|
0
|
1 <tool id="mira_4_0_mapping" name="MIRA v4.0 mapping" version="0.0.4">
|
|
|
2 <description>Maps 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">MIRA</requirement>
|
|
|
7 <requirement type="binary">samtools</requirement>
|
|
|
8 <requirement type="package" version="0.1.19">samtools</requirement>
|
|
|
9 </requirements>
|
|
|
10 <version_command interpreter="python">mira4.py --version</version_command>
|
|
|
11 <command interpreter="python">mira4.py
|
|
|
12 --manifest "$manifest"
|
|
|
13 #if str($maf_wanted) == "true":
|
|
|
14 --maf "$out_maf"
|
|
|
15 #end if
|
|
|
16 #if str($bam_wanted) == "true":
|
|
|
17 --bam "$out_bam"
|
|
|
18 #end if
|
|
|
19 --fasta "$out_fasta"
|
|
|
20 --log "$out_log"
|
|
|
21 </command>
|
|
|
22 <stdio>
|
|
|
23 <!-- Assume anything other than zero is an error -->
|
|
|
24 <exit_code range="1:" />
|
|
|
25 <exit_code range=":-1" />
|
|
|
26 </stdio>
|
|
|
27 <inputs>
|
|
|
28 <param name="job_type" type="select" label="Assembly type">
|
|
|
29 <option value="genome">Genome</option>
|
|
|
30 <option value="est">EST (transcriptome)</option>
|
|
|
31 </param>
|
|
|
32 <param name="job_quality" type="select" label="Assembly quality grade">
|
|
|
33 <option value="accurate">Accurate</option>
|
|
|
34 <option value="draft">Draft</option>
|
|
|
35 </param>
|
|
|
36 <!-- TODO? Allow technology type for references? -->
|
|
|
37 <!-- TODO? Allow strain settings for reference(s) and reads? -->
|
|
|
38 <!-- TODO? Use a repeat to allow for multi-strain references? -->
|
|
|
39 <!-- TODO? Add strain to the mapping read groups? -->
|
|
|
40 <param name="references" type="data" format="fasta,fastq,mira" multiple="true" required="true" label="Backbone reference file(s)"
|
|
|
41 help="Multiple files allowed, for example one FASTA file per chromosome or plasmid." />
|
|
|
42 <param name="strain_setup" type="select" label="Strain configuration (reference vs reads)">
|
|
|
43 <option value="default">Different strains - mapping reads onto a related reference ('StrainX' vs 'ReferenceStrain')</option>
|
|
|
44 <option value="same">Same strain - mapping reads from same reference (all 'StrainX')</option>
|
|
|
45 </param>
|
|
|
46 <repeat name="read_group" title="Read Group" min="1">
|
|
|
47 <param name="technology" type="select" label="Read technology">
|
|
|
48 <option value="solexa">Solexa/Illumina</option>
|
|
|
49 <option value="sanger">Sanger cappillary sequencing</option>
|
|
|
50 <option value="454">Roche 454</option>
|
|
|
51 <option value="iontor">Ion Torrent</option>
|
|
|
52 <option value="pcbiolq">PacBio low quality (raw)</option>
|
|
|
53 <option value="pcbiohq">PacBio high quality (corrected)</option>
|
|
|
54 <option value="text">Synthetic reads (database entries, consensus sequences, artifical reads, etc)</option>
|
|
|
55 </param>
|
|
|
56 <conditional name="segments">
|
|
|
57 <param name="type" type="select" label="Are these paired reads?">
|
|
|
58 <option value="paired">Paired reads</option>
|
|
|
59 <option value="none">Single reads or not relevant (e.g. primer walking with Sanger capillary sequencing)</option>
|
|
|
60 </param>
|
|
|
61 <when value="paired">
|
|
|
62 <param name="placement" type="select" label="Pairing type (segment placing)">
|
|
|
63 <option value="FR">---> <--- (e.g. Sanger capillary or Solexa/Illumina paired-end library)</option>
|
|
|
64 <option value="RF"><--- ---> (e.g. Solexa/Illumina mate-pair library)</option>
|
|
|
65 <option value="SB">2---> 1---> (e.g. Roche 454 paired-end libraries or IonTorrent long-mate; see note)</option>
|
|
|
66 </param>
|
|
|
67 <param name="naming" type="select" label="Pair naming convention">
|
|
|
68 <option value="solexa">Solexa/Illumina (using '/1' and '/2' suffixes, or later Illumina colon system)</option>
|
|
|
69 <option value="FR">Forward/Reverse scheme (using '.f*' and '.r*' suffixes)</option>
|
|
|
70 <option value="tigr">TIGR scheme (using 'TF*' and 'TR*' suffixes)</option>
|
|
|
71 <option value="sanger">Sanger scheme (see notes)</option>
|
|
|
72 <option value="stlouis">St. Louis scheme (see notes)</option>
|
|
|
73 </param>
|
|
|
74 </when>
|
|
|
75 <when value="none" /><!-- no further questions -->
|
|
|
76 </conditional>
|
|
|
77 <param name="filenames" type="data" format="fastq,mira" multiple="true" required="true" label="Read file(s)"
|
|
|
78 help="Multiple files allowed, for example paired reads can be given as two files (MIRA looks at read names to identify pairs)." />
|
|
|
79 </repeat>
|
|
|
80 <param name="maf_wanted" type="boolean" label="Output mapping in MIRA's own format?" checked="False" />
|
|
|
81 <param name="bam_wanted" type="boolean" label="Convert mapping into BAM format?" checked="True" />
|
|
|
82 </inputs>
|
|
|
83 <outputs>
|
|
|
84 <data name="out_fasta" format="fasta" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping contigs (FASTA)" />
|
|
|
85 <data name="out_bam" format="bam" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping assembly (BAM)">
|
|
|
86 <filter>bam_wanted is True</filter>
|
|
|
87 </data>
|
|
|
88 <data name="out_maf" format="mira" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping assembly">
|
|
|
89 <filter>maf_wanted is True</filter>
|
|
|
90 </data>
|
|
|
91 <data name="out_log" format="txt" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping log" />
|
|
|
92 </outputs>
|
|
|
93 <configfiles>
|
|
|
94 <configfile name="manifest">
|
|
|
95 project = MIRA
|
|
|
96 job = mapping,${job_type},${job_quality}
|
|
|
97 parameters = -NW:cmrnl=no -DI:trt=/tmp -OUT:orc=no
|
|
|
98 ## -GE:not is short for -GENERAL:number_of_threads and using one (1)
|
|
|
99 ## can be useful for repeatability of assemblies and bug hunting.
|
|
|
100 ## This is overriden by the command line -t switch which is easier
|
|
|
101 ## to set from within Galaxy.
|
|
|
102 ##
|
|
|
103 ## -NW:cmrnl is short for -NAG_AND_WARN:check_maxreadnamelength
|
|
|
104 ## and without this MIRA aborts with read names over 40 characters
|
|
|
105 ## due to limitations of some downstream tools.
|
|
|
106 ##
|
|
|
107 ## -DI:trt is short for -DIRECTORY:tmp_redirected_to and should
|
|
|
108 ## point to a local hard drive (not something like NFS on network).
|
|
|
109 ## We replace /tmp with an environment variable via mira4.py
|
|
|
110 ##
|
|
|
111 ## -OUT:orc=no is short for -OUTPUT:output_result_caf=no
|
|
|
112 ## which turns off an output file we don't want anyway.
|
|
|
113
|
|
|
114 ##This bar goes into the manifest as a comment line
|
|
|
115 #------------------------------------------------------------------------------
|
|
|
116
|
|
|
117 readgroup
|
|
|
118 is_reference
|
|
|
119 #if str($strain_setup)=="same"
|
|
|
120 strain = StrainX
|
|
|
121 #end if
|
|
|
122 #for $f in $references
|
|
|
123 ##Must now map Galaxy datatypes to MIRA file types...
|
|
|
124 #if $f.ext.startswith("fastq")
|
|
|
125 ##MIRA doesn't like fastqsanger etc, just plain old fastq:
|
|
|
126 data = fastq::$f
|
|
|
127 #elif $f.ext == "mira"
|
|
|
128 ##We're calling *.maf the "mira" format in Galaxy (name space collision)
|
|
|
129 data = maf::$f
|
|
|
130 #elif $f.ext == "fasta"
|
|
|
131 ##We're calling MIRA with the file type as "fna" as otherwise it wants quals
|
|
|
132 data = fna::$f
|
|
|
133 #else
|
|
|
134 ##Currently don't expect anything else...
|
|
|
135 data = ${f.ext}::$f
|
|
|
136 #end if
|
|
|
137 #end for
|
|
|
138 #for $rg in $read_group
|
|
|
139
|
|
|
140 ##This bar goes into the manifest as a comment line
|
|
|
141 #------------------------------------------------------------------------------
|
|
|
142
|
|
|
143 readgroup
|
|
|
144 technology = ${rg.technology}
|
|
|
145 #if str($strain_setup)=="same"
|
|
|
146 ##This is perhaps redundant as MIRA defaults to StrainX for the reads:
|
|
|
147 strain = StrainX
|
|
|
148 #end if
|
|
|
149 ##Record the segment placement (if any)
|
|
|
150 #if str($rg.segments.type) == "paired"
|
|
|
151 segment_placement = ${rg.segments.placement}
|
|
|
152 segment_naming = ${rg.segments.naming}
|
|
|
153 #end if
|
|
|
154 ##if str($rg.segments.type) == "none"
|
|
|
155 ##MIRA4 manual says use segment_placement = unknown or ? for unpaired data
|
|
|
156 ##but this stopped working in MIRA 4.0 RC5 and 4.0 (final). See:
|
|
|
157 ##http://www.freelists.org/post/mira_talk/Unpaired-reads-and-segment-placement--or-unknown
|
|
|
158 ##segment_placement = ?
|
|
|
159 ##end if
|
|
|
160 ##MIRA will accept multiple filenames on one data line, or multiple data lines
|
|
|
161 #for $f in $rg.filenames
|
|
|
162 ##Must now map Galaxy datatypes to MIRA file types...
|
|
|
163 #if $f.ext.startswith("fastq")
|
|
|
164 ##MIRA doesn't like fastqsanger etc, just plain old fastq:
|
|
|
165 data = fastq::$f
|
|
|
166 #elif $f.ext == "mira"
|
|
|
167 ##We're calling *.maf the "mira" format in Galaxy (name space collision)
|
|
|
168 data = maf::$f
|
|
|
169 #else
|
|
|
170 ##Currently don't expect anything else...
|
|
|
171 data = ${f.ext}::$f
|
|
|
172 #end if
|
|
|
173 #end for
|
|
|
174 #end for
|
|
|
175 </configfile>
|
|
|
176 </configfiles>
|
|
|
177 <tests>
|
|
|
178 <test>
|
|
|
179 <param name="job_type" value="genome" />
|
|
|
180 <param name="job_quality" value="accurate" />
|
|
|
181 <param name="references" value="tvc_contigs.fasta" ftype="fasta" />
|
|
|
182 <param name="strain_setup" value="default" />
|
|
|
183 <param name="type" value="none" />
|
|
|
184 <param name="filenames" value="tvc_mini.fastq" ftype="fastqsanger" />
|
|
|
185 <param name="maf_wanted" value="true"/>
|
|
|
186 <param name="bam_wanted" value="true"/>
|
|
|
187 <output name="out_fasta" file="tvc_map_ref_strain.fasta" ftype="fasta" />
|
|
|
188 <output name="out_bam" file="empty_file.dat" compare="contains" />
|
|
|
189 <!-- TODO: Suggest startswith as a compare method? -->
|
|
|
190 <output name="out_maf" file="header.mira" compare="contains" />
|
|
|
191 <output name="out_log" file="empty_file.dat" compare="contains" />
|
|
|
192 </test>
|
|
|
193 <test>
|
|
|
194 <param name="job_type" value="genome" />
|
|
|
195 <param name="job_quality" value="accurate" />
|
|
|
196 <param name="references" value="tvc_contigs.fasta" ftype="fasta" />
|
|
|
197 <param name="strain_setup" value="same" />
|
|
|
198 <param name="type" value="none" />
|
|
|
199 <param name="filenames" value="tvc_mini.fastq" ftype="fastqsanger" />
|
|
|
200 <param name="maf_wanted" value="false"/>
|
|
|
201 <param name="bam_wanted" value="false"/>
|
|
|
202 <output name="out_fasta" file="tvc_map_same_strain.fasta" ftype="fasta" />
|
|
|
203 <output name="out_log" file="empty_file.dat" compare="contains" />
|
|
|
204 </test>
|
|
|
205 </tests>
|
|
|
206 <help>
|
|
|
207
|
|
|
208 **What it does**
|
|
|
209
|
|
|
210 Runs MIRA v4.0 in mapping mode, collects the output, generates a sorted BAM
|
|
|
211 file, and throws away all the temporary files.
|
|
|
212
|
|
|
213 MIRA is an open source assembly tool capable of handling sequence data from
|
|
|
214 a range of platforms (Sanger capillary, Solexa/Illumina, Roche 454, Ion Torrent
|
|
|
215 and also PacBio).
|
|
|
216
|
|
|
217 It is particularly suited to small genomes such as bacteria.
|
|
|
218
|
|
|
219
|
|
|
220 **Notes on paired reads**
|
|
|
221
|
|
|
222 .. class:: warningmark
|
|
|
223
|
|
|
224 MIRA uses read naming conventions to identify paired read partners
|
|
|
225 (and does not care about their order in the input files). In most cases,
|
|
|
226 the Solexa/Illumina setting is fine. For Sanger capillary sequencing,
|
|
|
227 you may need to rename your reads to match one of the standard conventions
|
|
|
228 supported by MIRA. For Roche 454 or Ion Torrent the appropriate settings
|
|
|
229 depend on how the FASTQ file was produced:
|
|
|
230
|
|
|
231 * If using Roche's ``sffinfo`` or older versions of ``sff_extract``
|
|
|
232 to convert SFF files to FASTQ, your reads will probably have the
|
|
|
233 ``---> <---`` orientation and use the ``.f`` and ``.r``
|
|
|
234 suffixes (FR naming).
|
|
|
235
|
|
|
236 * If using a recent version of ``sff_extract``, then the ``/1`` and ``/2``
|
|
|
237 suffixes are used (Solexa/Illumina style naming) and the original
|
|
|
238 ``2---> 1--->`` orientation is preserved.
|
|
|
239
|
|
|
240 The reason for this is the raw data for Roche 454 and Ion Torrent paired-end
|
|
|
241 libraries sequences a circularised fragment such that the raw data begins
|
|
|
242 with the end of the fragment, a linker, then the start of the fragment.
|
|
|
243 This means both the start and end are sequenced from the same strand, and
|
|
|
244 have the orientation ``2---> 1--->``. However, in order to use the data
|
|
|
245 with traditional tools expecting Sanger capillary style ``---> <---``
|
|
|
246 orientation it was common to reverse complement one of the pair to mimic this.
|
|
|
247
|
|
|
248
|
|
|
249 **Citation**
|
|
|
250
|
|
|
251 If you use this Galaxy tool in work leading to a scientific publication please
|
|
|
252 cite the following papers:
|
|
|
253
|
|
|
254 Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
|
|
|
255 Galaxy tools and workflows for sequence analysis with applications
|
|
|
256 in molecular plant pathology. PeerJ 1:e167
|
|
|
257 http://dx.doi.org/10.7717/peerj.167
|
|
|
258
|
|
|
259 Bastien Chevreux, Thomas Wetter and Sándor Suhai (1999).
|
|
|
260 Genome Sequence Assembly Using Trace Signals and Additional Sequence Information.
|
|
|
261 Computer Science and Biology: Proceedings of the German Conference on Bioinformatics (GCB) 99, pp. 45-56.
|
|
|
262 http://www.bioinfo.de/isb/gcb99/talks/chevreux/main.html
|
|
|
263
|
|
|
264 This wrapper is available to install into other Galaxy Instances via the Galaxy
|
|
|
265 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/mira4_assembler
|
|
|
266 </help>
|
|
|
267 </tool>
|
