|
20
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_dada2_denoise-single" name="qiime dada2 denoise-single"
|
|
|
3 version="2020.8">
|
|
|
4 <description>Denoise and dereplicate single-end sequences</description>
|
|
|
5 <requirements>
|
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command><![CDATA[
|
|
|
9 qiime dada2 denoise-single
|
|
|
10
|
|
|
11 --i-demultiplexed-seqs=$idemultiplexedseqs
|
|
|
12
|
|
|
13 --p-trunc-len=$ptrunclen
|
|
|
14
|
|
|
15 --p-trim-left=$ptrimleft
|
|
|
16
|
|
|
17 --p-max-ee=$pmaxee
|
|
|
18
|
|
|
19 --p-trunc-q=$ptruncq
|
|
|
20
|
|
|
21 #if str($ppoolingmethod) != 'None':
|
|
|
22 --p-pooling-method=$ppoolingmethod
|
|
|
23 #end if
|
|
|
24
|
|
|
25 #if str($pchimeramethod) != 'None':
|
|
|
26 --p-chimera-method=$pchimeramethod
|
|
|
27 #end if
|
|
|
28
|
|
|
29 --p-min-fold-parent-over-abundance=$pminfoldparentoverabundance
|
|
|
30
|
|
|
31 --p-n-threads=$pnthreads
|
|
|
32
|
|
|
33 --p-n-reads-learn=$pnreadslearn
|
|
|
34
|
|
|
35 #if $pnohashedfeatureids:
|
|
|
36 --p-no-hashed-feature-ids
|
|
|
37 #end if
|
|
|
38
|
|
|
39 --o-table=otable
|
|
|
40
|
|
|
41 --o-representative-sequences=orepresentativesequences
|
|
|
42
|
|
|
43 --o-denoising-stats=odenoisingstats
|
|
|
44
|
|
|
45 #if str($examples) != 'None':
|
|
|
46 --examples=$examples
|
|
|
47 #end if
|
|
|
48
|
|
|
49 ;
|
|
|
50 cp odenoisingstats.qza $odenoisingstats
|
|
|
51
|
|
|
52 ]]></command>
|
|
|
53 <inputs>
|
|
|
54 <param format="qza,no_unzip.zip" label="--i-demultiplexed-seqs: ARTIFACT SampleData[SequencesWithQuality | PairedEndSequencesWithQuality] The single-end demultiplexed sequences to be denoised. [required]" name="idemultiplexedseqs" optional="False" type="data" />
|
|
|
55 <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 provided, no truncation or length filtering will be performed [required]" name="ptrunclen" optional="False" type="text" />
|
|
|
56 <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" />
|
|
|
57 <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" />
|
|
|
58 <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" />
|
|
|
59 <param label="--p-pooling-method: " name="ppoolingmethod" optional="True" type="select">
|
|
|
60 <option selected="True" value="None">Selection is Optional</option>
|
|
|
61 <option value="independent">independent</option>
|
|
|
62 <option value="pseudo">pseudo</option>
|
|
|
63 </param>
|
|
|
64 <param label="--p-chimera-method: " name="pchimeramethod" optional="True" type="select">
|
|
|
65 <option selected="True" value="None">Selection is Optional</option>
|
|
|
66 <option value="none">none</option>
|
|
|
67 <option value="consensus">consensus</option>
|
|
|
68 <option value="pooled">pooled</option>
|
|
|
69 </param>
|
|
|
70 <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" />
|
|
|
71 <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" />
|
|
|
72 <param label="--p-no-hashed-feature-ids: Do not 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. [default: True]" name="pnohashedfeatureids" selected="False" type="boolean" />
|
|
|
73 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
|
74
|
|
|
75 </inputs>
|
|
|
76
|
|
|
77 <outputs>
|
|
|
78 <data format="qza" label="${tool.name} on ${on_string}: table.qza" name="otable" />
|
|
|
79 <data format="qza" label="${tool.name} on ${on_string}: representativesequences.qza" name="orepresentativesequences" />
|
|
|
80 <data format="qza" label="${tool.name} on ${on_string}: denoisingstats.qza" name="odenoisingstats" />
|
|
|
81
|
|
|
82 </outputs>
|
|
|
83
|
|
|
84 <help><![CDATA[
|
|
|
85 Denoise and dereplicate single-end sequences
|
|
|
86 ###############################################################
|
|
|
87
|
|
|
88 This method denoises single-end sequences, dereplicates them, and filters
|
|
|
89 chimeras.
|
|
|
90
|
|
|
91 Parameters
|
|
|
92 ----------
|
|
|
93 demultiplexed_seqs : SampleData[SequencesWithQuality | PairedEndSequencesWithQuality]
|
|
|
94 The single-end demultiplexed sequences to be denoised.
|
|
|
95 trunc_len : Int
|
|
|
96 Position at which sequences should be truncated due to decrease in
|
|
|
97 quality. This truncates the 3' end of the of the input sequences, which
|
|
|
98 will be the bases that were sequenced in the last cycles. Reads that
|
|
|
99 are shorter than this value will be discarded. If 0 is provided, no
|
|
|
100 truncation or length filtering will be performed
|
|
|
101 trim_left : Int, optional
|
|
|
102 Position at which sequences should be trimmed due to low quality. This
|
|
|
103 trims the 5' end of the of the input sequences, which will be the bases
|
|
|
104 that were sequenced in the first cycles.
|
|
|
105 max_ee : Float, optional
|
|
|
106 Reads with number of expected errors higher than this value will be
|
|
|
107 discarded.
|
|
|
108 trunc_q : Int, optional
|
|
|
109 Reads are truncated at the first instance of a quality score less than
|
|
|
110 or equal to this value. If the resulting read is then shorter than
|
|
|
111 `trunc_len`, it is discarded.
|
|
|
112 pooling_method : Str % Choices('independent', 'pseudo'), optional
|
|
|
113 The method used to pool samples for denoising. "independent": Samples
|
|
|
114 are denoised independently. "pseudo": The pseudo-pooling method is used
|
|
|
115 to approximate pooling of samples. In short, samples are denoised
|
|
|
116 independently once, ASVs detected in at least 2 samples are recorded,
|
|
|
117 and samples are denoised independently a second time, but this time
|
|
|
118 with prior knowledge of the recorded ASVs and thus higher sensitivity
|
|
|
119 to those ASVs.
|
|
|
120 chimera_method : Str % Choices('consensus', 'none', 'pooled'), optional
|
|
|
121 The method used to remove chimeras. "none": No chimera removal is
|
|
|
122 performed. "pooled": All reads are pooled prior to chimera detection.
|
|
|
123 "consensus": Chimeras are detected in samples individually, and
|
|
|
124 sequences found chimeric in a sufficient fraction of samples are
|
|
|
125 removed.
|
|
|
126 min_fold_parent_over_abundance : Float, optional
|
|
|
127 The minimum abundance of potential parents of a sequence being tested
|
|
|
128 as chimeric, expressed as a fold-change versus the abundance of the
|
|
|
129 sequence being tested. Values should be greater than or equal to 1
|
|
|
130 (i.e. parents should be more abundant than the sequence being tested).
|
|
|
131 This parameter has no effect if chimera_method is "none".
|
|
|
132 n_threads : Int, optional
|
|
|
133 The number of threads to use for multithreaded processing. If 0 is
|
|
|
134 provided, all available cores will be used.
|
|
|
135 n_reads_learn : Int, optional
|
|
|
136 The number of reads to use when training the error model. Smaller
|
|
|
137 numbers will result in a shorter run time but a less reliable error
|
|
|
138 model.
|
|
|
139 hashed_feature_ids : Bool, optional
|
|
|
140 If true, the feature ids in the resulting table will be presented as
|
|
|
141 hashes of the sequences defining each feature. The hash will always be
|
|
|
142 the same for the same sequence so this allows feature tables to be
|
|
|
143 merged across runs of this method. You should only merge tables if the
|
|
|
144 exact same parameters are used for each run.
|
|
|
145
|
|
|
146 Returns
|
|
|
147 -------
|
|
|
148 table : FeatureTable[Frequency]
|
|
|
149 The resulting feature table.
|
|
|
150 representative_sequences : FeatureData[Sequence]
|
|
|
151 The resulting feature sequences. Each feature in the feature table will
|
|
|
152 be represented by exactly one sequence.
|
|
|
153 denoising_stats : SampleData[DADA2Stats]
|
|
|
154 ]]></help>
|
|
|
155 <macros>
|
|
|
156 <import>qiime_citation.xml</import>
|
|
|
157 </macros>
|
|
|
158 <expand macro="qiime_citation"/>
|
|
|
159 </tool> |
