Mercurial > repos > devteam > tophat

comparison tophat_wrapper.xml @ 0:1030acbecce6

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author devteam
date Mon, 27 Jan 2014 09:25:27 -0500
parents
children 6eaefb5f755a
comparison
equal deleted inserted replaced
-1:000000000000 0:1030acbecce6
1 <tool id="tophat" name="Tophat for Illumina" version="1.5.0">
2 <!-- Wrapper compatible with Tophat versions 1.3.0 to 1.4.1 -->
3 <description>Find splice junctions using RNA-seq data</description>
4 <version_command>tophat --version</version_command>
5 <requirements>
6 <requirement type="package" version="0.1.18">samtools</requirement>
7 <requirement type="package" version="0.12.7">bowtie</requirement>
8 <requirement type="package" version="1.4.0">tophat</requirement>
9 </requirements>
10 <command interpreter="python">
11 tophat_wrapper.py
12 ## Change this to accommodate the number of threads you have available.
13 --num-threads="\${GALAXY_SLOTS:-4}"
14 ## Provide outputs.
15 --junctions-output=$junctions
16 --hits-output=$accepted_hits
17
18 ## Handle reference file.
19 #if $refGenomeSource.genomeSource == "history":
20 --own-file=$refGenomeSource.ownFile
21 #else:
22 --indexes-path="${refGenomeSource.index.fields.path}"
23 #end if
24
25 ## Are reads single-end or paired?
26 --single-paired=$singlePaired.sPaired
27
28 ## First input file always required.
29 --input1=$input1
30
31 ## Set params based on whether reads are single-end or paired.
32 #if $singlePaired.sPaired == "single":
33 --settings=$singlePaired.sParams.sSettingsType
34 #if $singlePaired.sParams.sSettingsType == "full":
35 -a $singlePaired.sParams.anchor_length
36 -m $singlePaired.sParams.splice_mismatches
37 -i $singlePaired.sParams.min_intron_length
38 -I $singlePaired.sParams.max_intron_length
39 -g $singlePaired.sParams.max_multihits
40 --min-segment-intron $singlePaired.sParams.min_segment_intron
41 --max-segment-intron $singlePaired.sParams.max_segment_intron
42 --initial-read-mismatches=$singlePaired.sParams.initial_read_mismatches
43 --seg-mismatches=$singlePaired.sParams.seg_mismatches
44 --seg-length=$singlePaired.sParams.seg_length
45 --library-type=$singlePaired.sParams.library_type
46
47 ## Indel search.
48 #if $singlePaired.sParams.indel_search.allow_indel_search == "Yes":
49 ## --allow-indels
50 --max-insertion-length $singlePaired.sParams.indel_search.max_insertion_length
51 --max-deletion-length $singlePaired.sParams.indel_search.max_deletion_length
52 #else:
53 --no-novel-indels
54 #end if
55
56 ## Supplying junctions parameters.
57 #if $singlePaired.sParams.own_junctions.use_junctions == "Yes":
58 #if $singlePaired.sParams.own_junctions.gene_model_ann.use_annotations == "Yes":
59 -G $singlePaired.sParams.own_junctions.gene_model_ann.gene_annotation_model
60 #end if
61 #if $singlePaired.sParams.own_junctions.raw_juncs.use_juncs == "Yes":
62 -j $singlePaired.sParams.own_junctions.raw_juncs.raw_juncs
63 #end if
64 ## TODO: No idea why a string cast is necessary, but it is:
65 #if str($singlePaired.sParams.own_junctions.no_novel_juncs) == "Yes":
66 --no-novel-juncs
67 #end if
68 #end if
69
70 #if $singlePaired.sParams.closure_search.use_search == "Yes":
71 --closure-search
72 --min-closure-exon $singlePaired.sParams.closure_search.min_closure_exon
73 --min-closure-intron $singlePaired.sParams.closure_search.min_closure_intron
74 --max-closure-intron $singlePaired.sParams.closure_search.max_closure_intron
75 #else:
76 --no-closure-search
77 #end if
78 #if $singlePaired.sParams.coverage_search.use_search == "Yes":
79 --coverage-search
80 --min-coverage-intron $singlePaired.sParams.coverage_search.min_coverage_intron
81 --max-coverage-intron $singlePaired.sParams.coverage_search.max_coverage_intron
82 #else:
83 --no-coverage-search
84 #end if
85 ## TODO: No idea why the type conversion is necessary, but it seems to be.
86 #if str($singlePaired.sParams.microexon_search) == "Yes":
87 --microexon-search
88 #end if
89 #end if
90 #else:
91 --input2=$singlePaired.input2
92 -r $singlePaired.mate_inner_distance
93 --settings=$singlePaired.pParams.pSettingsType
94 #if $singlePaired.pParams.pSettingsType == "full":
95 --mate-std-dev=$singlePaired.pParams.mate_std_dev
96 -a $singlePaired.pParams.anchor_length
97 -m $singlePaired.pParams.splice_mismatches
98 -i $singlePaired.pParams.min_intron_length
99 -I $singlePaired.pParams.max_intron_length
100 -g $singlePaired.pParams.max_multihits
101 --min-segment-intron $singlePaired.pParams.min_segment_intron
102 --max-segment-intron $singlePaired.pParams.max_segment_intron
103 --initial-read-mismatches=$singlePaired.pParams.initial_read_mismatches
104 --seg-mismatches=$singlePaired.pParams.seg_mismatches
105 --seg-length=$singlePaired.pParams.seg_length
106 --library-type=$singlePaired.pParams.library_type
107
108 ## Indel search.
109 #if $singlePaired.pParams.indel_search.allow_indel_search == "Yes":
110 ## --allow-indels
111 --max-insertion-length $singlePaired.pParams.indel_search.max_insertion_length
112 --max-deletion-length $singlePaired.pParams.indel_search.max_deletion_length
113 #else:
114 --no-novel-indels
115 #end if
116
117 ## Supplying junctions parameters.
118 #if $singlePaired.pParams.own_junctions.use_junctions == "Yes":
119 #if $singlePaired.pParams.own_junctions.gene_model_ann.use_annotations == "Yes":
120 -G $singlePaired.pParams.own_junctions.gene_model_ann.gene_annotation_model
121 #end if
122 #if $singlePaired.pParams.own_junctions.raw_juncs.use_juncs == "Yes":
123 -j $singlePaired.pParams.own_junctions.raw_juncs.raw_juncs
124 #end if
125 ## TODO: No idea why type cast is necessary, but it is:
126 #if str($singlePaired.pParams.own_junctions.no_novel_juncs) == "Yes":
127 --no-novel-juncs
128 #end if
129 #end if
130
131 #if $singlePaired.pParams.closure_search.use_search == "Yes":
132 --closure-search
133 --min-closure-exon $singlePaired.pParams.closure_search.min_closure_exon
134 --min-closure-intron $singlePaired.pParams.closure_search.min_closure_intron
135 --max-closure-intron $singlePaired.pParams.closure_search.max_closure_intron
136 #else:
137 --no-closure-search
138 #end if
139 #if $singlePaired.pParams.coverage_search.use_search == "Yes":
140 --coverage-search
141 --min-coverage-intron $singlePaired.pParams.coverage_search.min_coverage_intron
142 --max-coverage-intron $singlePaired.pParams.coverage_search.max_coverage_intron
143 #else:
144 --no-coverage-search
145 #end if
146 ## TODO: No idea why the type conversion is necessary, but it seems to be.
147 #if str ($singlePaired.pParams.microexon_search) == "Yes":
148 --microexon-search
149 #end if
150 #end if
151 #end if
152 </command>
153 <inputs>
154 <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
155 <expand macro="refGenomeSourceConditional">
156 <options from_data_table="tophat_indexes">
157 <filter type="sort_by" column="2"/>
158 <validator type="no_options" message="No genomes are available for the selected input dataset"/>
159 </options>
160 </expand>
161 <conditional name="singlePaired">
162 <param name="sPaired" type="select" label="Is this library mate-paired?">
163 <option value="single">Single-end</option>
164 <option value="paired">Paired-end</option>
165 </param>
166 <when value="single">
167 <conditional name="sParams">
168 <param name="sSettingsType" type="select" label="TopHat settings to use" help="Use the Full parameter list to change default settings.">
169 <option value="preSet">Default settings</option>
170 <option value="full">Full parameter list</option>
171 </param>
172 <when value="preSet" />
173 <!-- Full/advanced params. -->
174 <when value="full">
175 <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol.">
176 <option value="fr-unstranded">FR Unstranded</option>
177 <option value="fr-firststrand">FR First Strand</option>
178 <option value="fr-secondstrand">FR Second Strand</option>
179 </param>
180 <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." />
181 <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" />
182 <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." />
183 <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." />
184 <conditional name="indel_search">
185 <param name="allow_indel_search" type="select" label="Allow indel search">
186 <option value="Yes">Yes</option>
187 <option value="No">No</option>
188 </param>
189 <when value="No"/>
190 <when value="Yes">
191 <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." />
192 <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." />
193 </when>
194 </conditional>
195 alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" />
196 <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" />
197 <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" />
198 <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" />
199 <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" />
200 <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" />
201 <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" />
202
203 <!-- Options for supplying own junctions. -->
204 <conditional name="own_junctions">
205 <param name="use_junctions" type="select" label="Use Own Junctions">
206 <option value="No">No</option>
207 <option value="Yes">Yes</option>
208 </param>
209 <when value="Yes">
210 <conditional name="gene_model_ann">
211 <param name="use_annotations" type="select" label="Use Gene Annotation Model">
212 <option value="No">No</option>
213 <option value="Yes">Yes</option>
214 </param>
215 <when value="No" />
216 <when value="Yes">
217 <param format="gtf,gff3" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/>
218 </when>
219 </conditional>
220 <conditional name="raw_juncs">
221 <param name="use_juncs" type="select" label="Use Raw Junctions">
222 <option value="No">No</option>
223 <option value="Yes">Yes</option>
224 </param>
225 <when value="No" />
226 <when value="Yes">
227 <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/>
228 </when>
229 </conditional>
230 <param name="no_novel_juncs" type="select" label="Only look for supplied junctions">
231 <option value="No">No</option>
232 <option value="Yes">Yes</option>
233 </param>
234 </when>
235 <when value="No" />
236 </conditional> <!-- /own_junctions -->
237
238 <!-- Closure search. -->
239 <conditional name="closure_search">
240 <param name="use_search" type="select" label="Use Closure Search">
241 <option value="No">No</option>
242 <option value="Yes">Yes</option>
243 </param>
244 <when value="Yes">
245 <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." />
246 <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" />
247 <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" />
248 </when>
249 <when value="No" />
250 </conditional>
251 <!-- Coverage search. -->
252 <conditional name="coverage_search">
253 <param name="use_search" type="select" label="Use Coverage Search">
254 <option selected="true" value="Yes">Yes</option>
255 <option value="No">No</option>
256 </param>
257 <when value="Yes">
258 <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" />
259 <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" />
260 </when>
261 <when value="No" />
262 </conditional>
263 <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.">
264 <option value="No">No</option>
265 <option value="Yes">Yes</option>
266 </param>
267 </when> <!-- full -->
268 </conditional> <!-- sParams -->
269 </when> <!-- single -->
270 <when value="paired">
271 <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
272 <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" />
273 <conditional name="pParams">
274 <param name="pSettingsType" type="select" label="TopHat settings to use" help="Use the Full parameter list to change default settings.">
275 <option value="preSet">Default settings</option>
276 <option value="full">Full parameter list</option>
277 </param>
278 <when value="preSet" />
279 <!-- Full/advanced params. -->
280 <when value="full">
281 <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol.">
282 <option value="fr-unstranded">FR Unstranded</option>
283 <option value="fr-firststrand">FR First Strand</option>
284 <option value="fr-secondstrand">FR Second Strand</option>
285 </param>
286 <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/>
287 <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." />
288 <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" />
289 <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." />
290 <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." />
291 <expand macro="indel_searchConditional" />
292 <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" />
293 <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" />
294 <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" />
295 <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" />
296 <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" />
297 <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" />
298 <!-- Options for supplying own junctions. -->
299 <expand macro="own_junctionsConditional" />
300 <!-- Closure search. -->
301 <conditional name="closure_search">
302 <param name="use_search" type="select" label="Use Closure Search">
303 <option value="No">No</option>
304 <option value="Yes">Yes</option>
305 </param>
306 <when value="Yes">
307 <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." />
308 <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" />
309 <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" />
310 </when>
311 <when value="No" />
312 </conditional>
313 <!-- Coverage search. -->
314 <conditional name="coverage_search">
315 <param name="use_search" type="select" label="Use Coverage Search">
316 <option selected="true" value="Yes">Yes</option>
317 <option value="No">No</option>
318 </param>
319 <when value="Yes">
320 <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" />
321 <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" />
322 </when>
323 <when value="No" />
324 </conditional>
325 <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.">
326 <option value="No">No</option>
327 <option value="Yes">Yes</option>
328 </param>
329 </when> <!-- full -->
330 </conditional> <!-- pParams -->
331 </when> <!-- paired -->
332 </conditional>
333 </inputs>
334
335 <outputs>
336 <data format="bed" name="insertions" label="${tool.name} on ${on_string}: insertions" from_work_dir="tophat_out/insertions.bed">
337 <expand macro="dbKeyActions" />
338 </data>
339 <data format="bed" name="deletions" label="${tool.name} on ${on_string}: deletions" from_work_dir="tophat_out/deletions.bed">
340 <expand macro="dbKeyActions" />
341 </data>
342 <data format="bed" name="junctions" label="${tool.name} on ${on_string}: splice junctions" from_work_dir="tophat_out/junctions.bed">
343 <expand macro="dbKeyActions" />
344 </data>
345 <data format="bam" name="accepted_hits" label="${tool.name} on ${on_string}: accepted_hits" from_work_dir="tophat_out/accepted_hits.bam">
346 <expand macro="dbKeyActions" />
347 </data>
348 </outputs>
349 <macros>
350 <import>tophat_macros.xml</import>
351 <macro name="dbKeyActions">
352 <actions>
353 <conditional name="refGenomeSource.genomeSource">
354 <when value="indexed">
355 <action type="metadata" name="dbkey">
356 <option type="from_data_table" name="tophat_indexes" column="1" offset="0">
357 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
358 <filter type="param_value" ref="refGenomeSource.index" column="0"/>
359 </option>
360 </action>
361 </when>
362 <when value="history">
363 <action type="metadata" name="dbkey">
364 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
365 </action>
366 </when>
367 </conditional>
368 </actions>
369 </macro>
370 </macros>
371 <tests>
372 <!-- Test base-space single-end reads with pre-built index and preset parameters -->
373 <test>
374 <!-- TopHat commands:
375 tophat -o tmp_dir -p 1 tophat_in1 test-data/tophat_in2.fastqsanger
376 Rename the files in tmp_dir appropriately
377 -->
378 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" />
379 <param name="genomeSource" value="indexed" />
380 <param name="index" value="tophat_test" />
381 <param name="sPaired" value="single" />
382 <param name="sSettingsType" value="preSet" />
383 <output name="junctions" file="tophat_out1j.bed" />
384 <output name="accepted_hits" file="tophat_out1h.bam" compare="sim_size" />
385 </test>
386 <!-- Test using base-space test data: paired-end reads, index from history. -->
387 <test>
388 <!-- TopHat commands:
389 bowtie-build -f test-data/tophat_in1.fasta tophat_in1
390 tophat -o tmp_dir -p 1 -r 20 tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger
391 Rename the files in tmp_dir appropriately
392 -->
393 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" />
394 <param name="genomeSource" value="history" />
395 <param name="ownFile" ftype="fasta" value="tophat_in1.fasta" />
396 <param name="sPaired" value="paired" />
397 <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" />
398 <param name="mate_inner_distance" value="20" />
399 <param name="pSettingsType" value="preSet" />
400 <output name="junctions" file="tophat_out2j.bed" />
401 <output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" />
402 </test>
403 <!-- Test base-space single-end reads with user-supplied reference fasta and full parameters -->
404 <test>
405 <!-- Tophat commands:
406 bowtie-build -f test-data/tophat_in1.fasta tophat_in1
407 tophat -o tmp_dir -p 1 -a 8 -m 0 -i 70 -I 500000 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +closure-search +min-closure-exon 50 +min-closure-intron 50 +max-closure-intro 5000 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger
408 Replace the + with double-dash
409 Rename the files in tmp_dir appropriately
410 -->
411 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/>
412 <param name="genomeSource" value="history"/>
413 <param name="ownFile" value="tophat_in1.fasta"/>
414 <param name="sPaired" value="single"/>
415 <param name="sSettingsType" value="full"/>
416 <param name="library_type" value="FR Unstranded"/>
417 <param name="anchor_length" value="8"/>
418 <param name="splice_mismatches" value="0"/>
419 <param name="min_intron_length" value="70"/>
420 <param name="max_intron_length" value="500000"/>
421 <param name="max_multihits" value="40"/>
422 <param name="min_segment_intron" value="50" />
423 <param name="max_segment_intron" value="500000" />
424 <param name="seg_mismatches" value="2"/>
425 <param name="seg_length" value="25"/>
426 <param name="allow_indel_search" value="Yes"/>
427 <param name="max_insertion_length" value="3"/>
428 <param name="max_deletion_length" value="3"/>
429 <param name="use_junctions" value="Yes" />
430 <param name="use_annotations" value="No" />
431 <param name="use_juncs" value="No" />
432 <param name="no_novel_juncs" value="No" />
433 <param name="use_search" value="Yes" />
434 <param name="min_closure_exon" value="50" />
435 <param name="min_closure_intron" value="50" />
436 <param name="max_closure_intron" value="5000" />
437 <param name="use_search" value="Yes" />
438 <param name="min_coverage_intron" value="50" />
439 <param name="max_coverage_intron" value="20000" />
440 <param name="microexon_search" value="Yes" />
441 <output name="insertions" file="tophat_out3i.bed" />
442 <output name="deletions" file="tophat_out3d.bed" />
443 <output name="junctions" file="tophat_out3j.bed" />
444 <output name="accepted_hits" file="tophat_out3h.bam" compare="sim_size" />
445 </test>
446 <!-- Test base-space paired-end reads with user-supplied reference fasta and full parameters -->
447 <test>
448 <!-- TopHat commands:
449 tophat -o tmp_dir -r 20 -p 1 -a 8 -m 0 -i 70 -I 500000 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger
450 Replace the + with double-dash
451 Rename the files in tmp_dir appropriately
452 -->
453 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/>
454 <param name="genomeSource" value="indexed"/>
455 <param name="index" value="tophat_test"/>
456 <param name="sPaired" value="paired"/>
457 <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/>
458 <param name="mate_inner_distance" value="20"/>
459 <param name="pSettingsType" value="full"/>
460 <param name="library_type" value="FR Unstranded"/>
461 <param name="mate_std_dev" value="20"/>
462 <param name="anchor_length" value="8"/>
463 <param name="splice_mismatches" value="0"/>
464 <param name="min_intron_length" value="70"/>
465 <param name="max_intron_length" value="500000"/>
466 <param name="max_multihits" value="40"/>
467 <param name="min_segment_intron" value="50" />
468 <param name="max_segment_intron" value="500000" />
469 <param name="seg_mismatches" value="2"/>
470 <param name="seg_length" value="25"/>
471 <param name="allow_indel_search" value="No"/>
472 <param name="use_junctions" value="Yes" />
473 <param name="use_annotations" value="No" />
474 <param name="use_juncs" value="No" />
475 <param name="no_novel_juncs" value="No" />
476 <param name="use_search" value="No" />
477 <param name="microexon_search" value="Yes" />
478 <output name="junctions" file="tophat_out4j.bed" />
479 <output name="accepted_hits" file="tophat_out4h.bam" compare="sim_size" />
480 </test>
481 </tests>
482
483 <help>
484 **Tophat Overview**
485
486 TopHat_ is a fast splice junction mapper for RNA-Seq reads. It aligns RNA-Seq reads to mammalian-sized genomes using the ultra high-throughput short read aligner Bowtie, and then analyzes the mapping results to identify splice junctions between exons. Please cite: Trapnell, C., Pachter, L. and Salzberg, S.L. TopHat: discovering splice junctions with RNA-Seq. Bioinformatics 25, 1105-1111 (2009).
487
488 .. _Tophat: http://tophat.cbcb.umd.edu/
489
490 ------
491
492 **Know what you are doing**
493
494 .. class:: warningmark
495
496 There is no such thing (yet) as an automated gearshift in splice junction identification. It is all like stick-shift driving in San Francisco. In other words, running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.
497
498 .. __: http://tophat.cbcb.umd.edu/manual.html
499
500 ------
501
502 **Input formats**
503
504 Tophat accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.
505
506 ------
507
508 **Outputs**
509
510 Tophat produces two output files:
511
512 - junctions -- A UCSC BED_ track of junctions reported by TopHat. Each junction consists of two connected BED blocks, where each block is as long as the maximal overhang of any read spanning the junction. The score is the number of alignments spanning the junction.
513 - accepted_hits -- A list of read alignments in BAM_ format.
514
515 .. _BED: http://genome.ucsc.edu/FAQ/FAQformat.html#format1
516 .. _BAM: http://samtools.sourceforge.net/
517
518 Two other possible outputs, depending on the options you choose, are insertions and deletions, both of which are in BED format.
519
520 -------
521
522 **Tophat settings**
523
524 All of the options have a default value. You can change any of them. Some of the options in Tophat have been implemented here.
525
526 ------
527
528 **Tophat parameter list**
529
530 This is a list of implemented Tophat options::
531
532 -r This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments
533 selected at 300bp, where each end is 50bp, you should set -r to be 200. There is no default, and this parameter
534 is required for paired end runs.
535 --mate-std-dev INT The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp.
536 -a/--min-anchor-length INT The "anchor length". TopHat will report junctions spanned by reads with at least this many bases on each side of the junction. Note that individual spliced
537 alignments may span a junction with fewer than this many bases on one side. However, every junction involved in spliced alignments is supported by at least one
538 read with this many bases on each side. This must be at least 3 and the default is 8.
539 -m/--splice-mismatches INT The maximum number of mismatches that may appear in the "anchor" region of a spliced alignment. The default is 0.
540 -i/--min-intron-length INT The minimum intron length. TopHat will ignore donor/acceptor pairs closer than this many bases apart. The default is 70.
541 -I/--max-intron-length INT The maximum intron length. When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read. The default is 500000.
542 -g/--max-multihits INT Instructs TopHat to allow up to this many alignments to the reference for a given read, and suppresses all alignments for reads with more than this many
543 alignments. The default is 40.
544 -G/--GTF [GTF 2.2 file] Supply TopHat with a list of gene model annotations. TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping.
545 -j/--raw-juncs [juncs file] Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-], left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive.
546 -no-novel-juncs Only look for junctions indicated in the supplied GFF file. (ignored without -G)
547 --no-closure-search Disables the mate pair closure-based search for junctions. Currently, has no effect - closure search is off by default.
548 --closure-search Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (about or less than 50bp)
549 --no-coverage-search Disables the coverage based search for junctions.
550 --coverage-search Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity.
551 --microexon-search With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.
552 --butterfly-search TopHat will use a slower but potentially more sensitive algorithm to find junctions in addition to its standard search. Consider using this if you expect that your experiment produced a lot of reads from pre-mRNA, that fall within the introns of your transcripts.
553 --segment-mismatches Read segments are mapped independently, allowing up to this many mismatches in each segment alignment. The default is 2.
554 --segment-length Each read is cut up into segments, each at least this long. These segments are mapped independently. The default is 25.
555 --min-closure-exon During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50.
556 --min-closure-intron The minimum intron length that may be found during closure search. The default is 50.
557 --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000.
558 --min-coverage-intron The minimum intron length that may be found during coverage search. The default is 50.
559 --max-coverage-intron The maximum intron length that may be found during coverage search. The default is 20000.
560 --min-segment-intron The minimum intron length that may be found during split-segment search. The default is 50.
561 --max-segment-intron The maximum intron length that may be found during split-segment search. The default is 500000.
562 </help>
563 </tool>