to be found. [default: 3]" min="1" name="poverlap" optional="True" type="integer" value="3" /> <param label="--p-match-read-wildcards: --p-match-read-wildcards: / --p-no-match-read-wildcards Interpret IUPAC wildcards (e.g., N) in reads. [default: False]" name="pmatchreadwildcards" selected="False" type="boolean" /> <param label="--p-no-match-adapter-wildcards: Do not interpret IUPAC wildcards (e.g., N) in adapters. [default: True]" name="pnomatchadapterwildcards" selected="False" type="boolean" /> <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]" min="1" name="pminimumlength" optional="True" type="integer" value="1" /> <param label="--p-discard-untrimmed: --p-discard-untrimmed: / --p-no-discard-untrimmed Discard reads in which no adapter was found. [default: False]" name="pdiscarduntrimmed" 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 ${on_string}: trimmedsequences.qza" name="otrimmedsequences" /> </outputs> <help><![CDATA[ Find and remove adapters in demultiplexed single-end sequences. ############################################################### Search demultiplexed single-end sequences for adapters and remove them. The parameter descriptions in this method are adapted from the official cutadapt docs - please see those docs at https://cutadapt.readthedocs.io for complete details. Parameters ---------- demultiplexed_sequences : SampleData[SequencesWithQuality] The single-end sequences to be trimmed. cores : Int % Range(1, None), optional Number of CPU cores to use. adapter : List[Str], optional Sequence of an adapter ligated to the 3' end. The adapter and any subsequent bases are trimmed. If a `$` is appended, the adapter is only found if it is at the end of the read. If your sequence of interest is "framed" by a 5' and a 3' adapter, use this parameter to define a "linked" primer - see https://cutadapt.readthedocs.io for complete details. front : List[Str], optional Sequence of an adapter ligated to the 5' end. The adapter and any preceding bases are trimmed. Partial matches at the 5' end are allowed. If a `^` character is prepended, the adapter is only found if it is at the beginning of the read. anywhere : List[Str], optional Sequence of an adapter that may be ligated to the 5' or 3' end. Both types of matches as described under `adapter` and `front` are allowed. If the first base of the read is part of the match, the behavior is as with `front`, otherwise as with `adapter`. This option is mostly for rescuing failed library preparations - do not use if you know which end your adapter was ligated to. error_rate : Float % Range(0, 1, inclusive_end=True), optional Maximum allowed error rate. indels : Bool, optional Allow insertions or deletions of bases when matching adapters. times : Int % Range(1, None), optional Remove multiple occurrences of an adapter if it is repeated, up to `times` times. overlap : Int % Range(1, None), optional Require at least `overlap` bases of overlap between read and adapter for an adapter to be found. match_read_wildcards : Bool, optional Interpret IUPAC wildcards (e.g., N) in reads. match_adapter_wildcards : Bool, optional Interpret IUPAC wildcards (e.g., N) in adapters. 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. discard_untrimmed : Bool, optional Discard reads in which no adapter was found. Returns ------- trimmed_sequences : SampleData[SequencesWithQuality] The resulting trimmed sequences. ]]></help> <macros> <import>qiime_citation.xml</import> </macros> <expand macro="qiime_citation"/> </tool>