Mercurial > repos > yufei-luo > differential_expression_analysis_pipeline_for_rnaseq_data

comparison DiffExpAnal/tophat_parallel.xml @ 0:63799b789162 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author yufei-luo
date Tue, 22 Jan 2013 10:07:03 -0500
parents
children b8887c180d45
comparison
equal deleted inserted replaced
-1:000000000000 0:63799b789162
1 <tool id="tophat_parallel" name="Tophat parallel for Illumina" version="1.0.0">
2 <description>Find splice junctions using RNA-seq data, can have several input RNA-seq data.</description>
3 <version_command>tophat --version</version_command>
4 <requirements>
5 <requirement type="package">tophat</requirement>
6 </requirements>
7 <command interpreter="python">
8 tophat_parallel.py
9 ## Change this to accommodate the number of threads you have available.
10 --num-threads="4"
11
12 ## Provide outputs.
13 -o $outputFileName
14 ##--junctions-output=$junctions
15 ##--hits-output=$accepted_hits
16
17 ## Handle reference file.
18 #if $refGenomeSource.genomeSource == "history":
19 --own-file=$refGenomeSource.ownFile
20 #else:
21 --indexes-path="${ filter( lambda x: str( x[0] ) == str( $refGenomeSource.index ), $__app__.tool_data_tables[ 'tophat_indexes' ].get_fields() )[0][-1] }"
22 #end if
23
24 ## Are reads single-end or paired?
25 --single-paired=$singlePaired.sPaired
26
27 ## First input file always required.
28 --input1=$input1
29
30 ## Set params based on whether reads are single-end or paired.
31 #if $singlePaired.sPaired == "single":
32 --settings=$singlePaired.sParams.sSettingsType
33 #if $singlePaired.sParams.sSettingsType == "full":
34 -a $singlePaired.sParams.anchor_length
35 -m $singlePaired.sParams.splice_mismatches
36 -i $singlePaired.sParams.min_intron_length
37 -I $singlePaired.sParams.max_intron_length
38 -F $singlePaired.sParams.junction_filter
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 -F $singlePaired.pParams.junction_filter
101 -g $singlePaired.pParams.max_multihits
102 --min-segment-intron $singlePaired.pParams.min_segment_intron
103 --max-segment-intron $singlePaired.pParams.max_segment_intron
104 --initial-read-mismatches=$singlePaired.pParams.initial_read_mismatches
105 --seg-mismatches=$singlePaired.pParams.seg_mismatches
106 --seg-length=$singlePaired.pParams.seg_length
107 --library-type=$singlePaired.pParams.library_type
108
109 ## Indel search.
110 #if $singlePaired.pParams.indel_search.allow_indel_search == "Yes":
111 ## --allow-indels
112 --max-insertion-length $singlePaired.pParams.indel_search.max_insertion_length
113 --max-deletion-length $singlePaired.pParams.indel_search.max_deletion_length
114 #else:
115 --no-novel-indels
116 #end if
117
118 ## Supplying junctions parameters.
119 #if $singlePaired.pParams.own_junctions.use_junctions == "Yes":
120 #if $singlePaired.pParams.own_junctions.gene_model_ann.use_annotations == "Yes":
121 -G $singlePaired.pParams.own_junctions.gene_model_ann.gene_annotation_model
122 #end if
123 #if $singlePaired.pParams.own_junctions.raw_juncs.use_juncs == "Yes":
124 -j $singlePaired.pParams.own_junctions.raw_juncs.raw_juncs
125 #end if
126 ## TODO: No idea why type cast is necessary, but it is:
127 #if str($singlePaired.pParams.own_junctions.no_novel_juncs) == "Yes":
128 --no-novel-juncs
129 #end if
130 #end if
131
132 #if $singlePaired.pParams.closure_search.use_search == "Yes":
133 --closure-search
134 --min-closure-exon $singlePaired.pParams.closure_search.min_closure_exon
135 --min-closure-intron $singlePaired.pParams.closure_search.min_closure_intron
136 --max-closure-intron $singlePaired.pParams.closure_search.max_closure_intron
137 #else:
138 --no-closure-search
139 #end if
140 #if $singlePaired.pParams.coverage_search.use_search == "Yes":
141 --coverage-search
142 --min-coverage-intron $singlePaired.pParams.coverage_search.min_coverage_intron
143 --max-coverage-intron $singlePaired.pParams.coverage_search.max_coverage_intron
144 #else:
145 --no-coverage-search
146 #end if
147 ## TODO: No idea why the type conversion is necessary, but it seems to be.
148 #if str ($singlePaired.pParams.microexon_search) == "Yes":
149 --microexon-search
150 #end if
151 #end if
152 #end if
153 $tar $outputTarFile
154 </command>
155 <inputs>
156 <param format="txt" name="input1" type="data" label="RNA-Seq FASTQ file" help="Please identify a txt input file, which contains a list of fastqsanger files. Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33. " />
157 <conditional name="refGenomeSource">
158 <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
159 <option value="indexed">Use a built-in index</option>
160 <option value="history">Use one from the history</option>
161 </param>
162 <when value="indexed">
163 <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
164 <options from_data_table="tophat_indexes">
165 <filter type="sort_by" column="2"/>
166 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
167 </options>
168 </param>
169 </when>
170 <when value="history">
171 <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" />
172 </when> <!-- history -->
173 </conditional> <!-- refGenomeSource -->
174 <conditional name="singlePaired">
175 <param name="sPaired" type="select" label="Is this library mate-paired?">
176 <option value="single">Single-end</option>
177 <option value="paired">Paired-end</option>
178 </param>
179 <when value="single">
180 <conditional name="sParams">
181 <param name="sSettingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters.">
182 <option value="preSet">Use Defaults</option>
183 <option value="full">Full parameter list</option>
184 </param>
185 <when value="preSet" />
186 <!-- Full/advanced params. -->
187 <when value="full">
188 <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.">
189 <option value="fr-unstranded">FR Unstranded</option>
190 <option value="fr-firststrand">FR First Strand</option>
191 <option value="fr-secondstrand">FR Second Strand</option>
192 </param>
193 <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." />
194 <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" />
195 <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." />
196 <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." />
197 <conditional name="indel_search">
198 <param name="allow_indel_search" type="select" label="Allow indel search">
199 <option value="Yes">Yes</option>
200 <option value="No">No</option>
201 </param>
202 <when value="No"/>
203 <when value="Yes">
204 <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." />
205 <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." />
206 </when>
207 </conditional>
208 <param name="junction_filter" type="float" value="0.15" label="Minimum isoform fraction: filter out junctions supported by too few alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" />
209 <param name="max_multihits" type="integer" value="40" label="Maximum number of alignments to be allowed" />
210 <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" />
211 <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" />
212 <param name="initial_read_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in the initial read mapping" />
213 <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" />
214 <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" />
215
216 <!-- Options for supplying own junctions. -->
217 <conditional name="own_junctions">
218 <param name="use_junctions" type="select" label="Use Own Junctions">
219 <option value="No">No</option>
220 <option value="Yes">Yes</option>
221 </param>
222 <when value="Yes">
223 <conditional name="gene_model_ann">
224 <param name="use_annotations" type="select" label="Use Gene Annotation Model">
225 <option value="No">No</option>
226 <option value="Yes">Yes</option>
227 </param>
228 <when value="No" />
229 <when value="Yes">
230 <param format="gtf" 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."/>
231 </when>
232 </conditional>
233 <conditional name="raw_juncs">
234 <param name="use_juncs" type="select" label="Use Raw Junctions">
235 <option value="No">No</option>
236 <option value="Yes">Yes</option>
237 </param>
238 <when value="No" />
239 <when value="Yes">
240 <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."/>
241 </when>
242 </conditional>
243 <param name="no_novel_juncs" type="select" label="Only look for supplied junctions">
244 <option value="No">No</option>
245 <option value="Yes">Yes</option>
246 </param>
247 </when>
248 <when value="No" />
249 </conditional> <!-- /own_junctions -->
250
251 <!-- Closure search. -->
252 <conditional name="closure_search">
253 <param name="use_search" type="select" label="Use Closure Search">
254 <option value="No">No</option>
255 <option value="Yes">Yes</option>
256 </param>
257 <when value="Yes">
258 <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." />
259 <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" />
260 <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" />
261 </when>
262 <when value="No" />
263 </conditional>
264 <!-- Coverage search. -->
265 <conditional name="coverage_search">
266 <param name="use_search" type="select" label="Use Coverage Search">
267 <option selected="true" value="Yes">Yes</option>
268 <option value="No">No</option>
269 </param>
270 <when value="Yes">
271 <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" />
272 <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" />
273 </when>
274 <when value="No" />
275 </conditional>
276 <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.">
277 <option value="No">No</option>
278 <option value="Yes">Yes</option>
279 </param>
280 </when> <!-- full -->
281 </conditional> <!-- sParams -->
282 </when> <!-- single -->
283 <when value="paired">
284 <param format="txt" name="input2" type="data" label="list of RNA-Seq paired end FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
285 <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" />
286 <conditional name="pParams">
287 <param name="pSettingsType" type="select" label="TopHat settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list">
288 <option value="preSet">Commonly used</option>
289 <option value="full">Full parameter list</option>
290 </param>
291 <when value="preSet" />
292 <!-- Full/advanced params. -->
293 <when value="full">
294 <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.">
295 <option value="fr-unstranded">FR Unstranded</option>
296 <option value="fr-firststrand">FR First Strand</option>
297 <option value="fr-secondstrand">FR Second Strand</option>
298 </param>
299 <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."/>
300 <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." />
301 <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" />
302 <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." />
303 <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." />
304 <conditional name="indel_search">
305 <param name="allow_indel_search" type="select" label="Allow indel search">
306 <option value="Yes">Yes</option>
307 <option value="No">No</option>
308 </param>
309 <when value="No"/>
310 <when value="Yes">
311 <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." />
312 <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." />
313 </when>
314 </conditional>
315 <param name="junction_filter" type="float" value="0.15" label="Minimum isoform fraction: filter out junctions supported by too few alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" />
316 <param name="max_multihits" type="integer" value="40" label="Maximum number of alignments to be allowed" />
317 <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" />
318 <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" />
319 <param name="initial_read_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in the initial read mapping" />
320 <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" />
321 <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" />
322 <!-- Options for supplying own junctions. -->
323 <conditional name="own_junctions">
324 <param name="use_junctions" type="select" label="Use Own Junctions">
325 <option value="No">No</option>
326 <option value="Yes">Yes</option>
327 </param>
328 <when value="Yes">
329 <conditional name="gene_model_ann">
330 <param name="use_annotations" type="select" label="Use Gene Annotation Model">
331 <option value="No">No</option>
332 <option value="Yes">Yes</option>
333 </param>
334 <when value="No" />
335 <when value="Yes">
336 <param format="gtf" 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."/>
337 </when>
338 </conditional>
339 <conditional name="raw_juncs">
340 <param name="use_juncs" type="select" label="Use Raw Junctions">
341 <option value="No">No</option>
342 <option value="Yes">Yes</option>
343 </param>
344 <when value="No" />
345 <when value="Yes">
346 <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."/>
347 </when>
348 </conditional>
349 <param name="no_novel_juncs" type="select" label="Only look for supplied junctions">
350 <option value="No">No</option>
351 <option value="Yes">Yes</option>
352 </param>
353 </when>
354 <when value="No" />
355 </conditional> <!-- /own_junctions -->
356
357 <!-- Closure search. -->
358 <conditional name="closure_search">
359 <param name="use_search" type="select" label="Use Closure Search">
360 <option value="No">No</option>
361 <option value="Yes">Yes</option>
362 </param>
363 <when value="Yes">
364 <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." />
365 <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" />
366 <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" />
367 </when>
368 <when value="No" />
369 </conditional>
370 <!-- Coverage search. -->
371 <conditional name="coverage_search">
372 <param name="use_search" type="select" label="Use Coverage Search">
373 <option selected="true" value="Yes">Yes</option>
374 <option value="No">No</option>
375 </param>
376 <when value="Yes">
377 <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" />
378 <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" />
379 </when>
380 <when value="No" />
381 </conditional>
382 <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.">
383 <option value="No">No</option>
384 <option value="Yes">Yes</option>
385 </param>
386 </when> <!-- full -->
387 </conditional> <!-- pParams -->
388 </when> <!-- paired -->
389 </conditional>
390 <param name="tar" type="boolean" truevalue="-t" falsevalue="" checked="false" label="tar option" help="This option creates a tar file for all out results."/>
391 </inputs>
392
393 <outputs>
394 <!-- <data format="bed" name="insertions" label="${tool.name} on ${on_string}: insertions" from_work_dir="tophat_out/insertions.bed">
395 <filter>
396 (
397 ( ( 'sParams' in singlePaired ) and ( 'indel_search' in singlePaired['sParams'] ) and
398 ( singlePaired['sParams']['indel_search']['allow_indel_search'] == 'Yes' ) ) or
399 ( ( 'pParams' in singlePaired ) and ( 'indel_search' in singlePaired['pParams'] ) and
400 ( singlePaired['pParams']['indel_search']['allow_indel_search'] == 'Yes' ) )
401 )
402 </filter>
403 <actions>
404 <conditional name="refGenomeSource.genomeSource">
405 <when value="indexed">
406 <action type="metadata" name="dbkey">
407 <option type="from_data_table" name="tophat_indexes" column="1" offset="0">
408 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
409 <filter type="param_value" ref="refGenomeSource.index" column="0"/>
410 </option>
411 </action>
412 </when>
413 <when value="history">
414 <action type="metadata" name="dbkey">
415 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
416 </action>
417 </when>
418 </conditional>
419 </actions>
420 </data>
421 <data format="bed" name="deletions" label="${tool.name} on ${on_string}: deletions" from_work_dir="tophat_out/deletions.bed">
422 <filter>
423 (
424 ( ( 'sParams' in singlePaired ) and ( 'indel_search' in singlePaired['sParams'] ) and
425 ( singlePaired['sParams']['indel_search']['allow_indel_search'] == 'Yes' ) ) or
426 ( ( 'pParams' in singlePaired ) and ( 'indel_search' in singlePaired['pParams'] ) and
427 ( singlePaired['pParams']['indel_search']['allow_indel_search'] == 'Yes' ) )
428 )
429 </filter>
430 <actions>
431 <conditional name="refGenomeSource.genomeSource">
432 <when value="indexed">
433 <action type="metadata" name="dbkey">
434 <option type="from_data_table" name="tophat_indexes" column="1" offset="0">
435 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
436 <filter type="param_value" ref="refGenomeSource.index" column="0"/>
437 </option>
438 </action>
439 </when>
440 <when value="history">
441 <action type="metadata" name="dbkey">
442 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
443 </action>
444 </when>
445 </conditional>
446 </actions>
447 </data>
448 <data format="bed" name="junctions" label="${tool.name} on ${on_string}: splice junctions">
449 <actions>
450 <conditional name="refGenomeSource.genomeSource">
451 <when value="indexed">
452 <action type="metadata" name="dbkey">
453 <option type="from_data_table" name="tophat_indexes" column="1" offset="0">
454 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
455 <filter type="param_value" ref="refGenomeSource.index" column="0"/>
456 </option>
457 </action>
458 </when>
459 <when value="history">
460 <action type="metadata" name="dbkey">
461 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
462 </action>
463 </when>
464 </conditional>
465 </actions>
466 </data>
467 <data format="bam" name="accepted_hits" label="${tool.name} on ${on_string}: accepted_hits">
468 <actions>
469 <conditional name="refGenomeSource.genomeSource">
470 <when value="indexed">
471 <action type="metadata" name="dbkey">
472 <option type="from_data_table" name="tophat_indexes" column="1" offset="0">
473 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
474 <filter type="param_value" ref="refGenomeSource.index" column="0"/>
475 </option>
476 </action>
477 </when>
478 <when value="history">
479 <action type="metadata" name="dbkey">
480 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
481 </action>
482 </when>
483 </conditional>
484 </actions>
485 </data> -->
486 <data name="outputFileName" format="txt" label="[tophat_parallel] txt File"/>
487 <data name="outputTarFile" format="tar">
488 <filter>tar</filter>
489 </data>
490 </outputs>
491
492
493
494 <help>
495 **Tophat Overview**
496
497 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).
498
499 .. _Tophat: http://tophat.cbcb.umd.edu/
500
501 ------
502
503 **Know what you are doing**
504
505 .. class:: warningmark
506
507 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.
508
509 .. __: http://tophat.cbcb.umd.edu/manual.html
510
511 ------
512
513 **Input formats**
514
515 Tophat accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.
516
517 ------
518
519 **Outputs**
520
521 Tophat produces two output files:
522
523 - 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.
524 - accepted_hits -- A list of read alignments in BAM_ format.
525
526 .. _BED: http://genome.ucsc.edu/FAQ/FAQformat.html#format1
527 .. _BAM: http://samtools.sourceforge.net/
528
529 Two other possible outputs, depending on the options you choose, are insertions and deletions, both of which are in BED format.
530
531 -------
532
533 **Tophat settings**
534
535 All of the options have a default value. You can change any of them. Some of the options in Tophat have been implemented here.
536
537 ------
538
539 **Tophat parameter list**
540
541 This is a list of implemented Tophat options::
542
543 -r This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments
544 selected at 300bp, where each end is 50bp, you should set -r to be 200. There is no default, and this parameter
545 is required for paired end runs.
546 --mate-std-dev INT The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp.
547 -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
548 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
549 read with this many bases on each side. This must be at least 3 and the default is 8.
550 -m/--splice-mismatches INT The maximum number of mismatches that may appear in the "anchor" region of a spliced alignment. The default is 0.
551 -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.
552 -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.
553 -F/--min-isoform-fraction 0.0-1.0 TopHat filters out junctions supported by too few alignments. Suppose a junction spanning two exons, is supported by S reads. Let the average depth of coverage of
554 exon A be D, and assume that it is higher than B. If S / D is less than the minimum isoform fraction, the junction is not reported. A value of zero disables the
555 filter. The default is 0.15.
556 -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
557 alignments. The default is 40.
558 -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.
559 -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.
560 -no-novel-juncs Only look for junctions indicated in the supplied GFF file. (ignored without -G)
561 --no-closure-search Disables the mate pair closure-based search for junctions. Currently, has no effect - closure search is off by default.
562 --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)
563 --no-coverage-search Disables the coverage based search for junctions.
564 --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.
565 --microexon-search With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.
566 --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.
567 --segment-mismatches Read segments are mapped independently, allowing up to this many mismatches in each segment alignment. The default is 2.
568 --segment-length Each read is cut up into segments, each at least this long. These segments are mapped independently. The default is 25.
569 --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.
570 --min-closure-intron The minimum intron length that may be found during closure search. The default is 50.
571 --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000.
572 --min-coverage-intron The minimum intron length that may be found during coverage search. The default is 50.
573 --max-coverage-intron The maximum intron length that may be found during coverage search. The default is 20000.
574 --min-segment-intron The minimum intron length that may be found during split-segment search. The default is 50.
575 --max-segment-intron The maximum intron length that may be found during split-segment search. The default is 500000.
576 </help>
577 </tool>