Mercurial > repos > jjohnson > gatk2

comparison variant_select.xml @ 0:74c05070a3f8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jjohnson
date Thu, 01 Nov 2012 13:53:22 -0400
parents
children 7533db8dfb5b
comparison
equal deleted inserted replaced
-1:000000000000 0:74c05070a3f8
1 <tool id="gatk2_variant_select" name="Select Variants" version="0.0.4">
2 <description>from VCF files</description>
3 <requirements>
4 <requirement type="package" version="2.2">gatk</requirement>
5 </requirements>
6 <command interpreter="python">gatk2_wrapper.py
7 #from binascii import hexlify
8 --max_jvm_heap_fraction "1"
9 --stdout "${output_log}"
10 -d "--variant:variant,%(file_type)s" "${reference_source.input_variant}" "${reference_source.input_variant.ext}" "input_variant"
11 -p 'java
12 -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
13 -T "SelectVariants"
14 \$GATK2_SITE_OPTIONS
15 ##--num_threads 4 ##hard coded, for now
16 ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
17 -o "${output_vcf}"
18
19 #if $reference_source.reference_source_selector != "history":
20 -R "${reference_source.ref_file.fields.path}"
21 #end if
22 '
23 -p '
24 #if $input_concordance:
25 --concordance "${input_concordance}"
26 #end if
27 #if $input_discordance:
28 --discordance "${input_discordance}"
29 #end if
30
31 #for $exclude_sample_name in $exclude_sample_name_repeat:
32 --exclude_sample_name "${exclude_sample_name.exclude_sample_name}"
33 #end for
34
35 ${exclude_filtered}
36
37 #for $sample_name in $sample_name_repeat:
38 --sample_name "${sample_name.sample_name}"
39 #end for
40
41 '
42
43 #for $select_expressions in $select_expressions_repeat:
44 #set $select_expression = "--select_expressions '%s'" % ( str( $select_expressions.select_expressions ) )
45 -o '${ hexlify( $select_expression ) }'
46 #end for
47
48 ##start tool specific options
49 #if str( $analysis_param_type.analysis_param_type_selector ) == 'advanced':
50 -p '
51 #for $exclude_sample_file in $analysis_param_type.exclude_sample_file_repeat:
52 --exclude_sample_file "${exclude_sample_file.exclude_sample_file}"
53 #end for
54
55 #for $sample_file in $analysis_param_type.sample_file_repeat:
56 --sample_file "${ample_file.sample_file}"
57 #end for
58
59 #if $analysis_param_type.input_keep_ids:
60 --keepIDs "${analysis_param_type.input_keep_ids}"
61 #end if
62
63 ${analysis_param_type.keep_original_AC}
64
65 ${analysis_param_type.mendelian_violation}
66
67 --mendelianViolationQualThreshold "${analysis_param_type.mendelian_violation_qual_threshold}"
68
69 --remove_fraction_genotypes "${analysis_param_type.remove_fraction_genotypes}"
70
71 --restrictAllelesTo "${analysis_param_type.restrict_alleles_to}"
72
73 #if str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_fraction':
74 --select_random_fraction "${analysis_param_type.select_random_type.select_random_fraction}"
75 #elif str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_number':
76 --select_random_number "${analysis_param_type.select_random_type.select_random_number}"
77 #end if
78
79 #if $analysis_param_type.select_type_to_include:
80 #for $type_to_include in str( $analysis_param_type.select_type_to_include ).split( ',' ):
81 --selectTypeToInclude "${type_to_include}"
82 #end for
83 #end if
84
85 ${analysis_param_type.exclude_non_variants}
86 '
87
88 #for $sample_expressions in $analysis_param_type.sample_expressions_repeat:
89 #set $sample_expression = "--sample_expressions '%s'" % ( str( $sample_expressions.sample_expressions ) )
90 -o '${ hexlify( $sample_expression ) }'
91 #end for
92
93 #end if
94 ##end tool specific options
95
96 ##start standard gatk options
97 #if $gatk_param_type.gatk_param_type_selector == "advanced":
98 #for $pedigree in $gatk_param_type.pedigree:
99 -p '--pedigree "${pedigree.pedigree_file}"'
100 #end for
101 #for $pedigree_string in $gatk_param_type.pedigree_string_repeat:
102 -p '--pedigreeString "${pedigree_string.pedigree_string}"'
103 #end for
104 -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"'
105 #for $read_filter in $gatk_param_type.read_filter:
106 -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}"
107 ###raise Exception( str( dir( $read_filter ) ) )
108 #for $name, $param in $read_filter.read_filter_type.iteritems():
109 #if $name not in [ "__current_case__", "read_filter_type_selector" ]:
110 #if hasattr( $param.input, 'truevalue' ):
111 ${param}
112 #else:
113 --${name} "${param}"
114 #end if
115 #end if
116 #end for
117 '
118 #end for
119 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ):
120 -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}"
121 #end for
122
123 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ):
124 -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}"
125 #end for
126
127 -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"'
128
129 -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"'
130 #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE":
131 -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"'
132 #end if
133 -p '
134 --baq "${gatk_param_type.baq}"
135 --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}"
136 ${gatk_param_type.use_original_qualities}
137 --defaultBaseQualities "${gatk_param_type.default_base_qualities}"
138 --validation_strictness "${gatk_param_type.validation_strictness}"
139 --interval_merging "${gatk_param_type.interval_merging}"
140 ${gatk_param_type.disable_experimental_low_memory_sharding}
141 ${gatk_param_type.non_deterministic_random_seed}
142 '
143 #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ):
144 #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file":
145 -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}"
146 #else
147 -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"'
148 #end if
149 #end for
150 #end if
151
152 #if str( $reference_source.reference_source_selector ) == "history":
153 -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
154 #end if
155 ##end standard gatk options
156
157
158 </command>
159 <inputs>
160 <conditional name="reference_source">
161 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
162 <option value="cached">Locally cached</option>
163 <option value="history">History</option>
164 </param>
165 <when value="cached">
166 <param name="input_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &amp;lt;variant&amp;gt;" />
167 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
168 <options from_data_table="gatk2_picard_indexes">
169 <filter type="data_meta" key="dbkey" ref="input_variant" column="dbkey"/>
170 </options>
171 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
172 </param>
173 </when>
174 <when value="history"> <!-- FIX ME!!!! -->
175 <param name="input_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &amp;lt;variant&amp;gt;" />
176 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
177 </when>
178 </conditional>
179
180 <repeat name="select_expressions_repeat" title="Criteria to use when selecting the data" help="-select,--select_expressions &amp;lt;select_expressions&amp;gt;">
181 <param name="select_expressions" type="text" label="JEXL expression">
182 <sanitizer>
183 <valid initial="string.printable">
184 <remove value="&apos;"/>
185 </valid>
186 <mapping initial="none"/>
187 </sanitizer>
188 </param>
189 </repeat>
190
191 <param name="input_concordance" type="data" format="vcf" label="Output variants that were also called in this comparison track" optional="True" help="-conc,--concordance &amp;lt;concordance&amp;gt;"/>
192 <param name="input_discordance" type="data" format="vcf" label="Output variants that were not called in this comparison track" optional="True" help="-disc,--discordance &amp;lt;discordance&amp;gt;"/>
193
194 <repeat name="sample_name_repeat" title="Include Samples by name" help="-sn,--sample_name &amp;lt;sample_name&amp;gt;">
195 <param name="sample_name" type="text" label="Include genotypes from this sample"/>
196 </repeat>
197
198 <repeat name="exclude_sample_name_repeat" title="Exclude Samples by name" help="-xl_sn,--exclude_sample_name &amp;lt;exclude_sample_name&amp;gt;">
199 <param name="exclude_sample_name" type="text" label="Exclude genotypes from this sample"/>
200 </repeat>
201
202 <param name="exclude_filtered" type="boolean" truevalue="--excludeFiltered" falsevalue="" label="Don't include filtered loci in the analysis" help="-ef,--excludeFiltered" />
203
204 <conditional name="gatk_param_type">
205 <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options">
206 <option value="basic" selected="True">Basic</option>
207 <option value="advanced">Advanced</option>
208 </param>
209 <when value="basic">
210 <!-- Do nothing here -->
211 </when>
212 <when value="advanced">
213 <repeat name="pedigree" title="Pedigree file" help="-ped,--pedigree &amp;lt;pedigree&amp;gt;">
214 <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples"/>
215 </repeat>
216 <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &amp;lt;pedigreeString&amp;gt;">
217 <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/>
218 </repeat>
219 <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information" help="-pedValidationType,--pedigreeValidationType &amp;lt;pedigreeValidationType&amp;gt;">
220 <option value="STRICT" selected="True">STRICT</option>
221 <option value="SILENT">SILENT</option>
222 </param>
223 <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &amp;lt;read_filter&amp;gt;">
224 <conditional name="read_filter_type">
225 <param name="read_filter_type_selector" type="select" label="Read Filter Type">
226 <option value="BadCigar">BadCigar</option>
227 <option value="BadMate">BadMate</option>
228 <option value="DuplicateRead">DuplicateRead</option>
229 <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option>
230 <option value="MalformedRead">MalformedRead</option>
231 <option value="MappingQuality">MappingQuality</option>
232 <option value="MappingQualityUnavailable">MappingQualityUnavailable</option>
233 <option value="MappingQualityZero">MappingQualityZero</option>
234 <option value="MateSameStrand">MateSameStrand</option>
235 <option value="MaxInsertSize">MaxInsertSize</option>
236 <option value="MaxReadLength" selected="True">MaxReadLength</option>
237 <option value="MissingReadGroup">MissingReadGroup</option>
238 <option value="NoOriginalQualityScores">NoOriginalQualityScores</option>
239 <option value="NotPrimaryAlignment">NotPrimaryAlignment</option>
240 <option value="Platform454">Platform454</option>
241 <option value="Platform">Platform</option>
242 <option value="PlatformUnit">PlatformUnit</option>
243 <option value="ReadGroupBlackList">ReadGroupBlackList</option>
244 <option value="ReadName">ReadName</option>
245 <option value="ReadStrand">ReadStrand</option>
246 <option value="ReassignMappingQuality">ReassignMappingQuality</option>
247 <option value="Sample">Sample</option>
248 <option value="SingleReadGroup">SingleReadGroup</option>
249 <option value="UnmappedRead">UnmappedRead</option>
250 </param>
251 <when value="BadCigar">
252 <!-- no extra options -->
253 </when>
254 <when value="BadMate">
255 <!-- no extra options -->
256 </when>
257 <when value="DuplicateRead">
258 <!-- no extra options -->
259 </when>
260 <when value="FailsVendorQualityCheck">
261 <!-- no extra options -->
262 </when>
263 <when value="MalformedRead">
264 <!-- no extra options -->
265 </when>
266 <when value="MappingQuality">
267 <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/>
268 </when>
269 <when value="MappingQualityUnavailable">
270 <!-- no extra options -->
271 </when>
272 <when value="MappingQualityZero">
273 <!-- no extra options -->
274 </when>
275 <when value="MateSameStrand">
276 <!-- no extra options -->
277 </when>
278 <when value="MaxInsertSize">
279 <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/>
280 </when>
281 <when value="MaxReadLength">
282 <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/>
283 </when>
284 <when value="MissingReadGroup">
285 <!-- no extra options -->
286 </when>
287 <when value="NoOriginalQualityScores">
288 <!-- no extra options -->
289 </when>
290 <when value="NotPrimaryAlignment">
291 <!-- no extra options -->
292 </when>
293 <when value="Platform454">
294 <!-- no extra options -->
295 </when>
296 <when value="Platform">
297 <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/>
298 </when>
299 <when value="PlatformUnit">
300 <!-- no extra options -->
301 </when>
302 <when value="ReadGroupBlackList">
303 <!-- no extra options -->
304 </when>
305 <when value="ReadName">
306 <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/>
307 </when>
308 <when value="ReadStrand">
309 <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/>
310 </when>
311 <when value="ReassignMappingQuality">
312 <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/>
313 </when>
314 <when value="Sample">
315 <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/>
316 </when>
317 <when value="SingleReadGroup">
318 <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/>
319 </when>
320 <when value="UnmappedRead">
321 <!-- no extra options -->
322 </when>
323 </conditional>
324 </repeat>
325 <repeat name="input_interval_repeat" title="Operate on Genomic intervals" help="-L,--intervals &amp;lt;intervals&amp;gt;">
326 <param name="input_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
327 </repeat>
328 <repeat name="input_exclude_interval_repeat" title="Exclude Genomic intervals" help="-XL,--excludeIntervals &amp;lt;excludeIntervals&amp;gt;">
329 <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
330 </repeat>
331
332 <param name="interval_set_rule" type="select" label="Interval set rule" help="-isr,--interval_set_rule &amp;lt;interval_set_rule&amp;gt;">
333 <option value="UNION" selected="True">UNION</option>
334 <option value="INTERSECTION">INTERSECTION</option>
335 </param>
336
337 <conditional name="downsampling_type">
338 <param name="downsampling_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="-dt,--downsampling_type &amp;lt;downsampling_type&amp;gt;">
339 <option value="NONE" selected="True">NONE</option>
340 <option value="ALL_READS">ALL_READS</option>
341 <option value="BY_SAMPLE">BY_SAMPLE</option>
342 </param>
343 <when value="NONE">
344 <!-- no more options here -->
345 </when>
346 <when value="ALL_READS">
347 <conditional name="downsample_to_type">
348 <param name="downsample_to_type_selector" type="select" label="Downsample method">
349 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
350 <option value="downsample_to_coverage">Downsample by Coverage</option>
351 </param>
352 <when value="downsample_to_fraction">
353 <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &amp;lt;downsample_to_fraction&amp;gt;"/>
354 </when>
355 <when value="downsample_to_coverage">
356 <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &amp;lt;downsample_to_coverage&amp;gt;"/>
357 </when>
358 </conditional>
359 </when>
360 <when value="BY_SAMPLE">
361 <conditional name="downsample_to_type">
362 <param name="downsample_to_type_selector" type="select" label="Downsample method">
363 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
364 <option value="downsample_to_coverage">Downsample by Coverage</option>
365 </param>
366 <when value="downsample_to_fraction">
367 <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &amp;lt;downsample_to_fraction&amp;gt;"/>
368 </when>
369 <when value="downsample_to_coverage">
370 <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &amp;lt;downsample_to_coverage&amp;gt;"/>
371 </when>
372 </conditional>
373 </when>
374 </conditional>
375 <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine" help="-baq,--baq &amp;lt;baq&amp;gt;">
376 <option value="OFF" selected="True">OFF</option>
377 <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option>
378 <option value="RECALCULATE">RECALCULATE</option>
379 </param>
380 <param name="baq_gap_open_penalty" type="float" label="BAQ gap open penalty (Phred Scaled)" value="40" help="Default value is 40. 30 is perhaps better for whole genome call sets. -baqGOP,--baqGapOpenPenalty &amp;lt;baqGapOpenPenalty&amp;gt;" />
381 <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" help="-OQ,--useOriginalQualities" />
382 <param name="default_base_qualities" type="integer" label="Value to be used for all base quality scores, when some are missing" value="-1" help="-DBQ,--defaultBaseQualities &amp;lt;defaultBaseQualities&amp;gt;"/>
383 <param name="validation_strictness" type="select" label="How strict should we be with validation" help="-S,--validation_strictness &amp;lt;validation_strictness&amp;gt;">
384 <option value="STRICT" selected="True">STRICT</option>
385 <option value="LENIENT">LENIENT</option>
386 <option value="SILENT">SILENT</option>
387 <!-- <option value="DEFAULT_STRINGENCY">DEFAULT_STRINGENCY</option> listed in docs, but not valid value...-->
388 </param>
389 <param name="interval_merging" type="select" label="Interval merging rule" help="-im,--interval_merging &amp;lt;interval_merging&amp;gt;">
390 <option value="ALL" selected="True">ALL</option>
391 <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option>
392 </param>
393
394 <repeat name="read_group_black_list_repeat" title="Read group black list" help="-rgbl,--read_group_black_list &amp;lt;read_group_black_list&amp;gt;">
395 <conditional name="read_group_black_list_type">
396 <param name="read_group_black_list_type_selector" type="select" label="Type of reads read group black list">
397 <option value="file" selected="True">Filters in file</option>
398 <option value="text">Specify filters as a string</option>
399 </param>
400 <when value="file">
401 <param name="read_group_black_list" type="data" format="txt" label="Read group black list file" />
402 </when>
403 <when value="text">
404 <param name="read_group_black_list" type="text" value="tag:string" label="Read group black list tag:string" />
405 </when>
406 </conditional>
407 </repeat>
408
409 <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/>
410 <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/>
411
412 </when>
413 </conditional>
414
415
416 <conditional name="analysis_param_type">
417 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
418 <option value="basic" selected="True">Basic</option>
419 <option value="advanced">Advanced</option>
420 </param>
421 <when value="basic">
422 <!-- Do nothing here -->
423 </when>
424 <when value="advanced">
425
426 <repeat name="exclude_sample_file_repeat" title="Exclude Samples by file" help="-xl_sf,--exclude_sample_file &amp;lt;exclude_sample_file&amp;gt;">
427 <param name="exclude_sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to exclude"/>
428 </repeat>
429
430 <repeat name="sample_file_repeat" title="Samples by file" help="-sf,--sample_file &amp;lt;sample_file&amp;gt;">
431 <param name="sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to include" />
432 </repeat>
433
434 <param name="input_keep_ids" type="data" format="text" label="Only emit sites whose ID is found in this file" optional="True" help="-IDs,--keepIDs &amp;lt;keepIDs&amp;gt;"/>
435
436 <param name="keep_original_AC" type="boolean" truevalue="--keepOriginalAC" falsevalue="" label="Don't update the AC, AF, or AN values in the INFO field after selecting" help="-keepOriginalAC,--keepOriginalAC" />
437
438 <param name="mendelian_violation" type="boolean" truevalue="--mendelianViolation" falsevalue="" label="output mendelian violation sites only" help="-mv,--mendelianViolation" />
439
440 <param name="mendelian_violation_qual_threshold" type="float" label="Minimum genotype QUAL score for each trio member required to accept a site as a mendelian violation" value="0" help="-mvq,--mendelianViolationQualThreshold &amp;lt;mendelianViolationQualThreshold&amp;gt;" />
441
442 <param name="remove_fraction_genotypes" type="float" label="Selects a fraction (a number between 0 and 1) of the total genotypes at random from the variant track and sets them to nocall" value="0" min="0" max="1" help="-fractionGenotypes,--remove_fraction_genotypes &amp;lt;remove_fraction_genotypes&amp;gt;" />
443
444 <param name="restrict_alleles_to" type="select" label="Select only variants of a particular allelicity" help="-restrictAllelesTo,--restrictAllelesTo &amp;lt;restrictAllelesTo&amp;gt;">
445 <option value="ALL" selected="True">ALL</option>
446 <option value="MULTIALLELIC">MULTIALLELIC</option>
447 <option value="BIALLELIC">BIALLELIC</option>
448 </param>
449
450 <repeat name="sample_expressions_repeat" title="Regular expression to select many samples from the ROD tracks provided" help="-se,--sample_expressions &amp;lt;sample_expressions&amp;gt;">
451 <param name="sample_expressions" type="text" label="Regular expression">
452 <sanitizer>
453 <valid initial="string.printable">
454 <remove value="&apos;"/>
455 </valid>
456 <mapping initial="none"/>
457 </sanitizer>
458 </param>
459 </repeat>
460
461 <conditional name="select_random_type">
462 <param name="select_random_type_selector" type="select" label="Select a random subset of variants">
463 <option value="select_all" selected="True">Use all variants</option>
464 <option value="select_random_fraction">Select random fraction</option>
465 <option value="select_random_number">Select random number</option>
466 </param>
467 <when value="select_all">
468 <!-- Do nothing here -->
469 </when>
470 <when value="select_random_fraction">
471 <param name="select_random_fraction" type="float" value="0" label="Fraction" min="0" max="1" help="-fraction,--select_random_fraction &amp;lt;select_random_fraction&amp;gt;"/>
472 </when>
473 <when value="select_random_number">
474 <param name="select_random_number" type="integer" value="0" label="Count" help="-number,--select_random_number &amp;lt;select_random_number&amp;gt;" />
475 </when>
476 </conditional>
477
478 <param name="exclude_non_variants" type="boolean" truevalue="--excludeNonVariants" falsevalue="" label="Don't include loci found to be non-variant after the subsetting procedure" help="-env,--excludeNonVariants" />
479
480 <param name="select_type_to_include" type="select" label="Select only a certain type of variants from the input file" multiple="True" display="checkboxes" help="-selectType,--selectTypeToInclude &amp;lt;selectTypeToInclude&amp;gt;">
481 <option value="INDEL">INDEL</option>
482 <option value="SNP">SNP</option>
483 <option value="MIXED">MIXED</option>
484 <option value="MNP">MNP</option>
485 <option value="SYMBOLIC">SYMBOLIC</option>
486 <option value="NO_VARIATION">NO_VARIATION</option>
487 </param>
488
489 </when>
490 </conditional>
491
492 </inputs>
493 <outputs>
494 <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (Variant File)" />
495 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
496 </outputs>
497 <tests>
498 <test>
499 <param name="reference_source_selector" value="history" />
500 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
501 <param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" />
502 <param name="select_expressions_repeat" value="0" />
503 <param name="input_concordance" />
504 <param name="input_discordance" />
505 <param name="exclude_sample_name_repeat" value="0" />
506 <param name="exclude_filtered" />
507 <param name="sample_name_repeat" value="0" />
508 <param name="gatk_param_type_selector" value="basic" />
509 <param name="analysis_param_type_selector" value="basic" />
510 <output name="output_vcf" file="gatk/gatk_variant_select/gatk_variant_select_out_1.vcf" lines_diff="4" />
511 <output name="output_log" file="gatk/gatk_variant_select/gatk_variant_select_out_1.log.contains" compare="contains" />
512 </test>
513 </tests>
514 <help>
515 **What it does**
516
517 Often, a VCF containing many samples and/or variants will need to be subset in order to facilitate certain analyses (e.g. comparing and contrasting cases vs. controls; extracting variant or non-variant loci that meet certain requirements, displaying just a few samples in a browser like IGV, etc.). SelectVariants can be used for this purpose. Given a single VCF file, one or more samples can be extracted from the file (based on a complete sample name or a pattern match). Variants can be further selected by specifying criteria for inclusion, i.e. "DP &gt; 1000" (depth of coverage greater than 1000x), "AF &lt; 0.25" (sites with allele frequency less than 0.25). These JEXL expressions are documented in the `Using JEXL expressions section &lt;http://gatkforums.broadinstitute.org/discussion/1255/what-are-jexl-expressions-and-how-can-i-use-them-with-the-gatk&gt;`_. One can optionally include concordance or discordance tracks for use in selecting overlapping variants.
518
519 For more information on using the SelectVariants module, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_variantutils_SelectVariants.html&gt;`_.
520
521 To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gatk/guide/topic?name=best-practices&gt;`_.
522
523 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
524
525 ------
526
527 **Inputs**
528
529 GenomeAnalysisTK: SelectVariants accepts a VCF input file.
530
531
532 **Outputs**
533
534 The output is in VCF format.
535
536
537 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
538
539 -------
540
541 **Settings**::
542
543
544 out VCFWriter stdout File to which variants should be written
545 variant RodBinding[VariantContext] NA Input VCF file
546 concordance RodBinding[VariantContext] none Output variants that were also called in this comparison track
547 discordance RodBinding[VariantContext] none Output variants that were not called in this comparison track
548 exclude_sample_file Set[File] [] File containing a list of samples (one per line) to exclude. Can be specified multiple times
549 exclude_sample_name Set[String] [] Exclude genotypes from this sample. Can be specified multiple times
550 excludeFiltered boolean false Don't include filtered loci in the analysis
551 excludeNonVariants boolean false Don't include loci found to be non-variant after the subsetting procedure
552 keepIDs File NA Only emit sites whose ID is found in this file (one ID per line)
553 keepOriginalAC boolean false Don't update the AC, AF, or AN values in the INFO field after selecting
554 mendelianViolation Boolean false output mendelian violation sites only
555 mvq double 0.0 Minimum genotype QUAL score for each trio member required to accept a site as a violation
556 remove_fraction_genotypes double 0.0 Selects a fraction (a number between 0 and 1) of the total genotypes at random from the variant track and sets them to nocall
557 restrictAllelesTo NumberAlleleRestriction ALL Select only variants of a particular allelicity. Valid options are ALL (default), MULTIALLELIC or BIALLELIC
558 sample_expressions Set[String] NA Regular expression to select many samples from the ROD tracks provided. Can be specified multiple times
559 sample_file Set[File] NA File containing a list of samples (one per line) to include. Can be specified multiple times
560 sample_name Set[String] [] Include genotypes from this sample. Can be specified multiple times
561 select_expressions ArrayList[String] [] One or more criteria to use when selecting the data
562 select_random_fraction double 0.0 Selects a fraction (a number between 0 and 1) of the total variants at random from the variant track
563 select_random_number int 0 Selects a number of variants at random from the variant track
564 selectTypeToInclude List[Type] [] Select only a certain type of variants from the input file. Valid types are INDEL, SNP, MIXED, MNP, SYMBOLIC, NO_VARIATION. Can be specified multiple times
565
566 ------
567
568 **Citation**
569
570 For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_
571
572 Please also site `McKenna A, Hanna M, Banks E, Sivachenko A, Cibulskis K, Kernytsky A, Garimella K, Altshuler D, Gabriel S, Daly M, DePristo MA (2010). The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data. Genome Res. 20:1297-303. Epub 2010 Jul 19. &lt;http://www.ncbi.nlm.nih.gov/pubmed/20644199&gt;`_
573
574 If you use this tool in Galaxy, please cite `Blankenberg D, Von Kuster G, Coraor N, Ananda G, Lazarus R, Mangan M, Nekrutenko A, Taylor J. Galaxy: a web-based genome analysis tool for experimentalists. Curr Protoc Mol Biol. 2010 Jan;Chapter 19:Unit 19.10.1-21. &lt;http://www.ncbi.nlm.nih.gov/pubmed/20069535&gt;`_
575
576 </help>
577 </tool>