Mercurial > repos > artbio > artbio_mutect2

comparison artbio_mutect2.xml @ 0:504de035ac0f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/artbio_mutect2 commit b42fd0507a42663722f06ff0cedfee83a64c84b2"
author artbio
date Thu, 07 May 2020 12:29:36 -0400
parents
children 2b6ee93fd144
comparison
equal deleted inserted replaced
-1:000000000000 0:504de035ac0f
1 <tool id="artbio_mutect2" name="GATK4 Mutect2" version="@WRAPPER_VERSION@2" profile="18.05">
2 <description>- Call somatic SNVs and indels via local assembly of haplotypes</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="version_cmd"/>
8 <command detect_errors="exit_code">
9 <![CDATA[
10 #include source=$set_sections#
11 #include source=$pre_gatk_excl_ints_chth#
12 #include source=$tumor_bam_index_pre_chth#
13 #include source=$normal_bam_index_pre_chth#
14 #include source=$pre_gatk_ints_chth#
15
16 #set ref_flag='--reference="reference.fa"'
17
18 #if str($reference_source.reference_source_selector) == 'history'
19 ln -s '$reference_source.reference_sequence' reference.fa &&
20 samtools faidx reference.fa &&
21 gatk CreateSequenceDictionary --REFERENCE="reference.fa" --OUTPUT="reference.dict" &&
22 #else if str($reference_source.reference_source_selector) == 'history'
23 ln -s '$reference_source.reference_sequence.fields.path' reference.fa &&
24 samtools faidx reference.fa &&
25 gatk CreateSequenceDictionary --REFERENCE="reference.fa" --OUTPUT="reference.dict" &&
26 #else
27 #set ref_flag=''
28 #end if
29
30 #if str($outputs.output_parameters) == 'yes'
31 #if str($outputs.debug_activity) == 'yes'
32 ln -s '$activity_profile_out' activity-profile.tab &&
33 #end if
34 #if str($outputs.debug_assembly) == 'yes'
35 ln -s '$assembly_region_out' assembly-region.tab &&
36 #end if
37 #if str($outputs.debug_bam) == 'yes'
38 ln -s '$bam_output' debug.bam &&
39 #end if
40 #end if
41
42 gatk GetSampleName --input="tumor.bam" --output="samplename.txt" &&
43 sample=`cat samplename.txt | sed 's/"//g'` &&
44
45 #if str($optional.optional_parameters) == 'yes'
46 #if $optional.panel_of_normals
47 #set datatype = $optional.panel_of_normals.datatype
48 #if $optional.panel_of_normals.is_of_type("vcf_bgzip")
49 ln -s '$optional.panel_of_normals' panel_of_normals.vcf.gz &&
50 tabix panel_of_normals.vcf.gz &&
51 #else
52 ln -s '$optional.panel_of_normals' panel_of_normals.vcf &&
53 #end if
54 #end if
55
56 #if $optional.germline_resource
57 #set datatype = $optional.germline_resource.datatype
58 #if $optional.germline_resource.is_of_type("vcf_bgzip")
59 ln -s '$optional.germline_resource' germline_resource.vcf.gz &&
60 tabix germline_resource.vcf.gz &&
61 #else
62 ln -s '$optional.germline_resource' germline_resource.vcf &&
63 #end if
64 #end if
65
66 #if $optional.alleles
67 #set datatype = $optional.alleles.datatype
68 #if $optional.alleles.is_of_type("vcf_bgzip")
69 ln -s '$optional.alleles' alleles.vcf.gz &&
70 tabix alleles.vcf.gz &&
71 @CMD_BEGIN@ IndexFeatureFile --feature-file alleles.vcf.gz &&
72 #else
73 ln -s '$optional.alleles' alleles.vcf &&
74 @CMD_BEGIN@ IndexFeatureFile --feature-file alleles.vcf &&
75 #end if
76 #end if
77
78 #end if
79
80 gatk Mutect2 --QUIET $ref_flag --tumor-sample "\$sample"
81
82 #if str($mode.mode_parameters) == 'tumor_only'
83 #include source=$gatk_tumor_bam_input#
84 #else
85 #include source=$gatk_tumor_bam_input#
86 #include source=$gatk_normal_bam_input#
87 #end if
88
89 ## OPTIONAL PARAMETERS ##
90
91 #if str($optional.optional_parameters) == 'yes'
92
93 #if $optional.panel_of_normals
94 #if $optional.panel_of_normals.is_of_type("vcf_bgzip")
95 --panel-of-normals panel_of_normals.vcf.gz
96 #else
97 --panel-of-normals panel_of_normals.vcf
98 #end if
99 #end if
100
101 #if $optional.pedigree
102 --pedigree="$optional.pedigree"
103 #end if
104
105 #if $optional.germline_resource
106 #if $optional.germline_resource.is_of_type("vcf_bgzip")
107 --germline-resource germline_resource.vcf.gz
108 #else
109 --germline-resource germline_resource.vcf
110 #end if
111 #end if
112
113 #if $optional.annotation
114 #for $annot in str($optional.annotation).split(',')
115 --annotation="$annot"
116 #end for
117 #end if
118
119 #if $optional.annotation_group
120 #for $annot in str($optional.annotation_group).split(',')
121 --annotation-group="$annot"
122 #end for
123 #end if
124
125 #if $optional.annotations_to_exclude
126 #for $annot in str($optional.annotations_to_exclude).split(',')
127 --annotations-to-exclude="$annot"
128 #end for
129 #end if
130
131 #if $optional.founder_id
132 --founder-id="$optional.founder_id"
133 #end if
134
135 #if $optional.normal_sample
136 --normal-sample="$optional.normal_sample"
137 #end if
138
139 #if $optional.alleles
140 --alleles alleles.vcf
141 #end if
142
143 #if $optional.f1r2_max_depth:
144 --f1r2-max-depth="$optional.f1r2_max_depth"
145 #end if
146
147 #if $optional.f1r2_max_depth:
148 --f1r2-median-mq="$optional.f1r2_median_mq"
149 #end if
150
151 #if $optional.f1r2_max_depth:
152 --f1r2-min-bq="$optional.f1r2_min_bq"
153 #end if
154
155 #if $optional.interval_merging_rule:
156 --interval-merging-rule="$optional.interval_merging_rule"
157 #end if
158
159 #if $optional.interval_set_rule:
160 --interval-set-rule="$optional.interval_set_rule"
161 #end if
162
163 #if $optional.pcr_indel_qual:
164 --pcr-indel-qual="$optional.pcr_indel_qual"
165 #end if
166
167 #if $optional.pcr_snv_qual:
168 --pcr-snv-qual="$optional.pcr_snv_qual"
169 #end if
170
171 #if $optional.read_filter
172 #for $filter in str($optional.read_filter).split(',')
173 --read-filter="$filter"
174 #end for
175 #end if
176
177 #if $optional.disable_read_filter
178 #for $filter in str($optional.disable_read_filter).split(',')
179 --disable-read-filter="$filter"
180 #end for
181 #end if
182
183 --base-quality-score-threshold="$optional.base_quality_score_threshold"
184 --af-of-alleles-not-in-resource="$optional.af_of_alleles_not_in_resource"
185 --downsampling-stride="$optional.downsampling_stride"
186 --gcs-max-retries="$optional.gcs_max_retries"
187 --initial-tumor-lod="$optional.initial_tumor_lod"
188 --max-population-af="$optional.max_population_af"
189 --max-reads-per-alignment-start="$optional.max_reads_per_alignment_start"
190 --min-base-quality-score="$optional.min_base_quality_score"
191 --native-pair-hmm-threads="\${GALAXY_SLOTS:-1}"
192 --normal-lod="$optional.normal_lod"
193 --read-validation-stringency="$optional.read_validation_stringency"
194 --tumor-lod-to-emit="$optional.tumor_lod_to_emit"
195 --verbosity="ERROR"
196 $optional.lenient
197 $optional.annotate_with_num_discovered_alleles
198 $optional.add_output_sam_program_record
199 $optional.disable_bam_index_caching
200 $optional.disable_sequence_dictionary_validation
201 $optional.genotype_germline_sites
202 $optional.genotype_pon_sites
203 $optional.ignore_itr_artifacts
204 $optional.mitochondria_mode
205 $optional.native_pair_hmm_use_double_precision
206 $optional.sites_only_vcf_output
207 $optional.add_output_vcf_command_line
208 #end if
209
210 ## END OPTIONAL PARAMETERS ##
211
212 ## ADVANCED PARAMETERS ##
213
214 #if str($advanced.advanced_parameters) == 'yes'
215
216 #if $advanced.kmer_size
217 --kmer-size="$advanced.kmer_size"
218 #end if
219
220 #if $advanced.gvcf_lod_band
221 --gvcf-lod-band="$advanced.gvcf_lod_band"
222 #end if
223
224 #if $advanced.emit_ref_confidence
225 --emit-ref-confidence="$advanced.emit_ref_confidence"
226 #end if
227
228 #if $advanced.max_unpruned_variants
229 --max-unpruned-variants="$advanced.max_unpruned_variants"
230 #end if
231
232 --active-probability-threshold="$advanced.active_probability_threshold"
233 --assembly-region-padding="$advanced.assembly_region_padding"
234 --bam-writer-type="$advanced.bam_writer_type"
235 --max-assembly-region-size="$advanced.max_assembly_region_size"
236 --max-mnp-distance="$advanced.max_mnp_distance"
237 --max-num-haplotypes-in-population="$advanced.max_num_haplotypes_in_population"
238 --max-prob-propagation-distance="$advanced.max_prob_propagation_distance"
239 --max-suspicious-reads-per-alignment-start="$advanced.max_suspicious_reads_per_alignment_start"
240 --min-assembly-region-size="$advanced.min_assembly_region_size"
241 --min-dangling-branch-length="$advanced.min_dangling_branch_length"
242 --min-pruning="$advanced.min_pruning"
243 --minimum-allele-fraction="$advanced.minimum_allele_fraction"
244 --num-pruning-samples="$advanced.num_pruning_samples"
245 --pair-hmm-gap-continuation-penalty="$advanced.pair_hmm_gap_continuation_penalty"
246 --pair-hmm-implementation="$advanced.pair_hmm_implementation"
247 --pcr-indel-model="$advanced.pcr_indel_model"
248 --phred-scaled-global-read-mismapping-rate="$advanced.phred_scaled_global_read_mismapping_rate"
249 --pruning-lod-threshold="$advanced.pruning_lod_threshold"
250 --smith-waterman="$advanced.smith_waterman"
251 $advanced.allow_non_unique_kmers_in_ref
252 $advanced.disable_adaptive_pruning
253 $advanced.disable_tool_default_annotations
254 $advanced.disable_tool_default_read_filters
255 $advanced.dont_increase_kmer_sizes_for_cycles
256 $advanced.dont_trim_active_regions
257 $advanced.dont_use_soft_clipped_bases
258 $advanced.enable_all_annotations
259 $advanced.force_active
260 $advanced.force_call_filtered_alleles
261 $advanced.independent_mates
262 $advanced.recover_all_dangling_branches
263 $advanced.use_filtered_reads_for_annotations
264
265 #end if
266
267 ## END ADVANCED PARAMETERS ##
268
269 ## ADDITIONAL OUTPUT PARAMETERS ##
270
271 #if str($outputs.output_parameters) == 'yes'
272 #if str($outputs.debug_activity) == 'yes'
273 --activity-profile-out="activity-profile.tab"
274 #end if
275 #if str($outputs.debug_assembly) == 'yes'
276 --assembly-region-out="assembly-region.tab"
277 #end if
278 #if str($outputs.debug_bam) == 'yes'
279 --bam-output="debug.bam"
280 #end if
281 #end if
282
283 #include source=$gatk_excl_ints_chth#
284 #include source=$gatk_ints_chth#
285 #include source=$vcf_output_opts#
286 #include source=$gatk_seqdict#
287 ]]>
288 </command>
289 <inputs>
290 <conditional name="mode">
291 <param name="mode_parameters" type="select" label="Type of analysis">
292 <option value="tumor_only">Tumor-only</option>
293 <option value="somatic">Somatic</option>
294 </param>
295 <when value="tumor_only">
296 <expand macro="gatk_tumor_bam_req_params"/>
297 </when>
298 <when value="somatic">
299 <expand macro="gatk_tumor_bam_req_params"/>
300 <expand macro="gatk_normal_bam_req_params"/>
301 </when>
302 </conditional>
303 <expand macro="gzip_vcf_params"/>
304 <expand macro="ref_sel"/>
305 <conditional name="optional">
306 <param name="optional_parameters" type="select" label="Optional parameters">
307 <option value="no">Use internal defaults</option>
308 <option value="yes">Specify parameters</option>
309 </param>
310 <when value="yes">
311 <expand macro="gatk_excl_ints"/>
312 <expand macro="gatk_ints"/>
313 <expand macro="seq_dict_sel"/>
314 <param name="add_output_sam_program_record" argument="--add-output-sam-program-record" type="boolean" truevalue="--add-output-sam-program-record" falsevalue="" optional="true" checked="true" label="Add Output Sam Program Record" help="If true, adds a PG tag to created SAM/BAM/CRAM files."/>
315 <param name="add_output_vcf_command_line" argument="--add-output-vcf-command-line" type="boolean" truevalue="--add-output-vcf-command-line" falsevalue="" optional="true" checked="true" label="Add Output Vcf Command Line" help="If true, adds a command line header line to created VCF files."/>
316 <param name="af_of_alleles_not_in_resource" argument="--af-of-alleles-not-in-resource" type="float" optional="true" value="-1.0" label="Af Of Alleles Not In Resource" help="Population allele fraction assigned to alleles not found in germline resource. Please see docs/mutect/mutect2.pdf fora derivation of the default value."/>
317 <param name="annotate_with_num_discovered_alleles" argument="--annotate-with-num-discovered-alleles" type="boolean" truevalue="--annotate-with-num-discovered-alleles" falsevalue="" optional="true" checked="false" label="Annotate With Num Discovered Alleles" help="If provided, we will annotate records with the number of alternate alleles that were discovered (but not necessarily genotyped) at a given site"/>
318 <param argument="--annotation" type="select" multiple="true" label="Annotations" help="One or more specific annotations to add to variant calls">
319 <option value="AlleleFraction">AlleleFraction</option>
320 <option value="AS_BaseQualityRankSumTest">AS_BaseQualityRankSumTest</option>
321 <option value="AS_FisherStrand">AS_FisherStrand</option>
322 <option value="AS_InbreedingCoeff">AS_InbreedingCoeff</option>
323 <option value="AS_MappingQualityRankSumTest">AS_MappingQualityRankSumTest</option>
324 <option value="AS_QualByDepth">AS_QualByDepth</option>
325 <option value="AS_ReadPosRankSumTest">AS_ReadPosRankSumTest</option>
326 <option value="AS_RMSMappingQuality">AS_RMSMappingQuality</option>
327 <option value="AS_StrandOddsRatio">AS_StrandOddsRatio</option>
328 <option value="BaseQuality">BaseQuality</option>
329 <option value="BaseQualityHistogram">BaseQualityHistogram</option>
330 <option value="BaseQualityRankSumTest">BaseQualityRankSumTest</option>
331 <option value="ChromosomeCounts">ChromosomeCounts</option>
332 <option value="ClippingRankSumTest">ClippingRankSumTest</option>
333 <option value="CountNs">CountNs</option>
334 <option value="Coverage">Coverage</option>
335 <option value="DepthPerAlleleBySample">DepthPerAlleleBySample</option>
336 <option value="DepthPerSampleHC">DepthPerSampleHC</option>
337 <option value="ExcessHet">ExcessHet</option>
338 <option value="FisherStrand">FisherStrand</option>
339 <option value="FragmentLength">FragmentLength</option>
340 <option value="GenotypeSummaries">GenotypeSummaries</option>
341 <option value="InbreedingCoeff">InbreedingCoeff</option>
342 <option value="LikelihoodRankSumTest">LikelihoodRankSumTest</option>
343 <option value="MappingQuality">MappingQuality</option>
344 <option value="MappingQualityRankSumTest">MappingQualityRankSumTest</option>
345 <option value="MappingQualityZero">MappingQualityZero</option>
346 <option value="OrientationBiasReadCounts">OrientationBiasReadCounts</option>
347 <option value="OriginalAlignment">OriginalAlignment</option>
348 <option value="PossibleDeNovo">PossibleDeNovo</option>
349 <option value="QualByDepth">QualByDepth</option>
350 <option value="ReadPosition">ReadPosition</option>
351 <option value="ReadPosRankSumTest">ReadPosRankSumTest</option>
352 <option value="ReferenceBases">ReferenceBases</option>
353 <option value="RMSMappingQuality">RMSMappingQuality</option>
354 <option value="SampleList">SampleList</option>
355 <option value="StrandBiasBySample">StrandBiasBySample</option>
356 <option value="StrandOddsRatio">StrandOddsRatio</option>
357 <option value="TandemRepeat">TandemRepeat</option>
358 <option value="UniqueAltReadCount">UniqueAltReadCount</option>
359 </param>
360 <param name="annotation_group" argument="--annotation-group" type="select" multiple="true" label="Annotation groups" help="One or more annotation groups to add to variant calls">
361 <option value="AlleleSpecificAnnotation">AlleleSpecificAnnotation</option>
362 <option value="AS_StandardAnnotation">AS_StandardAnnotation</option>
363 <option value="ReducibleAnnotation">ReducibleAnnotation</option>
364 <option value="StandardAnnotation">StandardAnnotation</option>
365 <option value="StandardHCAnnotation">StandardHCAnnotation</option>
366 <option value="StandardMutectAnnotation">StandardMutectAnnotation</option>
367 </param>
368 <param name="annotations_to_exclude" argument="--annotations-to-exclude" type="select" multiple="true" label="Annotations to exclude" help="Specific annotations to exclude from variant calls">
369 <option value="AlleleFraction">AlleleFraction</option>
370 <option value="AS_BaseQualityRankSumTest">AS_BaseQualityRankSumTest</option>
371 <option value="AS_FisherStrand">AS_FisherStrand</option>
372 <option value="AS_InbreedingCoeff">AS_InbreedingCoeff</option>
373 <option value="AS_MappingQualityRankSumTest">AS_MappingQualityRankSumTest</option>
374 <option value="AS_QualByDepth">AS_QualByDepth</option>
375 <option value="AS_ReadPosRankSumTest">AS_ReadPosRankSumTest</option>
376 <option value="AS_RMSMappingQuality">AS_RMSMappingQuality</option>
377 <option value="AS_StrandOddsRatio">AS_StrandOddsRatio</option>
378 <option value="BaseQuality">BaseQuality</option>
379 <option value="BaseQualityHistogram">BaseQualityHistogram</option>
380 <option value="BaseQualityRankSumTest">BaseQualityRankSumTest</option>
381 <option value="ChromosomeCounts">ChromosomeCounts</option>
382 <option value="ClippingRankSumTest">ClippingRankSumTest</option>
383 <option value="CountNs">CountNs</option>
384 <option value="Coverage">Coverage</option>
385 <option value="DepthPerAlleleBySample">DepthPerAlleleBySample</option>
386 <option value="DepthPerSampleHC">DepthPerSampleHC</option>
387 <option value="ExcessHet">ExcessHet</option>
388 <option value="FisherStrand">FisherStrand</option>
389 <option value="FragmentLength">FragmentLength</option>
390 <option value="GenotypeSummaries">GenotypeSummaries</option>
391 <option value="InbreedingCoeff">InbreedingCoeff</option>
392 <option value="LikelihoodRankSumTest">LikelihoodRankSumTest</option>
393 <option value="MappingQuality">MappingQuality</option>
394 <option value="MappingQualityRankSumTest">MappingQualityRankSumTest</option>
395 <option value="MappingQualityZero">MappingQualityZero</option>
396 <option value="OrientationBiasReadCounts">OrientationBiasReadCounts</option>
397 <option value="OriginalAlignment">OriginalAlignment</option>
398 <option value="PossibleDeNovo">PossibleDeNovo</option>
399 <option value="QualByDepth">QualByDepth</option>
400 <option value="ReadPosition">ReadPosition</option>
401 <option value="ReadPosRankSumTest">ReadPosRankSumTest</option>
402 <option value="ReferenceBases">ReferenceBases</option>
403 <option value="RMSMappingQuality">RMSMappingQuality</option>
404 <option value="SampleList">SampleList</option>
405 <option value="StrandBiasBySample">StrandBiasBySample</option>
406 <option value="StrandOddsRatio">StrandOddsRatio</option>
407 <option value="TandemRepeat">TandemRepeat</option>
408 <option value="UniqueAltReadCount">UniqueAltReadCount</option>
409 </param>
410 <param name="pedigree" argument="--pedigree" type="data" optional="true" format="vcf,vcf_bgzip" label="Pedigree" help="Pedigree file for determining the population &quot;founders&quot;. If a file is provided here, a pedigree-based annotation must be added above."/>
411 <param name="base_quality_score_threshold" argument="--base-quality-score-threshold" type="integer" optional="true" value="18" label="Base Quality Score Threshold" help="Base qualities below this threshold will be reduced to the minimum (6)"/>
412 <param name="callable_depth" argument="--callable-depth" type="integer" optional="true" value="10" label="Minimum depth to be considered callable" help="Does not affect genotyping"/>
413 <param name="contamination_fraction_to_filter" argument="--contamination-fraction-to-filter" type="float" optional="true" value="0.0" label="Contamination Fraction To Filter" help="Fraction of contamination in sequencing data (for all samples) to aggressively remove"/>
414 <param name="disable_bam_index_caching" argument="--disable-bam-index-caching" type="boolean" truevalue="--disable-bam-index-caching" falsevalue="" optional="true" checked="false" label="Disable Bam Index Caching" help="If true, don&amp;apos;t cache bam indexes, this will reduce memory requirements but may harm performance if many intervals are specified. Caching is automatically disabled if there are no intervals specified."/>
415 <param name="disable_read_filter" argument="--disable-read-filter" type="select" multiple="true" value="" label="Disable Read Filter" help="Read filters to be disabled before analysis">
416 <option value="GoodCigarReadFilter">Good cigar string</option>
417 <option value="MappedReadFilter">Mapped read</option>
418 <option value="MappingQualityAvailableReadFilter">Mapping quality available</option>
419 <option value="MappingQualityNotZeroReadFilter">Mapping quality not zero</option>
420 <option value="NonChimericOriginalAlignmentReadFilter">Non-chimeric original alignment</option>
421 <option value="NonZeroReferenceLengthAlignmentReadFilter">Non-zero reference length alignment</option>
422 <option value="NotDuplicateReadFilter">Not a duplicate read</option>
423 <option value="NotSecondaryAlignmentReadFilter">Not a secondary alignment</option>
424 <option value="PassesVendorQualityCheckReadFilter">Passes vendor quality check</option>
425 <option value="WellformedReadFilter">Well-formed read</option>
426 </param>
427 <param name="read_filter" argument="--read-filter" type="select" multiple="true" value="" label="Read Filter" help="Read filters to be applied before analysis">
428 <option value="AlignmentAgreesWithHeaderReadFilter">Alignment agrees with header</option>
429 <option value="AllowAllReadsReadFilter">Allow all reads</option>
430 <option value="AmbiguousBaseReadFilter">Ambiguous base</option>
431 <option value="CigarContainsNoNOperator">Cigar contains no NO operator</option>
432 <option value="FirstOfPairReadFilter">First of pair</option>
433 <option value="GoodCigarReadFilter">Good cigar string</option>
434 <option value="HasReadGroupReadFilter">Has read group</option>
435 <option value="MappedReadFilter">Mapped read</option>
436 <option value="MappingQualityAvailableReadFilter">Mapping quality available</option>
437 <option value="MappingQualityNotZeroReadFilter">Mapping quality not zero</option>
438 <option value="MatchingBasesAndQualsReadFilter">Matching bases and quals</option>
439 <option value="MateDifferentStrandReadFilter">Mate different strand</option>
440 <option value="MateOnSameContigOrNoMappedMateReadFilter">Mate on same contig or no mapped mate</option>
441 <option value="MateUnmappedAndUnmappedReadFilter">Mate unmapped and mapped</option>
442 <option value="MetricsReadFilter">Metrics</option>
443 <option value="NonChimericOriginalAlignmentReadFilter">Non-chimeric original alignment</option>
444 <option value="NonZeroFragmentLengthReadFilter">Non-zero fragment length</option>
445 <option value="NonZeroReferenceLengthAlignmentReadFilter">Non-zero reference length alignment</option>
446 <option value="NotDuplicateReadFilter">Not duplicate</option>
447 <option value="NotOpticalDuplicateReadFilter">Not optical duplicate</option>
448 <option value="NotSecondaryAlignmentReadFilter">Not a secondary alignment</option>
449 <option value="NotSupplementaryAlignmentReadFilter">Not a supplementary alignment</option>
450 <option value="OverclippedReadFilter">Overclipped</option>
451 <option value="PairedReadFilter">Paired</option>
452 <option value="PassesVendorQualityCheckReadFilter">Passes vendor quality check</option>
453 <option value="PrimaryLineReadFilter">Primary line</option>
454 <option value="ProperlyPairedReadFilter">Properly paired</option>
455 <option value="ReadLengthEqualsCigarLengthReadFilter">Read length equals cigar length</option>
456 <option value="SecondOfPairReadFilter">Second of pair</option>
457 <option value="SeqIsStoredReadFilter">Sequence is stored</option>
458 <option value="SoftClippedReadFilter">Soft clipped</option>
459 <option value="ValidAlignmentStartReadFilter">Valid alignment start</option>
460 <option value="ValidAlignmentEndReadFilter">Valid alignment end</option>
461 <option value="WellformedReadFilter">Well-formed read</option>
462 </param>
463 <param name="disable_sequence_dictionary_validation" argument="--disable-sequence-dictionary-validation" type="boolean" truevalue="--disable-sequence-dictionary-validation" falsevalue="" optional="true" checked="false" label="Disable Sequence Dictionary Validation" help="If specified, do not check the sequence dictionaries from our inputs for compatibility. Use at your own risk!"/>
464 <param name="downsampling_stride" argument="--downsampling-stride" type="integer" optional="true" value="1" label="Downsampling Stride" help="Downsample a pool of reads starting within a range of one or more bases."/>
465 <param name="f1r2_max_depth" argument="--f1r2-max-depth" type="integer" optional="true" value="200" label="Sites with depth higher than this value will be grouped" />
466 <param name="f1r2_median_mq" argument="--f1r2-median-mq" type="integer" optional="true" value="50" label="Skip sites with median mapping quality below this value" />
467 <param name="f1r2_min_bq" argument="--base-quality-score-threshold" type="integer" optional="true" value="20" label="Exclude bases below this quality from pileup" />
468 <param name="founder_id" argument="--founder-id" type="text" optional="true" value="" label="Founder Id" help="Samples representing the population &amp;quot;founders&amp;quot;"/>
469 <param name="gcs_max_retries" argument="--gcs-max-retries" type="integer" optional="true" value="20" label="Gcs Max Retries" help="If the GCS bucket channel errors out, how many times it will attempt to re-initiate the connection"/>
470 <param name="genotype_germline_sites" argument="--genotype-germline-sites" type="boolean" truevalue="--genotype-germline-sites" falsevalue="" optional="true" checked="false" label="Genotype Germline Sites" help="(EXPERIMENTAL) Call all apparent germline site even though they will ultimately be filtered."/>
471 <param name="genotype_pon_sites" argument="--genotype-pon-sites" type="boolean" truevalue="--genotype-pon-sites" falsevalue="" optional="true" checked="false" label="Genotype PoN Sites" help="Call sites in the PoN even though they will ultimately be filtered."/>
472 <param name="alleles" argument="--alleles" type="data" optional="true" format="vcf" label="Alleles" help="The set of alleles at which to genotype"/>
473 <param name="germline_resource" argument="--germline-resource" type="data" optional="true" format="vcf,vcf_bgzip" label="Germline Resource" help="Population vcf of germline sequencing containing allele fractions."/>
474 <param name="heterozygosity" argument="--heterozygosity" type="float" optional="true" value="0.001" label="Heterozygosity" help="The expected heterozygosity value used to compute prior probability that a locus is non-reference. The default priors are for provided for humans: het = 1e-3 which means that the probability of N samples being hom-ref at a site is: 1 - sum_i_2N (het / i) Note that heterozygosity as used here is the population genetics concept: http://en.wikipedia.org/wiki/Zygosity#Heterozygosity_in_population_genetics That is, a hets value of 0.01 implies that two randomly chosen chromosomes from the population of organisms would differ from each other (one being A and the other B) at a rate of 1 in 100 bp. Note that this quantity has nothing to do with the likelihood of any given sample having a heterozygous genotype, which in the GATK is purely determined by the probability of the observed data P(D | AB) under the model that there may be a AB het genotype. The posterior probability of this AB genotype would use the het prior, but the GATK only uses this posterior probability in determining the prob. that a site is polymorphic. So changing the het parameters only increases the chance that a site will be called non-reference across all samples, but doesn't actually change the output genotype likelihoods at all, as these aren't posterior probabilities at all. The quantity that changes whether the GATK considers the possibility of a het genotype at all is the ploidy, which determines how many chromosomes each individual in the species carries."/>
475 <param name="heterozygosity_stdev" argument="--heterozygosity-stdev" type="float" optional="true" value="0.01" label="Heterozygosity Stdev" help="Standard deviation of heterozygosity for SNP and indel calling."/>
476 <param name="ignore_itr_artifacts" argument="--ignore-itr-artifacts" type="boolean" truevalue="--ignore-itr-artifacts" falsevalue="" optional="true" checked="false" label="Turn off read transformer that clips artifacts associated with end repair insertions near inverted tandem repeats" />
477 <param name="indel_heterozygosity" argument="--indel-heterozygosity" type="float" optional="true" value="0.000125" label="Indel Heterozygosity" help="Heterozygosity for indel calling. See the GATKDocs for heterozygosity for full details on the meaning of this population genetics concept"/>
478 <param name="initial_tumor_lod" argument="--initial-tumor-lod" type="float" optional="true" value="2.0" label="Initial Tumor Lod" help="LOD threshold to consider pileup active."/>
479 <param name="interval_exclusion_padding" argument="--interval-exclusion-padding" type="integer" value="0" label="Interval exclusion padding" help="Amount of padding (in bp) to add to each interval you are excluding" />
480 <param name="interval_padding" argument="--interval-padding" type="integer" value="0" label="Interval padding" help="Amount of padding (in bp) to add to each interval you are including" />
481 <param name="interval_merging_rule" argument="--interval-merging-rule" type="select" optional="true" label="Interval Merging Rule" help="Interval merging rule for abutting intervals">
482 <option selected="true" value="ALL">All</option>
483 <option value="OVERLAPPING_ONLY">Overlapping only</option>
484 </param>
485 <param name="interval_set_rule" argument="--interval-set-rule" type="select" optional="true" label="Interval Set Rule" help="Set merging approach to use for combining interval inputs">
486 <option selected="true" value="UNION">Union</option>
487 <option value="INTERSECTION">Intersection</option>
488 </param>
489 <param name="lenient" argument="--lenient" type="boolean" truevalue="--lenient" falsevalue="" optional="true" checked="false" label="Lenient" help="Lenient processing of VCF files"/>
490 <param name="max_population_af" argument="--max-population-af" type="float" optional="true" value="0.01" label="Max Population Af" help="Maximum population allele frequency in tumor-only mode."/>
491 <param name="max_reads_per_alignment_start" argument="--max-reads-per-alignment-start" type="integer" optional="true" value="50" label="Max Reads Per Alignment Start" help="Maximum number of reads to retain per alignment start position. Reads above this threshold will be downsampled. Set to 0 to disable."/>
492 <param name="min_base_quality_score" argument="--min-base-quality-score" type="integer" optional="true" value="10" label="Min Base Quality Score" help="Minimum base quality required to consider a base for calling"/>
493 <param name="mitochondria_mode" argument="--mitochondria-mode" type="boolean" truevalue="--mitochondria-mode" falsevalue="" label="Mitochondria mode sets emission and initial LODs to 0" />
494 <param name="native_pair_hmm_use_double_precision" argument="--native-pair-hmm-use-double-precision" type="boolean" truevalue="--native-pair-hmm-use-double-precision" falsevalue="" optional="true" checked="false" label="Native Pair Hmm Use Double Precision" help="use double precision in the native pairHmm. This is slower but matches the java implementation better"/>
495 <param name="normal_lod" argument="--normal-lod" type="float" optional="true" value="2.2" label="Normal Lod" help="LOD threshold for calling normal variant non-germline."/>
496 <param name="normal_sample" argument="--normal-sample" type="text" optional="true" value="" label="Normal Sample" help="BAM sample name of normal. May be URL-encoded as output by GetSampleName with -encode argument."/>
497 <param name="panel_of_normals" argument="--panel-of-normals" type="data" optional="true" format="vcf,vcf_bgzip" label="Panel Of Normals" help="VCF file of sites observed in normal."/>
498 <param name="pcr_indel_qual" argument="--pcr-indel-qual" type="integer" optional="true" value="40" label="Phred-scaled PCR indel qual for overlapping fragments" />
499 <param name="pcr_snv_qual" argument="--pcr-snv-qual" type="integer" optional="true" value="40" label="Phred-scaled PCR SNV qual for overlapping fragments" />
500 <param name="sites_only_vcf_output" argument="--sites-only-vcf-output" type="boolean" truevalue="--sites-only-vcf-output" falsevalue="" optional="true" checked="false" label="Sites Only Vcf Output" help="If true, don&apos;t emit genotype fields when writing vcf file output."/>
501 <param name="read_validation_stringency" argument="--read-validation-stringency" type="select" optional="true" label="Read Validation Stringency" help="Validation stringency for all SAM/BAM/CRAM/SRA files read by this program. The default stringency value SILENT can improve performance when processing a BAM file in which variable-length data (read, qualities, tags) do not otherwise need to be decoded.">
502 <option selected="true" value="SILENT">Silent</option>
503 <option value="STRICT">Strict</option>
504 <option value="LENIENT">Lenient</option>
505 </param>
506 <param name="sites_only_vcf_output" argument="--sites-only-vcf-output" type="boolean" truevalue="--sites-only-vcf-output" falsevalue="" optional="true" checked="false" label="Sites Only Vcf Output" help="If true, don&amp;apos;t emit genotype fields when writing vcf file output."/>
507 <param name="tumor_lod_to_emit" argument="--tumor-lod-to-emit" type="float" optional="true" value="3.0" label="Tumor Lod To Emit" help="LOD threshold to emit tumor variant to VCF."/>
508 </when>
509 <when value="no" />
510 </conditional>
511 <conditional name="advanced">
512 <param name="advanced_parameters" type="select" label="Advanced parameters">
513 <option value="no">Use internal defaults</option>
514 <option value="yes">Specify parameters</option>
515 </param>
516 <when value="yes">
517 <param name="active_probability_threshold" argument="--active-probability-threshold" type="float" optional="true" value="0.002" label="Active Probability Threshold" help="Minimum probability for a locus to be considered active."/>
518 <param name="allow_non_unique_kmers_in_ref" argument="--allow-non-unique-kmers-in-ref" type="boolean" truevalue="--allow-non-unique-kmers-in-ref" falsevalue="" optional="true" checked="false" label="Allow Non Unique Kmers In Ref" help="Allow graphs that have non-unique kmers in the reference"/>
519 <param name="assembly_region_padding" argument="--assembly-region-padding" type="integer" optional="true" value="100" label="Assembly Region Padding" help="Number of additional bases of context to include around each assembly region"/>
520 <param name="bam_writer_type" argument="--bam-writer-type" type="select" optional="true" label="Bam Writer Type" help="Which haplotypes should be written to the BAM">
521 <option selected="true" value="CALLED_HAPLOTYPES">Called haplotypes</option>
522 <option value="ALL_POSSIBLE_HAPLOTYPES">All possible haplotypes</option>
523 </param>
524
525 <param name="disable_adaptive_pruning" argument="--disable-adaptive-pruning" type="boolean" truevalue="--disable-adaptive-pruning" falsevalue="" optional="true" checked="false" label="Disable adaptive pruning" help="Disable the adaptive algorithm for pruning paths in the graph"/>
526 <param name="disable_tool_default_annotations" argument="--disable-tool-default-annotations" type="boolean" truevalue="--disable-tool-default-annotations" falsevalue="" optional="true" checked="false" label="Disable Default Annotations" help="Disable all tool default annotations"/>
527 <param name="disable_tool_default_read_filters" argument="--disable-tool-default-read-filters" type="boolean" truevalue="--disable-tool-default-read-filters" falsevalue="" optional="true" checked="false" label="Disable default read filters" help="WARNING: many tools will not function correctly without their default read filters on"/>
528 <param name="dont_increase_kmer_sizes_for_cycles" argument="--dont-increase-kmer-sizes-for-cycles" type="boolean" truevalue="--dont-increase-kmer-sizes-for-cycles" falsevalue="" optional="true" checked="false" label="Dont Increase Kmer Sizes For Cycles" help="Disable iterating over kmer sizes when graph cycles are detected"/>
529 <param name="dont_trim_active_regions" argument="--dont-trim-active-regions" type="boolean" truevalue="--dont-trim-active-regions" falsevalue="" optional="true" checked="false" label="Dont Trim Active Regions" help="If specified, we will not trim down the active region from the full region (active + extension) to just the active interval for genotyping"/>
530 <param name="dont_use_soft_clipped_bases" argument="--dont-use-soft-clipped-bases" type="boolean" truevalue="--dont-use-soft-clipped-bases" falsevalue="" optional="true" checked="false" label="Dont Use Soft Clipped Bases" help="Do not analyze soft clipped bases in the reads"/>
531 <param name="emit_ref_confidence" argument="--emit-ref-confidence" type="select" label="Mode for emitting reference confidence scores" help="NOTE: This is a beta feature in Mutect2">
532 <option value="NONE">None</option>
533 <option value="BP_RESOLUTION">Basepair resolution</option>
534 <option value="GVCF">Genomic VCF</option>
535 </param>
536 <param name="enable_all_annotations" argument="--enable-all-annotations" type="boolean" truevalue="--enable-all-annotations" falsevalue="" optional="true" checked="false" label="Enable All Annotations" help="Use all possible annotations (not for the faint of heart)"/>
537 <param name="force_active" argument="--force-active" type="boolean" truevalue="--force-active" falsevalue="" optional="true" checked="false" label="Mark all regions active" help="If selected, all regions will be marked as active"/>
538 <param name="force_call_filtered_alleles" argument="--force-call-filtered-alleles" type="boolean" truevalue="--force-call-filtered-alleles" falsevalue="" optional="true" checked="false" label="Force-call filtered alleles" help="Force-call filtered alleles included in the resource specified by --alleles"/>
539 <param name="gvcf_lod_band" argument="--gvcf-lod-band" type="float" optional="true" label="Upper bounds for reference confidence" help="Exclusive upper bounds for reference confidence LOD bands (must be specified in increasing order)" />
540 <param name="independent_mates" argument="--independent-mates" type="boolean" truevalue="--independent-mates" falsevalue="" label="Independent mates" help="Allow paired reads to independently support different haplotypes. Useful for validations with ill-designed synthetic data" />
541 <param name="kmer_size" argument="--kmer-size" type="integer" optional="true" value="" label="Kmer Size" help="Kmer size to use in the read threading assembler"/>
542 <param name="max_assembly_region_size" argument="--max-assembly-region-size" type="integer" optional="true" value="300" label="Max Assembly Region Size" help="Maximum size of an assembly region"/>
543 <param name="max_mnp_distance" argument="--max-mnp-distance" type="integer" optional="true" value="1" label="Max Mnp Distance" help="Two or more phased substitutions separated by this distance or less are merged into MNPs."/>
544 <param name="max_num_haplotypes_in_population" argument="--max-num-haplotypes-in-population" type="integer" optional="true" value="128" label="Max Num Haplotypes In Population" help="Maximum number of haplotypes to consider for your population"/>
545 <param name="max_prob_propagation_distance" argument="--max-prob-propagation-distance" type="integer" optional="true" value="50" label="Max Prob Propagation Distance" help="Upper limit on how many bases away probability mass can be moved around when calculating the boundaries between active and inactive assembly regions"/>
546 <param name="max_suspicious_reads_per_alignment_start" argument="--max-suspicious-reads-per-alignment-start" type="integer" optional="true" value="0" label="Max Suspicious Reads Per Alignment Start" help="Maximum number of suspicious reads (mediocre mapping quality or too many substitutions) allowed in a downsampling stride. Set to 0 to disable."/>
547 <param name="max_unpruned_variants" argument="--max-unpruned-variants" type="integer" optional="true" value="100" label="Maximum number of variants" help="Maximum number of variants in graph the adaptive pruner will allow"/>
548 <param name="min_assembly_region_size" argument="--min-assembly-region-size" type="integer" optional="true" value="50" label="Min Assembly Region Size" help="Minimum size of an assembly region"/>
549 <param name="min_dangling_branch_length" argument="--min-dangling-branch-length" type="integer" optional="true" value="4" label="Min Dangling Branch Length" help="Minimum length of a dangling branch to attempt recovery"/>
550 <param name="min_pruning" argument="--min-pruning" type="integer" optional="true" value="2" label="Min Pruning" help="Minimum support to not prune paths in the graph"/>
551 <param name="minimum_allele_fraction" argument="--minimum-allele-fraction" type="float" optional="true" value="0.0" label="Fractions to consider" help="Lower bound of variant allele fractions to consider when calculating variant LOD"/>
552 <param name="num_pruning_samples" argument="--num-pruning-samples" type="integer" optional="true" value="1" label="Num Pruning Samples" help="Number of samples that must pass the minPruning threshold"/>
553 <param name="pair_hmm_gap_continuation_penalty" argument="--pair-hmm-gap-continuation-penalty" type="integer" optional="true" value="10" label="Pair Hmm Gap Continuation Penalty" help="Flat gap continuation penalty for use in the Pair HMM"/>
554 <param name="pair_hmm_implementation" argument="--pair-hmm-implementation" type="select" optional="true" label="Pair Hmm Implementation" help="The PairHMM implementation to use for genotype likelihood calculations">
555 <option selected="true" value="FASTEST_AVAILABLE">Fastest Available</option>
556 <option value="EXACT">Exact</option>
557 <option value="ORIGINAL">Original</option>
558 <option value="LOGLESS_CACHING">Logless Caching</option>
559 <option value="AVX_LOGLESS_CACHING">Logless Caching (AVX)</option>
560 <option value="AVX_LOGLESS_CACHING_OMP">Logless Caching (AVX+OMP)</option>
561 <option value="EXPERIMENTAL_FPGA_LOGLESS_CACHING">Logless Caching (FPGA, Experimental)</option>
562 </param>
563 <param name="pcr_indel_model" argument="--pcr-indel-model" type="select" optional="true" label="Pcr Indel Model" help="The PCR indel model to use">
564 <option selected="true" value="CONSERVATIVE">Conservative</option>
565 <option value="NONE">None</option>
566 <option value="HOSTILE">Hostile</option>
567 <option value="AGGRESSIVE">Aggressive</option>
568 </param>
569 <param name="phred_scaled_global_read_mismapping_rate" argument="--phred-scaled-global-read-mismapping-rate" type="integer" optional="true" value="45" label="Phred Scaled Global Read Mismapping Rate" help="The global assumed mismapping rate for reads"/>
570 <param name="pruning_lod_threshold" argument="--pruning-lod-threshold" type="float" optional="true" value="2.302585092994046" label="Pruning LOD threshold" help="Likelihood ratio threshold for adaptive pruning algorithm" />
571 <param name="recover_all_dangling_branches" argument="--recover-all-dangling-branches" type="boolean" truevalue="--recover-all-dangling-branches" falsevalue="" label="Recover all dangling branches" />
572 <param name="smith_waterman" argument="--smith-waterman" type="select" optional="true" label="Smith Waterman" help="Which Smith-Waterman implementation to use, generally 'Fastest available' is the right choice">
573 <option selected="true" value="FASTEST_AVAILABLE">Fastest available</option>
574 <option value="AVX_ENABLED">AVX-Enabled</option>
575 <option value="JAVA">JAVA</option>
576 </param>
577 <param name="use_filtered_reads_for_annotations" argument="--use-filtered-reads-for-annotations" type="boolean" truevalue="--use-filtered-reads-for-annotations" falsevalue="" optional="true" checked="false" label="Use Filtered Reads For Annotations" help="Use the contamination-filtered read maps for the purposes of annotating variants"/>
578 </when>
579 <when value="no" />
580 </conditional>
581 <conditional name="outputs">
582 <param name="output_parameters" type="select" label="Output parameters" help="Additional outputs for debugging purposes">
583 <option value="no">Output only variants</option>
584 <option value="yes">Generate debugging information</option>
585 </param>
586 <when value="yes">
587 <param name="debug_activity" argument="--activity-profile-out" type="boolean" checked="false" truevalue="yes" falsevalue="" label="Activity Profile Out" help="Output the raw activity profile results in IGV format"/>
588 <param name="debug_assembly" argument="--assembly-region-out" type="boolean" checked="false" truevalue="yes" falsevalue="" label="Assembly Region Out" help="Output the assembly region to this IGV formatted file"/>
589 <param name="debug_bam" argument="--bam-output" type="boolean" checked="false" truevalue="yes" falsevalue="" label="Bam Output" help="The assembled haplotypes and locally realigned reads will be written as BAM to this file if requested. This is intended to be used only for troubleshooting purposes, in specific areas where you want to better understand why the caller is making specific calls"/>
590 </when>
591 <when value="no" />
592 </conditional>
593 </inputs>
594 <outputs>
595 <expand macro="gzip_vcf_output_params"/>
596 <data format="tabular" name="activity_profile_out" label="${tool.name} on ${on_string}: Activity profile">
597 <filter>str(outputs['output_parameters']) == 'yes' and outputs['debug_activity']</filter>
598 </data>
599 <data format="tabular" name="assembly_region_out" label="${tool.name} on ${on_string}: Assembly region">
600 <filter>str(outputs['output_parameters']) == 'yes' and outputs['debug_assembly']</filter>
601 </data>
602 <data format="bam" name="bam_output" label="${tool.name} on ${on_string}: Debug BAM output">
603 <filter>str(outputs['output_parameters']) == 'yes' and outputs['debug_bam']</filter>
604 </data>
605 </outputs>
606 <tests>
607 <test>
608 <conditional name="mode">
609 <param name="mode_parameters" value="tumor_only"/>
610 <param name="tumor" ftype="bam" value="Mutect2-in1.bam" />
611 </conditional>
612 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
613 <param name="gzipped_output" value="false" />
614 <param name="reference_source_selector" value="history" />
615 <param name="optional_parameters" value="no" />
616 <param name="advanced_parameters" value="no" />
617 <param name="output_parameters" value="no" />
618 <output name="output_vcf" file="Mutect2-out1.vcf" lines_diff="2" />
619 </test>
620 <test>
621 <conditional name="mode">
622 <param name="mode_parameters" value="tumor_only"/>
623 <param name="tumor" ftype="bam" value="Mutect2-in2.bam" />
624 </conditional>
625 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
626 <param name="gzipped_output" value="false" />
627 <param name="reference_source_selector" value="history" />
628 <param name="read_filter" value="AmbiguousBaseReadFilter,FirstOfPairReadFilter,GoodCigarReadFilter" />
629 <param name="seqdict_source" value="history" />
630 <param name="seqdict_sequence" value="Mutect2-in2.dict" />
631 <param name="optional_parameters" value="no" />
632 <param name="advanced_parameters" value="no" />
633 <param name="output_parameters" value="no" />
634 <output name="output_vcf" file="Mutect2-out2.vcf" lines_diff="2" />
635 </test>
636 <test>
637 <conditional name="mode">
638 <param name="mode_parameters" value="tumor_only"/>
639 <param name="tumor" ftype="bam" value="Mutect2-in3.bam" />
640 </conditional>
641 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
642 <param name="gzipped_output" value="false" />
643 <param name="reference_source_selector" value="history" />
644 <param name="optional_parameters" value="yes" />
645 <param name="annotation" value="StrandBiasBySample,BaseQualityHistogram,OrientationBiasReadCounts" />
646 <param name="annotation_group" value="StandardMutectAnnotation" />
647 <param name="advanced_parameters" value="no" />
648 <param name="output_parameters" value="no" />
649 <output name="output_vcf" file="Mutect2-out3.vcf" lines_diff="2" />
650 </test>
651 <test>
652 <conditional name="mode">
653 <param name="mode_parameters" value="tumor_only"/>
654 <param name="tumor" ftype="bam" value="Mutect2-in4.bam" />
655 </conditional>
656 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
657 <param name="gzipped_output" value="false" />
658 <param name="reference_source_selector" value="history" />
659 <param name="optional_parameters" value="yes" />
660 <param name="advanced_parameters" value="yes" />
661 <param name="dont_trim_active_regions" value="true" />
662 <param name="output_parameters" value="no" />
663 <output name="output_vcf" file="Mutect2-out4.vcf" lines_diff="2" />
664 </test>
665 <test>
666 <conditional name="mode">
667 <param name="mode_parameters" value="tumor_only"/>
668 <param name="tumor" ftype="bam" value="Mutect2-in5.bam" />
669 </conditional>
670 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
671 <param name="gzipped_output" value="false" />
672 <param name="reference_source_selector" value="history" />
673 <param name="optional_parameters" value="no" />
674 <param name="advanced_parameters" value="no" />
675 <param name="output_parameters" value="yes" />
676 <param name="debug_activity" value="true" />
677 <param name="debug_assembly" value="true" />
678 <param name="debug_bam" value="true" />
679 <output name="output_vcf" file="Mutect2-out5.vcf" lines_diff="2" />
680 <output name="activity_profile_out" file="Mutect2-out5-1.tabular" />
681 <output name="assembly_region_out" file="Mutect2-out5-2.tabular" />
682 <output name="bam_output" file="Mutect2-out5.bam" />
683 </test>
684 <test>
685 <conditional name="mode">
686 <param name="mode_parameters" value="somatic"/>
687 <param name="tumor" ftype="bam" value="tumor.bam" />
688 <param name="normal" ftype="bam" value="normal.bam" />
689 </conditional>
690 <param name="reference_sequence" ftype="fasta" value="chr20.fa" />
691 <param name="gzipped_output" value="false" />
692 <param name="reference_source_selector" value="history" />
693 <param name="optional_parameters" value="no" />
694 <param name="advanced_parameters" value="no" />
695 <param name="output_parameters" value="no" />
696 <output name="output_vcf" file="Mutect2-out6.vcf" lines_diff="2" />
697 </test>
698 </tests>
699 <help><![CDATA[IMPORTANT: This wrapper constitutes a copy of the developed by the IUC
700 (https://github.com/galaxyproject/tools-iuc/blob/master/tools/gatk4/gatk4_Mutect2.xml).
701 We have introduced some changes for including the BAM files from both normal and tumor
702 samples. However, until these changes are approved, we use this tool by working with a copy
703 of the original wrapper.
704
705 Call somatic short variants via local assembly of haplotypes. Short
706 variants include single nucleotide (SNV) and insertion and deletion
707 (indel) variants. The caller combines the DREAM challenge-winning
708 somatic genotyping engine of the original MuTect (`Cibulskis et al.,
709 2013 <http://www.nature.com/nbt/journal/v31/n3/full/nbt.2514.html>`__)
710 with the assembly-based machinery of
711 `HaplotypeCaller <https://www.broadinstitute.org/gatk/documentation/tooldocs/org_broadinstitute_gatk_tools_walkers_haplotypecaller_HaplotypeCaller.php>`__.
712
713 This tool is featured in the *Somatic Short Mutation calling Best
714 Practice Workflow*. See
715 `Tutorial#11136 <https://software.broadinstitute.org/gatk/documentation/article?id=11136>`__
716 for a step-by-step description of the workflow and
717 `Article#11127 <https://software.broadinstitute.org/gatk/documentation/article?id=11127>`__
718 for an overview of what traditional somatic calling entails. For the
719 latest pipeline scripts, see the `Mutect2 WDL scripts
720 directory <https://github.com/broadinstitute/gatk/tree/master/scripts/mutect2_wdl>`__.
721 Although we present the tool for somatic calling, it may apply to other
722 contexts, such as mitochondrial variant calling.
723
724 Usage examples
725 ~~~~~~~~~~~~~~
726
727 Example commands show how to run Mutect2 for typical scenarios. The two
728 modes are (i) *somatic mode* where a tumor sample is matched with a
729 normal sample in analysis and (ii) *tumor-only mode* where a single
730 sample's alignment data undergoes analysis.
731
732 (i) Tumor with matched normal
733 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
734
735 Given a matched normal, Mutect2 is designed to call somatic variants
736 only. The tool includes logic to skip emitting variants that are clearly
737 present in the germline based on provided evidence, e.g. in the matched
738 normal. This is done at an early stage to avoid spending computational
739 resources on germline events. If the variant's germline status is
740 borderline, then Mutect2 will emit the variant to the callset for
741 subsequent filtering and review.
742
743 ::
744
745 gatk Mutect2 \
746 -R reference.fa \
747 -I tumor.bam \
748 -tumor tumor_sample_name \
749 -I normal.bam \
750 -normal normal_sample_name \
751 --germline-resource af-only-gnomad.vcf.gz \
752 --af-of-alleles-not-in-resource 0.00003125 \
753 --panel-of-normals pon.vcf.gz \
754 -O somatic.vcf.gz
755
756
757 The --af-of-alleles-not-in-resource argument value should match
758 expectations for alleles not found in the provided germline resource.
759 Note the tool does not require a germline resource nor a panel of
760 normals (PoN) to run. The tool prefilters sites for the matched normal
761 and the PoN. For the germline resource, the tool prefilters on the
762 allele. Below is an excerpt of a known variants resource with population
763 allele frequencies
764
765 ::
766
767 #CHROM POS ID REF ALT QUAL FILTER INFO
768 1 10067 . T TAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCC 30.35 PASS AC=3;AF=7.384E-5
769 1 10108 . CAACCCT C 46514.32 PASS AC=6;AF=1.525E-4
770 1 10109 . AACCCTAACCCT AAACCCT,* 89837.27 PASS AC=48,5;AF=0.001223,1.273E-4
771 1 10114 . TAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAACCCTAACCCTAACCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAAACCCTA *,CAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAACCCTAACCCTAACCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAAACCCTA,T 36728.97 PASS AC=55,9,1;AF=0.001373,2.246E-4,2.496E-5
772 1 10119 . CT C,* 251.23 PASS AC=5,1;AF=1.249E-4,2.498E-5
773 1 10120 . TA CA,* 14928.74 PASS AC=10,6;AF=2.5E-4,1.5E-4
774 1 10128 . ACCCTAACCCTAACCCTAAC A,* 285.71 PASS AC=3,1;AF=7.58E-5,2.527E-5
775 1 10131 . CT C,* 378.93 PASS AC=7,5;AF=1.765E-4,1.261E-4
776 1 10132 . TAACCC *,T 18025.11 PASS AC=12,2;AF=3.03E-4,5.049E-5
777
778
779 (ii) Tumor-only mode
780 ^^^^^^^^^^^^^^^^^^^^
781
782 This mode runs on a single sample, e.g. single tumor or single normal
783 sample. To create a PoN, call on each normal sample in this mode, then
784 use CreateSomaticPanelOfNormals to generate the PoN.
785
786 ::
787
788 gatk Mutect2 \
789 -R reference.fa \
790 -I sample.bam \
791 -tumor sample_name \
792 -O single_sample.vcf.gz
793
794
795 Further points of interest
796 ~~~~~~~~~~~~~~~~~~~~~~~~~~
797
798 Additional parameters that factor towards filtering, including
799 normal-artifact-lod (default threshold 0.0) and tumor-lod (default
800 threshold 5.3), are available in FilterMutectCalls. While the tool
801 calculates normal-lod assuming a diploid genotype, it calculates
802 normal-artifact-lod with the same approach it uses for tumor-lod, i.e.
803 with a variable ploidy assumption.
804
805 - If the normal artifact log odds becomes large, then FilterMutectCalls applies the artifact-in-normal filter. For matched normal samples with tumor contamination, consider increasing the normal-artifact-lod threshold.
806
807 - The tumor log odds, which is calculated independently of any matched normal, determines whether to filter a tumor variant. Variants with tumor LODs exceeding the threshold pass filtering.
808
809
810 If a variant is absent from a given germline resource, then the value
811 for --af-of-alleles-not-in-resource applies. For example, gnomAD's
812 16,000 samples (~32,000 homologs per locus) becomes a probability of one
813 in 32,000 or less. Thus, an allele's absence from the germline resource
814 becomes evidence that it is not a germline variant.
815
816 Caveats
817 ~~~~~~~
818
819 Although GATK4 Mutect2 accomodates varying coverage depths, further
820 optimization of parameters may improve calling for extreme high depths,
821 e.g. 1000X.
822 ]]></help>
823 <citations>
824 <expand macro="citations"/>
825 </citations>
826 </tool>