Mercurial > repos > devteam > bowtie_color_wrappers

comparison bowtie_color_wrapper.xml @ 0:fd0914e451c5 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded tarball
author devteam
date Mon, 26 Nov 2012 09:47:13 -0500
parents
children 2506bd84cc54
comparison
equal deleted inserted replaced
-1:000000000000 0:fd0914e451c5
1 <tool id="bowtie_color_wrapper" name="Map with Bowtie for SOLiD" version="1.1.2">
2 <requirements>
3 <requirement type='package' version="0.12.7">bowtie</requirement>
4 </requirements>
5 <description></description>
6 <command interpreter="python">
7 bowtie_wrapper.py
8 ## Hackish setting of number of threads
9 --threads="4"
10 ## Outputs
11 --output=$output
12 #if str( $singlePaired.sPaired ) == "single"
13 #if $output_unmapped_reads_l
14 --output_unmapped_reads=$output_unmapped_reads_l
15 #end if
16 #if $output_suppressed_reads_l
17 --output_suppressed_reads=$output_suppressed_reads_l
18 #end if
19 #else
20 #if $output_unmapped_reads_l and $output_unmapped_reads_r
21 --output_unmapped_reads_l=$output_unmapped_reads_l
22 --output_unmapped_reads_r=$output_unmapped_reads_r
23 #end if
24 #if $output_suppressed_reads_l and $output_suppressed_reads_l
25 --output_suppressed_reads_l=$output_suppressed_reads_l
26 --output_suppressed_reads_r=$output_suppressed_reads_r
27 #end if
28 #end if
29 ## Inputs
30 --dataType="solid"
31 --suppressHeader=$suppressHeader
32 --genomeSource=$refGenomeSource.genomeSource
33 #if $refGenomeSource.genomeSource == "history":
34 ##index already exists
35 #if $refGenomeSource.ownFile.extension.startswith( 'bowtie_' ):
36 ##user previously built
37 --ref="${refGenomeSource.ownFile.extra_files_path}/${refGenomeSource.ownFile.metadata.base_name}"
38 --do_not_build_index
39 #else:
40 ##build index on the fly
41 --ref=$refGenomeSource.ownFile
42 --indexSettings=$refGenomeSource.indexParams.indexSettings
43 #if $refGenomeSource.indexParams.indexSettings == "indexFull":
44 --iautoB=$refGenomeSource.indexParams.autoBehavior.autoB
45 #if $refGenomeSource.indexParams.autoBehavior.autoB == "set":
46 --ipacked=$refGenomeSource.indexParams.autoBehavior.packed
47 --ibmax=$refGenomeSource.indexParams.autoBehavior.bmax
48 --ibmaxdivn=$refGenomeSource.indexParams.autoBehavior.bmaxdivn
49 --idcv=$refGenomeSource.indexParams.autoBehavior.dcv
50 #end if
51 --inodc=$refGenomeSource.indexParams.nodc
52 --inoref=$refGenomeSource.indexParams.noref
53 --ioffrate=$refGenomeSource.indexParams.offrate
54 --iftab=$refGenomeSource.indexParams.ftab
55 --intoa=$refGenomeSource.indexParams.ntoa
56 --iendian=$refGenomeSource.indexParams.endian
57 --iseed=$refGenomeSource.indexParams.seed
58 --icutoff=$refGenomeSource.indexParams.cutoff
59 #end if
60 #end if
61 #else
62 ##use pre-built index
63 --ref="${refGenomeSource.index.fields.path}"
64 #end if
65 --paired=$singlePaired.sPaired
66 #if $singlePaired.sPaired == "single":
67 --input1=$singlePaired.sInput1
68 --params=$singlePaired.sParams.sSettingsType
69 #if $singlePaired.sParams.sSettingsType == "full":
70 --skip=$singlePaired.sParams.sSkip
71 --alignLimit=$singlePaired.sParams.sAlignLimit
72 --trimH=$singlePaired.sParams.sTrimH
73 --trimL=$singlePaired.sParams.sTrimL
74 --mismatchSeed=$singlePaired.sParams.sMismatchSeed
75 --mismatchQual=$singlePaired.sParams.sMismatchQual
76 --seedLen=$singlePaired.sParams.sSeedLen
77 --rounding=$singlePaired.sParams.sRounding
78 --maqSoapAlign=$singlePaired.sParams.sMaqSoapAlign
79 --tryHard=$singlePaired.sParams.sTryHard
80 --valAlign=$singlePaired.sParams.sValAlign
81 --allValAligns=$singlePaired.sParams.sAllValAligns
82 --suppressAlign=$singlePaired.sParams.sSuppressAlign
83 --best=$singlePaired.sParams.sBestOption.sBest
84 #if $singlePaired.sParams.sBestOption.sBest == "doBest":
85 --maxBacktracks=$singlePaired.sParams.sBestOption.sdMaxBacktracks
86 --strata=$singlePaired.sParams.sBestOption.sdStrata
87 #else:
88 --maxBacktracks=$singlePaired.sParams.sBestOption.snMaxBacktracks
89 #end if
90 --offrate=$singlePaired.sParams.sOffrate
91 --seed=$singlePaired.sParams.sSeed
92 --snpphred=$singlePaired.sParams.sSnpphred
93 --snpfrac=$singlePaired.sParams.sSnpfrac
94 --keepends=$singlePaired.sParams.sKeepends
95 #end if
96 #else:
97 --input1=$singlePaired.pInput1
98 --input2=$singlePaired.pInput2
99 --maxInsert=$singlePaired.pMaxInsert
100 --mateOrient=$singlePaired.pMateOrient
101 --params=$singlePaired.pParams.pSettingsType
102 #if $singlePaired.pParams.pSettingsType == "full":
103 --skip=$singlePaired.pParams.pSkip
104 --alignLimit=$singlePaired.pParams.pAlignLimit
105 --trimH=$singlePaired.pParams.pTrimH
106 --trimL=$singlePaired.pParams.pTrimL
107 --mismatchSeed=$singlePaired.pParams.pMismatchSeed
108 --mismatchQual=$singlePaired.pParams.pMismatchQual
109 --seedLen=$singlePaired.pParams.pSeedLen
110 --rounding=$singlePaired.pParams.pRounding
111 --maqSoapAlign=$singlePaired.pParams.pMaqSoapAlign
112 --minInsert=$singlePaired.pParams.pMinInsert
113 --maxAlignAttempt=$singlePaired.pParams.pMaxAlignAttempt
114 --forwardAlign=$singlePaired.pParams.pForwardAlign
115 --reverseAlign=$singlePaired.pParams.pReverseAlign
116 --tryHard=$singlePaired.pParams.pTryHard
117 --valAlign=$singlePaired.pParams.pValAlign
118 --allValAligns=$singlePaired.pParams.pAllValAligns
119 --suppressAlign=$singlePaired.pParams.pSuppressAlign
120 --best=$singlePaired.pParams.pBestOption.pBest
121 #if $singlePaired.pParams.pBestOption.pBest == "doBest":
122 --maxBacktracks=$singlePaired.pParams.pBestOption.pdMaxBacktracks
123 --strata=$singlePaired.pParams.pBestOption.pdStrata
124 #else:
125 --maxBacktracks=$singlePaired.pParams.pBestOption.pnMaxBacktracks
126 #end if
127 --offrate=$singlePaired.pParams.pOffrate
128 --seed=$singlePaired.pParams.pSeed
129 --snpphred=$singlePaired.pParams.pSnpphred
130 --snpfrac=$singlePaired.pParams.pSnpfrac
131 --keepends=$singlePaired.pParams.pKeepends
132 #end if
133 #end if
134 </command>
135 <inputs>
136 <conditional name="refGenomeSource">
137 <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">
138 <option value="indexed">Use a built-in index</option>
139 <option value="history">Use one from the history</option>
140 </param>
141 <when value="indexed">
142 <param name="index" type="select" label="Select the reference genome" help="if your genome of interest is not listed - contact Galaxy team">
143 <options from_data_table="bowtie_indexes_color">
144 <filter type="sort_by" column="2" />
145 <validator type="no_options" message="No indexes are available" />
146 </options>
147 </param>
148 </when>
149 <when value="history">
150 <param name="ownFile" type="data" format="bowtie_color_index,fasta" metadata_name="dbkey" label="Select the reference genome" />
151 <conditional name="indexParams">
152 <param name="indexSettings" type="select" label="Choose whether to use Default options for building indices or to Set your own" help="These settings are ignored when using a prebuilt index">
153 <option value="indexPreSet">Default</option>
154 <option value="indexFull">Set your own</option>
155 </param>
156 <when value="indexPreSet" />
157 <when value="indexFull">
158 <conditional name="autoBehavior">
159 <param name="autoB" type="select" label="Choose to use automatic or specified behavior for some parameters (-a)" help="Allows you to set --packed, --bmax, --bmaxdivn, and --dcv">
160 <option value="auto">Automatic behavior</option>
161 <option value="set">Set values (sets --noauto and allows others to be set)</option>
162 </param>
163 <when value="auto" />
164 <when value="set">
165 <param name="packed" type="select" label="Whether or not to use a packed representation for DNA strings (--packed)">
166 <option value="unpacked">Use regular representation</option>
167 <option value="packed">Use packed representation</option>
168 </param>
169 <param name="bmax" type="integer" value="-1" label="Maximum number of suffixes allowed in a block (--bmax)" help="-1 for not specified. Must be at least 1" />
170 <param name="bmaxdivn" type="integer" value="4" label="Maximum number of suffixes allowed in a block as a fraction of the length of the reference (--bmaxdivn)" />
171 <param name="dcv" type="integer" value="1024" label="The period for the difference-cover sample (--dcv)" />
172 </when>
173 </conditional>
174 <param name="nodc" type="select" label="Whether or not to disable the use of the difference-cover sample (--nodc)" help="Suffix sorting becomes quadratic-time in the worst case (with a very repetitive reference)">
175 <option value="dc">Use difference-cover sample</option>
176 <option value="nodc">Disable difference-cover sample</option>
177 </param>
178 <param name="noref" type="select" label="Whether or not to build the part of the reference index used only in paired-end alignment (-r)">
179 <option value="ref">Build all index files</option>
180 <option value="noref">Do not build paired-end alignment index files</option>
181 </param>
182 <param name="offrate" type="integer" value="5" label="How many rows get marked during annotation of some or all of the Burrows-Wheeler rows (-o)" />
183 <param name="ftab" type="integer" value="10" label="The size of the lookup table used to calculate an initial Burrows-Wheeler range with respect to the first n characters of the query (-t)" help="ftab is 4^(n+1) bytes" />
184 <param name="ntoa" type="select" label="Whether or not to convert Ns in the reference sequence to As (--ntoa)">
185 <option value="no">Do not convert Ns</option>
186 <option value="yes">Convert Ns to As</option>
187 </param>
188 <param name="endian" type="select" label="Endianness to use when serializing integers to the index file (--big/--little)" help="Little is most appropriate for Intel- and AMD-based architecture">
189 <option value="little">Little</option>
190 <option value="big">Big</option>
191 </param>
192 <param name="seed" type="integer" value="-1" label="Seed for the pseudorandom number generator (--seed)" help="Use -1 to use default" />
193 <param name="cutoff" type="integer" value="-1" label="Number of first bases of the reference sequence to index (--cutoff)" help="Use -1 to use default" />
194 </when> <!-- indexFull -->
195 </conditional> <!-- indexParams -->
196 </when> <!-- history -->
197 </conditional> <!-- refGenomeSource -->
198 <conditional name="singlePaired">
199 <param name="sPaired" type="select" label="Is this library mate-paired?">
200 <option value="single">Single-end</option>
201 <option value="paired">Paired-end</option>
202 </param>
203 <when value="single">
204 <param name="sInput1" type="data" format="fastqcssanger" label="FASTQ file" help="Must have Sanger-scaled quality values with ASCII offset 33"/>
205 <conditional name="sParams">
206 <param name="sSettingsType" type="select" label="Bowtie settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list">
207 <option value="preSet">Commonly used</option>
208 <option value="full">Full parameter list</option>
209 </param>
210 <when value="preSet" />
211 <when value="full">
212 <param name="sSkip" type="integer" value="0" label="Skip the first n reads (-s)" />
213 <param name="sAlignLimit" type="integer" value="-1" label="Only align the first n reads (-u)" help="-1 for off" />
214 <param name="sTrimH" type="integer" value="0" label="Trim n bases from high-quality (left) end of each read before alignment (-5)" />
215 <param name="sTrimL" type="integer" value="0" label="Trim n bases from low-quality (right) end of each read before alignment (-3)" />
216 <param name="sMismatchSeed" type="integer" value="2" label="Maximum number of mismatches permitted in the seed (-n)" help="May be 0, 1, 2, or 3" />
217 <param name="sMismatchQual" type="integer" value="70" label="Maximum permitted total of quality values at mismatched read positions (-e)" />
218 <param name="sSeedLen" type="integer" value="28" label="Seed length (-l)" help="Minimum value is 5" />
219 <param name="sRounding" type="select" label="Whether or not to round to the nearest 10 and saturating at 30 (--nomaqround)">
220 <option value="round">Round to nearest 10</option>
221 <option value="noRound">Do not round to nearest 10</option>
222 </param>
223 <param name="sMaqSoapAlign" type="integer" value="-1" label="Number of mismatches for SOAP-like alignment policy (-v)" help="-1 for default MAQ-like alignment policy" />
224 <param name="sTryHard" type="select" label="Whether or not to try as hard as possible to find valid alignments when they exist (-y)" help="Tryhard mode is much slower than regular mode">
225 <option value="noTryHard">Do not try hard</option>
226 <option value="doTryHard">Try hard</option>
227 </param>
228 <param name="sValAlign" type="integer" value="1" label="Report up to n valid alignments per read (-k)" />
229 <param name="sAllValAligns" type="select" label="Whether or not to report all valid alignments per read (-a)">
230 <option value="noAllValAligns">Do not report all valid alignments</option>
231 <option value="doAllValAligns">Report all valid alignments</option>
232 </param>
233 <param name="sSuppressAlign" type="integer" value="-1" label="Suppress all alignments for a read if more than n reportable alignments exist (-m)" help="-1 for no limit" />
234 <param name="sMaxFile" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write all reads with a number of valid alignments exceeding the limit set with the -m option to a file (--max)" />
235 <param name="sUnmappedFile" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write all reads that could not be aligned to a file (--un)" />
236 <conditional name="sBestOption">
237 <param name="sBest" type="select" label="Whether or not to make Bowtie guarantee that reported singleton alignments are 'best' in terms of stratum and in terms of the quality values at the mismatched positions (--best)" help="Removes all strand bias. Only affects which alignments are reported by Bowtie. Runs slower with best option">
238 <option value="noBest">Do not use best</option>
239 <option value="doBest">Use best</option>
240 </param>
241 <when value="noBest">
242 <param name="snMaxBacktracks" type="integer" value="125" label="Maximum number of backtracks permitted when aligning a read (--maxbts)" />
243 </when>
244 <when value="doBest">
245 <param name="sdMaxBacktracks" type="integer" value="800" label="Maximum number of backtracks permitted when aligning a read (--maxbts)" />
246 <param name="sdStrata" type="select" label="Whether or not to report only those alignments that fall in the best stratum if many valid alignments exist and are reportable (--strata)">
247 <option value="noStrata">Do not use strata option</option>
248 <option value="doStrata">Use strata option</option>
249 </param>
250 </when>
251 </conditional> <!-- sBestOption -->
252 <param name="sOffrate" type="integer" value="-1" label="Override the offrate of the index to n (-o)" help="-1 for default" />
253 <param name="sSeed" type="integer" value="-1" label="Seed for pseudo-random number generator (--seed)" help="-1 for default" />
254 <param name="sSnpphred" type="integer" value="-1" label="SNP penalty (ratio of SNPs per base in the subject genome) (--snpphred)" help="Enter this OR Ratio of SNPs per base" />
255 <param name="sSnpfrac" type="float" value="0.001" label="Ratio of SNPs per base (estimated ratio for colorspace alignments) (--snpfrac)" help="Enter this OR SNP penalty" />
256 <param name="sKeepends" type="select" label="Keep the extreme-ends nucleotides and qualities rather than trimming them (--col-keepends)">
257 <option value="doKeepends">Keep ends</option>
258 <option value="noKeepends">Trim ends</option>
259 </param>
260 </when> <!-- full -->
261 </conditional> <!-- sParams -->
262 </when> <!-- single -->
263 <when value="paired">
264 <param name="pInput1" type="data" format="fastqcssanger" label="FASTQ file" help="Must have Sanger-scaled quality values with ASCII offset 33"/>
265 <param name="pInput2" type="data" format="fastqcssanger" label="Reverse FASTQ file" help="Must have Sanger-scaled quality values with ASCII offset 33"/>
266 <param name="pMaxInsert" type="integer" value="1000" label="Maximum insert size for valid paired-end alignments (-X)" />
267 <param name="pMateOrient" type="select" label="The upstream/downstream mate orientation for valid paired-end alignment against the forward reference strand (--fr/--rf/--ff)">
268 <option value="ff">FF (for SOLiD)</option>
269 <option value="fr">FR (for Illumina)</option>
270 <option value="rf">RF</option>
271 </param>
272 <conditional name="pParams">
273 <param name="pSettingsType" type="select" label="Bowtie settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list">
274 <option value="preSet">Commonly used</option>
275 <option value="full">Full parameter list</option>
276 </param>
277 <when value="preSet" />
278 <when value="full">
279 <param name="pSkip" type="integer" value="0" label="Skip the first n pairs (-s)" />
280 <param name="pAlignLimit" type="integer" value="-1" label="Only align the first n pairs (-u)" help="-1 for off" />
281 <param name="pTrimH" type="integer" value="0" label="Trim n bases from high-quality (left) end of each read before alignment (-5)" />
282 <param name="pTrimL" type="integer" value="0" label="Trim n bases from low-quality (right) end of each read before alignment (-3)" />
283 <param name="pMismatchSeed" type="integer" value="2" label="Maximum number of mismatches permitted in the seed (-n)" help="May be 0, 1, 2, or 3" />
284 <param name="pMismatchQual" type="integer" value="70" label="Maximum permitted total of quality values at mismatched read positions (-e)" />
285 <param name="pSeedLen" type="integer" value="28" label="Seed length (-l)" help="Minimum value is 5" />
286 <param name="pRounding" type="select" label="Whether or not to round to the nearest 10 and saturating at 30 (--nomaqround)">
287 <option value="round">Round to nearest 10</option>
288 <option value="noRound">Do not round to nearest 10</option>
289 </param>
290 <param name="pMaqSoapAlign" type="integer" value="-1" label="Number of mismatches for SOAP-like alignment policy (-v)" help="-1 for default MAQ-like alignment policy" />
291 <param name="pMinInsert" type="integer" value="0" label="Minimum insert size for valid paired-end alignments (-I)" />
292 <param name="pMaxAlignAttempt" type="integer" value="100" label="Maximum number of attempts Bowtie will make to match an alignment for one mate with an alignment for the opposite mate (--pairtries)" />
293 <param name="pForwardAlign" type="select" label="Choose whether or not to attempt to align the forward reference strand (--nofw)">
294 <option value="forward">Align against the forward reference strand</option>
295 <option value="noForward">Do not align against the forward reference strand</option>
296 </param>
297 <param name="pReverseAlign" type="select" label="Choose whether or not to align against the reverse-complement reference strand (--norc)">
298 <option value="reverse">Align against the reverse-complement reference strand</option>
299 <option value="noReverse">Do not align against the reverse-complement reference strand</option>
300 </param>
301 <param name="pTryHard" type="select" label="Whether or not to try as hard as possible to find valid alignments when they exist (-y)" help="Tryhard mode is much slower than regular mode">
302 <option value="noTryHard">Do not try hard</option>
303 <option value="doTryHard">Try hard</option>
304 </param>
305 <param name="pValAlign" type="integer" value="1" label="Report up to n valid arguments per pair (-k)" />
306 <param name="pAllValAligns" type="select" label="Whether or not to report all valid alignments per pair (-a)">
307 <option value="noAllValAligns">Do not report all valid alignments</option>
308 <option value="doAllValAligns">Report all valid alignments</option>
309 </param>
310 <param name="pSuppressAlign" type="integer" value="-1" label="Suppress all alignments for a pair if more than n reportable alignments exist (-m)" help="-1 for no limit" />
311 <param name="pMaxFile" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write all reads with a number of valid alignments exceeding the limit set with the -m option to a file (--max)" />
312 <param name="pUnmappedFile" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write all reads that could not be aligned to a file (--un)" />
313 <conditional name="pBestOption">
314 <param name="pBest" type="select" label="Whether or not to make Bowtie guarantee that reported singleton alignments are 'best' in terms of stratum and in terms of the quality values at the mismatched positions (--best)" help="Removes all strand bias. Only affects which alignments are reported by Bowtie. Runs slower with best option">
315 <option value="noBest">Do not use best</option>
316 <option value="doBest">Use best</option>
317 </param>
318 <when value="noBest">
319 <param name="pnMaxBacktracks" type="integer" value="125" label="Maximum number of backtracks permitted when aligning a read (--maxbts)" />
320 </when>
321 <when value="doBest">
322 <param name="pdMaxBacktracks" type="integer" value="800" label="Maximum number of backtracks permitted when aligning a read (--maxbts)" />
323 <param name="pdStrata" type="select" label="Whether or not to report only those alignments that fall in the best stratum if many valid alignments exist and are reportable (--strata)">
324 <option value="noStrata">Do not use strata option</option>
325 <option value="doStrata">Use strata option</option>
326 </param>
327 </when>
328 </conditional> <!-- pBestOption -->
329 <param name="pOffrate" type="integer" value="-1" label="Override the offrate of the index to n (-o)" help="-1 for default" />
330 <param name="pSeed" type="integer" value="-1" label="Seed for pseudo-random number generator (--seed)" help="-1 for default" />
331 <param name="pSnpphred" type="integer" value="-1" label="SNP penalty (ratio of SNPs per base in the subject genome) (--snpphred)" help="Enter this OR Ratio of SNPs per base" />
332 <param name="pSnpfrac" type="float" value="0.001" label="Ratio of SNPs per base (estimated ratio for colorspace alignments) (--snpfrac)" help="Enter this OR SNP penalty" />
333 <param name="pKeepends" type="select" label="Keep the extreme-ends nucleotides and qualities rather than trimming them (--col-keepends)">
334 <option value="doKeepends">Keep ends</option>
335 <option value="noKeepends">Trim ends</option>
336 </param>
337 </when> <!-- full -->
338 </conditional> <!-- pParams -->
339 </when> <!-- paired -->
340 </conditional> <!-- singlePaired -->
341 <param name="suppressHeader" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Suppress the header in the output SAM file" help="Bowtie produces SAM with several lines of header information by default" />
342 </inputs>
343 <outputs>
344 <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
345 <actions>
346 <conditional name="refGenomeSource.genomeSource">
347 <when value="indexed">
348 <action type="metadata" name="dbkey">
349 <option type="from_data_table" name="bowtie_indexes_color" column="1" offset="0">
350 <filter type="param_value" column="0" value="#" filter_by="startswith" keep="False"/>
351 <filter type="param_value" ref="refGenomeSource.index" column="0"/>
352 </option>
353 </action>
354 </when>
355 <when value="history">
356 <action type="metadata" name="dbkey">
357 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
358 </action>
359 </when>
360 </conditional>
361 </actions>
362 </data>
363 <data format="fastqcssanger" name="output_suppressed_reads_l" label="${tool.name} on ${on_string}: suppressed reads (L)">
364 <filter>((
365 singlePaired['sPaired'] == "single" and
366 singlePaired['sParams']['sSettingsType'] == "full" and
367 singlePaired['sParams']['sMaxFile'] is True
368 ) or (
369 singlePaired['sPaired'] == "paired" and
370 singlePaired['pParams']['pSettingsType'] == "full" and
371 singlePaired['pParams']['pMaxFile'] is True
372 ))
373 </filter>
374 </data>
375 <data format="fastqcssanger" name="output_suppressed_reads_r" label="${tool.name} on ${on_string}: suppressed reads (R)">
376 <filter>singlePaired['sPaired'] == "paired"</filter>
377 <filter>singlePaired['pParams']['pSettingsType'] == "full"</filter>
378 <filter>singlePaired['pParams']['pMaxFile'] is True</filter>
379 </data>
380 <data format="fastqcssanger" name="output_unmapped_reads_l" label="${tool.name} on ${on_string}: unmapped reads (L)">
381 <filter>
382 ((
383 singlePaired['sPaired'] == "single" and
384 singlePaired['sParams']['sSettingsType'] == "full" and
385 singlePaired['sParams']['sUnmappedFile'] is True
386 ) or (
387 singlePaired['sPaired'] == "paired" and
388 singlePaired['pParams']['pSettingsType'] == "full" and
389 singlePaired['pParams']['pUnmappedFile'] is True
390 ))
391 </filter>
392 </data>
393 <data format="fastqcssanger" name="output_unmapped_reads_r" label="${tool.name} on ${on_string}: unmapped reads (R)">
394 <filter>singlePaired['sPaired'] == "paired"</filter>
395 <filter>singlePaired['pParams']['pSettingsType'] == "full"</filter>
396 <filter>singlePaired['pParams']['pUnmappedFile'] is True</filter>
397 </data>
398 </outputs>
399 <tests>
400 <test>
401 <!--
402 Bowtie command:
403 bowtie -q -p 4 -S +sam-nohead -C chrM_color test-data/bowtie_in1.fastqcssanger > bowtie_out1_u.sam
404 sort bowtie_out1_u.sam > bowtie_out1.sam
405 -p is the number of threads, which is hardcoded above. You need to replace the + with 2 dashes.
406 chrM_color needs to be the base location/name of the index files.
407 -->
408 <param name="genomeSource" value="indexed" />
409 <param name="index" value="equCab2chrM" />
410 <param name="sPaired" value="single" />
411 <param name="sInput1" ftype="fastqcssanger" value="bowtie_in1.fastqcssanger" />
412 <param name="sSettingsType" value="preSet" />
413 <param name="suppressHeader" value="true" />
414 <output name="output" ftype="sam" file="bowtie_out1.sam" sort="True" />
415 </test>
416 <test>
417 <!--
418 Bowtie command:
419 bowtie-build -C -f test-data/chr_m.fasta chrM_color
420 bowtie -q -X 1000 +ff -p 4 -S +sam-nohead -C -n 2 -e 70 -l 28 -X 250 +pairtries 100 +maxbts 125 -k 1 +snpfrac 0.001 +col-keepends +un bowtie_out3_u.fastq chrM_color -1 test-data/bowtie_in3.fastqcssanger -2 test-data/bowtie_in4.fastqcssanger > bowtie_out2_u.sam
421 sort bowtie_out2_u.sam > bowtie_out2.sam
422 sort bowtie_out3_u_1.sam > bowtie_out3_1.sam
423 sort bowtie_out3_u_2.sam > bowtie_out3_2.sam
424 Then also need to modify bowtie_out3_1.sam and bowtie_out3_2.sam so that all @ lines come before sequence lines.
425 The two unmapped output files will be named bowtie_out4_1.fastq and bowtie_out4_2.fastq
426 -p is the number of threads, hardcoded above. You need to replace the + with 2 dashes.
427 chrM_base is the index files' location/base name.
428 -->
429 <param name="genomeSource" value="history" />
430 <param name="ownFile" value="chr_m.fasta" />
431 <param name="indexSettings" value="indexPreSet" />
432 <param name="sPaired" value="paired" />
433 <param name="pInput1" ftype="fastqcssanger" value="bowtie_in3.fastqcssanger" />
434 <param name="pInput2" ftype="fastqcssanger" value="bowtie_in4.fastqcssanger" />
435 <param name="pMaxInsert" value="1000" />
436 <param name="pMateOrient" value="ff" />
437 <param name="pSettingsType" value="full" />
438 <param name="pSkip" value="0" />
439 <param name="pAlignLimit" value="-1" />
440 <param name="pTrimH" value="0" />
441 <param name="pTrimL" value="0" />
442 <param name="pMismatchSeed" value="2" />
443 <param name="pMismatchQual" value="70" />
444 <param name="pSeedLen" value="28" />
445 <param name="pRounding" value="round" />
446 <param name="pMaqSoapAlign" value="-1" />
447 <param name="pMinInsert" value="0" />
448 <param name="pMaxAlignAttempt" value="100" />
449 <param name="pForwardAlign" value="forward" />
450 <param name="pReverseAlign" value="reverse" />
451 <param name="pTryHard" value="noTryHard" />
452 <param name="pValAlign" value="1" />
453 <param name="pAllValAligns" value="noAllValAligns" />
454 <param name="pSuppressAlign" value="-1" />
455 <param name="pUnmappedFile" value="true" />
456 <param name="pMaxFile" value="false" />
457 <param name="pBest" value="noBest" />
458 <param name="pnMaxBacktracks" value="125" />
459 <param name="pOffrate" value="-1" />
460 <param name="pSeed" value="-1" />
461 <param name="pSnpphred" value="-1" />
462 <param name="pSnpfrac" value="0.001" />
463 <param name="pKeepends" value="doKeepends" />
464 <param name="suppressHeader" value="true" />
465 <output name="output" ftype="sam" file="bowtie_out2.sam" sort="True" />
466 <output name="output_unmapped_reads_l" ftype="fastqcssanger" file="bowtie_out3_1.fastq" sort="True" />
467 <output name="output_unmapped_reads_r" ftype="fastqcssanger" file="bowtie_out3_2.fastq" sort="True" />
468 </test>
469 <test>
470 <!--
471 Bowtie command:
472 bowtie -q -p 4 -S +sam-nohead -C -n 2 -e 70 -l 28 +maxbts 125 -k 1 +snpfrac 0.001 +col-keepends chrM_color test-data/bowtie_in1.fastqcssanger > bowtie_out4_u.sam
473 sort bowtie_out4_u.sam > bowtie_out4.sam
474 -p is the number of threads, hardcoded above. You need to replace the + with 2 dashes.
475 chrM_base is the index files' location/base name.
476 -->
477 <param name="genomeSource" value="indexed" />
478 <param name="index" value="equCab2chrM" />
479 <param name="sPaired" value="single" />
480 <param name="sInput1" ftype="fastqcssanger" value="bowtie_in1.fastqcssanger" />
481 <param name="sSettingsType" value="full" />
482 <param name="sSkip" value="0" />
483 <param name="sAlignLimit" value="-1" />
484 <param name="sTrimH" value="0" />
485 <param name="sTrimL" value="0" />
486 <param name="sMismatchSeed" value="2" />
487 <param name="sMismatchQual" value="70" />
488 <param name="sSeedLen" value="28" />
489 <param name="sRounding" value="round" />
490 <param name="sMaqSoapAlign" value="-1" />
491 <param name="sTryHard" value="noTryHard" />
492 <param name="sValAlign" value="1" />
493 <param name="sAllValAligns" value="noAllValAligns" />
494 <param name="sSuppressAlign" value="-1" />
495 <param name="sUnmappedFile" value="false" />
496 <param name="sMaxFile" value="false" />
497 <param name="sBest" value="noBest" />
498 <param name="snMaxBacktracks" value="125" />
499 <param name="sOffrate" value="-1" />
500 <param name="sSeed" value="-1" />
501 <param name="sSnpphred" value="-1" />
502 <param name="sSnpfrac" value="0.001" />
503 <param name="sKeepends" value="doKeepends" />
504 <param name="suppressHeader" value="true" />
505 <output name="output" ftype="sam" file="bowtie_out4.sam" sort="True" />
506 </test>
507 <test>
508 <!--
509 Bowtie command:
510 bowtie-build +noauto +bmaxdivn 4 +dcv 1024 +offrate 5 +ftabchars 10 +little -C -f test-data/chr_m.fasta chrM_color
511 bowtie -q -X 1000 +ff -p 4 -S +sam-nohead -C chrM_color -1 test-data/bowtie_in3.fastqcssanger -2 test-data/bowtie_in4.fastqcssanger > bowtie_out5_u.sam
512 sort bowtie_out5_u.sam > bowtie_out5.sam
513 -p is the number of threads, hardcoded above. You need to replace the + with 2 dashes.
514 chrM_base is the index files' location/base name.
515 -->
516 <param name="genomeSource" value="history" />
517 <param name="ownFile" value="chr_m.fasta" />
518 <param name="indexSettings" value="indexFull" />
519 <param name="autoB" value="set" />
520 <param name="packed" value="unpacked" />
521 <param name="bmax" value="-1" />
522 <param name="bmaxdivn" value="4" />
523 <param name="dcv" value="1024" />
524 <param name="nodc" value="dc" />
525 <param name="noref" value="ref" />
526 <param name="offrate" value="5" />
527 <param name="ftab" value="10" />
528 <param name="ntoa" value="no" />
529 <param name="endian" value="little" />
530 <param name="seed" value="-1" />
531 <param name="cutoff" value="-1" />
532 <param name="sPaired" value="paired" />
533 <param name="pInput1" ftype="fastqcssanger" value="bowtie_in3.fastqcssanger" />
534 <param name="pInput2" ftype="fastqcssanger" value="bowtie_in4.fastqcssanger" />
535 <param name="pMaxInsert" value="1000" />
536 <param name="pMateOrient" value="ff" />
537 <param name="pSettingsType" value="preSet" />
538 <param name="suppressHeader" value="true" />
539 <output name="output" ftype="sam" file="bowtie_out5.sam" sort="True" />
540 </test>
541 </tests>
542
543 <help>
544
545 **What it does**
546
547 Bowtie_ is a short read aligner designed to be ultrafast and memory-efficient. It is developed by Ben Langmead and Cole Trapnell. Please cite: Langmead B, Trapnell C, Pop M, Salzberg SL. Ultrafast and memory-efficient alignment of short DNA sequences to the human genome. Genome Biology 10:R25.
548
549 .. _Bowtie: http://bowtie-bio.sourceforge.net/index.shtml
550
551 ------
552
553 **Know what you are doing**
554
555 .. class:: warningmark
556
557 There is no such thing (yet) as an automated gearshift in short read mapping. 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.
558
559 .. __: http://bowtie-bio.sourceforge.net/index.shtml
560
561 ------
562
563 **Input formats**
564
565 Bowtie accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.
566
567 ------
568
569 **A Note on Built-in Reference Genomes**
570
571 The default variant for all genomes is "Full", defined as all primary chromosomes (or scaffolds/contigs) including mitochondrial plus associated unmapped, plasmid, and other segments. When only one version of a genome is available in this tool, it represents the default "Full" variant. Some genomes will have more than one variant available. The "Canonical Male" or sometimes simply "Canonical" variant contains the primary chromosomes for a genome. For example a human "Canonical" variant contains chr1-chr22, chrX, chrY, and chrM. The "Canonical Female" variant contains the primary chromosomes excluding chrY.
572
573 ------
574
575 **Outputs**
576
577 The output is in SAM format, and has the following columns::
578
579 Column Description
580 -------- --------------------------------------------------------
581 1 QNAME Query (pair) NAME
582 2 FLAG bitwise FLAG
583 3 RNAME Reference sequence NAME
584 4 POS 1-based leftmost POSition/coordinate of clipped sequence
585 5 MAPQ MAPping Quality (Phred-scaled)
586 6 CIGAR extended CIGAR string
587 7 MRNM Mate Reference sequence NaMe ('=' if same as RNAME)
588 8 MPOS 1-based Mate POSition
589 9 ISIZE Inferred insert SIZE
590 10 SEQ query SEQuence on the same strand as the reference
591 11 QUAL query QUALity (ASCII-33 gives the Phred base quality)
592 12 OPT variable OPTional fields in the format TAG:VTYPE:VALUE
593
594 The flags are as follows::
595
596 Flag Description
597 ------ -------------------------------------
598 0x0001 the read is paired in sequencing
599 0x0002 the read is mapped in a proper pair
600 0x0004 the query sequence itself is unmapped
601 0x0008 the mate is unmapped
602 0x0010 strand of the query (1 for reverse)
603 0x0020 strand of the mate
604 0x0040 the read is the first read in a pair
605 0x0080 the read is the second read in a pair
606 0x0100 the alignment is not primary
607
608 It looks like this (scroll sideways to see the entire example)::
609
610 QNAME FLAG RNAME POS MAPQ CIAGR MRNM MPOS ISIZE SEQ QUAL OPT
611 HWI-EAS91_1_30788AAXX:1:1:1761:343 4 * 0 0 * * 0 0 AAAAAAANNAAAAAAAAAAAAAAAAAAAAAAAAAAACNNANNGAGTNGNNNNNNNGCTTCCCACAGNNCTGG hhhhhhh;;hhhhhhhhhhh^hOhhhhghhhfhhhgh;;h;;hhhh;h;;;;;;;hhhhhhghhhh;;Phhh
612 HWI-EAS91_1_30788AAXX:1:1:1578:331 4 * 0 0 * * 0 0 GTATAGANNAATAAGAAAAAAAAAAATGAAGACTTTCNNANNTCTGNANNNNNNNTCTTTTTTCAGNNGTAG hhhhhhh;;hhhhhhhhhhhhhhhhhhhhhhhhhhhh;;h;;hhhh;h;;;;;;;hhhhhhhhhhh;;hhVh
613
614 -------
615
616 **Bowtie settings**
617
618 All of the options have a default value. You can change any of them. Most of the options in Bowtie have been implemented here.
619
620 ------
621
622 **Bowtie parameter list**
623
624 This is an exhaustive list of Bowtie options:
625
626 For indexing (bowtie-build)::
627
628 -a No auto behavior. Disable the default behavior where bowtie automatically
629 selects values for --bmax/--bmaxdivn/--dcv/--packed parameters according
630 to the memory available. [off]
631 --packed Packing. Use a packed representation for DNA strings. [auto]
632 --bmax INT Suffix maximum. The maximum number of suffixes allowed in a block. [auto]
633 --bmaxdivn INT Suffix maximum fraction. The maximum number of suffixes allowed in a block
634 expressed as a fraction of the length of the reference. [4]
635 --dcv INT Difference-cover sample. Use INT as the period for the difference-cover
636 sample. [1024]
637 --nodc INT No difference-cover sample. Disable the difference-cover sample. [off]
638 -r No reference indexes. Do not build the NAME.3.ebwt and NAME.4.ebwt portions
639 of the index. Used only for paired-end alignment. [off]
640 -o Offrate. How many Burrows-Wheeler rows get marked by the indexer. The
641 indexer will mark every 2^INT rows. The marked rows correspond to rows on
642 the genome. [5]
643 -t INT Ftab. The lookup table used to calculate an initial Burrows-Wheeler range
644 with respect to the first INT characters of the query. Ftab is 4^INT+1
645 bytes. [10]
646 --ntoa N conversion. Convert Ns to As before building the index. Otherwise, Ns are
647 simply excluded from the index and Bowtie will not find alignments that
648 overlap them. [off]
649 --big Endianness. Endianness to use when serializing integers to the index file. [off]
650 --little Endianness. [--little]
651 --seed INT Random seed. Use INT as the seed for the pseudo-random number generator. [off]
652 --cutoff INT Cutoff. Index only the first INT bases of the reference sequences (cumulative
653 across sequences) and ignore the rest. [off]
654
655 For aligning (bowtie)::
656
657 -s INT Skip. Do not align the first INT reads or pairs in the input. [off]
658 -u INT Align limit. Only align the first INT reads/pairs from the input. [no limit]
659 -5 INT High-quality trim. Trim INT bases from the high-quality (left) end of each
660 read before alignment. [0]
661 -3 INT Low-quality trim. Trim INT bases from the low-quality (right) end of each
662 read before alignment. [0]
663 -n INT Mismatch seed. Maximum number of mismatches permitted in the seed (defined
664 with seed length option). Can be 0, 1, 2, or 3. [2]
665 -e INT Mismatch quality. Maximum permitted total of quality values at mismatched
666 read positions. Bowtie rounds quality values to the nearest 10 and saturates
667 at 30. [70]
668 -l INT Seed length. The number of bases on the high-quality end of the read to
669 which the -n ceiling applies. Must be at least 5. [28]
670 --nomaqround Suppress MAQ rounding. Values are internally rounded to the nearest 10 and
671 saturate at 30. This options turns off that rounding. [off]
672 -v INT MAQ- or SOAP-like alignment policy. This option turns off the default
673 MAQ-like alignment policy in favor of a SOAP-like one. End-to-end alignments
674 with at most INT mismatches. [off]
675 -I INT Minimum insert. The minimum insert size for valid paired-end alignments.
676 Does checking on untrimmed reads if -5 or -3 is used. [0]
677 -X INT Maximum insert. The maximum insert size for valid paired-end alignments.
678 Does checking on untrimmed reads if -5 or -3 is used. [250]
679 --fr Mate orientation. The upstream/downstream mate orientations for a valid
680 paired-end alignment against the forward reference strand. [--fr]
681 --rf Mate orientation. [off]
682 --ff Mate orientation. [off]
683 --pairtries INT Maximum alignment attempts for paired-end data. [100]
684 --nofw No forward aligning. Choosing this option means that Bowtie will not attempt
685 to align against the forward reference strand. [off]
686 --norc No reverse-complement aligning. Setting this will mean that Bowtie will not
687 attempt to align against the reverse-complement reference strand. [off]
688 --maxbts INT Maximum backtracks. The maximum number of backtracks permitted when aligning
689 a read in -n 2 or -n 3 mode. [125 without --best] [800 with --best]
690 -y Try hard. Try as hard as possible to find valid alignments when they exist,
691 including paired-end alignments. [off]
692 --chunkmbs INT Thread memory. The number of megabytes of memory a given thread is given to
693 store path descriptors in --best mode. [32]
694 -k INT Valid alignments. The number of valid alignments per read or pair. [off]
695 -a All valid alignments. Choosing this means that all valid alignments per read
696 or pair will be reported. [off]
697 -m INT Suppress alignments. Suppress all alignments for a particular read or pair
698 if more than INT reportable alignments exist for it. [no limit]
699 --best Best mode. Make Bowtie guarantee that reported singleton alignments are
700 "best" in terms of stratum (the number of mismatches) and quality values at
701 mismatched position. [off]
702 --strata Best strata. When running in best mode, report alignments that fall into the
703 best stratum if there are ones falling into more than one. [off]
704 -o INT Offrate override. Override the offrate of the index with INT. Some row
705 markings are discarded when index read into memory. INT must be greater than
706 the value used to build the index (default: 5). [off]
707 --seed INT Random seed. Use INT as the seed for the pseudo-random number generator. [off]
708 --snpphred INT Use INT as the SNP penalty for decoding colorspace alignments. True ratio of
709 SNPs per base in the subject genome. [see --snpfrac]
710 --snpfrac DEC Use DEC as the estimated ratio of SNPs per base when decoding colorspace
711 alignments. [0.001]
712 --col-keepends Keep the extreme-end nucleotides and qualities when decoding colorspace
713 alignments. [off]
714
715 </help>
716 </tool>