|
29
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_dada2_denoise-paired" name="qiime dada2 denoise-paired"
|
|
|
3 version="2020.8">
|
|
|
4 <description>Denoise and dereplicate paired-end sequences</description>
|
|
|
5 <requirements>
|
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command><![CDATA[
|
|
|
9 qiime dada2 denoise-paired
|
|
|
10
|
|
|
11 --i-demultiplexed-seqs=$idemultiplexedseqs
|
|
|
12
|
|
|
13 --p-trunc-len-f=$ptrunclenf
|
|
|
14
|
|
|
15 --p-trunc-len-r=$ptrunclenr
|
|
|
16
|
|
|
17 --p-trim-left-f=$ptrimleftf
|
|
|
18
|
|
|
19 --p-trim-left-r=$ptrimleftr
|
|
|
20
|
|
|
21 --p-max-ee-f=$pmaxeef
|
|
|
22
|
|
|
23 --p-max-ee-r=$pmaxeer
|
|
|
24
|
|
|
25 --p-trunc-q=$ptruncq
|
|
|
26
|
|
|
27 #if str($ppoolingmethod) != 'None':
|
|
|
28 --p-pooling-method=$ppoolingmethod
|
|
|
29 #end if
|
|
|
30
|
|
|
31 #if str($pchimeramethod) != 'None':
|
|
|
32 --p-chimera-method=$pchimeramethod
|
|
|
33 #end if
|
|
|
34
|
|
|
35 --p-min-fold-parent-over-abundance=$pminfoldparentoverabundance
|
|
|
36
|
|
|
37 --p-n-threads=$pnthreads
|
|
|
38
|
|
|
39 --p-n-reads-learn=$pnreadslearn
|
|
|
40
|
|
|
41 #if $pnohashedfeatureids:
|
|
|
42 --p-no-hashed-feature-ids
|
|
|
43 #end if
|
|
|
44
|
|
|
45 --o-table=otable
|
|
|
46
|
|
|
47 --o-representative-sequences=orepresentativesequences
|
|
|
48
|
|
|
49 --o-denoising-stats=odenoisingstats
|
|
|
50
|
|
|
51 #if str($examples) != 'None':
|
|
|
52 --examples=$examples
|
|
|
53 #end if
|
|
|
54
|
|
|
55 ;
|
|
|
56 cp odenoisingstats.qza $odenoisingstats
|
|
|
57
|
|
|
58 ]]></command>
|
|
|
59 <inputs>
|
|
|
60 <param format="qza,no_unzip.zip" label="--i-demultiplexed-seqs: ARTIFACT SampleData[PairedEndSequencesWithQuality] The paired-end demultiplexed sequences to be denoised. [required]" name="idemultiplexedseqs" optional="False" type="data" />
|
|
|
61 <param label="--p-trunc-len-f: INTEGER Position at which forward read 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. After this parameter is applied there must still be at least a 12 nucleotide overlap between the forward and reverse reads. If 0 is provided, no truncation or length filtering will be performed [required]" name="ptrunclenf" optional="False" type="text" />
|
|
|
62 <param label="--p-trunc-len-r: INTEGER Position at which reverse read 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. After this parameter is applied there must still be at least a 12 nucleotide overlap between the forward and reverse reads. If 0 is provided, no truncation or length filtering will be performed [required]" name="ptrunclenr" optional="False" type="text" />
|
|
|
63 <param label="--p-trim-left-f: INTEGER Position at which forward read sequences should be trimmed due to low quality. This trims the 5\' end of the input sequences, which will be the bases that were sequenced in the first cycles. [default: 0]" name="ptrimleftf" optional="True" type="integer" value="0" />
|
|
|
64 <param label="--p-trim-left-r: INTEGER Position at which reverse read sequences should be trimmed due to low quality. This trims the 5\' end of the input sequences, which will be the bases that were sequenced in the first cycles. [default: 0]" name="ptrimleftr" optional="True" type="integer" value="0" />
|
|
|
65 <param label="--p-max-ee-f: NUMBER Forward reads with number of expected errors higher than this value will be discarded. [default: 2.0]" name="pmaxeef" optional="True" type="float" value="2.0" />
|
|
|
66 <param label="--p-max-ee-r: NUMBER Reverse reads with number of expected errors higher than this value will be discarded. [default: 2.0]" name="pmaxeer" optional="True" type="float" value="2.0" />
|
|
|
67 <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-f` or `trunc-len-r` (depending on the direction of the read) it is discarded. [default: 2]" name="ptruncq" optional="True" type="integer" value="2" />
|
|
|
68 <param label="--p-pooling-method: " name="ppoolingmethod" optional="True" type="select">
|
|
|
69 <option selected="True" value="None">Selection is Optional</option>
|
|
|
70 <option value="independent">independent</option>
|
|
|
71 <option value="pseudo">pseudo</option>
|
|
|
72 </param>
|
|
|
73 <param label="--p-chimera-method: " name="pchimeramethod" optional="True" type="select">
|
|
|
74 <option selected="True" value="None">Selection is Optional</option>
|
|
|
75 <option value="none">none</option>
|
|
|
76 <option value="consensus">consensus</option>
|
|
|
77 <option value="pooled">pooled</option>
|
|
|
78 </param>
|
|
|
79 <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" />
|
|
|
80 <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" />
|
|
|
81 <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" />
|
|
|
82 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
|
83
|
|
|
84 </inputs>
|
|
|
85
|
|
|
86 <outputs>
|
|
|
87 <data format="qza" label="${tool.name} on ${on_string}: table.qza" name="otable" />
|
|
|
88 <data format="qza" label="${tool.name} on ${on_string}: representativesequences.qza" name="orepresentativesequences" />
|
|
|
89 <data format="qza" label="${tool.name} on ${on_string}: denoisingstats.qza" name="odenoisingstats" />
|
|
|
90
|
|
|
91 </outputs>
|
|
|
92
|
|
|
93 <help><![CDATA[
|
|
|
94 Denoise and dereplicate paired-end sequences
|
|
|
95 ###############################################################
|
|
|
96
|
|
|
97 This method denoises paired-end sequences, dereplicates them, and filters
|
|
|
98 chimeras.
|
|
|
99
|
|
|
100 Parameters
|
|
|
101 ----------
|
|
|
102 demultiplexed_seqs : SampleData[PairedEndSequencesWithQuality]
|
|
|
103 The paired-end demultiplexed sequences to be denoised.
|
|
|
104 trunc_len_f : Int
|
|
|
105 Position at which forward read sequences should be truncated due to
|
|
|
106 decrease in quality. This truncates the 3' end of the of the input
|
|
|
107 sequences, which will be the bases that were sequenced in the last
|
|
|
108 cycles. Reads that are shorter than this value will be discarded. After
|
|
|
109 this parameter is applied there must still be at least a 12 nucleotide
|
|
|
110 overlap between the forward and reverse reads. If 0 is provided, no
|
|
|
111 truncation or length filtering will be performed
|
|
|
112 trunc_len_r : Int
|
|
|
113 Position at which reverse read sequences should be truncated due to
|
|
|
114 decrease in quality. This truncates the 3' end of the of the input
|
|
|
115 sequences, which will be the bases that were sequenced in the last
|
|
|
116 cycles. Reads that are shorter than this value will be discarded. After
|
|
|
117 this parameter is applied there must still be at least a 12 nucleotide
|
|
|
118 overlap between the forward and reverse reads. If 0 is provided, no
|
|
|
119 truncation or length filtering will be performed
|
|
|
120 trim_left_f : Int, optional
|
|
|
121 Position at which forward read sequences should be trimmed due to low
|
|
|
122 quality. This trims the 5' end of the input sequences, which will be
|
|
|
123 the bases that were sequenced in the first cycles.
|
|
|
124 trim_left_r : Int, optional
|
|
|
125 Position at which reverse read sequences should be trimmed due to low
|
|
|
126 quality. This trims the 5' end of the input sequences, which will be
|
|
|
127 the bases that were sequenced in the first cycles.
|
|
|
128 max_ee_f : Float, optional
|
|
|
129 Forward reads with number of expected errors higher than this value
|
|
|
130 will be discarded.
|
|
|
131 max_ee_r : Float, optional
|
|
|
132 Reverse reads with number of expected errors higher than this value
|
|
|
133 will be discarded.
|
|
|
134 trunc_q : Int, optional
|
|
|
135 Reads are truncated at the first instance of a quality score less than
|
|
|
136 or equal to this value. If the resulting read is then shorter than
|
|
|
137 `trunc_len_f` or `trunc_len_r` (depending on the direction of the read)
|
|
|
138 it is discarded.
|
|
|
139 pooling_method : Str % Choices('independent', 'pseudo'), optional
|
|
|
140 The method used to pool samples for denoising. "independent": Samples
|
|
|
141 are denoised indpendently. "pseudo": The pseudo-pooling method is used
|
|
|
142 to approximate pooling of samples. In short, samples are denoised
|
|
|
143 independently once, ASVs detected in at least 2 samples are recorded,
|
|
|
144 and samples are denoised independently a second time, but this time
|
|
|
145 with prior knowledge of the recorded ASVs and thus higher sensitivity
|
|
|
146 to those ASVs.
|
|
|
147 chimera_method : Str % Choices('consensus', 'none', 'pooled'), optional
|
|
|
148 The method used to remove chimeras. "none": No chimera removal is
|
|
|
149 performed. "pooled": All reads are pooled prior to chimera detection.
|
|
|
150 "consensus": Chimeras are detected in samples individually, and
|
|
|
151 sequences found chimeric in a sufficient fraction of samples are
|
|
|
152 removed.
|
|
|
153 min_fold_parent_over_abundance : Float, optional
|
|
|
154 The minimum abundance of potential parents of a sequence being tested
|
|
|
155 as chimeric, expressed as a fold-change versus the abundance of the
|
|
|
156 sequence being tested. Values should be greater than or equal to 1
|
|
|
157 (i.e. parents should be more abundant than the sequence being tested).
|
|
|
158 This parameter has no effect if chimera_method is "none".
|
|
|
159 n_threads : Int, optional
|
|
|
160 The number of threads to use for multithreaded processing. If 0 is
|
|
|
161 provided, all available cores will be used.
|
|
|
162 n_reads_learn : Int, optional
|
|
|
163 The number of reads to use when training the error model. Smaller
|
|
|
164 numbers will result in a shorter run time but a less reliable error
|
|
|
165 model.
|
|
|
166 hashed_feature_ids : Bool, optional
|
|
|
167 If true, the feature ids in the resulting table will be presented as
|
|
|
168 hashes of the sequences defining each feature. The hash will always be
|
|
|
169 the same for the same sequence so this allows feature tables to be
|
|
|
170 merged across runs of this method. You should only merge tables if the
|
|
|
171 exact same parameters are used for each run.
|
|
|
172
|
|
|
173 Returns
|
|
|
174 -------
|
|
|
175 table : FeatureTable[Frequency]
|
|
|
176 The resulting feature table.
|
|
|
177 representative_sequences : FeatureData[Sequence]
|
|
|
178 The resulting feature sequences. Each feature in the feature table will
|
|
|
179 be represented by exactly one sequence, and these sequences will be the
|
|
|
180 joined paired-end sequences.
|
|
|
181 denoising_stats : SampleData[DADA2Stats]
|
|
|
182 ]]></help>
|
|
|
183 <macros>
|
|
|
184 <import>qiime_citation.xml</import>
|
|
|
185 </macros>
|
|
|
186 <expand macro="qiime_citation"/>
|
|
|
187 </tool> |
