|
4
|
1 <tool id="mira_4_0_mapping" name="MIRA v4.0 mapping" version="0.0.11">
|
|
2
|
2 <description>Maps Sanger, Roche 454, Solexa/Illumina, Ion Torrent and PacBio reads</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="4.0.2">MIRA</requirement>
|
|
|
5 <requirement type="package" version="0.1.19">samtools</requirement>
|
|
|
6 </requirements>
|
|
4
|
7 <version_command>
|
|
|
8 python $__tool_directory__/mira4.py --version
|
|
|
9 </version_command>
|
|
|
10 <command detect_errors="aggressive">
|
|
|
11 python $__tool_directory__/mira4.py
|
|
|
12 --manifest '$manifest'
|
|
2
|
13 #if str($maf_wanted) == "true":
|
|
4
|
14 --maf '$out_maf'
|
|
2
|
15 #end if
|
|
|
16 #if str($bam_wanted) == "true":
|
|
4
|
17 --bam '$out_bam'
|
|
2
|
18 #end if
|
|
4
|
19 --fasta '$out_fasta'
|
|
|
20 --log '$out_log'
|
|
2
|
21 </command>
|
|
|
22 <configfiles>
|
|
|
23 <configfile name="manifest">
|
|
|
24 project = MIRA
|
|
|
25 job = mapping,${job_type},${job_quality}
|
|
|
26 parameters = -NW:cmrnl=no -DI:trt=/tmp -OUT:orc=no
|
|
|
27 ## -GE:not is short for -GENERAL:number_of_threads and using one (1)
|
|
|
28 ## can be useful for repeatability of assemblies and bug hunting.
|
|
|
29 ## This is overriden by the command line -t switch which is easier
|
|
|
30 ## to set from within Galaxy.
|
|
|
31 ##
|
|
|
32 ## -NW:cmrnl is short for -NAG_AND_WARN:check_maxreadnamelength
|
|
|
33 ## and without this MIRA aborts with read names over 40 characters
|
|
|
34 ## due to limitations of some downstream tools.
|
|
|
35 ##
|
|
|
36 ## -DI:trt is short for -DIRECTORY:tmp_redirected_to and should
|
|
|
37 ## point to a local hard drive (not something like NFS on network).
|
|
|
38 ## We replace /tmp with an environment variable via mira4.py
|
|
|
39 ##
|
|
|
40 ## -OUT:orc=no is short for -OUTPUT:output_result_caf=no
|
|
|
41 ## which turns off an output file we don't want anyway.
|
|
|
42
|
|
|
43 ##This bar goes into the manifest as a comment line
|
|
|
44 #------------------------------------------------------------------------------
|
|
|
45
|
|
|
46 readgroup
|
|
|
47 is_reference
|
|
|
48 #if str($strain_setup)=="same"
|
|
|
49 strain = StrainX
|
|
|
50 #end if
|
|
|
51 #for $f in $references
|
|
|
52 ##Must now map Galaxy datatypes to MIRA file types...
|
|
|
53 #if $f.ext.startswith("fastq")
|
|
|
54 ##MIRA doesn't like fastqsanger etc, just plain old fastq:
|
|
|
55 data = fastq::$f
|
|
|
56 #elif $f.ext == "mira"
|
|
|
57 ##We're calling *.maf the "mira" format in Galaxy (name space collision)
|
|
|
58 data = maf::$f
|
|
|
59 #elif $f.ext == "fasta"
|
|
|
60 ##We're calling MIRA with the file type as "fna" as otherwise it wants quals
|
|
|
61 data = fna::$f
|
|
|
62 #else
|
|
|
63 ##Currently don't expect anything else...
|
|
|
64 data = ${f.ext}::$f
|
|
|
65 #end if
|
|
|
66 #end for
|
|
|
67 #for $rg in $read_group
|
|
|
68
|
|
|
69 ##This bar goes into the manifest as a comment line
|
|
|
70 #------------------------------------------------------------------------------
|
|
|
71
|
|
|
72 readgroup
|
|
|
73 technology = ${rg.technology}
|
|
|
74 #if str($strain_setup)=="same"
|
|
|
75 ##This is perhaps redundant as MIRA defaults to StrainX for the reads:
|
|
|
76 strain = StrainX
|
|
|
77 #end if
|
|
|
78 ##Record the segment placement (if any)
|
|
|
79 #if str($rg.segments.type) == "paired"
|
|
|
80 segment_placement = ${rg.segments.placement}
|
|
|
81 segment_naming = ${rg.segments.naming}
|
|
|
82 #end if
|
|
|
83 ##if str($rg.segments.type) == "none"
|
|
|
84 ##MIRA4 manual says use segment_placement = unknown or ? for unpaired data
|
|
|
85 ##but this stopped working in MIRA 4.0 RC5 and 4.0 (final). See:
|
|
|
86 ##http://www.freelists.org/post/mira_talk/Unpaired-reads-and-segment-placement--or-unknown
|
|
|
87 ##segment_placement = ?
|
|
|
88 ##end if
|
|
|
89 ##MIRA will accept multiple filenames on one data line, or multiple data lines
|
|
|
90 #for $f in $rg.filenames
|
|
|
91 ##Must now map Galaxy datatypes to MIRA file types...
|
|
|
92 #if $f.ext.startswith("fastq")
|
|
|
93 ##MIRA doesn't like fastqsanger etc, just plain old fastq:
|
|
|
94 data = fastq::$f
|
|
|
95 #elif $f.ext == "mira"
|
|
|
96 ##We're calling *.maf the "mira" format in Galaxy (name space collision)
|
|
|
97 data = maf::$f
|
|
|
98 #else
|
|
|
99 ##Currently don't expect anything else...
|
|
|
100 data = ${f.ext}::$f
|
|
|
101 #end if
|
|
|
102 #end for
|
|
|
103 #end for
|
|
|
104 </configfile>
|
|
|
105 </configfiles>
|
|
|
106 <inputs>
|
|
|
107 <param name="job_type" type="select" label="Assembly type">
|
|
|
108 <option value="genome">Genome</option>
|
|
|
109 <option value="est">EST (transcriptome)</option>
|
|
|
110 </param>
|
|
|
111 <param name="job_quality" type="select" label="Assembly quality grade">
|
|
|
112 <option value="accurate">Accurate</option>
|
|
|
113 <option value="draft">Draft</option>
|
|
|
114 </param>
|
|
|
115 <!-- TODO? Allow technology type for references? -->
|
|
|
116 <!-- TODO? Allow strain settings for reference(s) and reads? -->
|
|
|
117 <!-- TODO? Use a repeat to allow for multi-strain references? -->
|
|
|
118 <!-- TODO? Add strain to the mapping read groups? -->
|
|
4
|
119 <param name="references" type="data" format="fasta,fastq,mira" multiple="true" optional="false" label="Backbone reference file(s)"
|
|
2
|
120 help="Multiple files allowed, for example one FASTA file per chromosome or plasmid." />
|
|
|
121 <param name="strain_setup" type="select" label="Strain configuration (reference vs reads)">
|
|
|
122 <option value="default">Different strains - mapping reads onto a related reference ('StrainX' vs 'ReferenceStrain')</option>
|
|
|
123 <option value="same">Same strain - mapping reads from same reference (all 'StrainX')</option>
|
|
|
124 </param>
|
|
|
125 <repeat name="read_group" title="Read Group" min="1">
|
|
|
126 <param name="technology" type="select" label="Read technology">
|
|
|
127 <option value="solexa">Solexa/Illumina</option>
|
|
|
128 <option value="sanger">Sanger cappillary sequencing</option>
|
|
|
129 <option value="454">Roche 454</option>
|
|
|
130 <option value="iontor">Ion Torrent</option>
|
|
|
131 <option value="pcbiolq">PacBio low quality (raw)</option>
|
|
|
132 <option value="pcbiohq">PacBio high quality (corrected)</option>
|
|
|
133 <option value="text">Synthetic reads (database entries, consensus sequences, artifical reads, etc)</option>
|
|
|
134 </param>
|
|
|
135 <conditional name="segments">
|
|
|
136 <param name="type" type="select" label="Are these paired reads?">
|
|
|
137 <option value="paired">Paired reads</option>
|
|
|
138 <option value="none">Single reads or not relevant (e.g. primer walking with Sanger capillary sequencing)</option>
|
|
|
139 </param>
|
|
|
140 <when value="paired">
|
|
|
141 <param name="placement" type="select" label="Pairing type (segment placing)">
|
|
|
142 <option value="FR">---> <--- (e.g. Sanger capillary or Solexa/Illumina paired-end library)</option>
|
|
|
143 <option value="RF"><--- ---> (e.g. Solexa/Illumina mate-pair library)</option>
|
|
|
144 <option value="SB">2---> 1---> (e.g. Roche 454 paired-end libraries or IonTorrent long-mate; see note)</option>
|
|
|
145 </param>
|
|
|
146 <param name="naming" type="select" label="Pair naming convention">
|
|
|
147 <option value="solexa">Solexa/Illumina (using '/1' and '/2' suffixes, or later Illumina colon system)</option>
|
|
|
148 <option value="FR">Forward/Reverse scheme (using '.f*' and '.r*' suffixes)</option>
|
|
|
149 <option value="tigr">TIGR scheme (using 'TF*' and 'TR*' suffixes)</option>
|
|
|
150 <option value="sanger">Sanger scheme (see notes)</option>
|
|
|
151 <option value="stlouis">St. Louis scheme (see notes)</option>
|
|
|
152 </param>
|
|
|
153 </when>
|
|
|
154 <when value="none" /><!-- no further questions -->
|
|
|
155 </conditional>
|
|
4
|
156 <param name="filenames" type="data" format="fastq,mira" multiple="true" optional="false" label="Read file(s)"
|
|
2
|
157 help="Multiple files allowed, for example paired reads can be given as two files (MIRA looks at read names to identify pairs)." />
|
|
|
158 </repeat>
|
|
4
|
159 <param name="maf_wanted" type="boolean" label="Output mapping in MIRA's own format?" checked="false" />
|
|
|
160 <param name="bam_wanted" type="boolean" label="Convert mapping into BAM format?" checked="true" />
|
|
2
|
161 </inputs>
|
|
|
162 <outputs>
|
|
|
163 <data name="out_fasta" format="fasta" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping contigs (FASTA)" />
|
|
|
164 <data name="out_bam" format="bam" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping assembly (BAM)">
|
|
|
165 <filter>bam_wanted is True</filter>
|
|
|
166 </data>
|
|
|
167 <data name="out_maf" format="mira" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping assembly">
|
|
|
168 <filter>maf_wanted is True</filter>
|
|
|
169 </data>
|
|
|
170 <data name="out_log" format="txt" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping log" />
|
|
|
171 </outputs>
|
|
|
172 <tests>
|
|
|
173 <test>
|
|
|
174 <param name="job_type" value="genome" />
|
|
|
175 <param name="job_quality" value="accurate" />
|
|
|
176 <param name="references" value="tvc_contigs.fasta" ftype="fasta" />
|
|
|
177 <param name="strain_setup" value="default" />
|
|
|
178 <param name="type" value="none" />
|
|
|
179 <param name="filenames" value="tvc_mini.fastq" ftype="fastqsanger" />
|
|
|
180 <param name="maf_wanted" value="true"/>
|
|
|
181 <param name="bam_wanted" value="true"/>
|
|
|
182 <output name="out_fasta" file="tvc_map_ref_strain.fasta" ftype="fasta" />
|
|
|
183 <output name="out_bam" file="empty_file.dat" compare="contains" />
|
|
|
184 <!-- TODO: Suggest startswith as a compare method? -->
|
|
|
185 <output name="out_maf" file="header.mira" compare="contains" />
|
|
|
186 <output name="out_log" file="empty_file.dat" compare="contains" />
|
|
|
187 </test>
|
|
|
188 <test>
|
|
|
189 <param name="job_type" value="genome" />
|
|
|
190 <param name="job_quality" value="accurate" />
|
|
|
191 <param name="references" value="tvc_contigs.fasta" ftype="fasta" />
|
|
|
192 <param name="strain_setup" value="same" />
|
|
|
193 <param name="type" value="none" />
|
|
|
194 <param name="filenames" value="tvc_mini.fastq" ftype="fastqsanger" />
|
|
|
195 <param name="maf_wanted" value="false"/>
|
|
|
196 <param name="bam_wanted" value="false"/>
|
|
|
197 <output name="out_fasta" file="tvc_map_same_strain.fasta" ftype="fasta" />
|
|
|
198 <output name="out_log" file="empty_file.dat" compare="contains" />
|
|
|
199 </test>
|
|
|
200 </tests>
|
|
|
201 <help>
|
|
|
202
|
|
|
203 **What it does**
|
|
|
204
|
|
|
205 Runs MIRA v4.0 in mapping mode, collects the output, generates a sorted BAM
|
|
|
206 file, and throws away all the temporary files.
|
|
|
207
|
|
|
208 MIRA is an open source assembly tool capable of handling sequence data from
|
|
|
209 a range of platforms (Sanger capillary, Solexa/Illumina, Roche 454, Ion Torrent
|
|
|
210 and also PacBio).
|
|
|
211
|
|
|
212 It is particularly suited to small genomes such as bacteria.
|
|
|
213
|
|
|
214
|
|
|
215 **Notes on paired reads**
|
|
|
216
|
|
|
217 .. class:: warningmark
|
|
|
218
|
|
|
219 MIRA uses read naming conventions to identify paired read partners
|
|
|
220 (and does not care about their order in the input files). In most cases,
|
|
|
221 the Solexa/Illumina setting is fine. For Sanger capillary sequencing,
|
|
|
222 you may need to rename your reads to match one of the standard conventions
|
|
|
223 supported by MIRA. For Roche 454 or Ion Torrent the appropriate settings
|
|
|
224 depend on how the FASTQ file was produced:
|
|
|
225
|
|
|
226 * If using Roche's ``sffinfo`` or older versions of ``sff_extract``
|
|
|
227 to convert SFF files to FASTQ, your reads will probably have the
|
|
|
228 ``---> <---`` orientation and use the ``.f`` and ``.r``
|
|
|
229 suffixes (FR naming).
|
|
|
230
|
|
|
231 * If using a recent version of ``sff_extract``, then the ``/1`` and ``/2``
|
|
|
232 suffixes are used (Solexa/Illumina style naming) and the original
|
|
|
233 ``2---> 1--->`` orientation is preserved.
|
|
|
234
|
|
|
235 The reason for this is the raw data for Roche 454 and Ion Torrent paired-end
|
|
|
236 libraries sequences a circularised fragment such that the raw data begins
|
|
|
237 with the end of the fragment, a linker, then the start of the fragment.
|
|
|
238 This means both the start and end are sequenced from the same strand, and
|
|
|
239 have the orientation ``2---> 1--->``. However, in order to use the data
|
|
|
240 with traditional tools expecting Sanger capillary style ``---> <---``
|
|
|
241 orientation it was common to reverse complement one of the pair to mimic this.
|
|
|
242
|
|
|
243
|
|
|
244 **Citation**
|
|
|
245
|
|
|
246 If you use this Galaxy tool in work leading to a scientific publication please
|
|
|
247 cite the following papers:
|
|
|
248
|
|
|
249 Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
|
|
|
250 Galaxy tools and workflows for sequence analysis with applications
|
|
|
251 in molecular plant pathology. PeerJ 1:e167
|
|
|
252 http://dx.doi.org/10.7717/peerj.167
|
|
|
253
|
|
|
254 Bastien Chevreux, Thomas Wetter and Sándor Suhai (1999).
|
|
|
255 Genome Sequence Assembly Using Trace Signals and Additional Sequence Information.
|
|
|
256 Computer Science and Biology: Proceedings of the German Conference on Bioinformatics (GCB) 99, pp. 45-56.
|
|
|
257 http://www.bioinfo.de/isb/gcb99/talks/chevreux/main.html
|
|
|
258
|
|
|
259 This wrapper is available to install into other Galaxy Instances via the Galaxy
|
|
|
260 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/mira4_assembler
|
|
|
261 </help>
|
|
|
262 <citations>
|
|
|
263 <citation type="doi">10.7717/peerj.167</citation>
|
|
|
264 <citation type="bibtex">@ARTICLE{Chevreux1999-mira3,
|
|
|
265 author = {B. Chevreux and T. Wetter and S. Suhai},
|
|
|
266 year = {1999},
|
|
|
267 title = {Genome Sequence Assembly Using Trace Signals and Additional Sequence Information},
|
|
|
268 journal = {Computer Science and Biology: Proceedings of the German Conference on Bioinformatics (GCB)}
|
|
|
269 volume = {99},
|
|
|
270 pages = {45-56},
|
|
|
271 url = {http://www.bioinfo.de/isb/gcb99/talks/chevreux/main.html}
|
|
|
272 }</citation>
|
|
|
273 </citations>
|
|
|
274 </tool>
|
