Mercurial > repos > iuc > gatk4_mutect2

comparison gatk4_Mutect2.xml @ 0:f41a1e03538b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/gatk4 commit f9d04b348a43a799ab1624d3a7b211aab55ae522"
author iuc
date Wed, 30 Oct 2019 15:33:59 -0400
parents
children fd2d6e035c3f
comparison
equal deleted inserted replaced
-1:000000000000 0:f41a1e03538b
1 <tool id="gatk4_mutect2" name="GATK4 Mutect2" version="@WRAPPER_VERSION@0" 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=$bam_index_pre_chth#
13 #include source=$pre_gatk_ints_chth#
14
15 #set ref_flag='--reference="reference.fa"'
16
17 #if str($reference_source.reference_source_selector) == 'history'
18 ln -s '$reference_source.reference_sequence' reference.fa &&
19 samtools faidx reference.fa &&
20 gatk CreateSequenceDictionary --REFERENCE="reference.fa" --OUTPUT="reference.dict" &&
21 #else if str($reference_source.reference_source_selector) == 'history'
22 ln -s '$reference_source.reference_sequence.fields.path' reference.fa &&
23 samtools faidx reference.fa &&
24 gatk CreateSequenceDictionary --REFERENCE="reference.fa" --OUTPUT="reference.dict" &&
25 #else
26 #set ref_flag=''
27 #end if
28
29 #if str($outputs.output_parameters) == 'yes'
30 #if str($outputs.debug_activity) == 'yes'
31 ln -s '$activity_profile_out' activity-profile.tab &&
32 #end if
33 #if str($outputs.debug_assembly) == 'yes'
34 ln -s '$assembly_region_out' assembly-region.tab &&
35 #end if
36 #if str($outputs.debug_bam) == 'yes'
37 ln -s '$bam_output' debug.bam &&
38 #end if
39 #end if
40
41 @CMD_BEGIN@ GetSampleName --input="input.bam" --output="samplename.txt" &&
42 sample=`cat samplename.txt` &&
43
44 #if str($optional.optional_parameters) == 'yes'
45 #if $optional.panel_of_normals
46 #set datatype = $optional.panel_of_normals.datatype
47 #if $optional.panel_of_normals.is_of_type("vcf_bgzip")
48 ln -s '$optional.panel_of_normals' panel_of_normals.vcf.gz &&
49 tabix panel_of_normals.vcf.gz &&
50 #else
51 ln -s '$optional.panel_of_normals' panel_of_normals.vcf &&
52 #end if
53 #end if
54
55 #if $optional.germline_resource
56 #set datatype = $optional.germline_resource.datatype
57 #if $optional.germline_resource.is_of_type("vcf_bgzip")
58 ln -s '$optional.germline_resource' germline_resource.vcf.gz &&
59 tabix germline_resource.vcf.gz &&
60 #else
61 ln -s '$optional.germline_resource' germline_resource.vcf &&
62 #end if
63 #end if
64
65 #if $optional.population_callset
66 #set datatype = $optional.population_callset.datatype
67 #if $optional.population_callset.is_of_type("vcf_bgzip")
68 ln -s '$optional.population_callset' population_callset.vcf.gz &&
69 tabix population_callset.vcf.gz &&
70 #else
71 ln -s '$optional.population_callset' population_callset.vcf &&
72 #end if
73 #end if
74
75 #if $optional.alleles
76 #set datatype = $optional.alleles.datatype
77 #if $optional.alleles.is_of_type("vcf_bgzip")
78 ln -s '$optional.alleles' alleles.vcf.gz &&
79 tabix alleles.vcf.gz &&
80 @CMD_BEGIN@ IndexFeatureFile --feature-file alleles.vcf.gz &&
81 #else
82 ln -s '$optional.alleles' alleles.vcf &&
83 @CMD_BEGIN@ IndexFeatureFile --feature-file alleles.vcf &&
84 #end if
85 #end if
86
87 #end if
88
89 @CMD_BEGIN@ Mutect2 --QUIET $ref_flag --tumor-sample \$sample
90
91 #include source=$gatk_bam_input#
92
93 ## COMMON PARAMETERS ##
94
95 #if str($common.common_parameters) == 'yes'
96
97 #if $common.read_filter
98 #for $filter in str($common.read_filter).split(',')
99 --read-filter="$filter"
100 #end for
101 #end if
102
103 #if $common.disable_read_filter
104 #for $filter in str($common.disable_read_filter).split(',')
105 --disable-read-filter="$filter"
106 #end for
107 #end if
108
109 --verbosity="ERROR"
110 --read-validation-stringency="$common.read_validation_stringency"
111 --interval-set-rule="$common.interval_set_rule"
112 $common.lenient
113 $common.disable_tool_default_read_filters
114 $common.add_output_sam_program_record
115 $common.add_output_vcf_command_line
116
117 #end if
118
119 ## END COMMON PARAMETERS ##
120
121 ## OPTIONAL PARAMETERS ##
122
123 #if str($optional.optional_parameters) == 'yes'
124
125 #if $optional.panel_of_normals
126 #if $optional.panel_of_normals.is_of_type("vcf_bgzip")
127 --panel-of-normals panel_of_normals.vcf.gz
128 #else
129 --panel-of-normals panel_of_normals.vcf
130 #end if
131 #end if
132
133 #if $optional.pedigree
134 --pedigree="$optional.pedigree"
135 #end if
136
137 #if $optional.germline_resource
138 #if $optional.germline_resource.is_of_type("vcf_bgzip")
139 --germline-resource germline_resource.vcf.gz
140 #else
141 --germline-resource germline_resource.vcf
142 #end if
143 #end if
144
145 #if $optional.annotation
146 #for $annot in str($optional.annotation).split(',')
147 --annotation="$annot"
148 #end for
149 #end if
150
151 #if $optional.annotation_group
152 #for $annot in str($optional.annotation_group).split(',')
153 --annotation-group="$annot"
154 #end for
155 #end if
156
157 #if $optional.annotations_to_exclude
158 #for $annot in str($optional.annotations_to_exclude).split(',')
159 --annotations-to-exclude="$annot"
160 #end for
161 #end if
162
163 #if $optional.founder_id
164 --founder-id="$optional.founder_id"
165 #end if
166
167 #if $optional.normal_sample
168 --normal-sample="$optional.normal_sample"
169 #end if
170
171 #if $optional.alleles
172 --alleles alleles.vcf
173 #end if
174
175 --base-quality-score-threshold="$optional.base_quality_score_threshold"
176 --af-of-alleles-not-in-resource="$optional.af_of_alleles_not_in_resource"
177 --downsampling-stride="$optional.downsampling_stride"
178 --gcs-max-retries="$optional.gcs_max_retries"
179 --initial-tumor-lod="$optional.initial_tumor_lod"
180 --interval-merging-rule="$optional.interval_merging_rule"
181 --max-population-af="$optional.max_population_af"
182 --max-reads-per-alignment-start="$optional.max_reads_per_alignment_start"
183 --min-base-quality-score="$optional.min_base_quality_score"
184 --native-pair-hmm-threads="\${GALAXY_SLOTS:-1}"
185 --normal-lod="$optional.normal_lod"
186 --tumor-lod-to-emit="$optional.tumor_lod_to_emit"
187 $optional.annotate_with_num_discovered_alleles
188 $optional.disable_bam_index_caching
189 $optional.disable_sequence_dictionary_validation
190 $optional.genotype_germline_sites
191 $optional.genotype_pon_sites
192 $optional.native_pair_hmm_use_double_precision
193 $optional.sites_only_vcf_output
194 $optional.use_new_qual_calculator
195 #end if
196
197 ## END OPTIONAL PARAMETERS ##
198
199 ## ADVANCED PARAMETERS ##
200
201 #if str($advanced.advanced_parameters) == 'yes'
202
203 #if $advanced.input_prior
204 --input-prior="$advanced.input_prior"
205 #end if
206
207 #if $advanced.kmer_size
208 --kmer-size="$advanced.kmer_size"
209 #end if
210
211 --active-probability-threshold="$advanced.active_probability_threshold"
212 --assembly-region-padding="$advanced.assembly_region_padding"
213 --bam-writer-type="$advanced.bam_writer_type"
214 --max-assembly-region-size="$advanced.max_assembly_region_size"
215 --max-mnp-distance="$advanced.max_mnp_distance"
216 --max-num-haplotypes-in-population="$advanced.max_num_haplotypes_in_population"
217 --max-prob-propagation-distance="$advanced.max_prob_propagation_distance"
218 --max-suspicious-reads-per-alignment-start="$advanced.max_suspicious_reads_per_alignment_start"
219 --min-assembly-region-size="$advanced.min_assembly_region_size"
220 --min-dangling-branch-length="$advanced.min_dangling_branch_length"
221 --min-pruning="$advanced.min_pruning"
222 --num-pruning-samples="$advanced.num_pruning_samples"
223 --pair-hmm-gap-continuation-penalty="$advanced.pair_hmm_gap_continuation_penalty"
224 --pair-hmm-implementation="$advanced.pair_hmm_implementation"
225 --pcr-indel-model="$advanced.pcr_indel_model"
226 --phred-scaled-global-read-mismapping-rate="$advanced.phred_scaled_global_read_mismapping_rate"
227 --smith-waterman="$advanced.smith_waterman"
228 $advanced.all_site_pls
229 $advanced.allow_non_unique_kmers_in_ref
230 $advanced.consensus
231 $advanced.disable_tool_default_annotations
232 $advanced.do_not_run_physical_phasing
233 $advanced.dont_increase_kmer_sizes_for_cycles
234 $advanced.dont_trim_active_regions
235 $advanced.dont_use_soft_clipped_bases
236 $advanced.enable_all_annotations
237 $advanced.genotype_filtered_alleles
238 $advanced.use_filtered_reads_for_annotations
239
240 #end if
241
242 ## END ADVANCED PARAMETERS ##
243
244 ## ADDITIONAL OUTPUT PARAMETERS ##
245
246 #if str($outputs.output_parameters) == 'yes'
247 #if str($outputs.debug_activity) == 'yes'
248 --activity-profile-out="activity-profile.tab"
249 #end if
250 #if str($outputs.debug_assembly) == 'yes'
251 --assembly-region-out="assembly-region.tab"
252 #end if
253 #if str($outputs.debug_bam) == 'yes'
254 --bam-output="debug.bam"
255 #end if
256 #end if
257
258 #include source=$gatk_excl_ints_chth#
259 #include source=$gatk_ints_chth#
260 #include source=$vcf_output_opts#
261 #include source=$gatk_seqdict#
262 ]]>
263 </command>
264 <inputs>
265 <expand macro="gatk_bam_req_params"/>
266 <expand macro="gzip_vcf_params"/>
267 <expand macro="ref_sel"/>
268 <conditional name="common">
269 <param name="common_parameters" type="select" label="Common parameters">
270 <option value="no">Use internal defaults</option>
271 <option value="yes">Specify parameters</option>
272 </param>
273 <when value="yes">
274 <expand macro="gatk_excl_ints"/>
275 <expand macro="seq_dict_sel"/>
276 <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."/>
277 <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."/>
278 <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">
279 <option value="GoodCigarReadFilter">Good cigar string</option>
280 <option value="MappedReadFilter">Mapped read</option>
281 <option value="MappingQualityAvailableReadFilter">Mapping quality available</option>
282 <option value="MappingQualityNotZeroReadFilter">Mapping quality not zero</option>
283 <option value="NonChimericOriginalAlignmentReadFilter">Non-chimeric original alignment</option>
284 <option value="NonZeroReferenceLengthAlignmentReadFilter">Non-zero reference length alignment</option>
285 <option value="NotDuplicateReadFilter">Not a duplicate read</option>
286 <option value="NotSecondaryAlignmentReadFilter">Not a secondary alignment</option>
287 <option value="PassesVendorQualityCheckReadFilter">Passes vendor quality check</option>
288 <option value="WellformedReadFilter">Well-formed read</option>
289 </param>
290 <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 Tool Default Read Filters" help="Disable all tool default read filters (WARNING: many tools will not function correctly without their default read filters on)"/>
291 <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">
292 <option selected="true" value="UNION">Union</option>
293 <option value="INTERSECTION">Intersection</option>
294 </param>
295 <param name="lenient" argument="--lenient" type="boolean" truevalue="--lenient" falsevalue="" optional="true" checked="false" label="Lenient" help="Lenient processing of VCF files"/>
296 <param name="read_filter" argument="--read-filter" type="select" multiple="true" value="" label="Read Filter" help="Read filters to be applied before analysis">
297 <option value="AlignmentAgreesWithHeaderReadFilter">Alignment agrees with header</option>
298 <option value="AllowAllReadsReadFilter">Allow all reads</option>
299 <option value="AmbiguousBaseReadFilter">Ambiguous base</option>
300 <option value="CigarContainsNoNOperator">Cigar contains no NO operator</option>
301 <option value="FirstOfPairReadFilter">First of pair</option>
302 <option value="GoodCigarReadFilter">Good cigar string</option>
303 <option value="HasReadGroupReadFilter">Has read group</option>
304 <option value="MappedReadFilter">Mapped read</option>
305 <option value="MappingQualityAvailableReadFilter">Mapping quality available</option>
306 <option value="MappingQualityNotZeroReadFilter">Mapping quality not zero</option>
307 <option value="MatchingBasesAndQualsReadFilter">Matching bases and quals</option>
308 <option value="MateDifferentStrandReadFilter">Mate different strand</option>
309 <option value="MateOnSameContigOrNoMappedMateReadFilter">Mate on same contig or no mapped mate</option>
310 <option value="MateUnmappedAndUnmappedReadFilter">Mate unmapped and mapped</option>
311 <option value="MetricsReadFilter">Metrics</option>
312 <option value="NonChimericOriginalAlignmentReadFilter">Non-chimeric original alignment</option>
313 <option value="NonZeroFragmentLengthReadFilter">Non-zero fragment length</option>
314 <option value="NonZeroReferenceLengthAlignmentReadFilter">Non-zero reference length alignment</option>
315 <option value="NotDuplicateReadFilter">Not duplicate</option>
316 <option value="NotOpticalDuplicateReadFilter">Not optical duplicate</option>
317 <option value="NotSecondaryAlignmentReadFilter">Not a secondary alignment</option>
318 <option value="NotSupplementaryAlignmentReadFilter">Not a supplementary alignment</option>
319 <option value="OverclippedReadFilter">Overclipped</option>
320 <option value="PairedReadFilter">Paired</option>
321 <option value="PassesVendorQualityCheckReadFilter">Passes vendor quality check</option>
322 <option value="PrimaryLineReadFilter">Primary line</option>
323 <option value="ProperlyPairedReadFilter">Properly paired</option>
324 <option value="ReadLengthEqualsCigarLengthReadFilter">Read length equals cigar length</option>
325 <option value="SecondOfPairReadFilter">Second of pair</option>
326 <option value="SeqIsStoredReadFilter">Sequence is stored</option>
327 <option value="SoftClippedReadFilter">Soft clipped</option>
328 <option value="ValidAlignmentStartReadFilter">Valid alignment start</option>
329 <option value="ValidAlignmentEndReadFilter">Valid alignment end</option>
330 <option value="WellformedReadFilter">Well-formed read</option>
331 </param>
332 <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.">
333 <option selected="true" value="SILENT">Silent</option>
334 <option value="STRICT">Strict</option>
335 <option value="LENIENT">Lenient</option>
336 </param>
337 </when>
338 <when value="no" />
339 </conditional>
340 <conditional name="optional">
341 <param name="optional_parameters" type="select" label="Optional parameters">
342 <option value="no">Use internal defaults</option>
343 <option value="yes">Specify parameters</option>
344 </param>
345 <when value="yes">
346 <expand macro="gatk_ints"/>
347 <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."/>
348 <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"/>
349 <param argument="--annotation" type="select" multiple="true" label="Annotations" help="One or more specific annotations to add to variant calls">
350 <option value="AlleleFraction">AlleleFraction</option>
351 <option value="AS_BaseQualityRankSumTest">AS_BaseQualityRankSumTest</option>
352 <option value="AS_FisherStrand">AS_FisherStrand</option>
353 <option value="AS_InbreedingCoeff">AS_InbreedingCoeff</option>
354 <option value="AS_MappingQualityRankSumTest">AS_MappingQualityRankSumTest</option>
355 <option value="AS_QualByDepth">AS_QualByDepth</option>
356 <option value="AS_ReadPosRankSumTest">AS_ReadPosRankSumTest</option>
357 <option value="AS_RMSMappingQuality">AS_RMSMappingQuality</option>
358 <option value="AS_StrandOddsRatio">AS_StrandOddsRatio</option>
359 <option value="BaseQuality">BaseQuality</option>
360 <option value="BaseQualityHistogram">BaseQualityHistogram</option>
361 <option value="BaseQualityRankSumTest">BaseQualityRankSumTest</option>
362 <option value="ChromosomeCounts">ChromosomeCounts</option>
363 <option value="ClippingRankSumTest">ClippingRankSumTest</option>
364 <option value="CountNs">CountNs</option>
365 <option value="Coverage">Coverage</option>
366 <option value="DepthPerAlleleBySample">DepthPerAlleleBySample</option>
367 <option value="DepthPerSampleHC">DepthPerSampleHC</option>
368 <option value="ExcessHet">ExcessHet</option>
369 <option value="FisherStrand">FisherStrand</option>
370 <option value="FragmentLength">FragmentLength</option>
371 <option value="GenotypeSummaries">GenotypeSummaries</option>
372 <option value="InbreedingCoeff">InbreedingCoeff</option>
373 <option value="LikelihoodRankSumTest">LikelihoodRankSumTest</option>
374 <option value="MappingQuality">MappingQuality</option>
375 <option value="MappingQualityRankSumTest">MappingQualityRankSumTest</option>
376 <option value="MappingQualityZero">MappingQualityZero</option>
377 <option value="OrientationBiasReadCounts">OrientationBiasReadCounts</option>
378 <option value="OriginalAlignment">OriginalAlignment</option>
379 <option value="PossibleDeNovo">PossibleDeNovo</option>
380 <option value="QualByDepth">QualByDepth</option>
381 <option value="ReadPosition">ReadPosition</option>
382 <option value="ReadPosRankSumTest">ReadPosRankSumTest</option>
383 <option value="ReferenceBases">ReferenceBases</option>
384 <option value="RMSMappingQuality">RMSMappingQuality</option>
385 <option value="SampleList">SampleList</option>
386 <option value="StrandBiasBySample">StrandBiasBySample</option>
387 <option value="StrandOddsRatio">StrandOddsRatio</option>
388 <option value="TandemRepeat">TandemRepeat</option>
389 <option value="UniqueAltReadCount">UniqueAltReadCount</option>
390 </param>
391 <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">
392 <option value="AlleleSpecificAnnotation">AlleleSpecificAnnotation</option>
393 <option value="AS_StandardAnnotation">AS_StandardAnnotation</option>
394 <option value="ReducibleAnnotation">ReducibleAnnotation</option>
395 <option value="StandardAnnotation">StandardAnnotation</option>
396 <option value="StandardHCAnnotation">StandardHCAnnotation</option>
397 <option value="StandardMutectAnnotation">StandardMutectAnnotation</option>
398 </param>
399 <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">
400 <option value="AlleleFraction">AlleleFraction</option>
401 <option value="AS_BaseQualityRankSumTest">AS_BaseQualityRankSumTest</option>
402 <option value="AS_FisherStrand">AS_FisherStrand</option>
403 <option value="AS_InbreedingCoeff">AS_InbreedingCoeff</option>
404 <option value="AS_MappingQualityRankSumTest">AS_MappingQualityRankSumTest</option>
405 <option value="AS_QualByDepth">AS_QualByDepth</option>
406 <option value="AS_ReadPosRankSumTest">AS_ReadPosRankSumTest</option>
407 <option value="AS_RMSMappingQuality">AS_RMSMappingQuality</option>
408 <option value="AS_StrandOddsRatio">AS_StrandOddsRatio</option>
409 <option value="BaseQuality">BaseQuality</option>
410 <option value="BaseQualityHistogram">BaseQualityHistogram</option>
411 <option value="BaseQualityRankSumTest">BaseQualityRankSumTest</option>
412 <option value="ChromosomeCounts">ChromosomeCounts</option>
413 <option value="ClippingRankSumTest">ClippingRankSumTest</option>
414 <option value="CountNs">CountNs</option>
415 <option value="Coverage">Coverage</option>
416 <option value="DepthPerAlleleBySample">DepthPerAlleleBySample</option>
417 <option value="DepthPerSampleHC">DepthPerSampleHC</option>
418 <option value="ExcessHet">ExcessHet</option>
419 <option value="FisherStrand">FisherStrand</option>
420 <option value="FragmentLength">FragmentLength</option>
421 <option value="GenotypeSummaries">GenotypeSummaries</option>
422 <option value="InbreedingCoeff">InbreedingCoeff</option>
423 <option value="LikelihoodRankSumTest">LikelihoodRankSumTest</option>
424 <option value="MappingQuality">MappingQuality</option>
425 <option value="MappingQualityRankSumTest">MappingQualityRankSumTest</option>
426 <option value="MappingQualityZero">MappingQualityZero</option>
427 <option value="OrientationBiasReadCounts">OrientationBiasReadCounts</option>
428 <option value="OriginalAlignment">OriginalAlignment</option>
429 <option value="PossibleDeNovo">PossibleDeNovo</option>
430 <option value="QualByDepth">QualByDepth</option>
431 <option value="ReadPosition">ReadPosition</option>
432 <option value="ReadPosRankSumTest">ReadPosRankSumTest</option>
433 <option value="ReferenceBases">ReferenceBases</option>
434 <option value="RMSMappingQuality">RMSMappingQuality</option>
435 <option value="SampleList">SampleList</option>
436 <option value="StrandBiasBySample">StrandBiasBySample</option>
437 <option value="StrandOddsRatio">StrandOddsRatio</option>
438 <option value="TandemRepeat">TandemRepeat</option>
439 <option value="UniqueAltReadCount">UniqueAltReadCount</option>
440 </param>
441 <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."/>
442 <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)"/>
443 <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"/>
444 <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."/>
445 <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!"/>
446 <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."/>
447 <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;"/>
448 <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"/>
449 <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."/>
450 <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."/>
451 <param name="alleles" argument="--alleles" type="data" optional="true" format="vcf" label="Alleles" help="The set of alleles at which to genotype"/>
452 <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."/>
453 <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."/>
454 <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."/>
455 <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"/>
456 <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."/>
457 <param name="interval_merging_rule" argument="--interval-merging-rule" type="select" optional="true" label="Interval Merging Rule" help="Interval merging rule for abutting intervals">
458 <option selected="true" value="ALL">All</option>
459 <option value="OVERLAPPING_ONLY">Overlapping only</option>
460 </param>
461 <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."/>
462 <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."/>
463 <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"/>
464 <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"/>
465 <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."/>
466 <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."/>
467 <param name="num_reference_samples_if_no_call" argument="--num-reference-samples-if-no-call" type="integer" optional="true" value="0" label="Num Reference Samples If No Call" help="Number of hom-ref genotypes to infer at sites not present in a panel"/>
468 <param name="output_mode" argument="--output-mode" type="select" optional="true" label="Output Mode" help="Specifies which type of calls we should output">
469 <option selected="true" value="EMIT_VARIANTS_ONLY">Variants only</option>
470 <option value="EMIT_ALL_CONFIDENT_SITES">All confident sites</option>
471 <option value="EMIT_ALL_SITES">All sites</option>
472 </param>
473 <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."/>
474 <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."/>
475 <param name="population_callset" argument="--population-callset" type="data" optional="true" format="" label="Population Callset" help="Callset to use in calculating genotype priors"/>
476 <param name="sample_ploidy" argument="--sample-ploidy" type="integer" optional="true" value="2" label="Sample Ploidy" help="Ploidy (number of chromosomes) per sample. For pooled data, set to (Number of samples in each pool * Sample Ploidy)."/>
477 <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."/>
478 <param name="standard_min_confidence_threshold_for_calling" argument="--standard-min-confidence-threshold-for-calling" type="float" optional="true" value="10.0" label="Standard Min Confidence Threshold For Calling" help="The minimum phred-scaled confidence threshold at which variants should be called"/>
479 <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."/>
480 <param name="use_new_qual_calculator" argument="--use-new-qual-calculator" type="boolean" truevalue="--use-new-qual-calculator" falsevalue="" optional="true" checked="false" label="Use New Qual Calculator" help="If provided, we will use the new AF model instead of the so-called exact model"/>
481 </when>
482 <when value="no" />
483 </conditional>
484 <conditional name="advanced">
485 <param name="advanced_parameters" type="select" label="Advanced parameters">
486 <option value="no">Use internal defaults</option>
487 <option value="yes">Specify parameters</option>
488 </param>
489 <when value="yes">
490 <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."/>
491 <param name="all_site_pls" argument="--all-site-pls" type="boolean" truevalue="--all-site-pls" falsevalue="" optional="true" checked="false" label="All Site Pls" help="Annotate all sites with PLs"/>
492 <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"/>
493 <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"/>
494 <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">
495 <option selected="true" value="CALLED_HAPLOTYPES">Called haplotypes</option>
496 <option value="ALL_POSSIBLE_HAPLOTYPES">All possible haplotypes</option>
497 </param>
498 <param name="consensus" argument="--consensus" type="boolean" truevalue="--consensus" falsevalue="" optional="true" checked="false" label="Consensus" help="1000G consensus mode"/>
499 <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 Tool Default Annotations" help="Disable all tool default annotations"/>
500 <param name="do_not_run_physical_phasing" argument="--do-not-run-physical-phasing" type="boolean" truevalue="--do-not-run-physical-phasing" falsevalue="" optional="true" checked="false" label="Do Not Run Physical Phasing" help="Disable physical phasing"/>
501 <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"/>
502 <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"/>
503 <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"/>
504 <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)"/>
505 <param name="genotype_filtered_alleles" argument="--genotype-filtered-alleles" type="boolean" truevalue="--genotype-filtered-alleles" falsevalue="" optional="true" checked="false" label="Genotype Filtered Alleles" help="Whether to genotype all given alleles, even filtered ones, --genotyping_mode is GENOTYPE_GIVEN_ALLELES"/>
506 <param name="input_prior" argument="--input-prior" type="float" optional="true" value="" label="Input Prior" help="By default, the prior specified with the heterozygosity argument is used for variant discovery at a particular locus, using an infinite sites model, see e.g. Waterson (1975) or Tajima (1996). This model asserts that the probability of having a population of k variant sites in N chromosomes is proportional to theta/k, for 1=1:N There are instances where using this prior might not be desireable, e.g. for population studies where prior might not be appropriate, as for example when the ancestral status of the reference allele is not known. By using this argument, user can manually specify priors to be used for calling as a vector for doubles, with the following restriciotns: a) User must specify 2N values, where N is the number of samples. b) Only diploid calls supported. c) Probability values are specified in double format, in linear space. d) No negative values allowed. e) Values will be added and Pr(AC=0) will be 1-sum, so that they sum up to one. f) If user-defined values add to more than one, an error will be produced. If user wants completely flat priors, then user should specify the same value (=1/(2*N+1)) 2*N times,e.g. -inputPrior 0.33 -inputPrior 0.33 for the single-sample diploid case."/>
507 <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"/>
508 <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"/>
509 <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."/>
510 <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"/>
511 <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"/>
512 <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."/>
513 <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"/>
514 <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"/>
515 <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"/>
516 <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"/>
517 <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"/>
518 <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">
519 <option selected="true" value="FASTEST_AVAILABLE">Fastest Available</option>
520 <option value="EXACT">Exact</option>
521 <option value="ORIGINAL">Original</option>
522 <option value="LOGLESS_CACHING">Logless Caching</option>
523 <option value="AVX_LOGLESS_CACHING">Logless Caching (AVX)</option>
524 <option value="AVX_LOGLESS_CACHING_OMP">Logless Caching (AVX+OMP)</option>
525 <option value="EXPERIMENTAL_FPGA_LOGLESS_CACHING">Logless Caching (FPGA, Experimental)</option>
526 </param>
527 <param name="pcr_indel_model" argument="--pcr-indel-model" type="select" optional="true" label="Pcr Indel Model" help="The PCR indel model to use">
528 <option selected="true" value="CONSERVATIVE">Conservative</option>
529 <option value="NONE">None</option>
530 <option value="HOSTILE">Hostile</option>
531 <option value="AGGRESSIVE">Aggressive</option>
532 </param>
533 <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"/>
534 <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">
535 <option selected="true" value="FASTEST_AVAILABLE">Fastest available</option>
536 <option value="AVX_ENABLED">AVX-Enabled</option>
537 <option value="JAVA">JAVA</option>
538 </param>
539 <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"/>
540 </when>
541 <when value="no" />
542 </conditional>
543 <conditional name="outputs">
544 <param name="output_parameters" type="select" label="Output parameters" help="Additional outputs for debugging purposes">
545 <option value="no">Output only variants</option>
546 <option value="yes">Generate debugging information</option>
547 </param>
548 <when value="yes">
549 <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"/>
550 <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"/>
551 <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"/>
552 </when>
553 <when value="no" />
554 </conditional>
555 </inputs>
556 <outputs>
557 <expand macro="gzip_vcf_output_params"/>
558 <data format="tabular" name="activity_profile_out" label="${tool.name} on ${on_string}: Activity profile">
559 <filter>str(outputs['output_parameters']) == 'yes' and outputs['debug_activity']</filter>
560 </data>
561 <data format="tabular" name="assembly_region_out" label="${tool.name} on ${on_string}: Assembly region">
562 <filter>str(outputs['output_parameters']) == 'yes' and outputs['debug_assembly']</filter>
563 </data>
564 <data format="bam" name="bam_output" label="${tool.name} on ${on_string}: Debug BAM output">
565 <filter>str(outputs['output_parameters']) == 'yes' and outputs['debug_bam']</filter>
566 </data>
567 </outputs>
568 <tests>
569 <test>
570 <param name="input" ftype="bam" value="Mutect2-in1.bam" />
571 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
572 <param name="gzipped_output" value="false" />
573 <param name="reference_source_selector" value="history" />
574 <param name="common_parameters" value="no" />
575 <param name="optional_parameters" value="no" />
576 <param name="advanced_parameters" value="no" />
577 <param name="output_parameters" value="no" />
578 <output name="output_vcf" file="Mutect2-out1.vcf" lines_diff="2" />
579 </test>
580 <test>
581 <param name="input" ftype="bam" value="Mutect2-in2.bam" />
582 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
583 <param name="gzipped_output" value="false" />
584 <param name="reference_source_selector" value="history" />
585 <param name="common_parameters" value="yes" />
586 <param name="read_filter" value="AmbiguousBaseReadFilter,FirstOfPairReadFilter,GoodCigarReadFilter" />
587 <param name="seqdict_source" value="history" />
588 <param name="seqdict_sequence" value="Mutect2-in2.dict" />
589 <param name="optional_parameters" value="no" />
590 <param name="advanced_parameters" value="no" />
591 <param name="output_parameters" value="no" />
592 <output name="output_vcf" file="Mutect2-out2.vcf" lines_diff="2" />
593 </test>
594 <test>
595 <param name="input" ftype="bam" value="Mutect2-in3.bam" />
596 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
597 <param name="gzipped_output" value="false" />
598 <param name="reference_source_selector" value="history" />
599 <param name="common_parameters" value="no" />
600 <param name="optional_parameters" value="yes" />
601 <param name="annotation" value="StrandBiasBySample,BaseQualityHistogram,OrientationBiasReadCounts" />
602 <param name="annotation_group" value="StandardMutectAnnotation" />
603 <param name="advanced_parameters" value="no" />
604 <param name="output_parameters" value="no" />
605 <output name="output_vcf" file="Mutect2-out3.vcf" lines_diff="2" />
606 </test>
607 <test>
608 <param name="input" ftype="bam" value="Mutect2-in4.bam" />
609 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
610 <param name="gzipped_output" value="false" />
611 <param name="reference_source_selector" value="history" />
612 <param name="common_parameters" value="no" />
613 <param name="optional_parameters" value="yes" />
614 <param name="advanced_parameters" value="yes" />
615 <param name="dont_trim_active_regions" value="true" />
616 <param name="output_parameters" value="no" />
617 <output name="output_vcf" file="Mutect2-out4.vcf" lines_diff="2" />
618 </test>
619 <test>
620 <param name="input" ftype="bam" value="Mutect2-in5.bam" />
621 <param name="reference_sequence" ftype="fasta" value="reference.fa" />
622 <param name="gzipped_output" value="false" />
623 <param name="reference_source_selector" value="history" />
624 <param name="common_parameters" value="no" />
625 <param name="optional_parameters" value="no" />
626 <param name="advanced_parameters" value="no" />
627 <param name="output_parameters" value="yes" />
628 <param name="debug_activity" value="true" />
629 <param name="debug_assembly" value="true" />
630 <param name="debug_bam" value="true" />
631 <output name="output_vcf" file="Mutect2-out5.vcf" lines_diff="2" />
632 <output name="activity_profile_out" file="Mutect2-out5-1.tabular" />
633 <output name="assembly_region_out" file="Mutect2-out5-2.tabular" />
634 <output name="bam_output" file="Mutect2-out5.bam" />
635 </test>
636 </tests>
637 <help><![CDATA[Call somatic short variants via local assembly of haplotypes. Short
638 variants include single nucleotide (SNV) and insertion and deletion
639 (indel) variants. The caller combines the DREAM challenge-winning
640 somatic genotyping engine of the original MuTect (`Cibulskis et al.,
641 2013 <http://www.nature.com/nbt/journal/v31/n3/full/nbt.2514.html>`__)
642 with the assembly-based machinery of
643 `HaplotypeCaller <https://www.broadinstitute.org/gatk/documentation/tooldocs/org_broadinstitute_gatk_tools_walkers_haplotypecaller_HaplotypeCaller.php>`__.
644
645 This tool is featured in the *Somatic Short Mutation calling Best
646 Practice Workflow*. See
647 `Tutorial#11136 <https://software.broadinstitute.org/gatk/documentation/article?id=11136>`__
648 for a step-by-step description of the workflow and
649 `Article#11127 <https://software.broadinstitute.org/gatk/documentation/article?id=11127>`__
650 for an overview of what traditional somatic calling entails. For the
651 latest pipeline scripts, see the `Mutect2 WDL scripts
652 directory <https://github.com/broadinstitute/gatk/tree/master/scripts/mutect2_wdl>`__.
653 Although we present the tool for somatic calling, it may apply to other
654 contexts, such as mitochondrial variant calling.
655
656 Usage examples
657 ~~~~~~~~~~~~~~
658
659 Example commands show how to run Mutect2 for typical scenarios. The two
660 modes are (i) *somatic mode* where a tumor sample is matched with a
661 normal sample in analysis and (ii) *tumor-only mode* where a single
662 sample's alignment data undergoes analysis.
663
664 (i) Tumor with matched normal
665 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
666
667 Given a matched normal, Mutect2 is designed to call somatic variants
668 only. The tool includes logic to skip emitting variants that are clearly
669 present in the germline based on provided evidence, e.g. in the matched
670 normal. This is done at an early stage to avoid spending computational
671 resources on germline events. If the variant's germline status is
672 borderline, then Mutect2 will emit the variant to the callset for
673 subsequent filtering and review.
674
675 ::
676
677 gatk Mutect2 \
678 -R reference.fa \
679 -I tumor.bam \
680 -tumor tumor_sample_name \
681 -I normal.bam \
682 -normal normal_sample_name \
683 --germline-resource af-only-gnomad.vcf.gz \
684 --af-of-alleles-not-in-resource 0.00003125 \
685 --panel-of-normals pon.vcf.gz \
686 -O somatic.vcf.gz
687
688
689 The --af-of-alleles-not-in-resource argument value should match
690 expectations for alleles not found in the provided germline resource.
691 Note the tool does not require a germline resource nor a panel of
692 normals (PoN) to run. The tool prefilters sites for the matched normal
693 and the PoN. For the germline resource, the tool prefilters on the
694 allele. Below is an excerpt of a known variants resource with population
695 allele frequencies
696
697 ::
698
699 #CHROM POS ID REF ALT QUAL FILTER INFO
700 1 10067 . T TAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCC 30.35 PASS AC=3;AF=7.384E-5
701 1 10108 . CAACCCT C 46514.32 PASS AC=6;AF=1.525E-4
702 1 10109 . AACCCTAACCCT AAACCCT,* 89837.27 PASS AC=48,5;AF=0.001223,1.273E-4
703 1 10114 . TAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAACCCTAACCCTAACCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAAACCCTA *,CAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAACCCTAACCCTAACCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAAACCCTA,T 36728.97 PASS AC=55,9,1;AF=0.001373,2.246E-4,2.496E-5
704 1 10119 . CT C,* 251.23 PASS AC=5,1;AF=1.249E-4,2.498E-5
705 1 10120 . TA CA,* 14928.74 PASS AC=10,6;AF=2.5E-4,1.5E-4
706 1 10128 . ACCCTAACCCTAACCCTAAC A,* 285.71 PASS AC=3,1;AF=7.58E-5,2.527E-5
707 1 10131 . CT C,* 378.93 PASS AC=7,5;AF=1.765E-4,1.261E-4
708 1 10132 . TAACCC *,T 18025.11 PASS AC=12,2;AF=3.03E-4,5.049E-5
709
710
711 (ii) Tumor-only mode
712 ^^^^^^^^^^^^^^^^^^^^
713
714 This mode runs on a single sample, e.g. single tumor or single normal
715 sample. To create a PoN, call on each normal sample in this mode, then
716 use CreateSomaticPanelOfNormals to generate the PoN.
717
718 ::
719
720 gatk Mutect2 \
721 -R reference.fa \
722 -I sample.bam \
723 -tumor sample_name \
724 -O single_sample.vcf.gz
725
726
727 Further points of interest
728 ~~~~~~~~~~~~~~~~~~~~~~~~~~
729
730 Additional parameters that factor towards filtering, including
731 normal-artifact-lod (default threshold 0.0) and tumor-lod (default
732 threshold 5.3), are available in FilterMutectCalls. While the tool
733 calculates normal-lod assuming a diploid genotype, it calculates
734 normal-artifact-lod with the same approach it uses for tumor-lod, i.e.
735 with a variable ploidy assumption.
736
737 - 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.
738
739 - 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.
740
741
742 If a variant is absent from a given germline resource, then the value
743 for --af-of-alleles-not-in-resource applies. For example, gnomAD's
744 16,000 samples (~32,000 homologs per locus) becomes a probability of one
745 in 32,000 or less. Thus, an allele's absence from the germline resource
746 becomes evidence that it is not a germline variant.
747
748 Caveats
749 ~~~~~~~
750
751 Although GATK4 Mutect2 accomodates varying coverage depths, further
752 optimization of parameters may improve calling for extreme high depths,
753 e.g. 1000X.
754 ]]></help>
755 <citations>
756 <expand macro="citations"/>
757 </citations>
758 </tool>