Mercurial > repos > jjohnson > gatk2

comparison variant_eval.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_eval" name="Eval Variants" version="0.0.4">
2 <description></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 #for $var_count, $variant in enumerate( $reference_source.variants ):
11 -d "--eval:input_${var_count},%(file_type)s" "${variant.input_variant}" "${variant.input_variant.ext}" "input_variants_${var_count}"
12 #end for
13 -p 'java
14 -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
15 -T "VariantEval"
16 --out "${output_report}"
17 \$GATK2_SITE_OPTIONS
18 ##--num_threads 4 ##hard coded, for now
19 ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
20 ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
21 #if $reference_source.reference_source_selector != "history":
22 -R "${reference_source.ref_file.fields.path}"
23 #end if
24 '
25
26 #for $rod_binding in $comp_rod_bind:
27 -d "--comp:${rod_binding.comp_rod_name},%(file_type)s" "${rod_binding.comp_input_rod}" "${rod_binding.comp_input_rod.ext}" "input_comp_${rod_binding.comp_rod_name}"
28 #if str( $rod_binding.comp_known_names ):
29 -p '--known_names "${rod_binding.comp_rod_name}"'
30 #end if
31 #end for
32
33 #if str( $dbsnp_rod_bind_type.dbsnp_rod_bind_type_selector ) == 'set_dbsnp':
34 -d "--dbsnp:${dbsnp_rod_bind_type.dbsnp_rod_name},%(file_type)s" "${dbsnp_rod_bind_type.dbsnp_input_rod}" "${dbsnp_rod_bind_type.dbsnp_input_rod.ext}" "input_dbsnp_${dbsnp_rod_bind_type.dbsnp_rod_name}"
35 #if str( $dbsnp_rod_bind_type.dbsnp_known_names ):
36 -p '--known_names "${dbsnp_rod_bind_type.dbsnp_rod_name}"'
37 #end if
38 #end if
39
40 ##start standard gatk options
41 #if $gatk_param_type.gatk_param_type_selector == "advanced":
42 #for $pedigree in $gatk_param_type.pedigree:
43 -p '--pedigree "${pedigree.pedigree_file}"'
44 #end for
45 #for $pedigree_string in $gatk_param_type.pedigree_string_repeat:
46 -p '--pedigreeString "${pedigree_string.pedigree_string}"'
47 #end for
48 -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"'
49 #for $read_filter in $gatk_param_type.read_filter:
50 -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}"
51 ###raise Exception( str( dir( $read_filter ) ) )
52 #for $name, $param in $read_filter.read_filter_type.iteritems():
53 #if $name not in [ "__current_case__", "read_filter_type_selector" ]:
54 #if hasattr( $param.input, 'truevalue' ):
55 ${param}
56 #else:
57 --${name} "${param}"
58 #end if
59 #end if
60 #end for
61 '
62 #end for
63 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ):
64 -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}"
65 #end for
66
67 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ):
68 -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}"
69 #end for
70
71 -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"'
72
73 -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"'
74 #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE":
75 -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"'
76 #end if
77 -p '
78 --baq "${gatk_param_type.baq}"
79 --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}"
80 ${gatk_param_type.use_original_qualities}
81 --defaultBaseQualities "${gatk_param_type.default_base_qualities}"
82 --validation_strictness "${gatk_param_type.validation_strictness}"
83 --interval_merging "${gatk_param_type.interval_merging}"
84 ${gatk_param_type.disable_experimental_low_memory_sharding}
85 ${gatk_param_type.non_deterministic_random_seed}
86 '
87 #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ):
88 #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file":
89 -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}"
90 #else
91 -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"'
92 #end if
93 #end for
94 #end if
95
96 #if $reference_source.reference_source_selector == "history":
97 -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
98 #end if
99 ##end standard gatk options
100
101
102 ##start analysis specific options
103 #if $analysis_param_type.analysis_param_type_selector == "advanced":
104 #for $stratification in $analysis_param_type.stratifications:
105 #set $select_string = "--select_exps '%s' --select_names '%s'" % ( str( $stratification.select_exps ), str( $stratification.select_name ) )
106 -o '${ hexlify( $select_string ) }'
107 #end for
108 -p '
109
110 #for $sample in $analysis_param_type.samples:
111 --sample "${sample.sample}"
112 #end for
113
114 #if str( $analysis_param_type.stratification_modules ) != "None":
115 #for $stratification_module in str( $analysis_param_type.stratification_modules).split( ',' ):
116 --stratificationModule "${stratification_module}"
117 #end for
118 #end if
119
120 ${analysis_param_type.do_not_use_all_standard_stratifications}
121
122 #for $variant_type in $analysis_param_type.only_variants_of_type:
123 --onlyVariantsOfType "${variant_type.variant_type}"
124 #end for
125
126 #if str( $analysis_param_type.eval_modules ) != "None":
127 #for $eval_module in str( $analysis_param_type.eval_modules).split( ',' ):
128 --evalModule "${eval_module}"
129 #end for
130 #end if
131
132 ${analysis_param_type.do_not_use_all_standard_modules}
133
134 #if str( $analysis_param_type.num_samples ) != "0":
135 --numSamples "${analysis_param_type.num_samples}"
136 #end if
137
138 --minPhaseQuality "${analysis_param_type.min_phase_quality}"
139
140 #if str( $analysis_param_type.family ):
141 --family_structure "${analysis_param_type.family}"
142 #end if
143
144 --mendelianViolationQualThreshold "${analysis_param_type.mendelian_violation_qual_threshold}"
145
146 #if str( $analysis_param_type.ancestral_alignments ) != "None":
147 --ancestralAlignments "${analysis_param_type.ancestral_alignments}"
148 #end if
149 '
150 #if str( $analysis_param_type.known_cnvs ) != "None":
151 -d "--knownCNVs" "${analysis_param_type.known_cnvs}" "${analysis_param_type.known_cnvs.ext}" "input_known_cnvs"
152 #end if
153
154 #if str( $analysis_param_type.strat_intervals ) != "None":
155 -d "--stratIntervals" "${analysis_param_type.strat_intervals}" "${analysis_param_type.strat_intervals.ext}" "input_strat_intervals"
156 #end if
157 #end if
158 </command>
159 <inputs>
160
161 <conditional name="reference_source">
162 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
163 <option value="cached">Locally cached</option>
164 <option value="history">History</option>
165 </param>
166 <when value="cached">
167 <repeat name="variants" title="Variant" min="1" help="-eval,--eval &amp;lt;eval&amp;gt;">
168 <param name="input_variant" type="data" format="vcf" label="Input variant file" />
169 </repeat>
170 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
171 <options from_data_table="gatk2_picard_indexes">
172 <!-- <filter type="data_meta" key="dbkey" ref="input_variant" column="dbkey"/> -->
173 </options>
174 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
175 </param>
176 </when>
177 <when value="history"> <!-- FIX ME!!!! -->
178 <repeat name="variants" title="Variant" min="1" help="-eval,--eval &amp;lt;eval&amp;gt;">
179 <param name="input_variant" type="data" format="vcf" label="Input variant file" />
180 </repeat>
181 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
182 </when>
183 </conditional>
184
185 <repeat name="comp_rod_bind" title="Binding for reference-ordered comparison data" help="-comp,--comp &amp;lt;comp&amp;gt;">
186 <param name="comp_input_rod" type="data" format="vcf" label="Comparison ROD file" />
187 <param name="comp_rod_name" type="text" value="Unnamed" label="Comparison ROD Name"/>
188 <param name="comp_known_names" type="boolean" truevalue="--known_names" falsevalue="" label="Use Comparison ROD as known_names" help="-knownName,--known_names &amp;lt;known_names&amp;gt;"/>
189 </repeat>
190
191 <conditional name="dbsnp_rod_bind_type">
192 <param name="dbsnp_rod_bind_type_selector" type="select" label="Provide a dbSNP reference-ordered data file" help="-D,--dbsnp &amp;lt;dbsnp&amp;gt;">
193 <option value="set_dbsnp" selected="True">Set dbSNP</option>
194 <option value="exclude_dbsnp">Don't set dbSNP</option>
195 </param>
196 <when value="exclude_dbsnp">
197 <!-- Do nothing here -->
198 </when>
199 <when value="set_dbsnp">
200 <param name="dbsnp_input_rod" type="data" format="vcf" label="dbSNP ROD file" />
201 <param name="dbsnp_rod_name" type="hidden" value="dbsnp" label="dbSNP ROD Name"/>
202 <param name="dbsnp_known_names" type="boolean" truevalue="--known_names" falsevalue="" label="Use dbSNP ROD as known_names" help="-knownName,--known_names &amp;lt;known_names&amp;gt;" />
203 </when>
204 </conditional>
205
206 <conditional name="gatk_param_type">
207 <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options">
208 <option value="basic" selected="True">Basic</option>
209 <option value="advanced">Advanced</option>
210 </param>
211 <when value="basic">
212 <!-- Do nothing here -->
213 </when>
214 <when value="advanced">
215 <repeat name="pedigree" title="Pedigree file" help="-ped,--pedigree &amp;lt;pedigree&amp;gt;">
216 <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples"/>
217 </repeat>
218 <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &amp;lt;pedigreeString&amp;gt;">
219 <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/>
220 </repeat>
221 <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;">
222 <option value="STRICT" selected="True">STRICT</option>
223 <option value="SILENT">SILENT</option>
224 </param>
225 <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &amp;lt;read_filter&amp;gt;">
226 <conditional name="read_filter_type">
227 <param name="read_filter_type_selector" type="select" label="Read Filter Type">
228 <option value="BadCigar">BadCigar</option>
229 <option value="BadMate">BadMate</option>
230 <option value="DuplicateRead">DuplicateRead</option>
231 <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option>
232 <option value="MalformedRead">MalformedRead</option>
233 <option value="MappingQuality">MappingQuality</option>
234 <option value="MappingQualityUnavailable">MappingQualityUnavailable</option>
235 <option value="MappingQualityZero">MappingQualityZero</option>
236 <option value="MateSameStrand">MateSameStrand</option>
237 <option value="MaxInsertSize">MaxInsertSize</option>
238 <option value="MaxReadLength" selected="True">MaxReadLength</option>
239 <option value="MissingReadGroup">MissingReadGroup</option>
240 <option value="NoOriginalQualityScores">NoOriginalQualityScores</option>
241 <option value="NotPrimaryAlignment">NotPrimaryAlignment</option>
242 <option value="Platform454">Platform454</option>
243 <option value="Platform">Platform</option>
244 <option value="PlatformUnit">PlatformUnit</option>
245 <option value="ReadGroupBlackList">ReadGroupBlackList</option>
246 <option value="ReadName">ReadName</option>
247 <option value="ReadStrand">ReadStrand</option>
248 <option value="ReassignMappingQuality">ReassignMappingQuality</option>
249 <option value="Sample">Sample</option>
250 <option value="SingleReadGroup">SingleReadGroup</option>
251 <option value="UnmappedRead">UnmappedRead</option>
252 </param>
253 <when value="BadCigar">
254 <!-- no extra options -->
255 </when>
256 <when value="BadMate">
257 <!-- no extra options -->
258 </when>
259 <when value="DuplicateRead">
260 <!-- no extra options -->
261 </when>
262 <when value="FailsVendorQualityCheck">
263 <!-- no extra options -->
264 </when>
265 <when value="MalformedRead">
266 <!-- no extra options -->
267 </when>
268 <when value="MappingQuality">
269 <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/>
270 </when>
271 <when value="MappingQualityUnavailable">
272 <!-- no extra options -->
273 </when>
274 <when value="MappingQualityZero">
275 <!-- no extra options -->
276 </when>
277 <when value="MateSameStrand">
278 <!-- no extra options -->
279 </when>
280 <when value="MaxInsertSize">
281 <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/>
282 </when>
283 <when value="MaxReadLength">
284 <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/>
285 </when>
286 <when value="MissingReadGroup">
287 <!-- no extra options -->
288 </when>
289 <when value="NoOriginalQualityScores">
290 <!-- no extra options -->
291 </when>
292 <when value="NotPrimaryAlignment">
293 <!-- no extra options -->
294 </when>
295 <when value="Platform454">
296 <!-- no extra options -->
297 </when>
298 <when value="Platform">
299 <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/>
300 </when>
301 <when value="PlatformUnit">
302 <!-- no extra options -->
303 </when>
304 <when value="ReadGroupBlackList">
305 <!-- no extra options -->
306 </when>
307 <when value="ReadName">
308 <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/>
309 </when>
310 <when value="ReadStrand">
311 <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/>
312 </when>
313 <when value="ReassignMappingQuality">
314 <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/>
315 </when>
316 <when value="Sample">
317 <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/>
318 </when>
319 <when value="SingleReadGroup">
320 <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/>
321 </when>
322 <when value="UnmappedRead">
323 <!-- no extra options -->
324 </when>
325 </conditional>
326 </repeat>
327 <repeat name="input_interval_repeat" title="Operate on Genomic intervals" help="-L,--intervals &amp;lt;intervals&amp;gt;">
328 <param name="input_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
329 </repeat>
330 <repeat name="input_exclude_interval_repeat" title="Exclude Genomic intervals" help="-XL,--excludeIntervals &amp;lt;excludeIntervals&amp;gt;">
331 <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
332 </repeat>
333
334 <param name="interval_set_rule" type="select" label="Interval set rule" help="-isr,--interval_set_rule &amp;lt;interval_set_rule&amp;gt;">
335 <option value="UNION" selected="True">UNION</option>
336 <option value="INTERSECTION">INTERSECTION</option>
337 </param>
338
339 <conditional name="downsampling_type">
340 <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;">
341 <option value="NONE" selected="True">NONE</option>
342 <option value="ALL_READS">ALL_READS</option>
343 <option value="BY_SAMPLE">BY_SAMPLE</option>
344 </param>
345 <when value="NONE">
346 <!-- no more options here -->
347 </when>
348 <when value="ALL_READS">
349 <conditional name="downsample_to_type">
350 <param name="downsample_to_type_selector" type="select" label="Downsample method">
351 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
352 <option value="downsample_to_coverage">Downsample by Coverage</option>
353 </param>
354 <when value="downsample_to_fraction">
355 <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;"/>
356 </when>
357 <when value="downsample_to_coverage">
358 <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;"/>
359 </when>
360 </conditional>
361 </when>
362 <when value="BY_SAMPLE">
363 <conditional name="downsample_to_type">
364 <param name="downsample_to_type_selector" type="select" label="Downsample method">
365 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
366 <option value="downsample_to_coverage">Downsample by Coverage</option>
367 </param>
368 <when value="downsample_to_fraction">
369 <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;"/>
370 </when>
371 <when value="downsample_to_coverage">
372 <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;"/>
373 </when>
374 </conditional>
375 </when>
376 </conditional>
377 <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine" help="-baq,--baq &amp;lt;baq&amp;gt;">
378 <option value="OFF" selected="True">OFF</option>
379 <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option>
380 <option value="RECALCULATE">RECALCULATE</option>
381 </param>
382 <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;" />
383 <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" help="-OQ,--useOriginalQualities" />
384 <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;"/>
385 <param name="validation_strictness" type="select" label="How strict should we be with validation" help="-S,--validation_strictness &amp;lt;validation_strictness&amp;gt;">
386 <option value="STRICT" selected="True">STRICT</option>
387 <option value="LENIENT">LENIENT</option>
388 <option value="SILENT">SILENT</option>
389 <!-- <option value="DEFAULT_STRINGENCY">DEFAULT_STRINGENCY</option> listed in docs, but not valid value...-->
390 </param>
391 <param name="interval_merging" type="select" label="Interval merging rule" help="-im,--interval_merging &amp;lt;interval_merging&amp;gt;">
392 <option value="ALL" selected="True">ALL</option>
393 <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option>
394 </param>
395
396 <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;">
397 <conditional name="read_group_black_list_type">
398 <param name="read_group_black_list_type_selector" type="select" label="Type of reads read group black list">
399 <option value="file" selected="True">Filters in file</option>
400 <option value="text">Specify filters as a string</option>
401 </param>
402 <when value="file">
403 <param name="read_group_black_list" type="data" format="txt" label="Read group black list file" />
404 </when>
405 <when value="text">
406 <param name="read_group_black_list" type="text" value="tag:string" label="Read group black list tag:string" />
407 </when>
408 </conditional>
409 </repeat>
410
411 <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"/>
412 <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"/>
413
414 </when>
415 </conditional>
416
417
418 <conditional name="analysis_param_type">
419 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
420 <option value="basic" selected="True">Basic</option>
421 <option value="advanced">Advanced</option>
422 </param>
423 <when value="basic">
424 <!-- Do nothing here -->
425 </when>
426 <when value="advanced">
427 <repeat name="stratifications" title="Stratification">
428 <param name="select_exps" value="" type="text" label="Stratification Expression" help="-select,--select_exps &amp;lt;select_exps&amp;gt;">
429 <sanitizer>
430 <valid initial="string.printable">
431 <remove value="&apos;"/>
432 </valid>
433 <mapping initial="none"/>
434 </sanitizer>
435 </param>
436 <param name="select_name" value="" type="text" label="Name" help="-selectName,--select_names &amp;lt;select_names&amp;gt;"/>
437 </repeat>
438
439 <repeat name="samples" title="Sample" help="-sn,--sample &amp;lt;sample&amp;gt;">
440 <param name="sample" value="" type="text" label="Derive eval and comp contexts using only these sample genotypes, when genotypes are available in the original context"/>
441 </repeat>
442
443 <param name="stratification_modules" type="select" multiple="True" display="checkboxes" label="Stratification modules to apply to the eval track(s)" help="-ST,--stratificationModule &amp;lt;stratificationModule&amp;gt;" >
444 <!-- do these need individual options also? gatk wiki has little info -->
445 <option value="AlleleFrequency" />
446 <option value="AlleleCount" />
447 <option value="CompRod" />
448 <option value="Contig" />
449 <option value="CpG" />
450 <option value="Degeneracy" />
451 <option value="EvalRod" />
452 <option value="Filter" />
453 <option value="FunctionalClass" />
454 <option value="JexlExpression" />
455 <option value="Sample" />
456 <option value="IntervalStratification" />
457 </param>
458 <param name="do_not_use_all_standard_stratifications" checked="false" type="boolean" truevalue="--doNotUseAllStandardStratifications" falsevalue="" label="Do not use the standard stratification modules by default" help="-noST,--doNotUseAllStandardStratifications" />
459
460 <repeat name="only_variants_of_type" title="only Variants Of Type" help="--onlyVariantsOfType">
461 <param name="variant_type" type="text" value="" label="only variants of these types will be considered during the evaluation"/>
462 </repeat>
463
464 <param name="eval_modules" type="select" multiple="True" display="checkboxes" label="Eval modules to apply to the eval track(s)" help="-EV,--evalModule &amp;lt;evalModule&amp;gt;" >
465 <!-- do these need individual options also? gatk wiki has little info -->
466 <option value="ACTransitionTable" />
467 <option value="AlleleFrequencyComparison" />
468 <option value="AminoAcidTransition" />
469 <option value="CompOverlap" />
470 <option value="CountVariants" />
471 <option value="GenotypeConcordance" />
472 <option value="GenotypePhasingEvaluator" />
473 <option value="IndelMetricsByAC" />
474 <option value="IndelStatistics" />
475 <option value="MendelianViolationEvaluator" />
476 <option value="PrintMissingComp" />
477 <option value="PrivatePermutations" />
478 <option value="SimpleMetricsByAC" />
479 <option value="ThetaVariantEvaluator" />
480 <option value="TiTvVariantEvaluator" />
481 <option value="VariantQualityScore" />
482 </param>
483 <param name="do_not_use_all_standard_modules" checked="false" type="boolean" truevalue="--doNotUseAllStandardModules" falsevalue="" label="Do not use the standard eval modules by default" help="-noEV,--doNotUseAllStandardModules" />
484
485 <param name="num_samples" type="integer" label="Number of samples (used if no samples are available in the VCF file" value="0" help="-ns,--numSamples &amp;lt;numSamples&amp;gt;"/>
486 <param name="min_phase_quality" type="float" label="Minimum phasing quality " value="10.0" help="-mpq,--minPhaseQuality &amp;lt;minPhaseQuality&amp;gt;"/>
487 <param name="family" type="text" value="" label="If provided, genotypes in will be examined for mendelian violations: this argument is a string formatted as dad+mom=child where these parameters determine which sample names are examined" help="--family_structure"/>
488 <param name="mendelian_violation_qual_threshold" type="integer" label="Minimum genotype QUAL score for each trio member required to accept a site as a violation" value="50" help="-mvq,--mendelianViolationQualThreshold &amp;lt;mendelianViolationQualThreshold&amp;gt;"/>
489 <param name="ancestral_alignments" type="data" format="fasta" optional="True" label="Fasta file with ancestral alleles" help="-aa,--ancestralAlignments &amp;lt;ancestralAlignments&amp;gt;" />
490 <param name="known_cnvs" type="data" format="bed,gatk_interval,picard_interval_list" optional="True" label="File containing tribble-readable features describing a known list of copy number variants" help="-knownCNVs,--knownCNVs &amp;lt;knownCNVs&amp;gt;" />
491 <param name="strat_intervals" type="data" format="bed,gatk_interval,picard_interval_list" optional="True" label="File containing tribble-readable features for the IntervalStratificiation" help="-stratIntervals,--stratIntervals &amp;lt;stratIntervals&amp;gt;" />
492
493 </when>
494 </conditional>
495
496
497 </inputs>
498 <outputs>
499 <data format="gatk_report" name="output_report" label="${tool.name} on ${on_string} (report)" />
500 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
501 </outputs>
502 <tests>
503 <test>
504 <param name="reference_source_selector" value="history" />
505 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
506 <param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" />
507 <param name="dbsnp_rod_bind_type_selector" value="set_dbsnp" />
508 <param name="dbsnp_input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" />
509 <param name="dbsnp_known_names" value="True"/>
510 <param name="comp_rod_bind" value="0" />
511 <param name="gatk_param_type_selector" value="basic" />
512 <param name="analysis_param_type_selector" value="basic" />
513 <output name="output_report" file="gatk/gatk_variant_eval/gatk_variant_eval_out_1.gatk_report" />
514 <output name="output_log" file="gatk/gatk_variant_eval/gatk_variant_eval_out_1.log.contains" compare="contains" />
515 </test>
516 </tests>
517 <help>
518 **What it does**
519
520 General-purpose tool for variant evaluation (% in dbSNP, genotype concordance, Ti/Tv ratios, and a lot more)
521
522 For more information on using the VariantEval module, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_varianteval_VariantEval.html&gt;`_.
523
524 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;`_.
525
526 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
527
528 ------
529
530 **Inputs**
531
532 GenomeAnalysisTK: VariantEval accepts variant files as input.
533
534
535 **Outputs**
536
537 The output is a table of variant evaluation.
538
539
540 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
541
542 -------
543
544 **Settings**::
545
546 out An output file presented to the walker. Will overwrite contents if file exists.
547 list List the available eval modules and exit
548 select_exps One or more stratifications to use when evaluating the data
549 select_names Names to use for the list of stratifications (must be a 1-to-1 mapping)
550 sample Derive eval and comp contexts using only these sample genotypes, when genotypes are available in the original context
551 known_names Name of ROD bindings containing variant sites that should be treated as known when splitting eval rods into known and novel subsets
552 stratificationModule One or more specific stratification modules to apply to the eval track(s) (in addition to the standard stratifications, unless -noS is specified)
553 doNotUseAllStandardStratifications Do not use the standard stratification modules by default (instead, only those that are specified with the -S option)
554 onlyVariantsOfType If provided, only variants of these types will be considered during the evaluation, in
555 evalModule One or more specific eval modules to apply to the eval track(s) (in addition to the standard modules, unless -noE is specified)
556 doNotUseAllStandardModules Do not use the standard modules by default (instead, only those that are specified with the -E option)
557 numSamples Number of samples (used if no samples are available in the VCF file
558 minPhaseQuality Minimum phasing quality
559 family_structure If provided, genotypes in will be examined for mendelian violations: this argument is a string formatted as dad+mom=child where these parameters determine which sample names are examined
560 mendelianViolationQualThreshold Minimum genotype QUAL score for each trio member required to accept a site as a violation
561 ancestralAlignments Fasta file with ancestral alleles
562
563 ------
564
565 **Citation**
566
567 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;`_
568
569 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;`_
570
571 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;`_
572
573 </help>
574 </tool>