|
0
|
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 ln -s '$reference_source.reference_sequence' reference.fa &&
|
|
|
15 samtools faidx reference.fa &&
|
|
|
16 gatk CreateSequenceDictionary --REFERENCE="reference.fa" --OUTPUT="reference.dict" &&
|
|
|
17 @CMD_BEGIN@ Mutect2
|
|
|
18
|
|
|
19 #include source=$gatk_bam_input#
|
|
|
20
|
|
|
21 ## COMMON PARAMETERS ##
|
|
|
22
|
|
|
23 #if str($common.common_parameters) == 'yes'
|
|
|
24
|
|
|
25 --read-filter="$common.read_filter"
|
|
|
26 --seconds-between-progress-updates="$common.seconds_between_progress_updates"
|
|
|
27 --verbosity="$common.verbosity"
|
|
|
28 --read-validation-stringency="$common.read_validation_stringency"
|
|
|
29 --interval-set-rule="$common.interval_set_rule"
|
|
|
30 --gatk-config-file="$common.gatk_config_file"
|
|
|
31 --disable-read-filter="$common.disable_read_filter"
|
|
|
32 $common.QUIET
|
|
|
33 $common.use_jdk_deflater
|
|
|
34 $common.use_jdk_inflater
|
|
|
35 $common.lenient
|
|
|
36 $common.disable_tool_default_read_filters
|
|
|
37 $common.add_output_sam_program_record
|
|
|
38 $common.add_output_vcf_command_line
|
|
|
39
|
|
|
40 #end if
|
|
|
41
|
|
|
42 ## END COMMON PARAMETERS ##
|
|
|
43
|
|
|
44 ## OPTIONAL PARAMETERS ##
|
|
|
45
|
|
|
46 #if str($optional.optional_parameters) == 'yes'
|
|
|
47
|
|
|
48 #if $optional.population_callset
|
|
|
49 #set datatype = $optional.population_callset.datatype
|
|
|
50 #if $optional.population_callset.is_of_type("vcf_bgzip")
|
|
|
51 ln -s $optional.population_callset population_callset.vcf.gz &&
|
|
|
52 tabix population_callset.vcf.gz &&
|
|
|
53 #else
|
|
|
54 ln -s $optional.population_callset population_callset.vcf &&
|
|
|
55 #end if
|
|
|
56 #end if
|
|
|
57
|
|
|
58 #if $optional.panel_of_normals
|
|
|
59 #set datatype = $optional.panel_of_normals.datatype
|
|
|
60 #if $optional.panel_of_normals.is_of_type("vcf_bgzip")
|
|
|
61 ln -s $optional.panel_of_normals panel_of_normals.vcf.gz &&
|
|
|
62 tabix panel_of_normals.vcf.gz &&
|
|
|
63 #else
|
|
|
64 ln -s $optional.panel_of_normals panel_of_normals.vcf &&
|
|
|
65 #end if
|
|
|
66 #end if
|
|
|
67
|
|
|
68 #if $optional.germline_resource
|
|
|
69 #set datatype = $optional.germline_resource.datatype
|
|
|
70 #if $optional.germline_resource.is_of_type("vcf_bgzip")
|
|
|
71 ln -s $optional.germline_resource germline_resource.vcf.gz &&
|
|
|
72 tabix germline_resource.vcf.gz &&
|
|
|
73 #else
|
|
|
74 ln -s $optional.germline_resource germline_resource.vcf &&
|
|
|
75 #end if
|
|
|
76 #end if
|
|
|
77
|
|
|
78 #if $optional.alleles
|
|
|
79 #set datatype = $optional.alleles.datatype
|
|
|
80 #if $optional.alleles.is_of_type("vcf_bgzip")
|
|
|
81 ln -s $optional.alleles alleles.vcf.gz &&
|
|
|
82 tabix alleles.vcf.gz &&
|
|
|
83 #else
|
|
|
84 ln -s $optional.alleles alleles.vcf &&
|
|
|
85 #end if
|
|
|
86 #end if
|
|
|
87
|
|
|
88 #if $optional.panel_of_normals
|
|
|
89 #if $optional.panel_of_normals.is_of_type("vcf_bgzip")
|
|
|
90 --panel-of-normals panel_of_normals.vcf.gz
|
|
|
91 #else
|
|
|
92 --panel-of-normals panel_of_normals.vcf
|
|
|
93 #end if
|
|
|
94 #end if
|
|
|
95
|
|
|
96 #if $optional.pedigree
|
|
|
97 --pedigree="$optional.pedigree"
|
|
|
98 #end if
|
|
|
99
|
|
|
100 #if $optional.alleles
|
|
|
101 #if $optional.alleles.is_of_type("vcf_bgzip")
|
|
|
102 --alleles alleles.vcf.gz
|
|
|
103 #else
|
|
|
104 --alleles alleles.vcf
|
|
|
105 #end if
|
|
|
106 #end if
|
|
|
107
|
|
|
108 #if $optional.germline_resource
|
|
|
109 #if $optional.germline_resource.is_of_type("vcf_bgzip")
|
|
|
110 --germline-resource germline_resource.vcf.gz
|
|
|
111 #else
|
|
|
112 --germline-resource germline_resource.vcf
|
|
|
113 #end if
|
|
|
114 #end if
|
|
|
115
|
|
|
116 #if $optional.population_callset
|
|
|
117 #if $optional.population_callset.is_of_type("vcf_bgzip")
|
|
|
118 --population-callset population_callset.vcf.gz
|
|
|
119 #else
|
|
|
120 --population-callset population_callset.vcf
|
|
|
121 #end if
|
|
|
122 #end if
|
|
|
123
|
|
|
124 #if $optional.arguments_file
|
|
|
125 --arguments_file="$optional.arguments_file"
|
|
|
126 #end if
|
|
|
127
|
|
|
128 --base-quality-score-threshold="$optional.base_quality_score_threshold"
|
|
|
129 --cloud-index-prefetch-buffer="$optional.cloud_index_prefetch_buffer"
|
|
|
130 --cloud-prefetch-buffer="$optional.cloud_prefetch_buffer"
|
|
|
131 --annotation="$optional.annotation"
|
|
|
132 --annotation-group="$optional.annotation_group"
|
|
|
133 --annotations-to-exclude="$optional.annotations_to_exclude"
|
|
|
134 --af-of-alleles-not-in-resource="$optional.af_of_alleles_not_in_resource"
|
|
|
135 --contamination-fraction-to-filter="$optional.contamination_fraction_to_filter"
|
|
|
136 --downsampling-stride="$optional.downsampling_stride"
|
|
|
137 --founder-id="$optional.founder_id"
|
|
|
138 --gcs-max-retries="$optional.gcs_max_retries"
|
|
|
139 --genotyping-mode="$optional.genotyping_mode"
|
|
|
140 --heterozygosity="$optional.heterozygosity"
|
|
|
141 --heterozygosity-stdev="$optional.heterozygosity_stdev"
|
|
|
142 --indel-heterozygosity="$optional.indel_heterozygosity"
|
|
|
143 --initial-tumor-lod="$optional.initial_tumor_lod"
|
|
|
144 --interval-merging-rule="$optional.interval_merging_rule"
|
|
|
145 --max-population-af="$optional.max_population_af"
|
|
|
146 --max-reads-per-alignment-start="$optional.max_reads_per_alignment_start"
|
|
|
147 --min-base-quality-score="$optional.min_base_quality_score"
|
|
|
148 --native-pair-hmm-threads="$optional.native_pair_hmm_threads"
|
|
|
149 --normal-lod="$optional.normal_lod"
|
|
|
150 --normal-sample="$optional.normal_sample"
|
|
|
151 --num-reference-samples-if-no-call="$optional.num_reference_samples_if_no_call"
|
|
|
152 --output-mode="$optional.output_mode"
|
|
|
153 --sample-ploidy="$optional.sample_ploidy"
|
|
|
154 --standard-min-confidence-threshold-for-calling="$optional.standard_min_confidence_threshold_for_calling"
|
|
|
155 --tumor-lod-to-emit="$optional.tumor_lod_to_emit"
|
|
|
156 $optional.annotate_with_num_discovered_alleles
|
|
|
157 $optional.disable_bam_index_caching
|
|
|
158 $optional.disable_sequence_dictionary_validation
|
|
|
159 $optional.genotype_germline_sites
|
|
|
160 $optional.genotype_pon_sites
|
|
|
161 $optional.native_pair_hmm_use_double_precision
|
|
|
162 $optional.sites_only_vcf_output
|
|
|
163 $optional.use_new_qual_calculator
|
|
|
164 #end if
|
|
|
165
|
|
|
166 ## END OPTIONAL PARAMETERS ##
|
|
|
167
|
|
|
168 ## ADVANCED PARAMETERS ##
|
|
|
169
|
|
|
170 #if str($advanced.advanced_parameters) == 'yes'
|
|
|
171 --active-probability-threshold="$advanced.active_probability_threshold"
|
|
|
172 --assembly-region-padding="$advanced.assembly_region_padding"
|
|
|
173 --bam-writer-type="$advanced.bam_writer_type"
|
|
|
174 --contamination-fraction-per-sample-file="$advanced.contamination_fraction_per_sample_file"
|
|
|
175 --input-prior="$advanced.input_prior"
|
|
|
176 --kmer-size="$advanced.kmer_size"
|
|
|
177 --max-alternate-alleles="$advanced.max_alternate_alleles"
|
|
|
178 --max-assembly-region-size="$advanced.max_assembly_region_size"
|
|
|
179 --max-genotype-count="$advanced.max_genotype_count"
|
|
|
180 --max-mnp-distance="$advanced.max_mnp_distance"
|
|
|
181 --max-num-haplotypes-in-population="$advanced.max_num_haplotypes_in_population"
|
|
|
182 --max-prob-propagation-distance="$advanced.max_prob_propagation_distance"
|
|
|
183 --max-suspicious-reads-per-alignment-start="$advanced.max_suspicious_reads_per_alignment_start"
|
|
|
184 --min-assembly-region-size="$advanced.min_assembly_region_size"
|
|
|
185 --min-dangling-branch-length="$advanced.min_dangling_branch_length"
|
|
|
186 --min-pruning="$advanced.min_pruning"
|
|
|
187 --num-pruning-samples="$advanced.num_pruning_samples"
|
|
|
188 --pair-hmm-gap-continuation-penalty="$advanced.pair_hmm_gap_continuation_penalty"
|
|
|
189 --pair-hmm-implementation="$advanced.pair_hmm_implementation"
|
|
|
190 --pcr-indel-model="$advanced.pcr_indel_model"
|
|
|
191 --phred-scaled-global-read-mismapping-rate="$advanced.phred_scaled_global_read_mismapping_rate"
|
|
|
192 --smith-waterman="$advanced.smith_waterman"
|
|
|
193 $advanced.all_site_pls
|
|
|
194 $advanced.allow_non_unique_kmers_in_ref
|
|
|
195 $advanced.consensus
|
|
|
196 $advanced.debug
|
|
|
197 $advanced.disable_tool_default_annotations
|
|
|
198 $advanced.do_not_run_physical_phasing
|
|
|
199 $advanced.dont_increase_kmer_sizes_for_cycles
|
|
|
200 $advanced.dont_trim_active_regions
|
|
|
201 $advanced.dont_use_soft_clipped_bases
|
|
|
202 $advanced.enable_all_annotations
|
|
|
203 $advanced.genotype_filtered_alleles
|
|
|
204 $advanced.use_filtered_reads_for_annotations
|
|
|
205
|
|
|
206 #end if
|
|
|
207
|
|
|
208 ## END ADVANCED PARAMETERS ##
|
|
|
209
|
|
|
210 ## ADDITIONAL OUTPUT PARAMETERS ##
|
|
|
211
|
|
|
212 #if str($advanced.advanced_parameters) == 'yes'
|
|
|
213
|
|
|
214 --activity-profile-out="$activity_profile_out"
|
|
|
215 --assembly-region-out="$assembly_region_out"
|
|
|
216 --bam-output="$bam_output"
|
|
|
217 --graph-output="$graph_output"
|
|
|
218
|
|
|
219 #end if
|
|
|
220
|
|
|
221 #include source=$gatk_excl_ints_chth#
|
|
|
222 #include source=$gatk_ints_chth#
|
|
|
223 #include source=$vcf_output_opts#
|
|
|
224 #include source=$ref_opts#
|
|
|
225 #include source=$gatk_seqdict#
|
|
|
226 #if $tumor_sample
|
|
|
227 --tumor-sample="$tumor_sample"
|
|
|
228 #end if
|
|
|
229 ]]>
|
|
|
230 </command>
|
|
|
231 <inputs>
|
|
|
232 <expand macro="gatk_bam_req_params"/>
|
|
|
233 <expand macro="gzip_vcf_params"/>
|
|
|
234 <expand macro="ref_sel"/>
|
|
|
235 <param name="tumor_sample" argument="--tumor-sample" type="text" optional="false" value="" label="Tumor Sample" help="BAM sample name of tumor. May be URL-encoded as output by GetSampleName with -encode argument."/>
|
|
|
236 <conditional name="common">
|
|
|
237 <param name="common_parameters" type="select" label="Common parameters">
|
|
|
238 <option value="no">Use internal defaults</option>
|
|
|
239 <option value="yes">Specify parameters</option>
|
|
|
240 </param>
|
|
|
241 <when value="yes">
|
|
|
242 <expand macro="gatk_excl_ints"/>
|
|
|
243 <expand macro="seq_dict_sel"/>
|
|
|
244 <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."/>
|
|
|
245 <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."/>
|
|
|
246 <param name="disable_read_filter" argument="--disable-read-filter" type="text" optional="true" value="" label="Disable Read Filter" help="Read filters to be disabled before analysis"/>
|
|
|
247 <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)"/>
|
|
|
248 <param name="gatk_config_file" argument="--gatk-config-file" type="data" optional="true" format="" label="Gatk Config File" help="A configuration file to use with the GATK."/>
|
|
|
249 <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">
|
|
|
250 <option selected="true" value="UNION">UNION</option>
|
|
|
251 <option selected="false" value="INTERSECTION">INTERSECTION</option>
|
|
|
252 </param>
|
|
|
253 <param name="lenient" argument="--lenient" type="boolean" truevalue="--lenient" falsevalue="" optional="true" checked="false" label="Lenient" help="Lenient processing of VCF files"/>
|
|
|
254 <param name="QUIET" argument="--QUIET" type="boolean" truevalue="--QUIET" falsevalue="" optional="true" checked="false" label="Quiet" help="Whether to suppress job-summary info on System.err."/>
|
|
|
255 <param name="read_filter" argument="--read-filter" type="text" optional="true" value="" label="Read Filter" help="Read filters to be applied before analysis"/>
|
|
|
256 <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.">
|
|
|
257 <option selected="false" value="STRICT">STRICT</option>
|
|
|
258 <option selected="false" value="LENIENT">LENIENT</option>
|
|
|
259 <option selected="true" value="SILENT">SILENT</option>
|
|
|
260 </param>
|
|
|
261 <param name="seconds_between_progress_updates" argument="--seconds-between-progress-updates" type="float" optional="true" value="10.0" label="Seconds Between Progress Updates" help="Output traversal statistics every time this many seconds elapse"/>
|
|
|
262 <param name="use_jdk_deflater" argument="--use-jdk-deflater" type="boolean" truevalue="--use-jdk-deflater" falsevalue="" optional="true" checked="false" label="Use Jdk Deflater" help="Whether to use the JdkDeflater (as opposed to IntelDeflater)"/>
|
|
|
263 <param name="use_jdk_inflater" argument="--use-jdk-inflater" type="boolean" truevalue="--use-jdk-inflater" falsevalue="" optional="true" checked="false" label="Use Jdk Inflater" help="Whether to use the JdkInflater (as opposed to IntelInflater)"/>
|
|
|
264 <param name="verbosity" argument="--verbosity" type="select" optional="true" label="Verbosity" help="Control verbosity of logging.">
|
|
|
265 <option selected="false" value="ERROR">ERROR</option>
|
|
|
266 <option selected="false" value="WARNING">WARNING</option>
|
|
|
267 <option selected="true" value="INFO">INFO</option>
|
|
|
268 <option selected="false" value="DEBUG">DEBUG</option>
|
|
|
269 </param>
|
|
|
270 </when>
|
|
|
271 <when value="no" />
|
|
|
272 </conditional>
|
|
|
273 <conditional name="optional">
|
|
|
274 <param name="optional_parameters" type="select" label="Optional parameters">
|
|
|
275 <option value="no">Use internal defaults</option>
|
|
|
276 <option value="yes">Specify parameters</option>
|
|
|
277 </param>
|
|
|
278 <when value="yes">
|
|
|
279 <expand macro="gatk_ints"/>
|
|
|
280 <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."/>
|
|
|
281 <param name="alleles" argument="--alleles" type="data" optional="true" format="" label="Alleles" help="The set of alleles at which to genotype when --genotyping_mode is GENOTYPE_GIVEN_ALLELES"/>
|
|
|
282 <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"/>
|
|
|
283 <param name="annotation" argument="--annotation" type="text" optional="true" value="" label="Annotation" help="One or more specific annotations to add to variant calls"/>
|
|
|
284 <param name="annotation_group" argument="--annotation-group" type="text" optional="true" value="" label="Annotation Group" help="One or more groups of annotations to apply to variant calls"/>
|
|
|
285 <param name="annotations_to_exclude" argument="--annotations-to-exclude" type="text" optional="true" value="" label="Annotations To Exclude" help="One or more specific annotations to exclude from variant calls"/>
|
|
|
286 <param name="arguments_file" argument="--arguments_file" type="data" optional="true" format="" label="Arguments_File" help="read one or more arguments files and add them to the command line"/>
|
|
|
287 <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)"/>
|
|
|
288 <param name="cloud_index_prefetch_buffer" argument="--cloud-index-prefetch-buffer" type="integer" optional="true" value="-1" label="Cloud Index Prefetch Buffer" help="Size of the cloud-only prefetch buffer (in MB; 0 to disable). Defaults to cloudPrefetchBuffer if unset."/>
|
|
|
289 <param name="cloud_prefetch_buffer" argument="--cloud-prefetch-buffer" type="integer" optional="true" value="40" label="Cloud Prefetch Buffer" help="Size of the cloud-only prefetch buffer (in MB; 0 to disable)."/>
|
|
|
290 <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"/>
|
|
|
291 <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&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."/>
|
|
|
292 <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!"/>
|
|
|
293 <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."/>
|
|
|
294 <param name="founder_id" argument="--founder-id" type="text" optional="true" value="" label="Founder Id" help="Samples representing the population &quot;founders&quot;"/>
|
|
|
295 <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"/>
|
|
|
296 <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."/>
|
|
|
297 <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."/>
|
|
|
298 <param name="genotyping_mode" argument="--genotyping-mode" type="select" optional="true" label="Genotyping Mode" help="Specifies how to determine the alternate alleles to use for genotyping">
|
|
|
299 <option selected="true" value="DISCOVERY">DISCOVERY</option>
|
|
|
300 <option selected="false" value="GENOTYPE_GIVEN_ALLELES">GENOTYPE_GIVEN_ALLELES</option>
|
|
|
301 </param>
|
|
|
302 <param name="germline_resource" argument="--germline-resource" type="data" optional="true" format="" label="Germline Resource" help="Population vcf of germline sequencing containing allele fractions."/>
|
|
|
303 <param name="heterozygosity" argument="--heterozygosity" type="float" optional="true" value="0.001" label="Heterozygosity" help="Heterozygosity value used to compute prior likelihoods for any locus. See the GATKDocs for full details on the meaning of this population genetics concept"/>
|
|
|
304 <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."/>
|
|
|
305 <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"/>
|
|
|
306 <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."/>
|
|
|
307 <param name="interval_merging_rule" argument="--interval-merging-rule" type="select" optional="true" label="Interval Merging Rule" help="Interval merging rule for abutting intervals">
|
|
|
308 <option selected="true" value="ALL">ALL</option>
|
|
|
309 <option selected="false" value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option>
|
|
|
310 </param>
|
|
|
311 <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."/>
|
|
|
312 <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."/>
|
|
|
313 <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"/>
|
|
|
314 <param name="native_pair_hmm_threads" argument="--native-pair-hmm-threads" type="integer" optional="true" value="4" label="Native Pair Hmm Threads" help="How many threads should a native pairHMM implementation use"/>
|
|
|
315 <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"/>
|
|
|
316 <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."/>
|
|
|
317 <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."/>
|
|
|
318 <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"/>
|
|
|
319 <param name="output_mode" argument="--output-mode" type="select" optional="true" label="Output Mode" help="Specifies which type of calls we should output">
|
|
|
320 <option selected="true" value="EMIT_VARIANTS_ONLY">EMIT_VARIANTS_ONLY</option>
|
|
|
321 <option selected="false" value="EMIT_ALL_CONFIDENT_SITES">EMIT_ALL_CONFIDENT_SITES</option>
|
|
|
322 <option selected="false" value="EMIT_ALL_SITES">EMIT_ALL_SITES</option>
|
|
|
323 </param>
|
|
|
324 <param name="panel_of_normals" argument="--panel-of-normals" type="data" optional="true" format="" label="Panel Of Normals" help="VCF file of sites observed in normal."/>
|
|
|
325 <param name="pedigree" argument="--pedigree" type="data" optional="true" format="" label="Pedigree" help="Pedigree file for determining the population &quot;founders&quot;"/>
|
|
|
326 <param name="population_callset" argument="--population-callset" type="data" optional="true" format="" label="Population Callset" help="Callset to use in calculating genotype priors"/>
|
|
|
327 <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)."/>
|
|
|
328 <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."/>
|
|
|
329 <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"/>
|
|
|
330 <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."/>
|
|
|
331 <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"/>
|
|
|
332 </when>
|
|
|
333 <when value="no" />
|
|
|
334 </conditional>
|
|
|
335 <conditional name="advanced">
|
|
|
336 <param name="advanced_parameters" type="select" label="Advanced parameters">
|
|
|
337 <option value="no">Use internal defaults</option>
|
|
|
338 <option value="yes">Specify parameters</option>
|
|
|
339 </param>
|
|
|
340 <when value="yes">
|
|
|
341 <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."/>
|
|
|
342 <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"/>
|
|
|
343 <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"/>
|
|
|
344 <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"/>
|
|
|
345 <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">
|
|
|
346 <option selected="false" value="ALL_POSSIBLE_HAPLOTYPES">ALL_POSSIBLE_HAPLOTYPES</option>
|
|
|
347 <option selected="true" value="CALLED_HAPLOTYPES">CALLED_HAPLOTYPES</option>
|
|
|
348 </param>
|
|
|
349 <param name="consensus" argument="--consensus" type="boolean" truevalue="--consensus" falsevalue="" optional="true" checked="false" label="Consensus" help="1000G consensus mode"/>
|
|
|
350 <param name="contamination_fraction_per_sample_file" argument="--contamination-fraction-per-sample-file" type="data" optional="true" format="" label="Contamination Fraction Per Sample File" help="Tab-separated File containing fraction of contamination in sequencing data (per sample) to aggressively remove. Format should be &quot;&lt;SampleID&gt;&lt;TAB&gt;&lt;Contamination&gt;&quot; (Contamination is double) per line; No header."/>
|
|
|
351 <param name="debug" argument="--debug" type="boolean" truevalue="--debug" falsevalue="" optional="true" checked="false" label="Debug" help="Print out very verbose debug information about each triggering active region"/>
|
|
|
352 <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"/>
|
|
|
353 <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"/>
|
|
|
354 <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"/>
|
|
|
355 <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"/>
|
|
|
356 <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"/>
|
|
|
357 <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)"/>
|
|
|
358 <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"/>
|
|
|
359 <param name="input_prior" argument="--input-prior" type="text" optional="true" value="" label="Input Prior" help="Input prior for calls"/>
|
|
|
360 <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"/>
|
|
|
361 <param name="max_alternate_alleles" argument="--max-alternate-alleles" type="integer" optional="true" value="6" label="Max Alternate Alleles" help="Maximum number of alternate alleles to genotype"/>
|
|
|
362 <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"/>
|
|
|
363 <param name="max_genotype_count" argument="--max-genotype-count" type="integer" optional="true" value="1024" label="Max Genotype Count" help="Maximum number of genotypes to consider at any site"/>
|
|
|
364 <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."/>
|
|
|
365 <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"/>
|
|
|
366 <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"/>
|
|
|
367 <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."/>
|
|
|
368 <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"/>
|
|
|
369 <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"/>
|
|
|
370 <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"/>
|
|
|
371 <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"/>
|
|
|
372 <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"/>
|
|
|
373 <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">
|
|
|
374 <option selected="false" value="EXACT">EXACT</option>
|
|
|
375 <option selected="false" value="ORIGINAL">ORIGINAL</option>
|
|
|
376 <option selected="false" value="LOGLESS_CACHING">LOGLESS_CACHING</option>
|
|
|
377 <option selected="false" value="AVX_LOGLESS_CACHING">AVX_LOGLESS_CACHING</option>
|
|
|
378 <option selected="false" value="AVX_LOGLESS_CACHING_OMP">AVX_LOGLESS_CACHING_OMP</option>
|
|
|
379 <option selected="false" value="EXPERIMENTAL_FPGA_LOGLESS_CACHING">EXPERIMENTAL_FPGA_LOGLESS_CACHING</option>
|
|
|
380 <option selected="true" value="FASTEST_AVAILABLE">FASTEST_AVAILABLE</option>
|
|
|
381 </param>
|
|
|
382 <param name="pcr_indel_model" argument="--pcr-indel-model" type="select" optional="true" label="Pcr Indel Model" help="The PCR indel model to use">
|
|
|
383 <option selected="false" value="NONE">NONE</option>
|
|
|
384 <option selected="false" value="HOSTILE">HOSTILE</option>
|
|
|
385 <option selected="false" value="AGGRESSIVE">AGGRESSIVE</option>
|
|
|
386 <option selected="true" value="CONSERVATIVE">CONSERVATIVE</option>
|
|
|
387 </param>
|
|
|
388 <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"/>
|
|
|
389 <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">
|
|
|
390 <option selected="false" value="FASTEST_AVAILABLE">FASTEST_AVAILABLE</option>
|
|
|
391 <option selected="false" value="AVX_ENABLED">AVX_ENABLED</option>
|
|
|
392 <option selected="true" value="JAVA">JAVA</option>
|
|
|
393 </param>
|
|
|
394 <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"/>
|
|
|
395 </when>
|
|
|
396 <when value="no" />
|
|
|
397 </conditional>
|
|
|
398 <conditional name="output">
|
|
|
399 <param name="output_parameters" type="select" label="Output parameters">
|
|
|
400 <option value="no">Use internal defaults</option>
|
|
|
401 <option value="yes">Specify parameters</option>
|
|
|
402 </param>
|
|
|
403 <when value="yes">
|
|
|
404 <param name="activity_profile_out_sel" argument="--activity_profile_out_sel" type="boolean" truevalue="--activity_profile_out_sel" falsevalue="" optional="true" checked="false" label="Activity Profile Out" help="Output the raw activity profile results in IGV format"/>
|
|
|
405 <param name="assembly_region_out_sel" argument="--assembly_region_out_sel" type="boolean" truevalue="--assembly_region_out_sel" falsevalue="" optional="true" checked="false" label="Assembly Region Out" help="Output the assembly region to this IGV formatted file"/>
|
|
|
406 <param name="bam_output_sel" argument="--bam_output_sel" type="boolean" truevalue="--bam_output_sel" falsevalue="" optional="true" checked="false" label="Bam Output" help="File to which assembled haplotypes should be written"/>
|
|
|
407 <param name="graph_output_sel" argument="--graph_output_sel" type="boolean" truevalue="--graph_output_sel" falsevalue="" optional="true" checked="false" label="Graph Output" help="Write debug assembly graph information to this file"/>
|
|
|
408 </when>
|
|
|
409 <when value="no" />
|
|
|
410 </conditional>
|
|
|
411 </inputs>
|
|
|
412 <outputs>
|
|
|
413 <expand macro="gzip_vcf_output_params"/>
|
|
|
414 <data format="tabular" name="activity_profile_out" label="${tool.name} on ${on_string}: activity_profile_out tabular">
|
|
|
415 <filter>output_opt['activity_profile_out_sel']</filter>
|
|
|
416 </data>
|
|
|
417 <data format="tabular" name="assembly_region_out" label="${tool.name} on ${on_string}: assembly_region_out tabular">
|
|
|
418 <filter>output_opt['assembly_region_out_sel']</filter>
|
|
|
419 </data>
|
|
|
420 <data format="bam" name="bam_output" label="${tool.name} on ${on_string}: bam_output bam">
|
|
|
421 <filter>output_opt['bam_output_sel']</filter>
|
|
|
422 </data>
|
|
|
423 <data format="txt" name="graph_output" label="${tool.name} on ${on_string}: graph_output txt">
|
|
|
424 <filter>output_opt['graph_output_sel']</filter>
|
|
|
425 </data>
|
|
|
426 </outputs>
|
|
|
427 <tests>
|
|
|
428 <test />
|
|
|
429 </tests>
|
|
|
430 <help><![CDATA[Call somatic short variants via local assembly of haplotypes. Short
|
|
|
431 variants include single nucleotide (SNV) and insertion and deletion
|
|
|
432 (indel) variants. The caller combines the DREAM challenge-winning
|
|
|
433 somatic genotyping engine of the original MuTect (`Cibulskis et al.,
|
|
|
434 2013 <http://www.nature.com/nbt/journal/v31/n3/full/nbt.2514.html>`__)
|
|
|
435 with the assembly-based machinery of
|
|
|
436 `HaplotypeCaller <https://www.broadinstitute.org/gatk/documentation/tooldocs/org_broadinstitute_gatk_tools_walkers_haplotypecaller_HaplotypeCaller.php>`__.
|
|
|
437
|
|
|
438 This tool is featured in the *Somatic Short Mutation calling Best
|
|
|
439 Practice Workflow*. See
|
|
|
440 `Tutorial#11136 <https://software.broadinstitute.org/gatk/documentation/article?id=11136>`__
|
|
|
441 for a step-by-step description of the workflow and
|
|
|
442 `Article#11127 <https://software.broadinstitute.org/gatk/documentation/article?id=11127>`__
|
|
|
443 for an overview of what traditional somatic calling entails. For the
|
|
|
444 latest pipeline scripts, see the `Mutect2 WDL scripts
|
|
|
445 directory <https://github.com/broadinstitute/gatk/tree/master/scripts/mutect2_wdl>`__.
|
|
|
446 Although we present the tool for somatic calling, it may apply to other
|
|
|
447 contexts, such as mitochondrial variant calling.
|
|
|
448
|
|
|
449 Usage examples
|
|
|
450 ~~~~~~~~~~~~~~
|
|
|
451
|
|
|
452 Example commands show how to run Mutect2 for typical scenarios. The two
|
|
|
453 modes are (i) *somatic mode* where a tumor sample is matched with a
|
|
|
454 normal sample in analysis and (ii) *tumor-only mode* where a single
|
|
|
455 sample's alignment data undergoes analysis.
|
|
|
456
|
|
|
457 (i) Tumor with matched normal
|
|
|
458 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
|
459
|
|
|
460 Given a matched normal, Mutect2 is designed to call somatic variants
|
|
|
461 only. The tool includes logic to skip emitting variants that are clearly
|
|
|
462 present in the germline based on provided evidence, e.g. in the matched
|
|
|
463 normal. This is done at an early stage to avoid spending computational
|
|
|
464 resources on germline events. If the variant's germline status is
|
|
|
465 borderline, then Mutect2 will emit the variant to the callset for
|
|
|
466 subsequent filtering and review.
|
|
|
467
|
|
|
468 ::
|
|
|
469
|
|
|
470 gatk Mutect2 \
|
|
|
471 -R reference.fa \
|
|
|
472 -I tumor.bam \
|
|
|
473 -tumor tumor_sample_name \
|
|
|
474 -I normal.bam \
|
|
|
475 -normal normal_sample_name \
|
|
|
476 --germline-resource af-only-gnomad.vcf.gz \
|
|
|
477 --af-of-alleles-not-in-resource 0.00003125 \
|
|
|
478 --panel-of-normals pon.vcf.gz \
|
|
|
479 -O somatic.vcf.gz
|
|
|
480
|
|
|
481
|
|
|
482 The --af-of-alleles-not-in-resource argument value should match
|
|
|
483 expectations for alleles not found in the provided germline resource.
|
|
|
484 Note the tool does not require a germline resource nor a panel of
|
|
|
485 normals (PoN) to run. The tool prefilters sites for the matched normal
|
|
|
486 and the PoN. For the germline resource, the tool prefilters on the
|
|
|
487 allele. Below is an excerpt of a known variants resource with population
|
|
|
488 allele frequencies
|
|
|
489
|
|
|
490 ::
|
|
|
491
|
|
|
492 #CHROM POS ID REF ALT QUAL FILTER INFO
|
|
|
493 1 10067 . T TAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCC 30.35 PASS AC=3;AF=7.384E-5
|
|
|
494 1 10108 . CAACCCT C 46514.32 PASS AC=6;AF=1.525E-4
|
|
|
495 1 10109 . AACCCTAACCCT AAACCCT,* 89837.27 PASS AC=48,5;AF=0.001223,1.273E-4
|
|
|
496 1 10114 . TAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAACCCTAACCCTAACCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAAACCCTA *,CAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAACCCTAACCCTAACCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCTAACCCCTAACCCTAACCCTAAACCCTA,T 36728.97 PASS AC=55,9,1;AF=0.001373,2.246E-4,2.496E-5
|
|
|
497 1 10119 . CT C,* 251.23 PASS AC=5,1;AF=1.249E-4,2.498E-5
|
|
|
498 1 10120 . TA CA,* 14928.74 PASS AC=10,6;AF=2.5E-4,1.5E-4
|
|
|
499 1 10128 . ACCCTAACCCTAACCCTAAC A,* 285.71 PASS AC=3,1;AF=7.58E-5,2.527E-5
|
|
|
500 1 10131 . CT C,* 378.93 PASS AC=7,5;AF=1.765E-4,1.261E-4
|
|
|
501 1 10132 . TAACCC *,T 18025.11 PASS AC=12,2;AF=3.03E-4,5.049E-5
|
|
|
502
|
|
|
503
|
|
|
504 (ii) Tumor-only mode
|
|
|
505 ^^^^^^^^^^^^^^^^^^^^
|
|
|
506
|
|
|
507 This mode runs on a single sample, e.g. single tumor or single normal
|
|
|
508 sample. To create a PoN, call on each normal sample in this mode, then
|
|
|
509 use CreateSomaticPanelOfNormals to generate the PoN.
|
|
|
510
|
|
|
511 ::
|
|
|
512
|
|
|
513 gatk Mutect2 \
|
|
|
514 -R reference.fa \
|
|
|
515 -I sample.bam \
|
|
|
516 -tumor sample_name \
|
|
|
517 -O single_sample.vcf.gz
|
|
|
518
|
|
|
519
|
|
|
520 Further points of interest
|
|
|
521 ~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
522
|
|
|
523 Additional parameters that factor towards filtering, including
|
|
|
524 normal-artifact-lod (default threshold 0.0) and tumor-lod (default
|
|
|
525 threshold 5.3), are available in FilterMutectCalls. While the tool
|
|
|
526 calculates normal-lod assuming a diploid genotype, it calculates
|
|
|
527 normal-artifact-lod with the same approach it uses for tumor-lod, i.e.
|
|
|
528 with a variable ploidy assumption.
|
|
|
529
|
|
|
530 - 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.
|
|
|
531
|
|
|
532 - 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.
|
|
|
533
|
|
|
534
|
|
|
535 If a variant is absent from a given germline resource, then the value
|
|
|
536 for --af-of-alleles-not-in-resource applies. For example, gnomAD's
|
|
|
537 16,000 samples (~32,000 homologs per locus) becomes a probability of one
|
|
|
538 in 32,000 or less. Thus, an allele's absence from the germline resource
|
|
|
539 becomes evidence that it is not a germline variant.
|
|
|
540
|
|
|
541 Caveats
|
|
|
542 ~~~~~~~
|
|
|
543
|
|
|
544 Although GATK4 Mutect2 accomodates varying coverage depths, further
|
|
|
545 optimization of parameters may improve calling for extreme high depths,
|
|
|
546 e.g. 1000X.
|
|
|
547 ]]></help>
|
|
|
548 <citations>
|
|
|
549 <expand macro="citations"/>
|
|
|
550 </citations>
|
|
|
551 </tool>
|
