|
0
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_dada2_denoise-paired" name="qiime dada2 denoise-paired" version="2019.4">
|
|
|
3 <description> - Denoise and dereplicate paired-end sequences</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2019.4">qiime2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command><![CDATA[
|
|
|
8 qiime dada2 denoise-paired
|
|
|
9
|
|
|
10 --i-demultiplexed-seqs=$idemultiplexedseqs
|
|
|
11 --p-trunc-len-f="$ptrunclenf"
|
|
|
12 --p-trunc-len-r="$ptrunclenr"
|
|
|
13 #if $ptrimleftf:
|
|
|
14 --p-trim-left-f=$ptrimleftf
|
|
|
15 #end if
|
|
|
16
|
|
|
17 #if $ptrimleftr:
|
|
|
18 --p-trim-left-r=$ptrimleftr
|
|
|
19 #end if
|
|
|
20
|
|
|
21 #if $pmaxee:
|
|
|
22 --p-max-ee=$pmaxee
|
|
|
23 #end if
|
|
|
24
|
|
|
25 #if $ptruncq:
|
|
|
26 --p-trunc-q=$ptruncq
|
|
|
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
|
|
|
39 #if str($pnthreads):
|
|
|
40 --p-n-threads="$pnthreads"
|
|
|
41 #end if
|
|
|
42
|
|
|
43
|
|
|
44 #if $pnreadslearn:
|
|
|
45 --p-n-reads-learn=$pnreadslearn
|
|
|
46 #end if
|
|
|
47
|
|
|
48 #if $pnohashedfeatureids:
|
|
|
49 --p-no-hashed-feature-ids
|
|
|
50 #end if
|
|
|
51
|
|
|
52 --o-table=otable
|
|
|
53 --o-representative-sequences=orepresentativesequences
|
|
|
54 --o-denoising-stats=odenoisingstats
|
|
|
55 ;
|
|
|
56 cp otable.qza $otable;
|
|
|
57 cp orepresentativesequences.qza $orepresentativesequences;
|
|
|
58 cp odenoisingstats.qza $odenoisingstats
|
|
|
59 ]]></command>
|
|
|
60 <inputs>
|
|
|
61 <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"/>
|
|
|
62 <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 20 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" value="" type="integer"/>
|
|
|
63 <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 20 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" value="" type="integer"/>
|
|
|
64 <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"/>
|
|
|
65 <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"/>
|
|
|
66 <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"/>
|
|
|
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-chimera-method: " name="pchimeramethod" optional="True" type="select">
|
|
|
69 <option selected="True" value="None">Selection is Optional</option>
|
|
|
70 <option value="consensus">consensus</option>
|
|
|
71 <option value="pooled">pooled</option>
|
|
|
72 <option value="none">none</option>
|
|
|
73 </param>
|
|
|
74 <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"/>
|
|
|
75 <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"/>
|
|
|
76 <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"/>
|
|
|
77 </inputs>
|
|
|
78 <outputs>
|
|
|
79 <data format="qza" label="${tool.name} on ${on_string}: table.qza" name="otable"/>
|
|
|
80 <data format="qza" label="${tool.name} on ${on_string}: representativesequences.qza" name="orepresentativesequences"/>
|
|
|
81 <data format="qza" label="${tool.name} on ${on_string}: denoisingstats.qza" name="odenoisingstats"/>
|
|
|
82 </outputs>
|
|
|
83 <help><![CDATA[
|
|
|
84 Denoise and dereplicate paired-end sequences
|
|
|
85 ############################################
|
|
|
86
|
|
|
87 This method denoises paired-end sequences, dereplicates them, and filters
|
|
|
88 chimeras.
|
|
|
89
|
|
|
90 Parameters
|
|
|
91 ----------
|
|
|
92 demultiplexed_seqs : SampleData[PairedEndSequencesWithQuality]
|
|
|
93 The paired-end demultiplexed sequences to be denoised.
|
|
|
94 trunc_len_f : Int
|
|
|
95 Position at which forward read sequences should be truncated due to
|
|
|
96 decrease in quality. This truncates the 3' end of the of the input
|
|
|
97 sequences, which will be the bases that were sequenced in the last
|
|
|
98 cycles. Reads that are shorter than this value will be discarded. After
|
|
|
99 this parameter is applied there must still be at least a 20 nucleotide
|
|
|
100 overlap between the forward and reverse reads. If 0 is provided, no
|
|
|
101 truncation or length filtering will be performed
|
|
|
102 trunc_len_r : Int
|
|
|
103 Position at which reverse read sequences should be truncated due to
|
|
|
104 decrease in quality. This truncates the 3' end of the of the input
|
|
|
105 sequences, which will be the bases that were sequenced in the last
|
|
|
106 cycles. Reads that are shorter than this value will be discarded. After
|
|
|
107 this parameter is applied there must still be at least a 20 nucleotide
|
|
|
108 overlap between the forward and reverse reads. If 0 is provided, no
|
|
|
109 truncation or length filtering will be performed
|
|
|
110 trim_left_f : Int, optional
|
|
|
111 Position at which forward read sequences should be trimmed due to low
|
|
|
112 quality. This trims the 5' end of the input sequences, which will be
|
|
|
113 the bases that were sequenced in the first cycles.
|
|
|
114 trim_left_r : Int, optional
|
|
|
115 Position at which reverse read sequences should be trimmed due to low
|
|
|
116 quality. This trims the 5' end of the input sequences, which will be
|
|
|
117 the bases that were sequenced in the first cycles.
|
|
|
118 max_ee : Float, optional
|
|
|
119 Reads with number of expected errors higher than this value will be
|
|
|
120 discarded.
|
|
|
121 trunc_q : Int, optional
|
|
|
122 Reads are truncated at the first instance of a quality score less than
|
|
|
123 or equal to this value. If the resulting read is then shorter than
|
|
|
124 `trunc_len_f` or `trunc_len_r` (depending on the direction of the read)
|
|
|
125 it is discarded.
|
|
|
126 chimera_method : Str % Choices('consensus', 'pooled', 'none'), optional
|
|
|
127 The method used to remove chimeras. "none": No chimera removal is
|
|
|
128 performed. "pooled": All reads are pooled prior to chimera detection.
|
|
|
129 "consensus": Chimeras are detected in samples individually, and
|
|
|
130 sequences found chimeric in a sufficient fraction of samples are
|
|
|
131 removed.
|
|
|
132 min_fold_parent_over_abundance : Float, optional
|
|
|
133 The minimum abundance of potential parents of a sequence being tested
|
|
|
134 as chimeric, expressed as a fold-change versus the abundance of the
|
|
|
135 sequence being tested. Values should be greater than or equal to 1
|
|
|
136 (i.e. parents should be more abundant than the sequence being tested).
|
|
|
137 This parameter has no effect if chimera_method is "none".
|
|
|
138 provided, all available cores will be used.
|
|
|
139 n_reads_learn : Int, optional
|
|
|
140 The number of reads to use when training the error model. Smaller
|
|
|
141 numbers will result in a shorter run time but a less reliable error
|
|
|
142 model.
|
|
|
143 hashed_feature_ids : Bool, optional
|
|
|
144 If true, the feature ids in the resulting table will be presented as
|
|
|
145 hashes of the sequences defining each feature. The hash will always be
|
|
|
146 the same for the same sequence so this allows feature tables to be
|
|
|
147 merged across runs of this method. You should only merge tables if the
|
|
|
148 exact same parameters are used for each run.
|
|
|
149
|
|
|
150 Returns
|
|
|
151 -------
|
|
|
152 table : FeatureTable[Frequency]
|
|
|
153 The resulting feature table.
|
|
|
154 representative_sequences : FeatureData[Sequence]
|
|
|
155 The resulting feature sequences. Each feature in the feature table will
|
|
|
156 be represented by exactly one sequence, and these sequences will be the
|
|
|
157 joined paired-end sequences.
|
|
|
158 denoising_stats : SampleData[DADA2Stats]
|
|
|
159 ]]></help>
|
|
|
160 <macros>
|
|
|
161 <import>qiime_citation.xml</import>
|
|
|
162 </macros>
|
|
|
163 <expand macro="qiime_citation"/>
|
|
|
164 </tool>
|
