|
0
|
1 <tool id="repeatmasker_wrapper" name="RepeatMasker" version="0.1">
|
|
|
2 <description>Masks different kind of repeats</description>
|
|
|
3 <command>
|
|
|
4 ## The command is a Cheetah template which allows some Python based syntax.
|
|
|
5 ## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
|
|
|
6
|
|
|
7 ## create temp directory
|
|
|
8 #import tempfile, os
|
|
|
9 #set $dirname = os.path.abspath(tempfile.mkdtemp())
|
|
|
10 #set $input_filename = os.path.split(str($query))[-1]
|
|
|
11 #set $output_basename = os.path.join($dirname, $input_filename)
|
|
|
12
|
|
|
13
|
|
|
14 RepeatMasker
|
|
|
15 -parallel 8
|
|
|
16
|
|
|
17 $nolow
|
|
|
18 $noint
|
|
|
19 $norna
|
|
|
20
|
|
|
21 #if str($species)!="all":
|
|
|
22 $species
|
|
|
23 #end if
|
|
|
24
|
|
|
25
|
|
|
26 -dir $dirname
|
|
|
27
|
|
|
28 #if $adv_opts.adv_opts_selector=="advanced":
|
|
|
29
|
|
|
30 #if str($adv_opts.gc)!="0":
|
|
|
31 -gc $adv_opts.gc
|
|
|
32 #end if
|
|
|
33
|
|
|
34 $adv_opts.gccalc
|
|
|
35
|
|
|
36 #set $output_files_list = str($adv_opts.output_files).split(',')
|
|
|
37 #if "gff" in $output_files_list:
|
|
|
38 -gff
|
|
|
39 #end if
|
|
|
40 #if "html" in $output_files_list:
|
|
|
41 -html
|
|
|
42 #end if
|
|
|
43
|
|
|
44 $adv_opts.slow_search
|
|
|
45 $adv_opts.quick_search
|
|
|
46 $adv_opts.rush_search
|
|
|
47 $adv_opts.only_alus
|
|
|
48 $adv_opts.is_only
|
|
|
49
|
|
|
50 #else:
|
|
|
51 ## Set defaults
|
|
|
52 -gff
|
|
|
53
|
|
|
54 ## End of advanced options:
|
|
|
55 #end if
|
|
|
56
|
|
|
57 $query
|
|
|
58
|
|
|
59
|
|
|
60 > /dev/null 2> /dev/null;
|
|
|
61 ## Copy the output files to galaxy
|
|
|
62 #if $adv_opts.adv_opts_selector=="advanced":
|
|
|
63
|
|
|
64 #if "summary" in $output_files_list:
|
|
|
65 ## Write out the summary file (default)
|
|
|
66 #set $summary_file = $output_basename + '.tbl'
|
|
|
67 cp $summary_file $output_summary;
|
|
|
68 #end if
|
|
|
69
|
|
|
70 #if "gff" in $output_files_list:
|
|
|
71 ## Write out the gff file (default)
|
|
|
72 #set $gff_file = $output_basename + '.out.gff'
|
|
|
73 cp $gff_file $output_gff;
|
|
|
74 #end if
|
|
|
75
|
|
|
76 #if "html" in $output_files_list:
|
|
|
77 ## Write out the html file
|
|
|
78 #set $html_file = $output_basename + '.out.html'
|
|
|
79 cp $html_file $output_html;
|
|
|
80 #end if
|
|
|
81
|
|
|
82 #else:
|
|
|
83
|
|
|
84 ## Write out the summary file (default)
|
|
|
85 #set $summary_file = $output_basename + '.tbl'
|
|
|
86 cp $summary_file $output_summary;
|
|
|
87
|
|
|
88 ## Write out the gff file (default)
|
|
|
89 #set $gff_file = $output_basename + '.out.gff'
|
|
|
90 cp $gff_file $output_gff;
|
|
|
91
|
|
|
92
|
|
|
93 ## End of advanced options:
|
|
|
94 #end if
|
|
|
95
|
|
|
96 ## Write out mask sequence file
|
|
|
97 #set $mask_sequence_file = $output_basename + '.masked'
|
|
|
98 cp $mask_sequence_file $output_mask;
|
|
|
99
|
|
|
100 ## Write out standard file (default)
|
|
|
101 ## The default '.out' file from RepeatMasker has a 3-line header and spaces rather
|
|
|
102 ## than tabs. Remove the header and replace the whitespaces with tab
|
|
|
103 #set $standard_file = $output_basename + '.out'
|
|
|
104 tail -n +4 $standard_file | tr -s ' ' '\t' > $output_std;
|
|
|
105
|
|
|
106 ## Delete all temporary files
|
|
|
107 rm $dirname -r;
|
|
|
108
|
|
|
109
|
|
|
110 </command>
|
|
|
111 <inputs>
|
|
|
112 <param name="query" type="data" format="fasta" label="Nucleotide query sequence(s)"/>
|
|
|
113
|
|
|
114 <param name="nolow" type="boolean" label="No low complexity DNA" truevalue="-nolow" falsevalue="" checked="false" help="Does not mask low_complexity DNA or simple repeats."/>
|
|
|
115 <param name="noint" type="boolean" label="No interspersed repeats" truevalue="-noint" falsevalue="" checked="false" help="Only masks low complex/simple repeats (no interspersed repeats)."/>
|
|
|
116
|
|
|
117 <param name="norna" type="boolean" label="No small RNA genes" truevalue="-norna" falsevalue="" checked="false" help="Does not mask small RNA (pseudo) genes."/>
|
|
|
118
|
|
|
119 <!--
|
|
|
120 Specify the species or clade of the input sequence. The species name
|
|
|
121 must be a valid NCBI Taxonomy Database species name and be contained
|
|
|
122 in the RepeatMasker repeat database. The following collection is not complete.
|
|
|
123 -->
|
|
|
124 <param name="species" type="select" label="Species" help="The list is not complete, if you need other species contact your administrator.">
|
|
|
125 <option value="-species anopheles">anopheles</option>
|
|
|
126 <option value="-species arabidopsis">arabidopsis</option>
|
|
|
127 <option value="-species artiodactyl">artiodactyl</option>
|
|
|
128 <option value="-species aspergillus">aspergillus</option>
|
|
|
129 <option value="-species carnivore">carnivore</option>
|
|
|
130 <option value="-species cat">cat</option>
|
|
|
131 <option value="-species chicken">chicken</option>
|
|
|
132 <option value="-species 'ciona intestinalis'">ciona intestinalis</option>
|
|
|
133 <option value="-species 'ciona savignyi'">ciona savignyi</option>
|
|
|
134 <option value="-species cow">cow</option>
|
|
|
135 <option value="-species danio">danio</option>
|
|
|
136 <option value="-species diatoaea">diatoaea</option>
|
|
|
137 <option value="-species dog">dog</option>
|
|
|
138 <option value="-species drosophila">drosophila</option>
|
|
|
139 <option value="-species elegans">elegans</option>
|
|
|
140 <option value="-species fugu">fugu</option>
|
|
|
141 <option value="-species fungi" selected="true">fungi</option>
|
|
|
142 <option value="-species human">human</option>
|
|
|
143 <option value="-species maize">maize</option>
|
|
|
144 <option value="-species mammal">mammal</option>
|
|
|
145 <option value="-species mouse">mouse</option>
|
|
|
146 <option value="-species pig">pig</option>
|
|
|
147 <option value="-species rat">rat</option>
|
|
|
148 <option value="-species rice">rice</option>
|
|
|
149 <option value="-species rodentia">rodentia</option>
|
|
|
150 <option value="-species wheat">wheat</option>
|
|
|
151 </param>
|
|
|
152
|
|
|
153 <conditional name="adv_opts">
|
|
|
154 <param name="adv_opts_selector" type="select" label="Advanced Options">
|
|
|
155 <option value="basic" selected="True">Hide Advanced Options</option>
|
|
|
156 <option value="advanced">Show Advanced Options</option>
|
|
|
157 </param>
|
|
|
158 <when value="basic" />
|
|
|
159 <when value="advanced">
|
|
|
160
|
|
|
161
|
|
|
162 <param name="is_only" type="boolean" label="Mask only E coli insertion elements" truevalue="-is_only" falsevalue="" checked="false" help="Only clips E coli insertion elements out of fasta and .qual files."/>
|
|
|
163
|
|
|
164
|
|
|
165 <param name="slow_search" type="boolean" label="Slow search" truevalue="-s" falsevalue="" checked="false" help="0-5% more sensitive, 2-3 times slower than default."/>
|
|
|
166 <param name="quick_search" type="boolean" label="Quick search" truevalue="-q" falsevalue="" checked="false" help="5-10% less sensitive, 2-5 times faster than default."/>
|
|
|
167 <param name="rush_search" type="boolean" label="Rush search" truevalue="-qq" falsevalue="" checked="false" help="about 10% less sensitive, 4->10 times faster than default."/>
|
|
|
168
|
|
|
169 <param name="only_alus" type="boolean" label="Only Alus" truevalue="-alu" falsevalue="" checked="false" help="Only masks Alus (and 7SLRNA, SVA and LTR5)(only for primate DNA)."/>
|
|
|
170
|
|
|
171 <param name="gccalc" type="boolean" label="Use GC depended matrices, automaticly" truevalue="-gccalc" falsevalue="" checked="true" help="RepeatMasker calculates the GC content even for batch files/small seqs"/>
|
|
|
172
|
|
|
173 <param name="output_files" type="select" multiple="true" label="Additional output files">
|
|
|
174 <option selected="true" value="summary">Summary file</option>
|
|
|
175 <option value="gff">GFF file</option>
|
|
|
176 <option value="html">HTML file</option>
|
|
|
177 <option value="mask">Mask FastA file</option>
|
|
|
178 </param>
|
|
|
179
|
|
|
180
|
|
|
181 <param name="gc" type="integer" value="0" label="Use GC depended matrices" help="Use matrices calculated for 'number' percentage background GC level">
|
|
|
182 <validator type="in_range" min="0" />
|
|
|
183 <validator type="in_range" max="100" />
|
|
|
184 </param>
|
|
|
185
|
|
|
186 </when>
|
|
|
187 </conditional>
|
|
|
188
|
|
|
189 </inputs>
|
|
|
190 <outputs>
|
|
|
191 <data name="output_std" format="tabular" label="${tool.name} on ${on_string}: Standard" />
|
|
|
192 <data name="output_mask" format="fasta" label="${tool.name} on ${on_string}: Mask sequence">
|
|
|
193 <filter>
|
|
|
194 (adv_opts['adv_opts_selector'] == 'advanced' and 'mask' in adv_opts['output_files'])
|
|
|
195 </filter>
|
|
|
196 </data>
|
|
|
197 <data name="output_summary" format="txt" label="${tool.name} on ${on_string}: Summary">
|
|
|
198 <filter>(
|
|
|
199 (adv_opts['adv_opts_selector'] == 'advanced' and 'summary' in adv_opts['output_files'])
|
|
|
200 or
|
|
|
201 (adv_opts['adv_opts_selector'] == 'basic')
|
|
|
202 )
|
|
|
203 </filter>
|
|
|
204 </data>
|
|
|
205 <data name="output_html" format="html" label="${tool.name} on ${on_string}: HTML">
|
|
|
206 <filter>(adv_opts['adv_opts_selector'] == 'advanced' and 'html' in adv_opts['output_files'])</filter>
|
|
|
207 </data>
|
|
|
208 <data name="output_gff" format="gff" label="${tool.name} on ${on_string}: GFF">
|
|
|
209 <filter>
|
|
|
210 (adv_opts['adv_opts_selector'] == 'advanced' and 'gff' in adv_opts['output_files'])
|
|
|
211 </filter>
|
|
|
212 </data>
|
|
|
213 </outputs>
|
|
|
214 <requirements>
|
|
|
215 <requirement type="binary">RepeatMasker</requirement>
|
|
|
216 </requirements>
|
|
|
217 <help>
|
|
|
218
|
|
|
219 .. class:: warningmark
|
|
|
220
|
|
|
221
|
|
|
222 -----
|
|
|
223
|
|
|
224 **What it does**
|
|
|
225
|
|
|
226 RepeatMasker is a program that screens DNA sequences for *interspersed repeats*
|
|
|
227 and *low complexity* DNA sequences. The output of the program is a detailed
|
|
|
228 annotation of the repeats that are present in the query sequence as well as a
|
|
|
229 modified version of the query sequence in which all the annotated repeats have
|
|
|
230 been masked (default: replaced by Ns).
|
|
|
231
|
|
|
232 -----
|
|
|
233
|
|
|
234 **How to read the results**
|
|
|
235
|
|
|
236
|
|
|
237
|
|
|
238 The annotation file contains the cross_match output lines. It lists all best matches
|
|
|
239 (above a set minimum score) between the query sequence and any of the sequences in
|
|
|
240 the repeat database or with low complexity DNA. The term "best matches" reflects
|
|
|
241 that a match is not shown if its domain is over 80% contained within the domain
|
|
|
242 of a higher scoring match, where the "domain" of a match is the region in
|
|
|
243 the query sequence that is defined by the alignment start and stop. These domains
|
|
|
244 have been masked in the returned masked sequence file. In the output, matches are
|
|
|
245 ordered by query name, and for each query by position of the start of the alignment.
|
|
|
246
|
|
|
247 Example:
|
|
|
248
|
|
|
249 ======== ========= ========= ========= ========== =========== ========= ========= ============ =============== =================== ================ ============== ======= ==
|
|
|
250 SW score perc div. perc del. perc ins. query seq. q-pos begin q-pos end (left) w complement matching repeat repeat class/family repeat-pos begin repeat-pos end (left) ID
|
|
|
251 ======== ========= ========= ========= ========== =========== ========= ========= ============ =============== =================== ================ ============== ======= ==
|
|
|
252 1306 15.6 6.2 0.0 HSU08988 6563 6781 \(22462) C MER7A DNA/MER2_type 336 103 \(0) 1
|
|
|
253 12204 10.0 2.4 1.8 HSU08988 6782 7714 \(21529) C TIGGER1 DNA/MER2_type 2418 1493 \(0) 2
|
|
|
254 279 3.0 0.0 0.0 HSU08988 7719 7751 \(21492) + (TTTTA)n Simple_repeat 1 33 \(0) 3
|
|
|
255 1765 13.4 6.5 1.8 HSU08988 7752 8022 \(21221) C AluSx SINE/Alu 289 1 \(23) 4
|
|
|
256 12204 10.0 2.4 1.8 HSU08988 8023 8694 \(20549) C TIGGER1 DNA/MER2_type 1493 827 \(925) 5
|
|
|
257 1984 11.1 0.3 0.7 HSU08988 8695 9000 \(20243) C AluSg SINE/Alu 305 1 \(5) 6
|
|
|
258 12204 10.0 2.4 1.8 HSU08988 9001 9695 \(19548) C TIGGER1 DNA/MER2_type 827 2 \(1591) 7
|
|
|
259 711 21.2 1.4 0.0 HSU08988 9696 9816 \(19427) C MER7A DNA/MER2_type 122 2 \(224) 8
|
|
|
260 ======== ========= ========= ========= ========== =========== ========= ========= ============ =============== =================== ================ ============== ======= ==
|
|
|
261
|
|
|
262 This is a sequence in which a Tigger1 DNA transposon has integrated into a MER7 DNA transposon copy.
|
|
|
263 Subsequently two Alus integrated in the Tigger1 sequence. The simple repeat is derived from the
|
|
|
264 poly A of the Alu element. The first line is interpreted like this:
|
|
|
265
|
|
|
266 :Table description:
|
|
|
267
|
|
|
268 1. **1306** = Smith-Waterman score of the match, usually complexity adjusted
|
|
|
269 The SW scores are not always directly comparable. Sometimes
|
|
|
270 the complexity adjustment has been turned off, and a variety of
|
|
|
271 scoring-matrices are used.
|
|
|
272
|
|
|
273 #. **15.6** = % substitutions in matching region compared to the consensus
|
|
|
274 #. **6.2** = % of bases opposite a gap in the query sequence (deleted bp)
|
|
|
275 #. **0.0** = % of bases opposite a gap in the repeat consensus (inserted bp)
|
|
|
276 #. **HSU08988** = name of query sequence
|
|
|
277 #. **6563** = starting position of match in query sequence
|
|
|
278 #. **7714** = ending position of match in query sequence
|
|
|
279 #. **(22462)** = no. of bases in query sequence past the ending position of match
|
|
|
280 #. **C** = match is with the Complement of the consensus sequence in the database
|
|
|
281 #. **MER7A** = name of the matching interspersed repeat
|
|
|
282 #. **DNA/MER2_type** = the class of the repeat, in this case a DNA transposon fossil of the MER2 group (see below for list and references)
|
|
|
283 #. **2418** = starting position of match in database sequence (using top-strand numbering)
|
|
|
284 #. **1465** = ending position of match in database sequence
|
|
|
285 #. **(0)** = no. of bases in (complement of) the repeat consensus sequence prior to beginning of the match (so 0 means that the match extended all the way to the end of the repeat consensus sequence)
|
|
|
286 #. **1** = Identifier
|
|
|
287
|
|
|
288 An asterisk (\*) in the final column (no example shown) indicates that there is
|
|
|
289 a higher-scoring match whose domain partly (<80%) includes the domain of this match.
|
|
|
290
|
|
|
291 Note that the SW score and divergence numbers for the three Tigger1 lines are identical.
|
|
|
292 This is because the information is derived from a single alignment (the Alus were deleted
|
|
|
293 from the query before the alignment with the Tigger element was performed).
|
|
|
294 The program makes educated guesses about many fragments if they are derived from
|
|
|
295 the same element (e.g. it knows that the MER7A fragments represent one insert).
|
|
|
296 In a next version I can identify each element with a unique ID, if interest exists
|
|
|
297 (this could help to represent repeats cleaner in graphic displays).
|
|
|
298
|
|
|
299
|
|
|
300 -------
|
|
|
301
|
|
|
302 **References**
|
|
|
303
|
|
|
304 Smit, AFA, Hubley, R and Green, P. RepeatMasker Open-3.0.
|
|
|
305
|
|
|
306 http://www.repeatmasker.org/
|
|
|
307
|
|
|
308 </help>
|
|
|
309 </tool>
|
