|
2
|
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[
|
|
4
|
8
|
|
|
9 #def parse_file(file):
|
|
|
10 #import csv
|
|
|
11 #set $read = csv.reader(open($file, "r"))
|
|
|
12 #set $qc = 0
|
|
|
13 #for l in $read:
|
|
|
14 #if "50%" in l:
|
|
|
15 #set $num = 0.0
|
|
|
16 #for i in l[1:]:
|
|
|
17 #if float(i) <= 25.0
|
|
|
18 #set $num = i
|
|
|
19 #set $qc = l.index($num) - 1
|
|
|
20 #break
|
|
|
21 #end if
|
|
|
22 #end for
|
|
|
23 #end if
|
|
|
24 #end for
|
|
|
25 #return $qc
|
|
|
26 #end def
|
|
|
27
|
|
|
28 #def find_QC(file):
|
|
|
29 #set $f_file_path=str(file).split(".dat")[0] + '_files/forward-seven-number-summaries.csv'
|
|
|
30 #set $r_file_path=str(file).split(".dat")[0] + '_files/reverse-seven-number-summaries.csv'
|
|
|
31 #set $qc_f = $parse_file($f_file_path)
|
|
|
32 #set $qc_r = $parse_file($r_file_path)
|
|
|
33 #return $qc_f, $qc_r
|
|
|
34 #end def
|
|
|
35
|
|
|
36 #def find_adapters(mapping_fp):
|
|
|
37 #import csv
|
|
|
38 #set $forward = 0
|
|
|
39 #set $reversed = 0
|
|
|
40 #set $reader = csv.reader(open(str(mapping_fp)), delimiter='\t')
|
|
|
41 #for row in $reader:
|
|
|
42 #if "#" not in str(row[0]):
|
|
|
43 #set $forward = len(row[2])
|
|
|
44 #set $reversed = len(row[3])
|
|
|
45 #break
|
|
|
46 #end if
|
|
|
47 #end for
|
|
|
48 #return int($forward), int($reversed)
|
|
|
49 #end def
|
|
|
50
|
|
|
51 #if str($mapping_fp) != 'None' and (int($ptrimleftf) == -1 or int($ptrimleftr) == -1):
|
|
|
52 #set $both_adapters = $find_adapters($mapping_fp)
|
|
|
53 #set $ptrimleftf=$both_adapters[0]
|
|
|
54 #set $ptrimleftr=$both_adapters[1]
|
|
|
55 #end if
|
|
|
56
|
|
|
57 #if str($sum_fp) != 'None' and (int($ptrunclenf) == -1 or int($ptrunclenr) == -1):
|
|
|
58 #set $both_qc = $find_QC($sum_fp)
|
|
|
59 #set $ptrunclenf=$both_qc[0]
|
|
|
60 #set $ptrunclenr=$both_qc[1]
|
|
|
61 #end if
|
|
|
62
|
|
|
63
|
|
2
|
64 qiime dada2 denoise-paired
|
|
|
65
|
|
|
66 --i-demultiplexed-seqs=$idemultiplexedseqs
|
|
4
|
67
|
|
|
68
|
|
|
69 #if str($ptrunclenf):
|
|
|
70 --p-trunc-len-f="$ptrunclenf"
|
|
|
71 #end if
|
|
|
72
|
|
|
73 #if str($ptrunclenf):
|
|
|
74 --p-trunc-len-r="$ptrunclenr"
|
|
|
75 #end if
|
|
|
76
|
|
|
77 #if str($ptrimleftf):
|
|
2
|
78 --p-trim-left-f=$ptrimleftf
|
|
|
79 #end if
|
|
|
80
|
|
4
|
81 #if str($ptrimleftr):
|
|
2
|
82 --p-trim-left-r=$ptrimleftr
|
|
|
83 #end if
|
|
|
84
|
|
4
|
85 #if str($pmaxee):
|
|
2
|
86 --p-max-ee=$pmaxee
|
|
|
87 #end if
|
|
|
88
|
|
4
|
89 #if str($ptruncq):
|
|
2
|
90 --p-trunc-q=$ptruncq
|
|
|
91 #end if
|
|
|
92
|
|
|
93 #if str($pchimeramethod) != 'None':
|
|
|
94 --p-chimera-method=$pchimeramethod
|
|
|
95 #end if
|
|
|
96
|
|
4
|
97 #if str($pminfoldparentoverabundance):
|
|
2
|
98 --p-min-fold-parent-over-abundance=$pminfoldparentoverabundance
|
|
|
99 #end if
|
|
|
100
|
|
|
101 #set $pnthreads = '${GALAXY_SLOTS:-4}'
|
|
|
102
|
|
|
103 #if str($pnthreads):
|
|
|
104 --p-n-threads="$pnthreads"
|
|
|
105 #end if
|
|
|
106
|
|
|
107
|
|
4
|
108 #if str($pnreadslearn):
|
|
2
|
109 --p-n-reads-learn=$pnreadslearn
|
|
|
110 #end if
|
|
|
111
|
|
|
112 #if $pnohashedfeatureids:
|
|
|
113 --p-no-hashed-feature-ids
|
|
|
114 #end if
|
|
|
115
|
|
|
116 --o-table=otable
|
|
|
117 --o-representative-sequences=orepresentativesequences
|
|
|
118 --o-denoising-stats=odenoisingstats
|
|
|
119 ;
|
|
|
120 cp otable.qza $otable;
|
|
|
121 cp orepresentativesequences.qza $orepresentativesequences;
|
|
|
122 cp odenoisingstats.qza $odenoisingstats
|
|
|
123 ]]></command>
|
|
|
124 <inputs>
|
|
4
|
125 <param format="tabular" label="Mapping file where 3rd and 4th columns must be forward and reverse primers respectively" name="mapping_fp" optional="True" type="data"/>
|
|
|
126 <param format="html" label="Summary file" name="sum_fp" optional="True" type="data"/>
|
|
|
127
|
|
2
|
128 <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"/>
|
|
|
129 <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"/>
|
|
|
130 <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"/>
|
|
|
131 <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"/>
|
|
|
132 <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"/>
|
|
|
133 <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"/>
|
|
|
134 <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"/>
|
|
|
135 <param label="--p-chimera-method: " name="pchimeramethod" optional="True" type="select">
|
|
|
136 <option selected="True" value="None">Selection is Optional</option>
|
|
|
137 <option value="consensus">consensus</option>
|
|
|
138 <option value="pooled">pooled</option>
|
|
|
139 <option value="none">none</option>
|
|
|
140 </param>
|
|
|
141 <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"/>
|
|
|
142 <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"/>
|
|
|
143 <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"/>
|
|
|
144 </inputs>
|
|
|
145 <outputs>
|
|
|
146 <data format="qza" label="${tool.name} on ${on_string}: table.qza" name="otable"/>
|
|
|
147 <data format="qza" label="${tool.name} on ${on_string}: representativesequences.qza" name="orepresentativesequences"/>
|
|
|
148 <data format="qza" label="${tool.name} on ${on_string}: denoisingstats.qza" name="odenoisingstats"/>
|
|
|
149 </outputs>
|
|
|
150 <help><![CDATA[
|
|
|
151 Denoise and dereplicate paired-end sequences
|
|
|
152 ############################################
|
|
|
153
|
|
|
154 This method denoises paired-end sequences, dereplicates them, and filters
|
|
|
155 chimeras.
|
|
|
156
|
|
|
157 Parameters
|
|
|
158 ----------
|
|
|
159 demultiplexed_seqs : SampleData[PairedEndSequencesWithQuality]
|
|
|
160 The paired-end demultiplexed sequences to be denoised.
|
|
|
161 trunc_len_f : Int
|
|
|
162 Position at which forward read sequences should be truncated due to
|
|
|
163 decrease in quality. This truncates the 3' end of the of the input
|
|
|
164 sequences, which will be the bases that were sequenced in the last
|
|
|
165 cycles. Reads that are shorter than this value will be discarded. After
|
|
|
166 this parameter is applied there must still be at least a 20 nucleotide
|
|
|
167 overlap between the forward and reverse reads. If 0 is provided, no
|
|
|
168 truncation or length filtering will be performed
|
|
|
169 trunc_len_r : Int
|
|
|
170 Position at which reverse read sequences should be truncated due to
|
|
|
171 decrease in quality. This truncates the 3' end of the of the input
|
|
|
172 sequences, which will be the bases that were sequenced in the last
|
|
|
173 cycles. Reads that are shorter than this value will be discarded. After
|
|
|
174 this parameter is applied there must still be at least a 20 nucleotide
|
|
|
175 overlap between the forward and reverse reads. If 0 is provided, no
|
|
|
176 truncation or length filtering will be performed
|
|
|
177 trim_left_f : Int, optional
|
|
|
178 Position at which forward read sequences should be trimmed due to low
|
|
|
179 quality. This trims the 5' end of the input sequences, which will be
|
|
|
180 the bases that were sequenced in the first cycles.
|
|
|
181 trim_left_r : Int, optional
|
|
|
182 Position at which reverse read sequences should be trimmed due to low
|
|
|
183 quality. This trims the 5' end of the input sequences, which will be
|
|
|
184 the bases that were sequenced in the first cycles.
|
|
|
185 max_ee : Float, optional
|
|
|
186 Reads with number of expected errors higher than this value will be
|
|
|
187 discarded.
|
|
|
188 trunc_q : Int, optional
|
|
|
189 Reads are truncated at the first instance of a quality score less than
|
|
|
190 or equal to this value. If the resulting read is then shorter than
|
|
|
191 `trunc_len_f` or `trunc_len_r` (depending on the direction of the read)
|
|
|
192 it is discarded.
|
|
|
193 chimera_method : Str % Choices('consensus', 'pooled', 'none'), optional
|
|
|
194 The method used to remove chimeras. "none": No chimera removal is
|
|
|
195 performed. "pooled": All reads are pooled prior to chimera detection.
|
|
|
196 "consensus": Chimeras are detected in samples individually, and
|
|
|
197 sequences found chimeric in a sufficient fraction of samples are
|
|
|
198 removed.
|
|
|
199 min_fold_parent_over_abundance : Float, optional
|
|
|
200 The minimum abundance of potential parents of a sequence being tested
|
|
|
201 as chimeric, expressed as a fold-change versus the abundance of the
|
|
|
202 sequence being tested. Values should be greater than or equal to 1
|
|
|
203 (i.e. parents should be more abundant than the sequence being tested).
|
|
|
204 This parameter has no effect if chimera_method is "none".
|
|
|
205 provided, all available cores will be used.
|
|
|
206 n_reads_learn : Int, optional
|
|
|
207 The number of reads to use when training the error model. Smaller
|
|
|
208 numbers will result in a shorter run time but a less reliable error
|
|
|
209 model.
|
|
|
210 hashed_feature_ids : Bool, optional
|
|
|
211 If true, the feature ids in the resulting table will be presented as
|
|
|
212 hashes of the sequences defining each feature. The hash will always be
|
|
|
213 the same for the same sequence so this allows feature tables to be
|
|
|
214 merged across runs of this method. You should only merge tables if the
|
|
|
215 exact same parameters are used for each run.
|
|
|
216
|
|
|
217 Returns
|
|
|
218 -------
|
|
|
219 table : FeatureTable[Frequency]
|
|
|
220 The resulting feature table.
|
|
|
221 representative_sequences : FeatureData[Sequence]
|
|
|
222 The resulting feature sequences. Each feature in the feature table will
|
|
|
223 be represented by exactly one sequence, and these sequences will be the
|
|
|
224 joined paired-end sequences.
|
|
|
225 denoising_stats : SampleData[DADA2Stats]
|
|
|
226 ]]></help>
|
|
|
227 <macros>
|
|
|
228 <import>qiime_citation.xml</import>
|
|
|
229 </macros>
|
|
|
230 <expand macro="qiime_citation"/>
|
|
|
231 </tool>
|
