|
2
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_dada2_denoise-pyro" name="qiime dada2 denoise-pyro" version="2019.4">
|
|
|
3 <description> - Denoise and dereplicate single-end pyrosequences</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2019.4">qiime2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command><![CDATA[
|
|
|
8 qiime dada2 denoise-pyro
|
|
|
9
|
|
|
10 --i-demultiplexed-seqs=$idemultiplexedseqs
|
|
|
11 --p-trunc-len="$ptrunclen"
|
|
|
12
|
|
|
13 #if $ptrimleft:
|
|
|
14 --p-trim-left=$ptrimleft
|
|
|
15 #end if
|
|
|
16
|
|
|
17 #if $pmaxee:
|
|
|
18 --p-max-ee=$pmaxee
|
|
|
19 #end if
|
|
|
20
|
|
|
21 #if $ptruncq:
|
|
|
22 --p-trunc-q=$ptruncq
|
|
|
23 #end if
|
|
|
24
|
|
|
25 #if $pmaxlen:
|
|
|
26 --p-max-len=$pmaxlen
|
|
|
27 #end if
|
|
|
28
|
|
|
29 #if str($pchimeramethod) != 'None':
|
|
|
30 --p-chimera-method=$pchimeramethod
|
|
|
31 #end if
|
|
|
32
|
|
|
33 #if $pminfoldparentoverabundance:
|
|
|
34 --p-min-fold-parent-over-abundance=$pminfoldparentoverabundance
|
|
|
35 #end if
|
|
|
36
|
|
|
37 #set $pnthreads = '${GALAXY_SLOTS:-4}'
|
|
|
38 #if str($pnthreads):
|
|
|
39 --p-n-threads="$pnthreads"
|
|
|
40 #end if
|
|
|
41
|
|
|
42
|
|
|
43 #if $pnreadslearn:
|
|
|
44 --p-n-reads-learn=$pnreadslearn
|
|
|
45 #end if
|
|
|
46
|
|
|
47 #if $pnohashedfeatureids:
|
|
|
48 --p-no-hashed-feature-ids
|
|
|
49 #end if
|
|
|
50
|
|
|
51 --o-table=otable
|
|
|
52 --o-representative-sequences=orepresentativesequences
|
|
|
53 --o-denoising-stats=odenoisingstats
|
|
|
54 ;
|
|
|
55 cp otable.qza $otable;
|
|
|
56 cp orepresentativesequences.qza $orepresentativesequences;
|
|
|
57 cp odenoisingstats.qza $odenoisingstats
|
|
|
58 ]]></command>
|
|
|
59 <inputs>
|
|
|
60 <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"/>
|
|
|
61 <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 prov#ided, no truncation or length filtering will be performed [required]" name="ptrunclen" optional="False" value="" type="integer"/>
|
|
|
62 <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"/>
|
|
|
63 <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"/>
|
|
|
64 <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"/>
|
|
|
65 <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"/>
|
|
|
66 <param label="--p-chimera-method: 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." name="pchimeramethod" optional="True" type="select">
|
|
|
67 <option selected="True" value="None">Selection is Optional</option>
|
|
|
68 <option value="consensus">consensus</option>
|
|
|
69 <option value="pooled">pooled</option>
|
|
|
70 <option value="none">none</option>
|
|
|
71 </param>
|
|
|
72 <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"/>
|
|
|
73 <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"/>
|
|
|
74 <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"/>
|
|
|
75 </inputs>
|
|
|
76 <outputs>
|
|
|
77 <data format="qza" label="${tool.name} on ${on_string}: table.qza" name="otable"/>
|
|
|
78 <data format="qza" label="${tool.name} on ${on_string}: representativesequences.qza" name="orepresentativesequences"/>
|
|
|
79 <data format="qza" label="${tool.name} on ${on_string}: denoisingstats.qza" name="odenoisingstats"/>
|
|
|
80 </outputs>
|
|
|
81 <help><![CDATA[
|
|
|
82 Denoise and dereplicate single-end pyrosequences
|
|
|
83 ################################################
|
|
|
84
|
|
|
85 This method denoises single-end pyrosequencing sequences, dereplicates
|
|
|
86 them, and filters chimeras.
|
|
|
87
|
|
|
88 Parameters
|
|
|
89 ----------
|
|
|
90 demultiplexed_seqs : SampleData[SequencesWithQuality]
|
|
|
91 The single-end demultiplexed pyrosequencing sequences (e.g. 454,
|
|
|
92 IonTorrent) to be denoised.
|
|
|
93 trunc_len : Int
|
|
|
94 Position at which sequences should be truncated due to decrease in
|
|
|
95 quality. This truncates the 3' end of the of the input sequences, which
|
|
|
96 will be the bases that were sequenced in the last cycles. Reads that
|
|
|
97 are shorter than this value will be discarded. If 0 is provided, no
|
|
|
98 truncation or length filtering will be performed
|
|
|
99 trim_left : Int, optional
|
|
|
100 Position at which sequences should be trimmed due to low quality. This
|
|
|
101 trims the 5' end of the of the input sequences, which will be the bases
|
|
|
102 that were sequenced in the first cycles.
|
|
|
103 max_ee : Float, optional
|
|
|
104 Reads with number of expected errors higher than this value will be
|
|
|
105 discarded.
|
|
|
106 trunc_q : Int, optional
|
|
|
107 Reads are truncated at the first instance of a quality score less than
|
|
|
108 or equal to this value. If the resulting read is then shorter than
|
|
|
109 `trunc_len`, it is discarded.
|
|
|
110 max_len : Int, optional
|
|
|
111 Remove reads prior to trimming or truncation which are longer than this
|
|
|
112 value. If 0 is provided no reads will be removed based on length.
|
|
|
113 chimera_method : Str % Choices('consensus', 'pooled', 'none'), optional
|
|
|
114 The method used to remove chimeras. "none": No chimera removal is
|
|
|
115 performed. "pooled": All reads are pooled prior to chimera detection.
|
|
|
116 "consensus": Chimeras are detected in samples individually, and
|
|
|
117 sequences found chimeric in a sufficient fraction of samples are
|
|
|
118 removed.
|
|
|
119 min_fold_parent_over_abundance : Float, optional
|
|
|
120 The minimum abundance of potential parents of a sequence being tested
|
|
|
121 as chimeric, expressed as a fold-change versus the abundance of the
|
|
|
122 sequence being tested. Values should be greater than or equal to 1
|
|
|
123 (i.e. parents should be more abundant than the sequence being tested).
|
|
|
124 This parameter has no effect if chimera_method is "none".
|
|
|
125 n_reads_learn : Int, optional
|
|
|
126 The number of reads to use when training the error model. Smaller
|
|
|
127 numbers will result in a shorter run time but a less reliable error
|
|
|
128 model.
|
|
|
129 hashed_feature_ids : Bool, optional
|
|
|
130 If true, the feature ids in the resulting table will be presented as
|
|
|
131 hashes of the sequences defining each feature. The hash will always be
|
|
|
132 the same for the same sequence so this allows feature tables to be
|
|
|
133 merged across runs of this method. You should only merge tables if the
|
|
|
134 exact same parameters are used for each run.
|
|
|
135
|
|
|
136 Returns
|
|
|
137 -------
|
|
|
138 table : FeatureTable[Frequency]
|
|
|
139 The resulting feature table.
|
|
|
140 representative_sequences : FeatureData[Sequence]
|
|
|
141 The resulting feature sequences. Each feature in the feature table will
|
|
|
142 be represented by exactly one sequence.
|
|
|
143 denoising_stats : SampleData[DADA2Stats]
|
|
|
144 ]]></help>
|
|
|
145 <macros>
|
|
|
146 <import>qiime_citation.xml</import>
|
|
|
147 </macros>
|
|
|
148 <expand macro="qiime_citation"/>
|
|
|
149 </tool>
|
