Mercurial > repos > jjohnson > gatk2

comparison unified_genotyper.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 9b8e2a158073
comparison
equal deleted inserted replaced
-1:000000000000 0:74c05070a3f8
1 <tool id="gatk2_unified_genotyper" name="Unified Genotyper" version="0.0.4">
2 <description>SNP and indel caller</description>
3 <requirements>
4 <requirement type="package" version="2.2">gatk</requirement>
5 <requirement type="package" version="0.1.18" version="0.1.18">samtools</requirement>
6 </requirements>
7 <command interpreter="python">gatk2_wrapper.py
8 --max_jvm_heap_fraction "1"
9 --stdout "${output_log}"
10 #for $i, $input_bam in enumerate( $reference_source.input_bams ):
11 -d "-I" "${input_bam.input_bam}" "${input_bam.input_bam.ext}" "gatk_input_${i}"
12 #if str( $input_bam.input_bam.metadata.bam_index ) != "None":
13 -d "" "${input_bam.input_bam.metadata.bam_index}" "bam_index" "gatk_input_${i}" ##hardcode galaxy ext type as bam_index
14 #end if
15 #end for
16 -p 'java
17 -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
18 -T "UnifiedGenotyper"
19 ##--num_threads 4 ##hard coded, for now
20 --out "${output_vcf}"
21 --metrics_file "${output_metrics}"
22 \$GATK2_SITE_OPTIONS
23 ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
24 ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
25 #if $reference_source.reference_source_selector != "history":
26 -R "${reference_source.ref_file.fields.path}"
27 #end if
28 --genotype_likelihoods_model "${genotype_likelihoods_model}"
29 --standard_min_confidence_threshold_for_calling "${standard_min_confidence_threshold_for_calling}"
30 --standard_min_confidence_threshold_for_emitting "${standard_min_confidence_threshold_for_emitting}"
31 '
32 #set $rod_binding_names = dict()
33 #for $rod_binding in $rod_bind:
34 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
35 #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
36 #else
37 #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
38 #end if
39 #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
40 -d "--dbsnp:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}"
41 #end for
42
43 ##start standard gatk options
44 #if $gatk_param_type.gatk_param_type_selector == "advanced":
45 #for $pedigree in $gatk_param_type.pedigree:
46 -p '--pedigree "${pedigree.pedigree_file}"'
47 #end for
48 #for $pedigree_string in $gatk_param_type.pedigree_string_repeat:
49 -p '--pedigreeString "${pedigree_string.pedigree_string}"'
50 #end for
51 -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"'
52 #for $read_filter in $gatk_param_type.read_filter:
53 -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}"
54 ###raise Exception( str( dir( $read_filter ) ) )
55 #for $name, $param in $read_filter.read_filter_type.iteritems():
56 #if $name not in [ "__current_case__", "read_filter_type_selector" ]:
57 #if hasattr( $param.input, 'truevalue' ):
58 ${param}
59 #else:
60 --${name} "${param}"
61 #end if
62 #end if
63 #end for
64 '
65 #end for
66 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ):
67 -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}"
68 #end for
69
70 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ):
71 -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}"
72 #end for
73
74 -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"'
75
76 -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"'
77 #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE":
78 -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"'
79 #end if
80 -p '
81 --baq "${gatk_param_type.baq}"
82 --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}"
83 ${gatk_param_type.use_original_qualities}
84 --defaultBaseQualities "${gatk_param_type.default_base_qualities}"
85 --validation_strictness "${gatk_param_type.validation_strictness}"
86 --interval_merging "${gatk_param_type.interval_merging}"
87 ${gatk_param_type.disable_experimental_low_memory_sharding}
88 ${gatk_param_type.non_deterministic_random_seed}
89 '
90 #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ):
91 #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file":
92 -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}"
93 #else
94 -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"'
95 #end if
96 #end for
97 #end if
98
99 #if $reference_source.reference_source_selector == "history":
100 -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
101 #end if
102 ##end standard gatk options
103 ##start analysis specific options
104 #if $analysis_param_type.analysis_param_type_selector == "advanced":
105 -p '
106 --p_nonref_model "${analysis_param_type.p_nonref_model}"
107 --heterozygosity "${analysis_param_type.heterozygosity}"
108 --pcr_error_rate "${analysis_param_type.pcr_error_rate}"
109 --genotyping_mode "${analysis_param_type.genotyping_mode_type.genotyping_mode}"
110 #if str( $analysis_param_type.genotyping_mode_type.genotyping_mode ) == 'GENOTYPE_GIVEN_ALLELES':
111 --alleles "${analysis_param_type.genotyping_mode_type.input_alleles_rod}"
112 #end if
113 --output_mode "${analysis_param_type.output_mode}"
114 ${analysis_param_type.compute_SLOD}
115 --min_base_quality_score "${analysis_param_type.min_base_quality_score}"
116 --max_deletion_fraction "${analysis_param_type.max_deletion_fraction}"
117 --max_alternate_alleles "${analysis_param_type.max_alternate_alleles}"
118 --min_indel_count_for_genotyping "${analysis_param_type.min_indel_count_for_genotyping}"
119 --indel_heterozygosity "${analysis_param_type.indel_heterozygosity}"
120 --indelGapContinuationPenalty "${analysis_param_type.indelGapContinuationPenalty}"
121 --indelGapOpenPenalty "${analysis_param_type.indelGapOpenPenalty}"
122 --indelHaplotypeSize "${analysis_param_type.indelHaplotypeSize}"
123 ${analysis_param_type.doContextDependentGapPenalties}
124 #if str( $analysis_param_type.annotation ) != "None":
125 #for $annotation in str( $analysis_param_type.annotation.fields.gatk_value ).split( ','):
126 --annotation "${annotation}"
127 #end for
128 #end if
129 #for $additional_annotation in $analysis_param_type.additional_annotations:
130 --annotation "${additional_annotation.additional_annotation_name}"
131 #end for
132 #if str( $analysis_param_type.group ) != "None":
133 #for $group in str( $analysis_param_type.group ).split( ','):
134 --group "${group}"
135 #end for
136 #end if
137 #if str( $analysis_param_type.exclude_annotations ) != "None":
138 #for $annotation in str( $analysis_param_type.exclude_annotations.fields.gatk_value ).split( ','):
139 --excludeAnnotation "${annotation}"
140 #end for
141 #end if
142 ${analysis_param_type.multiallelic}
143 '
144 ## #if str( $analysis_param_type.snpEff_rod_bind_type.snpEff_rod_bind_type_selector ) == 'set_snpEff':
145 ## -p '--annotation "SnpEff"'
146 ## -d "--snpEffFile:${analysis_param_type.snpEff_rod_bind_type.snpEff_rod_name},%(file_type)s" "${analysis_param_type.snpEff_rod_bind_type.snpEff_input_rod}" "${analysis_param_type.snpEff_rod_bind_type.snpEff_input_rod.ext}" "input_snpEff_${analysis_param_type.snpEff_rod_bind_type.snpEff_rod_name}"
147 ## #else:
148 ## -p '--excludeAnnotation "SnpEff"'
149 ## #end if
150 #end if
151 </command>
152 <inputs>
153 <conditional name="reference_source">
154 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
155 <option value="cached">Locally cached</option>
156 <option value="history">History</option>
157 </param>
158 <when value="cached">
159 <repeat name="input_bams" title="BAM file" min="1" help="-I,--input_file &amp;lt;input_file&amp;gt;">
160 <param name="input_bam" type="data" format="bam" label="BAM file">
161 <validator type="unspecified_build" />
162 <validator type="dataset_metadata_in_data_table" table_name="gatk2_picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select -->
163 </param>
164 </repeat>
165 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
166 <options from_data_table="gatk2_picard_indexes">
167 <!-- <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> does not yet work in a repeat...-->
168 </options>
169 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
170 </param>
171 </when>
172 <when value="history"> <!-- FIX ME!!!! -->
173 <repeat name="input_bams" title="BAM file" min="1" help="-I,--input_file &amp;lt;input_file&amp;gt;">
174 <param name="input_bam" type="data" format="bam" label="BAM file" >
175 </param>
176 </repeat>
177 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
178 </when>
179 </conditional>
180
181 <repeat name="rod_bind" title="Binding for reference-ordered data" help="-D,--dbsnp &amp;lt;dbsnp&amp;gt;">
182 <conditional name="rod_bind_type">
183 <param name="rod_bind_type_selector" type="select" label="Binding Type">
184 <option value="dbsnp" selected="True">dbSNP</option>
185 <option value="snps">SNPs</option>
186 <option value="indels">INDELs</option>
187 <option value="custom">Custom</option>
188 </param>
189 <when value="dbsnp">
190 <param name="input_rod" type="data" format="vcf" label="ROD file" />
191 </when>
192 <when value="snps">
193 <param name="input_rod" type="data" format="vcf" label="ROD file" />
194 </when>
195 <when value="indels">
196 <param name="input_rod" type="data" format="vcf" label="ROD file" />
197 </when>
198 <when value="custom">
199 <param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/>
200 <param name="input_rod" type="data" format="vcf" label="ROD file" />
201 </when>
202 </conditional>
203 </repeat>
204
205 <param name="genotype_likelihoods_model" type="select" label="Genotype likelihoods calculation model to employ" help="-glm,--genotype_likelihoods_model &amp;lt;genotype_likelihoods_model&amp;gt;">
206 <option value="BOTH" selected="True">BOTH</option>
207 <option value="SNP">SNP</option>
208 <option value="INDEL">INDEL</option>
209 </param>
210
211 <param name="standard_min_confidence_threshold_for_calling" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called" help="-stand_call_conf,--standard_min_confidence_threshold_for_calling &amp;lt;standard_min_confidence_threshold_for_calling&amp;gt;" />
212 <param name="standard_min_confidence_threshold_for_emitting" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)" help="-stand_emit_conf,--standard_min_confidence_threshold_for_emitting &amp;lt;standard_min_confidence_threshold_for_emitting&amp;gt;" />
213
214
215 <conditional name="gatk_param_type">
216 <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options">
217 <option value="basic" selected="True">Basic</option>
218 <option value="advanced">Advanced</option>
219 </param>
220 <when value="basic">
221 <!-- Do nothing here -->
222 </when>
223 <when value="advanced">
224 <repeat name="pedigree" title="Pedigree file" help="-ped,--pedigree &amp;lt;pedigree&amp;gt;">
225 <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples"/>
226 </repeat>
227 <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &amp;lt;pedigreeString&amp;gt;">
228 <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/>
229 </repeat>
230 <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;">
231 <option value="STRICT" selected="True">STRICT</option>
232 <option value="SILENT">SILENT</option>
233 </param>
234 <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &amp;lt;read_filter&amp;gt;">
235 <conditional name="read_filter_type">
236 <param name="read_filter_type_selector" type="select" label="Read Filter Type">
237 <option value="BadCigar">BadCigar</option>
238 <option value="BadMate">BadMate</option>
239 <option value="DuplicateRead">DuplicateRead</option>
240 <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option>
241 <option value="MalformedRead">MalformedRead</option>
242 <option value="MappingQuality">MappingQuality</option>
243 <option value="MappingQualityUnavailable">MappingQualityUnavailable</option>
244 <option value="MappingQualityZero">MappingQualityZero</option>
245 <option value="MateSameStrand">MateSameStrand</option>
246 <option value="MaxInsertSize">MaxInsertSize</option>
247 <option value="MaxReadLength" selected="True">MaxReadLength</option>
248 <option value="MissingReadGroup">MissingReadGroup</option>
249 <option value="NoOriginalQualityScores">NoOriginalQualityScores</option>
250 <option value="NotPrimaryAlignment">NotPrimaryAlignment</option>
251 <option value="Platform454">Platform454</option>
252 <option value="Platform">Platform</option>
253 <option value="PlatformUnit">PlatformUnit</option>
254 <option value="ReadGroupBlackList">ReadGroupBlackList</option>
255 <option value="ReadName">ReadName</option>
256 <option value="ReadStrand">ReadStrand</option>
257 <option value="ReassignMappingQuality">ReassignMappingQuality</option>
258 <option value="Sample">Sample</option>
259 <option value="SingleReadGroup">SingleReadGroup</option>
260 <option value="UnmappedRead">UnmappedRead</option>
261 </param>
262 <when value="BadCigar">
263 <!-- no extra options -->
264 </when>
265 <when value="BadMate">
266 <!-- no extra options -->
267 </when>
268 <when value="DuplicateRead">
269 <!-- no extra options -->
270 </when>
271 <when value="FailsVendorQualityCheck">
272 <!-- no extra options -->
273 </when>
274 <when value="MalformedRead">
275 <!-- no extra options -->
276 </when>
277 <when value="MappingQuality">
278 <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/>
279 </when>
280 <when value="MappingQualityUnavailable">
281 <!-- no extra options -->
282 </when>
283 <when value="MappingQualityZero">
284 <!-- no extra options -->
285 </when>
286 <when value="MateSameStrand">
287 <!-- no extra options -->
288 </when>
289 <when value="MaxInsertSize">
290 <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/>
291 </when>
292 <when value="MaxReadLength">
293 <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/>
294 </when>
295 <when value="MissingReadGroup">
296 <!-- no extra options -->
297 </when>
298 <when value="NoOriginalQualityScores">
299 <!-- no extra options -->
300 </when>
301 <when value="NotPrimaryAlignment">
302 <!-- no extra options -->
303 </when>
304 <when value="Platform454">
305 <!-- no extra options -->
306 </when>
307 <when value="Platform">
308 <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/>
309 </when>
310 <when value="PlatformUnit">
311 <!-- no extra options -->
312 </when>
313 <when value="ReadGroupBlackList">
314 <!-- no extra options -->
315 </when>
316 <when value="ReadName">
317 <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/>
318 </when>
319 <when value="ReadStrand">
320 <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/>
321 </when>
322 <when value="ReassignMappingQuality">
323 <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/>
324 </when>
325 <when value="Sample">
326 <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/>
327 </when>
328 <when value="SingleReadGroup">
329 <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/>
330 </when>
331 <when value="UnmappedRead">
332 <!-- no extra options -->
333 </when>
334 </conditional>
335 </repeat>
336 <repeat name="input_interval_repeat" title="Operate on Genomic intervals" help="-L,--intervals &amp;lt;intervals&amp;gt;">
337 <param name="input_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
338 </repeat>
339 <repeat name="input_exclude_interval_repeat" title="Exclude Genomic intervals" help="-XL,--excludeIntervals &amp;lt;excludeIntervals&amp;gt;">
340 <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
341 </repeat>
342
343 <param name="interval_set_rule" type="select" label="Interval set rule" help="-isr,--interval_set_rule &amp;lt;interval_set_rule&amp;gt;">
344 <option value="UNION" selected="True">UNION</option>
345 <option value="INTERSECTION">INTERSECTION</option>
346 </param>
347
348 <conditional name="downsampling_type">
349 <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;">
350 <option value="NONE" selected="True">NONE</option>
351 <option value="ALL_READS">ALL_READS</option>
352 <option value="BY_SAMPLE">BY_SAMPLE</option>
353 </param>
354 <when value="NONE">
355 <!-- no more options here -->
356 </when>
357 <when value="ALL_READS">
358 <conditional name="downsample_to_type">
359 <param name="downsample_to_type_selector" type="select" label="Downsample method">
360 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
361 <option value="downsample_to_coverage">Downsample by Coverage</option>
362 </param>
363 <when value="downsample_to_fraction">
364 <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;"/>
365 </when>
366 <when value="downsample_to_coverage">
367 <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;"/>
368 </when>
369 </conditional>
370 </when>
371 <when value="BY_SAMPLE">
372 <conditional name="downsample_to_type">
373 <param name="downsample_to_type_selector" type="select" label="Downsample method">
374 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
375 <option value="downsample_to_coverage">Downsample by Coverage</option>
376 </param>
377 <when value="downsample_to_fraction">
378 <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;"/>
379 </when>
380 <when value="downsample_to_coverage">
381 <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;"/>
382 </when>
383 </conditional>
384 </when>
385 </conditional>
386 <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine" help="-baq,--baq &amp;lt;baq&amp;gt;">
387 <option value="OFF" selected="True">OFF</option>
388 <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option>
389 <option value="RECALCULATE">RECALCULATE</option>
390 </param>
391 <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;" />
392 <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" help="-OQ,--useOriginalQualities" />
393 <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;"/>
394 <param name="validation_strictness" type="select" label="How strict should we be with validation" help="-S,--validation_strictness &amp;lt;validation_strictness&amp;gt;">
395 <option value="STRICT" selected="True">STRICT</option>
396 <option value="LENIENT">LENIENT</option>
397 <option value="SILENT">SILENT</option>
398 <!-- <option value="DEFAULT_STRINGENCY">DEFAULT_STRINGENCY</option> listed in docs, but not valid value...-->
399 </param>
400 <param name="interval_merging" type="select" label="Interval merging rule" help="-im,--interval_merging &amp;lt;interval_merging&amp;gt;">
401 <option value="ALL" selected="True">ALL</option>
402 <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option>
403 </param>
404
405 <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;">
406 <conditional name="read_group_black_list_type">
407 <param name="read_group_black_list_type_selector" type="select" label="Type of reads read group black list">
408 <option value="file" selected="True">Filters in file</option>
409 <option value="text">Specify filters as a string</option>
410 </param>
411 <when value="file">
412 <param name="read_group_black_list" type="data" format="txt" label="Read group black list file" />
413 </when>
414 <when value="text">
415 <param name="read_group_black_list" type="text" value="tag:string" label="Read group black list tag:string" />
416 </when>
417 </conditional>
418 </repeat>
419
420 <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"/>
421 <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"/>
422
423 </when>
424 </conditional>
425
426 <conditional name="analysis_param_type">
427 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
428 <option value="basic" selected="True">Basic</option>
429 <option value="advanced">Advanced</option>
430 </param>
431 <when value="basic">
432 <!-- Do nothing here -->
433 </when>
434 <when value="advanced">
435 <param name="p_nonref_model" type="select" label="Non-reference probability calculation model to employ" help="-pnrm,--p_nonref_model &amp;lt;p_nonref_model&amp;gt;">
436 <option value="EXACT" selected="True">EXACT</option>
437 <option value="GRID_SEARCH">GRID_SEARCH</option>
438 </param>
439 <param name="heterozygosity" type="float" value="1e-3" label="Heterozygosity value used to compute prior likelihoods for any locus" help="-hets,--heterozygosity &amp;lt;heterozygosity&amp;gt;" />
440 <param name="pcr_error_rate" type="float" value="1e-4" label="The PCR error rate to be used for computing fragment-based likelihoods" help="-pcr_error,--pcr_error_rate &amp;lt;pcr_error_rate&amp;gt;" />
441 <conditional name="genotyping_mode_type">
442 <param name="genotyping_mode" type="select" label="How to determine the alternate allele to use for genotyping" help="-gt_mode,--genotyping_mode &amp;lt;genotyping_mode&amp;gt;">
443 <option value="DISCOVERY" selected="True">DISCOVERY</option>
444 <option value="GENOTYPE_GIVEN_ALLELES">GENOTYPE_GIVEN_ALLELES</option>
445 </param>
446 <when value="DISCOVERY">
447 <!-- Do nothing here -->
448 </when>
449 <when value="GENOTYPE_GIVEN_ALLELES">
450 <param name="input_alleles_rod" type="data" format="vcf" label="Alleles ROD file" help="-alleles,--alleles &amp;lt;alleles&amp;gt;" />
451 </when>
452 </conditional>
453 <param name="output_mode" type="select" label="Should we output confident genotypes (i.e. including ref calls) or just the variants?" help="-out_mode,--output_mode &amp;lt;output_mode&amp;gt;">
454 <option value="EMIT_VARIANTS_ONLY" selected="True">EMIT_VARIANTS_ONLY</option>
455 <option value="EMIT_ALL_CONFIDENT_SITES">EMIT_ALL_CONFIDENT_SITES</option>
456 <option value="EMIT_ALL_SITES">EMIT_ALL_SITES</option>
457 </param>
458 <param name="compute_SLOD" type="boolean" truevalue="--computeSLOD" falsevalue="" label="Compute the SLOD" help="--computeSLOD" />
459 <param name="min_base_quality_score" type="integer" value="17" label="Minimum base quality required to consider a base for calling" help="-mbq,--min_base_quality_score &amp;lt;min_base_quality_score&amp;gt;" />
460 <param name="max_deletion_fraction" type="float" value="0.05" label="Maximum fraction of reads with deletions spanning this locus for it to be callable" help="to disable, set to &lt; 0 or &gt; 1 (-deletions,--max_deletion_fraction &amp;lt;max_deletion_fraction&amp;gt;)" />
461 <param name="max_alternate_alleles" type="integer" value="5" label="Maximum number of alternate alleles to genotype" help="-maxAlleles,--max_alternate_alleles &amp;lt;max_alternate_alleles&amp;gt;" />
462 <param name="min_indel_count_for_genotyping" type="integer" value="5" label="Minimum number of consensus indels required to trigger genotyping run" help="-minIndelCnt,--min_indel_count_for_genotyping &amp;lt;min_indel_count_for_genotyping&amp;gt;" />
463 <param name="indel_heterozygosity" type="float" value="0.000125" label="Heterozygosity for indel calling" help="1.0/8000==0.000125 (-indelHeterozygosity,--indel_heterozygosity &amp;lt;indel_heterozygosity&amp;gt;)"/>
464 <param name="indelGapContinuationPenalty" type="float" value="10.0" label="Indel gap continuation penalty" help="--indelGapContinuationPenalty" />
465 <param name="indelGapOpenPenalty" type="float" value="45.0" label="Indel gap open penalty" help="--indelGapOpenPenalty" />
466 <param name="indelHaplotypeSize" type="integer" value="80" label="Indel haplotype size" help="--indelHaplotypeSize" />
467 <param name="doContextDependentGapPenalties" type="boolean" truevalue="--doContextDependentGapPenalties" falsevalue="" label="Vary gap penalties by context" help="--doContextDependentGapPenalties" />
468 <param name="annotation" type="select" multiple="True" display="checkboxes" label="Annotation Types" help="-A,--annotation &amp;lt;annotation&amp;gt;">
469 <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs -->
470 <options from_data_table="gatk2_annotations">
471 <filter type="multiple_splitter" column="tools_valid_for" separator=","/>
472 <filter type="static_value" value="UnifiedGenotyper" column="tools_valid_for"/>
473 </options>
474 </param>
475 <repeat name="additional_annotations" title="Additional annotation" help="-A,--annotation &amp;lt;annotation&amp;gt;">
476 <param name="additional_annotation_name" type="text" value="" label="Annotation name" />
477 </repeat>
478 <!--
479 <conditional name="snpEff_rod_bind_type">
480 <param name="snpEff_rod_bind_type_selector" type="select" label="Provide a snpEff reference-ordered data file">
481 <option value="set_snpEff">Set snpEff</option>
482 <option value="exclude_snpEff" selected="True">Don't set snpEff</option>
483 </param>
484 <when value="exclude_snpEff">
485 </when>
486 <when value="set_snpEff">
487 <param name="snpEff_input_rod" type="data" format="vcf" label="ROD file" />
488 <param name="snpEff_rod_name" type="hidden" value="snpEff" label="ROD Name"/>
489 </when>
490 </conditional>
491 -->
492 <param name="group" type="select" multiple="True" display="checkboxes" label="Annotation Interfaces/Groups" help="-G,--group &amp;lt;group&amp;gt;">
493 <option value="RodRequiringAnnotation">RodRequiringAnnotation</option>
494 <option value="Standard">Standard</option>
495 <option value="Experimental">Experimental</option>
496 <option value="WorkInProgress">WorkInProgress</option>
497 <option value="RankSumTest">RankSumTest</option>
498 <!-- <option value="none">none</option> -->
499 </param>
500 <!-- <param name="family_string" type="text" value="" label="Family String"/> -->
501 <param name="exclude_annotations" type="select" multiple="True" display="checkboxes" label="Annotations to exclude" help="-XA,--excludeAnnotation &amp;lt;excludeAnnotation&amp;gt;" >
502 <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs -->
503 <options from_data_table="gatk2_annotations">
504 <filter type="multiple_splitter" column="tools_valid_for" separator=","/>
505 <filter type="static_value" value="UnifiedGenotyper" column="tools_valid_for"/>
506 </options>
507 </param>
508 <param name="multiallelic" type="boolean" truevalue="--multiallelic" falsevalue="" label="Allow the discovery of multiple alleles (SNPs only)" help="--multiallelic" />
509 </when>
510 </conditional>
511 </inputs>
512 <outputs>
513 <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (VCF)" />
514 <data format="txt" name="output_metrics" label="${tool.name} on ${on_string} (metrics)" />
515 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
516 </outputs>
517 <trackster_conf/>
518 <tests>
519 <test>
520 <param name="reference_source_selector" value="history" />
521 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
522 <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" />
523 <param name="rod_bind_type_selector" value="dbsnp" />
524 <param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" />
525 <param name="standard_min_confidence_threshold_for_calling" value="0" />
526 <param name="standard_min_confidence_threshold_for_emitting" value="4" />
527 <param name="gatk_param_type_selector" value="basic" />
528 <param name="analysis_param_type_selector" value="advanced" />
529 <param name="genotype_likelihoods_model" value="BOTH" />
530 <param name="p_nonref_model" value="EXACT" />
531 <param name="heterozygosity" value="0.001" />
532 <param name="pcr_error_rate" value="0.0001" />
533 <param name="genotyping_mode" value="DISCOVERY" />
534 <param name="output_mode" value="EMIT_ALL_CONFIDENT_SITES" />
535 <param name="compute_SLOD" />
536 <param name="min_base_quality_score" value="17" />
537 <param name="max_deletion_fraction" value="-1" />
538 <param name="min_indel_count_for_genotyping" value="2" />
539 <param name="indel_heterozygosity" value="0.000125" />
540 <param name="indelGapContinuationPenalty" value="10" />
541 <param name="indelGapOpenPenalty" value="3" />
542 <param name="indelHaplotypeSize" value="80" />
543 <param name="doContextDependentGapPenalties" />
544 <!-- <param name="annotation" value="" />
545 <param name="group" value="" /> -->
546 <output name="output_vcf" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.vcf" lines_diff="4" />
547 <output name="output_metrics" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.metrics" />
548 <output name="output_log" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.log.contains" compare="contains" />
549 </test>
550 </tests>
551 <help>
552 **What it does**
553
554 A variant caller which unifies the approaches of several disparate callers. Works for single-sample and multi-sample data. The user can choose from several different incorporated calculation models.
555
556 For more information on the GATK Unified Genotyper, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_genotyper_UnifiedGenotyper.html&gt;`_.
557
558 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;`_.
559
560 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
561
562 ------
563
564 **Inputs**
565
566 GenomeAnalysisTK: UnifiedGenotyper accepts an aligned BAM input file.
567
568
569 **Outputs**
570
571 The output is in VCF format.
572
573
574 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
575
576 -------
577
578 **Settings**::
579
580 genotype_likelihoods_model Genotype likelihoods calculation model to employ -- BOTH is the default option, while INDEL is also available for calling indels and SNP is available for calling SNPs only (SNP|INDEL|BOTH)
581 p_nonref_model Non-reference probability calculation model to employ -- EXACT is the default option, while GRID_SEARCH is also available. (EXACT|GRID_SEARCH)
582 heterozygosity Heterozygosity value used to compute prior likelihoods for any locus
583 pcr_error_rate The PCR error rate to be used for computing fragment-based likelihoods
584 genotyping_mode Should we output confident genotypes (i.e. including ref calls) or just the variants? (DISCOVERY|GENOTYPE_GIVEN_ALLELES)
585 output_mode Should we output confident genotypes (i.e. including ref calls) or just the variants? (EMIT_VARIANTS_ONLY|EMIT_ALL_CONFIDENT_SITES|EMIT_ALL_SITES)
586 standard_min_confidence_threshold_for_calling The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called
587 standard_min_confidence_threshold_for_emitting The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)
588 noSLOD If provided, we will not calculate the SLOD
589 min_base_quality_score Minimum base quality required to consider a base for calling
590 max_deletion_fraction Maximum fraction of reads with deletions spanning this locus for it to be callable [to disable, set to &lt; 0 or &gt; 1; default:0.05]
591 min_indel_count_for_genotyping Minimum number of consensus indels required to trigger genotyping run
592 indel_heterozygosity Heterozygosity for indel calling
593 indelGapContinuationPenalty Indel gap continuation penalty
594 indelGapOpenPenalty Indel gap open penalty
595 indelHaplotypeSize Indel haplotype size
596 doContextDependentGapPenalties Vary gap penalties by context
597 indel_recal_file Filename for the input covariates table recalibration .csv file - EXPERIMENTAL, DO NO USE
598 indelDebug Output indel debug info
599 out File to which variants should be written
600 annotation One or more specific annotations to apply to variant calls
601 group One or more classes/groups of annotations to apply to variant calls
602
603 ------
604
605 **Citation**
606
607 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;`_
608
609 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;`_
610
611 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;`_
612
613 </help>
614 </tool>