|
1
|
1 <tool id="mira_4_0_de_novo" name="MIRA v4.0 de novo assember" version="0.0.7">
|
|
|
2 <description>Takes Sanger, Roche 454, Solexa/Illumina, Ion Torrent and PacBio reads</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="binary">mira</requirement>
|
|
|
5 <requirement type="binary">miraconvert</requirement>
|
|
|
6 <requirement type="package" version="4.0.2">MIRA</requirement>
|
|
|
7 <requirement type="binary">samtools</requirement>
|
|
|
8 <requirement type="package" version="0.1.19">samtools</requirement>
|
|
|
9 </requirements>
|
|
|
10 <code file="mira4_validator.py" />
|
|
|
11 <stdio>
|
|
|
12 <!-- Assume anything other than zero is an error -->
|
|
|
13 <exit_code range="1:" />
|
|
|
14 <exit_code range=":-1" />
|
|
|
15 </stdio>
|
|
|
16 <version_command interpreter="python">mira4.py --version</version_command>
|
|
|
17 <command interpreter="python">mira4.py
|
|
|
18 --manifest "$manifest"
|
|
|
19 #if str($maf_wanted)=="true":
|
|
|
20 --maf "$out_maf"
|
|
|
21 #end if
|
|
|
22 #if str($bam_wanted)=="true":
|
|
|
23 --bam "$out_bam"
|
|
|
24 #end if
|
|
|
25 --fasta "$out_fasta"
|
|
|
26 --log "$out_log"
|
|
|
27 </command>
|
|
|
28 <configfiles>
|
|
|
29 <configfile name="manifest">
|
|
|
30 project = MIRA
|
|
|
31 job = denovo,${job_type},${job_quality}
|
|
|
32 parameters = -NW:cmrnl=no -DI:trt=/tmp -OUT:orc=no
|
|
|
33 ## -GE:not is short for -GENERAL:number_of_threads and using one (1)
|
|
|
34 ## can be useful for repeatability of assemblies and bug hunting.
|
|
|
35 ## This is overriden by the command line -t switch which is easier
|
|
|
36 ## to set from within Galaxy.
|
|
|
37 ##
|
|
|
38 ## -NW:cmrnl is short for -NAG_AND_WARN:check_maxreadnamelength
|
|
|
39 ## and without this MIRA aborts with read names over 40 characters
|
|
|
40 ## due to limitations of some downstream tools.
|
|
|
41 ##
|
|
|
42 ## -DI:trt is short for -DIRECTORY:tmp_redirected_to and should
|
|
|
43 ## point to a local hard drive (not something like NFS on network).
|
|
|
44 ## We replace /tmp with an environment variable via mira4.py
|
|
|
45 ##
|
|
|
46 ## -OUT:orc=no is short for -OUTPUT:output_result_caf=no
|
|
|
47 ## which turns off an output file we don't want anyway.
|
|
|
48
|
|
|
49 #for $rg in $read_group
|
|
|
50
|
|
|
51 ##This bar goes into the manifest as a comment line
|
|
|
52 #------------------------------------------------------------------------------
|
|
|
53
|
|
|
54 readgroup
|
|
|
55 technology = ${rg.technology}
|
|
|
56 ##Record the segment placement (if any)
|
|
|
57 #if str($rg.segments.type) == "paired"
|
|
|
58 segment_placement = ${rg.segments.placement}
|
|
|
59 segment_naming = ${rg.segments.naming}
|
|
|
60 #if str($rg.segments.min_size) != "" or str($rg.segments.max_size) != ""
|
|
|
61 ##If our min/max validation failed I trust MIRA to give an error message...
|
|
|
62 template_size = $rg.segments.min_size $rg.segments.max_size
|
|
|
63 #end if
|
|
|
64 #end if
|
|
|
65 ##if str($rg.segments.type) == "none"
|
|
|
66 ##MIRA4 manual says use segment_placement = unknown or ? for unpaired data
|
|
|
67 ##but this stopped working in MIRA 4.0 RC5 and 4.0 (final). See:
|
|
|
68 ##http://www.freelists.org/post/mira_talk/Unpaired-reads-and-segment-placement--or-unknown
|
|
|
69 ##segment_placement = ?
|
|
|
70 ##end if
|
|
|
71 ##MIRA will accept multiple filenames on one data line, or multiple data lines
|
|
|
72 #for $f in $rg.filenames
|
|
|
73 ##Must now map Galaxy datatypes to MIRA file types...
|
|
|
74 #if $f.ext.startswith("fastq")
|
|
|
75 ##MIRA doesn't like fastqsanger etc, just plain old fastq:
|
|
|
76 data = fastq::$f
|
|
|
77 #elif $f.ext == "mira"
|
|
|
78 ##We're calling *.maf the "mira" format in Galaxy (name space collision)
|
|
|
79 data = maf::$f
|
|
|
80 #else
|
|
|
81 ##MIRA is happy with fasta as name,
|
|
|
82 data = ${f.ext}::$f
|
|
|
83 #end if
|
|
|
84 #end for
|
|
|
85 #end for
|
|
|
86 </configfile>
|
|
|
87 </configfiles>
|
|
|
88 <inputs>
|
|
|
89 <param name="job_type" type="select" label="Assembly type">
|
|
|
90 <option value="genome">Genome</option>
|
|
|
91 <option value="est">EST (transcriptome)</option>
|
|
|
92 </param>
|
|
|
93 <param name="job_quality" type="select" label="Assembly quality grade">
|
|
|
94 <option value="accurate">Accurate</option>
|
|
|
95 <option value="draft">Draft</option>
|
|
|
96 </param>
|
|
|
97 <repeat name="read_group" title="Read Group" min="1">
|
|
|
98 <param name="technology" type="select" label="Read technology">
|
|
|
99 <option value="solexa">Solexa/Illumina</option>
|
|
|
100 <option value="sanger">Sanger cappillary sequencing</option>
|
|
|
101 <option value="454">Roche 454</option>
|
|
|
102 <option value="iontor">Ion Torrent</option>
|
|
|
103 <option value="pcbiolq">PacBio low quality (raw)</option>
|
|
|
104 <option value="pcbiohq">PacBio high quality (corrected)</option>
|
|
|
105 <option value="text">Synthetic reads (database entries, consensus sequences, artifical reads, etc)</option>
|
|
|
106 <!-- TODO reference/backbone as an entry here? -->
|
|
|
107 </param>
|
|
|
108 <conditional name="segments">
|
|
|
109 <param name="type" type="select" label="Are these paired reads?">
|
|
|
110 <option value="paired">Paired reads</option>
|
|
|
111 <option value="none">Single reads or not relevant (e.g. primer walking with Sanger capillary sequencing)</option>
|
|
|
112 </param>
|
|
|
113 <when value="paired">
|
|
|
114 <param name="placement" type="select" label="Pairing type (segment placing)">
|
|
|
115 <option value="FR">---> <--- (e.g. Sanger capillary or Solexa/Illumina paired-end library)</option>
|
|
|
116 <option value="RF"><--- ---> (e.g. Solexa/Illumina mate-pair library)</option>
|
|
|
117 <option value="SB">2---> 1---> (e.g. Roche 454 paired-end libraries or IonTorrent long-mate; see note)</option>
|
|
|
118 </param>
|
|
|
119 <!-- min/max validation is done via the <code> tag -->
|
|
|
120 <param name="min_size" type="integer" optional="true" min="0" value=""
|
|
|
121 label="Minimum size of 'good' DNA templates in the library preparation"
|
|
|
122 help="Optional, but if used you must also supply a maximum value." />
|
|
|
123 <param name="max_size" type="integer" optional="true" min="0" value=""
|
|
|
124 label="Maximum size of 'good' DNA templates in the library preparation"
|
|
|
125 help="Optional, but if used you must also supply a minimum value." />
|
|
|
126 <param name="naming" type="select" label="Pair naming convention">
|
|
|
127 <option value="solexa">Solexa/Illumina (using '/1' and '/2' suffixes, or later Illumina colon system)</option>
|
|
|
128 <option value="FR">Forward/Reverse scheme (using '.f*' and '.r*' suffixes)</option>
|
|
|
129 <option value="tigr">TIGR scheme (using 'TF*' and 'TR*' suffixes)</option>
|
|
|
130 <option value="sanger">Sanger scheme (see notes)</option>
|
|
|
131 <option value="stlouis">St. Louis scheme (see notes)</option>
|
|
|
132 </param>
|
|
|
133 </when>
|
|
|
134 <when value="none" /><!-- no further questions -->
|
|
|
135 </conditional>
|
|
|
136 <param name="filenames" type="data" format="fastq,mira" multiple="true" required="true" label="Read file(s)"
|
|
|
137 help="Multiple files allowed, for example paired reads can be given as two files (MIRA looks at read names to identify pairs)." />
|
|
|
138 </repeat>
|
|
|
139 <param name="maf_wanted" type="boolean" label="Output assembly in MIRA's own format?" checked="False" />
|
|
|
140 <param name="bam_wanted" type="boolean" label="Convert assembly into BAM format?" checked="True" />
|
|
|
141 </inputs>
|
|
|
142 <outputs>
|
|
|
143 <data name="out_fasta" format="fasta" label="MIRA de novo contigs (FASTA)" />
|
|
|
144 <data name="out_bam" format="bam" label="MIRA de novo assembly (BAM)">
|
|
|
145 <filter>bam_wanted is True</filter>
|
|
|
146 </data>
|
|
|
147 <data name="out_maf" format="mira" label="MIRA de novo assembly">
|
|
|
148 <filter>maf_wanted is True</filter>
|
|
|
149 </data>
|
|
|
150 <!-- TODO?
|
|
|
151 <data name="out_contigstats" format="tabular" label="MIRA contig stats" />
|
|
|
152 -->
|
|
|
153 <data name="out_log" format="txt" label="MIRA de novo log" />
|
|
|
154 </outputs>
|
|
|
155 <tests>
|
|
|
156 <!-- Tiger mitochondria, selected paired end Illumina reads from SRR639755
|
|
|
157 Note we're using just one repeat group, and only the filenames parameter
|
|
|
158 within it, so this should work with current test framework limitations:
|
|
|
159 TODO: Revise example and/or -NW:cac=warn and -NW:acv=80 settings
|
|
|
160 MIRA 4.0 complains as coverage is about x93 which is over 80 limit.
|
|
|
161 Also MIRA 4.0 gives three contigs as output.
|
|
|
162 <test>
|
|
|
163 <param name="job_type" value="genome" />
|
|
|
164 <param name="job_quality" value="accurate" />
|
|
|
165 <param name="filenames" value="SRR639755_mito_pairs.fastq.gz" ftype="fastqsanger" />
|
|
|
166 <output name="out_fasta" file="SRR639755_mito_pairs.mira4_de_novo.fasta" ftype="fasta" />
|
|
|
167 </test>
|
|
|
168 -->
|
|
|
169 <!-- Simple assembly based on MIRA's minidemo/demo4 example
|
|
|
170 Note we're using just one repeat group,
|
|
|
171 but several parameters with the repeat
|
|
|
172 -->
|
|
|
173 <test>
|
|
|
174 <param name="job_type" value="genome" />
|
|
|
175 <param name="job_quality" value="accurate" />
|
|
|
176 <param name="technology" value="sanger" />
|
|
|
177 <param name="type" value="none" />
|
|
|
178 <param name="filenames" value="U13small_m.fastq" ftype="fastqsanger" />
|
|
|
179 <param name="maf_wanted" value="true"/>
|
|
|
180 <param name="bam_wanted" value="true"/>
|
|
|
181 <output name="out_fasta" file="U13small_m.mira4_de_novo.fasta" ftype="fasta" />
|
|
|
182 <output name="out_bam" file="empty_file.dat" compare="contains" />
|
|
|
183 <!-- TODO: Suggest startswith as a compare method? -->
|
|
|
184 <output name="out_maf" file="header.mira" compare="contains" />
|
|
|
185 <output name="out_log" file="empty_file.dat" compare="contains" />
|
|
|
186 </test>
|
|
|
187 <!-- Simple assembly based on MIRA's minidemo/solexa1 example
|
|
|
188 Note we're using just one repeat group,
|
|
|
189 but two parameters within the repeat (filename, no pairing)
|
|
|
190 -->
|
|
|
191 <test>
|
|
|
192 <param name="job_type" value="genome" />
|
|
|
193 <param name="job_quality" value="accurate" />
|
|
|
194 <param name="type" value="none" />
|
|
|
195 <param name="filenames" value="ecoli.fastq" ftype="fastqsanger" />
|
|
|
196 <param name="maf_wanted" value="false"/>
|
|
|
197 <param name="bam_wanted" value="false"/>
|
|
|
198 <output name="out_fasta" file="ecoli.mira4_de_novo.fasta" ftype="fasta" />
|
|
|
199 <output name="out_log" file="empty_file.dat" compare="contains" />
|
|
|
200 </test>
|
|
|
201 </tests>
|
|
|
202 <help>
|
|
|
203
|
|
|
204 **What it does**
|
|
|
205
|
|
|
206 Runs MIRA v4.0 in de novo mode, collects the output, generates a sorted BAM
|
|
|
207 file, and then throws away all the temporary files.
|
|
|
208
|
|
|
209 MIRA is an open source assembly tool capable of handling sequence data from
|
|
|
210 a range of platforms (Sanger capillary, Solexa/Illumina, Roche 454, Ion Torrent
|
|
|
211 and also PacBio).
|
|
|
212
|
|
|
213 It is particularly suited to small genomes such as bacteria.
|
|
|
214
|
|
|
215
|
|
|
216 **Notes on paired reads**
|
|
|
217
|
|
|
218 .. class:: warningmark
|
|
|
219
|
|
|
220 MIRA uses read naming conventions to identify paired read partners
|
|
|
221 (and does not care about their order in the input files). In most cases,
|
|
|
222 the Solexa/Illumina setting is fine. For Sanger capillary sequencing,
|
|
|
223 you may need to rename your reads to match one of the standard conventions
|
|
|
224 supported by MIRA. For Roche 454 or Ion Torrent the appropriate settings
|
|
|
225 depend on how the FASTQ file was produced:
|
|
|
226
|
|
|
227 * If using Roche's ``sffinfo`` or older versions of ``sff_extract``
|
|
|
228 to convert SFF files to FASTQ, your reads will probably have the
|
|
|
229 ``---> <---`` orientation and use the ``.f`` and ``.r``
|
|
|
230 suffixes (FR naming).
|
|
|
231
|
|
|
232 * If using a recent version of ``sff_extract``, then the ``/1`` and ``/2``
|
|
|
233 suffixes are used (Solexa/Illumina style naming) and the original
|
|
|
234 ``2---> 1--->`` orientation is preserved.
|
|
|
235
|
|
|
236 The reason for this is the raw data for Roche 454 and Ion Torrent paired-end
|
|
|
237 libraries sequences a circularised fragment such that the raw data begins
|
|
|
238 with the end of the fragment, a linker, then the start of the fragment.
|
|
|
239 This means both the start and end are sequenced from the same strand, and
|
|
|
240 have the orientation ``2---> 1--->``. However, in order to use the data
|
|
|
241 with traditional tools expecting Sanger capillary style ``---> <---``
|
|
|
242 orientation it was common to reverse complement one of the pair to mimic this.
|
|
|
243
|
|
|
244
|
|
|
245 **Citation**
|
|
|
246
|
|
|
247 If you use this Galaxy tool in work leading to a scientific publication please
|
|
|
248 cite the following papers:
|
|
|
249
|
|
|
250 Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
|
|
|
251 Galaxy tools and workflows for sequence analysis with applications
|
|
|
252 in molecular plant pathology. PeerJ 1:e167
|
|
|
253 http://dx.doi.org/10.7717/peerj.167
|
|
|
254
|
|
|
255 Bastien Chevreux, Thomas Wetter and Sándor Suhai (1999).
|
|
|
256 Genome Sequence Assembly Using Trace Signals and Additional Sequence Information.
|
|
|
257 Computer Science and Biology: Proceedings of the German Conference on Bioinformatics (GCB) 99, pp. 45-56.
|
|
|
258 http://www.bioinfo.de/isb/gcb99/talks/chevreux/main.html
|
|
|
259
|
|
|
260 This wrapper is available to install into other Galaxy Instances via the Galaxy
|
|
|
261 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/mira4_assembler
|
|
|
262 </help>
|
|
|
263 <citations>
|
|
|
264 <citation type="doi">10.7717/peerj.167</citation>
|
|
|
265 <citation type="bibtex">@ARTICLE{Chevreux1999-mira3,
|
|
|
266 author = {B. Chevreux and T. Wetter and S. Suhai},
|
|
|
267 year = {1999},
|
|
|
268 title = {Genome Sequence Assembly Using Trace Signals and Additional Sequence Information},
|
|
|
269 journal = {Computer Science and Biology: Proceedings of the German Conference on Bioinformatics (GCB)}
|
|
|
270 volume = {99},
|
|
|
271 pages = {45-56},
|
|
|
272 url = {http://www.bioinfo.de/isb/gcb99/talks/chevreux/main.html}
|
|
|
273 }</citation>
|
|
|
274 </citations>
|
|
|
275 </tool>
|
