|
0
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_dada2_denoise-pyro" name="qiime dada2 denoise-pyro"
|
|
|
3 version="2020.8">
|
|
|
4 <description>Denoise and dereplicate single-end pyrosequences</description>
|
|
|
5 <requirements>
|
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command><![CDATA[
|
|
|
9 qiime dada2 denoise-pyro
|
|
|
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=$ptruncq
|
|
|
20
|
|
|
21 --p-max-len=$pmaxlen
|
|
|
22
|
|
|
23 #if str($ppoolingmethod) != 'None':
|
|
|
24 --p-pooling-method=$ppoolingmethod
|
|
|
25 #end if
|
|
|
26
|
|
|
27 #if str($pchimeramethod) != 'None':
|
|
|
28 --p-chimera-method=$pchimeramethod
|
|
|
29 #end if
|
|
|
30
|
|
|
31 --p-min-fold-parent-over-abundance=$pminfoldparentoverabundance
|
|
|
32
|
|
|
33 --p-n-threads=$pnthreads
|
|
|
34
|
|
|
35 --p-n-reads-learn=$pnreadslearn
|
|
|
36
|
|
|
37 #if $pnohashedfeatureids:
|
|
|
38 --p-no-hashed-feature-ids
|
|
|
39 #end if
|
|
|
40
|
|
|
41 --o-table=otable
|
|
|
42
|
|
|
43 --o-representative-sequences=orepresentativesequences
|
|
|
44
|
|
|
45 --o-denoising-stats=odenoisingstats
|
|
|
46
|
|
|
47 #if str($examples) != 'None':
|
|
|
48 --examples=$examples
|
|
|
49 #end if
|
|
|
50
|
|
|
51 ;
|
|
|
52 cp odenoisingstats.qza $odenoisingstats
|
|
|
53
|
|
|
54 ]]></command>
|
|
|
55 <inputs>
|
|
|
56 <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" />
|
|
|
57 <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" />
|
|
|
58 <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" />
|
|
|
59 <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" />
|
|
|
60 <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" />
|
|
|
61 <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" />
|
|
|
62 <param label="--p-pooling-method: " name="ppoolingmethod" optional="True" type="select">
|
|
|
63 <option selected="True" value="None">Selection is Optional</option>
|
|
|
64 <option value="independent">independent</option>
|
|
|
65 <option value="pseudo">pseudo</option>
|
|
|
66 </param>
|
|
|
67 <param label="--p-chimera-method: " name="pchimeramethod" optional="True" type="select">
|
|
|
68 <option selected="True" value="None">Selection is Optional</option>
|
|
|
69 <option value="none">none</option>
|
|
|
70 <option value="consensus">consensus</option>
|
|
|
71 <option value="pooled">pooled</option>
|
|
|
72 </param>
|
|
|
73 <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" />
|
|
|
74 <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" />
|
|
|
75 <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" />
|
|
|
76 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
|
77
|
|
|
78 </inputs>
|
|
|
79
|
|
|
80 <outputs>
|
|
|
81 <data format="qza" label="${tool.name} on ${on_string}: table.qza" name="otable" />
|
|
|
82 <data format="qza" label="${tool.name} on ${on_string}: representativesequences.qza" name="orepresentativesequences" />
|
|
|
83 <data format="qza" label="${tool.name} on ${on_string}: denoisingstats.qza" name="odenoisingstats" />
|
|
|
84
|
|
|
85 </outputs>
|
|
|
86
|
|
|
87 <help><![CDATA[
|
|
|
88 Denoise and dereplicate single-end pyrosequences
|
|
|
89 ###############################################################
|
|
|
90
|
|
|
91 This method denoises single-end pyrosequencing sequences, dereplicates
|
|
|
92 them, and filters chimeras.
|
|
|
93
|
|
|
94 Parameters
|
|
|
95 ----------
|
|
|
96 demultiplexed_seqs : SampleData[SequencesWithQuality]
|
|
|
97 The single-end demultiplexed pyrosequencing sequences (e.g. 454,
|
|
|
98 IonTorrent) to be denoised.
|
|
|
99 trunc_len : Int
|
|
|
100 Position at which sequences should be truncated due to decrease in
|
|
|
101 quality. This truncates the 3' end of the of the input sequences, which
|
|
|
102 will be the bases that were sequenced in the last cycles. Reads that
|
|
|
103 are shorter than this value will be discarded. If 0 is provided, no
|
|
|
104 truncation or length filtering will be performed
|
|
|
105 trim_left : Int, optional
|
|
|
106 Position at which sequences should be trimmed due to low quality. This
|
|
|
107 trims the 5' end of the of the input sequences, which will be the bases
|
|
|
108 that were sequenced in the first cycles.
|
|
|
109 max_ee : Float, optional
|
|
|
110 Reads with number of expected errors higher than this value will be
|
|
|
111 discarded.
|
|
|
112 trunc_q : Int, optional
|
|
|
113 Reads are truncated at the first instance of a quality score less than
|
|
|
114 or equal to this value. If the resulting read is then shorter than
|
|
|
115 `trunc_len`, it is discarded.
|
|
|
116 max_len : Int, optional
|
|
|
117 Remove reads prior to trimming or truncation which are longer than this
|
|
|
118 value. If 0 is provided no reads will be removed based on length.
|
|
|
119 pooling_method : Str % Choices('independent', 'pseudo'), optional
|
|
|
120 The method used to pool samples for denoising. "independent": Samples
|
|
|
121 are denoised indpendently. "pseudo": The pseudo-pooling method is used
|
|
|
122 to approximate pooling of samples. In short, samples are denoised
|
|
|
123 independently once, ASVs detected in at least 2 samples are recorded,
|
|
|
124 and samples are denoised independently a second time, but this time
|
|
|
125 with prior knowledge of the recorded ASVs and thus higher sensitivity
|
|
|
126 to those ASVs.
|
|
|
127 chimera_method : Str % Choices('consensus', 'none', 'pooled'), optional
|
|
|
128 The method used to remove chimeras. "none": No chimera removal is
|
|
|
129 performed. "pooled": All reads are pooled prior to chimera detection.
|
|
|
130 "consensus": Chimeras are detected in samples individually, and
|
|
|
131 sequences found chimeric in a sufficient fraction of samples are
|
|
|
132 removed.
|
|
|
133 min_fold_parent_over_abundance : Float, optional
|
|
|
134 The minimum abundance of potential parents of a sequence being tested
|
|
|
135 as chimeric, expressed as a fold-change versus the abundance of the
|
|
|
136 sequence being tested. Values should be greater than or equal to 1
|
|
|
137 (i.e. parents should be more abundant than the sequence being tested).
|
|
|
138 This parameter has no effect if chimera_method is "none".
|
|
|
139 n_threads : Int, optional
|
|
|
140 The number of threads to use for multithreaded processing. If 0 is
|
|
|
141 provided, all available cores will be used.
|
|
|
142 n_reads_learn : Int, optional
|
|
|
143 The number of reads to use when training the error model. Smaller
|
|
|
144 numbers will result in a shorter run time but a less reliable error
|
|
|
145 model.
|
|
|
146 hashed_feature_ids : Bool, optional
|
|
|
147 If true, the feature ids in the resulting table will be presented as
|
|
|
148 hashes of the sequences defining each feature. The hash will always be
|
|
|
149 the same for the same sequence so this allows feature tables to be
|
|
|
150 merged across runs of this method. You should only merge tables if the
|
|
|
151 exact same parameters are used for each run.
|
|
|
152
|
|
|
153 Returns
|
|
|
154 -------
|
|
|
155 table : FeatureTable[Frequency]
|
|
|
156 The resulting feature table.
|
|
|
157 representative_sequences : FeatureData[Sequence]
|
|
|
158 The resulting feature sequences. Each feature in the feature table will
|
|
|
159 be represented by exactly one sequence.
|
|
|
160 denoising_stats : SampleData[DADA2Stats]
|
|
|
161 ]]></help>
|
|
|
162 <macros>
|
|
|
163 <import>qiime_citation.xml</import>
|
|
|
164 </macros>
|
|
|
165 <expand macro="qiime_citation"/>
|
|
|
166 </tool> |
