|
0
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_dada2_denoise-paired" name="qiime dada2 denoise-paired" version="2018.4">
|
|
|
3 <description> - Denoise and dereplicate paired-end sequences</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2018.4">qiime2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command><![CDATA[
|
|
|
8 qiime dada2 denoise-paired --i-demultiplexed-seqs=$idemultiplexedseqs --p-trunc-len-f="$ptrunclenf" --p-trunc-len-r="$ptrunclenr"
|
|
|
9
|
|
|
10 #if $pmaxee:
|
|
|
11 --p-max-ee=$pmaxee
|
|
|
12 #end if
|
|
|
13
|
|
|
14 #if $ptrimleftr:
|
|
|
15 --p-trim-left-r=$ptrimleftr
|
|
|
16 #end if
|
|
|
17
|
|
|
18 --o-table=otable
|
|
|
19
|
|
|
20 #if $phashedfeatureids:
|
|
|
21 --p-hashed-feature-ids
|
|
|
22 #else
|
|
|
23 --p-no-hashed-feature-ids
|
|
|
24 #end if
|
|
|
25
|
|
|
26 #set $pnthreads = '${GALAXY_SLOTS:-4}'
|
|
|
27
|
|
|
28 #if str($pnthreads):
|
|
|
29 --p-n-threads=$pnthreads
|
|
|
30 #end if
|
|
|
31
|
|
|
32 #if $ptrimleftf:
|
|
|
33 --p-trim-left-f=$ptrimleftf
|
|
|
34 #end if
|
|
|
35
|
|
|
36 #if str($pchimeramethod) != 'None':
|
|
|
37 --p-chimera-method=$pchimeramethod
|
|
|
38 #end if
|
|
|
39
|
|
|
40 #if $pnreadslearn:
|
|
|
41 --p-n-reads-learn=$pnreadslearn
|
|
|
42 #end if
|
|
|
43
|
|
|
44 --o-representative-sequences=orepresentativesequences
|
|
|
45
|
|
|
46 #if str($cmdconfig) != 'None':
|
|
|
47 --cmd-config=$cmdconfig
|
|
|
48 #end if
|
|
|
49
|
|
|
50 #if $ptruncq:
|
|
|
51 --p-trunc-q=$ptruncq
|
|
|
52 #end if
|
|
|
53
|
|
|
54 --o-denoising-stats=odenoisingstats
|
|
|
55
|
|
|
56 #if $pminfoldparentoverabundance:
|
|
|
57 --p-min-fold-parent-over-abundance=$pminfoldparentoverabundance
|
|
|
58 #end if
|
|
|
59 ;
|
|
|
60 cp otable.qza $otable;
|
|
|
61 cp odenoisingstats.qza $odenoisingstats;
|
|
|
62 cp orepresentativesequences.qza $orepresentativesequences;
|
|
|
63 ]]></command>
|
|
|
64 <inputs>
|
|
|
65 <param format="qza,no_unzip.zip" label="--i-demultiplexed-seqs: SampleData[PairedEndSequencesWithQuality] The paired-end demultiplexed sequences to be denoised. [required]" name="idemultiplexedseqs" optional="False" type="data"/>
|
|
|
66 <param label="--p-trunc-len-f: 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" type="integer" value="0"/>
|
|
|
67 <param label="--p-trunc-len-r: 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" type="integer" value="0"/>
|
|
|
68 <param label="--p-trim-left-f: 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"/>
|
|
|
69 <param label="--p-trim-left-r: 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"/>
|
|
|
70 <param label="--p-max-ee: 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"/>
|
|
|
71 <param label="--p-trunc-q: 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"/>
|
|
|
72 <param label="--p-chimera-method: The method used to remove chimeras. None:
|
|
|
73 No chimera removal is performed. Pooled:
|
|
|
74 All reads are pooled prior to chimera
|
|
|
75 detection. Consensus: Chimeras are
|
|
|
76 detected in samples individually, and
|
|
|
77 sequences found chimeric in a sufficient
|
|
|
78 fraction of samples are removed. [default:
|
|
|
79 consensus]" name="pchimeramethod" optional="True" type="select">
|
|
|
80 <option selected="True" value="None">Selection is Optional</option>
|
|
|
81 <option value="pooled">pooled</option>
|
|
|
82 <option value="consensus">consensus</option>
|
|
|
83 <option value="none">none</option>
|
|
|
84 </param>
|
|
|
85 <param label="--p-min-fold-parent-over-abundance: 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"/>
|
|
|
86 <param label="--p-n-reads-learn: 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"/>
|
|
|
87 <param label="--p-hashed-feature-ids /--p-no-hashed-feature-ids: 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="phashedfeatureids" checked="False" type="boolean"/>
|
|
|
88 <param label="--cmd-config: Use config file for command options" name="cmdconfig" optional="True" type="data"/>
|
|
|
89 </inputs>
|
|
|
90 <outputs>
|
|
|
91 <data format="qza" label="${tool.name} on ${on_string}: table.qza" name="otable"/>
|
|
|
92 <data format="qza" label="${tool.name} on ${on_string}: representative-sequences.qza" name="orepresentativesequences"/>
|
|
|
93 <data format="qza" label="${tool.name} on ${on_string}: denoising-stats.qza" name="odenoisingstats"/>
|
|
|
94 </outputs>
|
|
|
95
|
|
|
96 <help><![CDATA[
|
|
|
97 Denoise and dereplicate paired-end sequences
|
|
|
98 --------------------------------------------
|
|
|
99
|
|
|
100 This method denoises paired-end sequences, dereplicates them, and filters
|
|
|
101 chimeras.
|
|
|
102
|
|
|
103 Parameters
|
|
|
104 ----------
|
|
|
105 demultiplexed_seqs : SampleData[PairedEndSequencesWithQuality]
|
|
|
106 The paired-end demultiplexed sequences to be denoised.
|
|
|
107 trunc_len_f : Int
|
|
|
108 Position at which forward read sequences should be truncated due to
|
|
|
109 decrease in quality. This truncates the 3' end of the of the input
|
|
|
110 sequences, which will be the bases that were sequenced in the last
|
|
|
111 cycles. Reads that are shorter than this value will be discarded. After
|
|
|
112 this parameter is applied there must still be at least a 20 nucleotide
|
|
|
113 overlap between the forward and reverse reads. If 0 is provided, no
|
|
|
114 truncation or length filtering will be performed
|
|
|
115 trunc_len_r : Int
|
|
|
116 Position at which reverse read sequences should be truncated due to
|
|
|
117 decrease in quality. This truncates the 3' end of the of the input
|
|
|
118 sequences, which will be the bases that were sequenced in the last
|
|
|
119 cycles. Reads that are shorter than this value will be discarded. After
|
|
|
120 this parameter is applied there must still be at least a 20 nucleotide
|
|
|
121 overlap between the forward and reverse reads. If 0 is provided, no
|
|
|
122 truncation or length filtering will be performed
|
|
|
123 trim_left_f : Int, optional
|
|
|
124 Position at which forward read sequences should be trimmed due to low
|
|
|
125 quality. This trims the 5' end of the input sequences, which will be
|
|
|
126 the bases that were sequenced in the first cycles.
|
|
|
127 trim_left_r : Int, optional
|
|
|
128 Position at which reverse read sequences should be trimmed due to low
|
|
|
129 quality. This trims the 5' end of the input sequences, which will be
|
|
|
130 the bases that were sequenced in the first cycles.
|
|
|
131 max_ee : Float, optional
|
|
|
132 Reads with number of expected errors higher than this value will be
|
|
|
133 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 chimera_method : Str % Choices({'consensus', 'none', 'pooled'}), optional
|
|
|
140 The method used to remove chimeras. "none": No chimera removal is
|
|
|
141 performed. "pooled": All reads are pooled prior to chimera detection.
|
|
|
142 "consensus": Chimeras are detected in samples individually, and
|
|
|
143 sequences found chimeric in a sufficient fraction of samples are
|
|
|
144 removed.
|
|
|
145 min_fold_parent_over_abundance : Float, optional
|
|
|
146 The minimum abundance of potential parents of a sequence being tested
|
|
|
147 as chimeric, expressed as a fold-change versus the abundance of the
|
|
|
148 sequence being tested. Values should be greater than or equal to 1
|
|
|
149 (i.e. parents should be more abundant than the sequence being tested).
|
|
|
150 This parameter has no effect if chimera_method is "none".
|
|
|
151 n_reads_learn : Int, optional
|
|
|
152 The number of reads to use when training the error model. Smaller
|
|
|
153 numbers will result in a shorter run time but a less reliable error
|
|
|
154 model.
|
|
|
155 hashed_feature_ids : Bool, optional
|
|
|
156 If true, the feature ids in the resulting table will be presented as
|
|
|
157 hashes of the sequences defining each feature. The hash will always be
|
|
|
158 the same for the same sequence so this allows feature tables to be
|
|
|
159 merged across runs of this method. You should only merge tables if the
|
|
|
160 exact same parameters are used for each run.
|
|
|
161
|
|
|
162 Returns
|
|
|
163 -------
|
|
|
164 table : FeatureTable[Frequency]
|
|
|
165 The resulting feature table.
|
|
|
166 representative_sequences : FeatureData[Sequence]
|
|
|
167 The resulting feature sequences. Each feature in the feature table will
|
|
|
168 be represented by exactly one sequence, and these sequences will be the
|
|
|
169 joined paired-end sequences.
|
|
|
170 ]]>
|
|
|
171 </help>
|
|
|
172 <macros>
|
|
|
173 <import>qiime_citation.xml</import>
|
|
|
174 </macros>
|
|
|
175 <expand macro="qiime_citation" />
|
|
|
176 </tool>
|
