|
0
|
1 <?xml version="1.0" encoding="utf-8"?>
|
|
|
2 <tool id="sortmerna_wrapper" version="1.0" name="Filter with SortMeRNA">
|
|
|
3 <requirements>
|
|
|
4 <requirement type='package' version="1.7">sortmerna</requirement>
|
|
|
5 </requirements>
|
|
|
6 <description>Fast and accurate filtering of ribosomal RNAs in metatranscriptomic data</description>
|
|
|
7 <command interpreter="python">
|
|
|
8 sortmerna_wrapper.py
|
|
|
9 --sortmerna "
|
|
|
10 $strand_search
|
|
|
11 #if str( $read_family.read_family_selector ) == 'other':
|
|
|
12 --I $input_reads -r $read_family.ratio_parameter
|
|
|
13 #else:
|
|
|
14 $read_family.read_family_selector $input_reads
|
|
|
15 #end if
|
|
|
16 #if str( $sequencing_type.sequencing_type_selector ) == 'paired':
|
|
|
17 $sequencing_type.paired_type
|
|
|
18 #end if
|
|
|
19
|
|
|
20 #if $outputs_selected:
|
|
|
21 #if 'accept' in $outputs_selected.value:
|
|
|
22 --accept accept_file
|
|
|
23 #end if
|
|
|
24 #if 'other' in $outputs_selected.value:
|
|
|
25 --other other_file
|
|
|
26 #end if
|
|
|
27 #end if
|
|
|
28 $log
|
|
|
29 #if str( $options.options_type_selector ) == 'more':
|
|
|
30 -a $options.number_of_threads
|
|
|
31 #end if
|
|
|
32 "
|
|
|
33 #if str( $databases_type.databases_selector ) == 'history':
|
|
|
34 --buildtrie
|
|
|
35 #for $db in $databases_type.input_databases
|
|
|
36 $db.database_name
|
|
|
37 #end for
|
|
|
38 #else:
|
|
|
39 ## databases path is not directly accessible, must match by hand with LOC file contents
|
|
|
40 ${' '.join([dict([(x[0], x[2]) for x in $databases_type.input_databases.input.options.tool_data_table.data])[y]
|
|
|
41 for y in $databases_type.input_databases.value])}
|
|
|
42 #end if
|
|
|
43 </command>
|
|
|
44 <inputs>
|
|
|
45 <conditional name="read_family">
|
|
|
46 <param name="read_family_selector" type="select" format="text"
|
|
|
47 help="The Illumina platform is more common for large scale metatranscriptomic projects requiring a high throughput.">
|
|
|
48 <label>Sequencing technology of querying sequences (reads)</label>
|
|
|
49 <option value="--I">Illumina Solexa</option>
|
|
|
50 <option value="--454">454 Roche</option>
|
|
|
51 <option value="other">Other</option>
|
|
|
52 </param>
|
|
|
53 <when value="other">
|
|
|
54 <param name="ratio_parameter" type="float" value="1" min="0" max="1"
|
|
|
55 label="Ratio parameter (the number of hits on the read / read length)"
|
|
|
56 help="The ratio parameter for SortMeRNA has been set to r=0.25 for Illumina Solexa reads and to r=0.15 for 454 Roche reads.
|
|
|
57 For other read types, if the sequencing technology produces high quality reads with a low substitution error rate
|
|
|
58 (0.1 substitutions per 100 bases, such as Illumina), then the ratio parameter can be set to r=[0.23,0.27].
|
|
|
59 If the sequencing technology has a high indel error rate (1-2 indels per 100 bases, such as 454 or Ion Torrent),
|
|
|
60 then the ratio parameter can be set to r=[0.13,0.17]."/>
|
|
|
61 </when>
|
|
|
62 </conditional>
|
|
|
63 <param format="fasta,fastq" name="input_reads" type="data" label="Querying sequences (reads)" help=""/>
|
|
|
64
|
|
|
65 <conditional name="sequencing_type">
|
|
|
66 <param name="sequencing_type_selector" type="select" label="Sequencing type">
|
|
|
67 <option value="not_paired">Reads are not paired</option>
|
|
|
68 <option value="paired">Reads are paired</option>
|
|
|
69 </param>
|
|
|
70 <when value="paired">
|
|
|
71 <param name="paired_type" type="select" label="If one read of a pair is accepted and the other not, output both reads" display="radio"
|
|
|
72 help="SortMeRNA does not use the pairing information for filtering RNA,
|
|
|
73 however if one read of a pair is accepted and the other is not,
|
|
|
74 the resulting output may break apart the pair into two separate files.
|
|
|
75 The purpose of 'Reads are paired' option is to preserve the pairing of the reads.">
|
|
|
76 <option value="--paired-in">to accepted file</option>
|
|
|
77 <option value="--paired-out">to rejected file</option>
|
|
|
78 </param>
|
|
|
79 </when>
|
|
|
80 </conditional>
|
|
|
81
|
|
|
82 <param name="strand_search" type="select" label="Which strands to search" display="radio">
|
|
|
83 <option value="">Search both strands</option>
|
|
|
84 <option value="-F">Search only the forward strand</option>
|
|
|
85 <option value="-R">Search only the reverse-complementary strand</option>
|
|
|
86 </param>
|
|
|
87
|
|
|
88 <conditional name="databases_type">
|
|
|
89 <param name="databases_selector" type="select" label="Databases to query"
|
|
|
90 help="Public rRNA databases provided with SortMeRNA have been indexed.
|
|
|
91 On the contrary, personal databases must be indexed each time SortMeRNA is launched.
|
|
|
92 Please be patient, this may take some time depending on the size of the given database.">
|
|
|
93 <option value="cached" selected="true">Public ribosomal databases</option>
|
|
|
94 <option value="history">Databases from your history</option>
|
|
|
95 </param>
|
|
|
96 <when value="cached">
|
|
|
97 <param name="input_databases" label="rRNA database"
|
|
|
98 type="select" display="checkboxes" multiple="true">
|
|
|
99 <options from_data_table="rRNA_databases" />
|
|
|
100 <validator type="no_options" message="Select at least one database"/>
|
|
|
101 </param>
|
|
|
102 </when>
|
|
|
103 <when value="history">
|
|
|
104 <repeat name="input_databases" title="Database" min="1">
|
|
|
105 <param name="database_name" type="data" format="fasta" label="rRNA database"
|
|
|
106 help="Your database will be indexed first, which may take up to several minutes."/>
|
|
|
107 </repeat>
|
|
|
108 </when>
|
|
|
109 </conditional>
|
|
|
110
|
|
|
111 <!-- Outputs -->
|
|
|
112 <param name="outputs_selected" type="select" display="checkboxes" multiple="true" label="Output options">
|
|
|
113 <option value="accept" selected="True">Reads matching to at least one database</option>
|
|
|
114 <option value="other">Reads not found in any database</option>
|
|
|
115 </param>
|
|
|
116 <param name="log" type="boolean" checked="False" truevalue="--log log_file" falsevalue="" label="Statistics file"
|
|
|
117 help="Generates statistics for the rRNA content of reads, as well as rRNA subunit distribution.">
|
|
|
118 </param>
|
|
|
119
|
|
|
120 <!-- Advanced options -->
|
|
|
121 <conditional name="options">
|
|
|
122 <param name="options_type_selector" type="select" label="Advanced Options">
|
|
|
123 <option value="less" selected="True">Less options</option>
|
|
|
124 <option value="more">More options</option>
|
|
|
125 </param>
|
|
|
126 <when value="less">
|
|
|
127 <!-- no options -->
|
|
|
128 </when>
|
|
|
129 <when value="more">
|
|
|
130 <param name="number_of_threads" type="integer" label="Number of threads to use" value="1" min="1"/>
|
|
|
131 </when>
|
|
|
132 </conditional>
|
|
|
133 </inputs>
|
|
|
134 <outputs>
|
|
|
135 <data format="input" format_source="input_reads" name="output_accept" from_work_dir="accept_file.dat"
|
|
|
136 label="Matching reads on ${on_string} (${input_reads.datatype.file_ext})">
|
|
|
137 <filter>outputs_selected and 'accept' in outputs_selected</filter>
|
|
|
138 </data>
|
|
|
139 <data format="input" format_source="input_reads" name="output_other" from_work_dir="other_file.dat"
|
|
|
140 label="Reads not found on ${on_string} (${input_reads.datatype.file_ext})">
|
|
|
141 <filter>outputs_selected and 'other' in outputs_selected</filter>
|
|
|
142 </data>
|
|
|
143 <data format="txt" name="output_log" label="${tool.name} statistics (txt)" from_work_dir="log_file.log">
|
|
|
144 <filter>log</filter>
|
|
|
145 </data>
|
|
|
146 </outputs>
|
|
|
147 <stdio>
|
|
|
148 <regex match="This program builds a Burst trie on an input rRNA database"
|
|
|
149 source="both"
|
|
|
150 level="fatal"
|
|
|
151 description="Buildtrie program failed to execute." />
|
|
|
152 <regex match="The database name"
|
|
|
153 source="both"
|
|
|
154 level="fatal"
|
|
|
155 description="The database ${databases} has not been preprocessed using buildtrie before using SortMeRNA." />
|
|
|
156 </stdio>
|
|
|
157 <tests>
|
|
|
158 <test>
|
|
|
159 <param name="read_family_selector" value="I" />
|
|
|
160 <param name="input_reads" value="sortmerna_wrapper_in1.fastq" />
|
|
|
161 <param name="sequencing_type_selector" value ="not_paired" />
|
|
|
162 <param name="strand_search" value="" />
|
|
|
163 <param name="databases_selector" value="cached" />
|
|
|
164 <param name="input_databases" value="rfam-5.8s,rfam-5s" />
|
|
|
165 <param name="outputs_selected" value="accept,other" />
|
|
|
166 <param name="log" value="" />
|
|
|
167 <param name="options_type_selector" value="less" />
|
|
|
168 <output name="output_accept" file="sortmerna_wrapper_accept1.fastq" />
|
|
|
169 <output name="output_other" file="sortmerna_wrapper_other1.fastq" />
|
|
|
170 </test>
|
|
|
171 </tests>
|
|
|
172 <help>
|
|
|
173 **Overview**
|
|
|
174
|
|
|
175 SortMeRNA_ is a software designed to rapidly filter ribosomal RNA fragments
|
|
|
176 from metatransriptomic data produced by next-generation sequencers.
|
|
|
177 It is capable of handling large RNA databases and sorting out all fragments
|
|
|
178 matching to the database with high accuracy and specificity.
|
|
|
179
|
|
|
180 .. _SortMeRNA: http://bioinfo.lifl.fr/RNA/sortmerna/
|
|
|
181
|
|
|
182 If you use this tool, please cite Kopylova E., Noé L. and Touzet H.,
|
|
|
183 `"SortMeRNA: Fast and accurate filtering of ribosomal RNAs in metatranscriptomic data"`__,
|
|
|
184 Bioinformatics (2012), doi: 10.1093/bioinformatics/bts611.
|
|
|
185
|
|
|
186 .. __: http://bioinformatics.oxfordjournals.org/content/28/24/3211
|
|
|
187
|
|
|
188 ------
|
|
|
189
|
|
|
190 **Input**
|
|
|
191
|
|
|
192 The input is one file of reads in FASTA or FASTQ format and any number of rRNA databases to search against.
|
|
|
193 If the user has two foward-reverse paired-sequencing reads files, they may use
|
|
|
194 the script "merge_paired_reads.sh" to interleave the reads into one file, preserving their order.
|
|
|
195
|
|
|
196 If the sequencing type for the reads is paired-ended, the user has two options under
|
|
|
197 "Sequencing type" to filter the reads and preserve their order in the file.
|
|
|
198 For a further example of each option, please refer to Section 4.2.3 in the `SortMeRNA User Manual`_.
|
|
|
199
|
|
|
200 .. _sortmerna user manual: http://bioinfo.lifl.fr/RNA/sortmerna/code/SortMeRNA-user-manual-v1.7.pdf
|
|
|
201
|
|
|
202 ------
|
|
|
203
|
|
|
204 **Output**
|
|
|
205
|
|
|
206 The output will follow the same format (FASTA or FASTQ) as the reads.
|
|
|
207
|
|
|
208 In the standalone version of SortMeRNA, the user may output the matching reads in a separate file per database (--bydbs option). This option will be made available in a future version of Galaxy.
|
|
|
209
|
|
|
210 ------
|
|
|
211
|
|
|
212 **rRNA databases**
|
|
|
213
|
|
|
214 SortMeRNA is distributed with 8 representative rRNA databases, which were
|
|
|
215 all constructed from the SILVA SSU,LSU (version 111) and the RFAM 5/5.8S
|
|
|
216 (version 11.0) databases using the tool UCLUST.
|
|
|
217
|
|
|
218 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
219 | Representative database | id % | avergage id% | # seq | Origin | # seq | filtered to remove |
|
|
|
220 +==========================+======+==============+=======+========================+========+====================+
|
|
|
221 | SILVA 16S bacteria | 85 | 91.6 | 8174 | SILVA SSU Ref NR v.111 | 244077 | 23s |
|
|
|
222 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
223 | SILVA 16S archaea | 95 | 96.7 | 3845 | SILVA SSU Ref NR v.111 | 10919 | 23s |
|
|
|
224 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
225 | SILVA 18S eukarya | 95 | 96.7 | 4512 | SILVA SSU Ref NR v.111 | 31862 | 26s,28s,23s |
|
|
|
226 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
227 | |
|
|
|
228 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
229 | SILVA 23S bacteria | 98 | 99.4 | 3055 | SILVA LSU Ref v.111 | 19580 | 16s,26s,28s |
|
|
|
230 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
231 | SILVA 23s archaea | 98 | 99.5 | 164 | SILVA LSU Ref v.111 | 405 | 16s,26s,28s |
|
|
|
232 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
233 | SILVA 28S eukarya | 98 | 99.1 | 4578 | SILVA LSU Ref v.111 | 9321 | 18s |
|
|
|
234 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
235 | |
|
|
|
236 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
237 | Rfam 5S archaea/bacteria | 98 | 99.2 | 59513 | RFAM | 116760 | |
|
|
|
238 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
239 | Rfam 5.8S eukarya | 98 | 98.9 | 13034 | RFAM | 225185 | |
|
|
|
240 +--------------------------+------+--------------+-------+------------------------+--------+--------------------+
|
|
|
241
|
|
|
242
|
|
|
243 id % :
|
|
|
244 members of the cluster must have identity at least 'id %' identity with the representative sequence
|
|
|
245
|
|
|
246 average id % :
|
|
|
247 average identity of a cluster member to the representative sequence
|
|
|
248
|
|
|
249 The user may also choose to use their own rRNA databases.
|
|
|
250
|
|
|
251 .. class:: warningmark
|
|
|
252
|
|
|
253 Note that your personal databases are indexed each time, and that
|
|
|
254 this may take some time depending on the size of the given database.
|
|
|
255
|
|
|
256 ------
|
|
|
257
|
|
|
258 **SortMeRNA parameter list**
|
|
|
259
|
|
|
260 The standalone, command-line version of SortMeRNA uses the following parameters.
|
|
|
261
|
|
|
262 For indexing (buildtrie):
|
|
|
263
|
|
|
264 This program builds a Burst trie on an input rRNA database file in fasta format
|
|
|
265 and stores the material in binary files under the folder '/automata'::
|
|
|
266
|
|
|
267 ./buildtrie --db [path to rrnas database file name {.fasta}] {OPTIONS}
|
|
|
268
|
|
|
269 The list of OPTIONS can be left blank, the default values will be used::
|
|
|
270
|
|
|
271 -L length of the sliding window (the seed)
|
|
|
272 (default: 18)
|
|
|
273
|
|
|
274 -F search only the forward strand
|
|
|
275 -R search only the reverse-complementary strand
|
|
|
276 (default: both strands are searched)
|
|
|
277
|
|
|
278 -h help
|
|
|
279
|
|
|
280
|
|
|
281
|
|
|
282
|
|
|
283 For sorting (sortmerna):
|
|
|
284
|
|
|
285 To run SortMeRNA, type in any order after 'sortmerna'::
|
|
|
286
|
|
|
287 --I [illumina reads file name {fasta/fastq}]
|
|
|
288
|
|
|
289 --454 [roche 454 reads file name {fasta/fastq}]
|
|
|
290
|
|
|
291 -n number of databases to use (must precede --db)
|
|
|
292
|
|
|
293 --db [rrnas database name(s)]
|
|
|
294
|
|
|
295 One database,
|
|
|
296 ex 1. -n 1 --db /path1/database1.fasta
|
|
|
297
|
|
|
298 Multiple databases,
|
|
|
299 ex 2. -n 2 --db /path2/database2.fasta /path3/database3.fasta
|
|
|
300
|
|
|
301 {OPTIONS}
|
|
|
302
|
|
|
303 The list of OPTIONS can be left blank, the default values will be used::
|
|
|
304
|
|
|
305 --accept [accepted reads file name]
|
|
|
306 --other [rejected reads file name]
|
|
|
307 (default: no output file is created)
|
|
|
308
|
|
|
309 --bydbs output the accepted reads by database
|
|
|
310 (default: concatenated file of reads)
|
|
|
311
|
|
|
312 --log [overall statistics file name]
|
|
|
313 (default: no statistics file created)
|
|
|
314
|
|
|
315 --paired-in put both paired-end reads into --accept file
|
|
|
316 --paired-out put both paired-end reads into --other file
|
|
|
317 (default: if one read is accepted and the other is not,
|
|
|
318 separate the reads into --accept and --other files)
|
|
|
319
|
|
|
320 -r ratio of the number of hits on the read / read length
|
|
|
321 (default Illumina: 0.25, Roche 454: 0.15)
|
|
|
322
|
|
|
323 -F search only the forward strand
|
|
|
324 -R search only the reverse-complementary strand
|
|
|
325 (default: both strands are searched)
|
|
|
326
|
|
|
327 -a number of threads to use
|
|
|
328 (default: 1)
|
|
|
329
|
|
|
330 -m (m x 4096 bytes) for loading the reads into memory
|
|
|
331 ex. '-m 4' means 4*4096 = 16384 bytes will be allocated for the reads
|
|
|
332 note: maximum -m is 1020039
|
|
|
333 (default: m = 262144 = 1GB)
|
|
|
334
|
|
|
335 -v verbose
|
|
|
336 (default: deactivated)
|
|
|
337
|
|
|
338 -h help
|
|
|
339
|
|
|
340 --version version number
|
|
|
341
|
|
|
342 ------
|
|
|
343
|
|
|
344 **Bibliography**
|
|
|
345
|
|
|
346 [1] Quast C, Pruesse E, Yilmaz P, Gerken J, Schweer T, Yarza P, Peplies J, Glöckner FO (2013) The SILVA ribosomal RNA gene database project: improved data processing and web-based tools, Nucleic Acids Research, 41 (D1): D590-D596.
|
|
|
347
|
|
|
348 [2] Rfam 11.0: 10 years of RNA families. S.W. Burge, J. Daub, R. Eberhardt, J. Tate, L. Barquist, E.P. Nawrocki, S.R. Eddy, P.P. Gardner, A. Bateman. Nucleic Acids Research (2012), doi: 10.1093/nar/gks1005
|
|
|
349
|
|
|
350 [3] Edgar, R.C. (2010) Search and clustering orders of magnitude faster than BLAST, Bioinformatics 26(19), 2460-2461, doi: 10.1093/bioinformatics/btq461
|
|
|
351
|
|
|
352 [4] Loman, N. J. and Misra, Raju V and Dallman, Timothy J and Constantinidou, Chrystala and Gharbia, Saheer E and Wain, John and Pallen, Mark J., Performance comparison of benchtop high-throughput sequencing platforms (2012), Nature Biotechnology, 30 (5). pp. 434-439
|
|
|
353 </help>
|
|
|
354 </tool>
|
