Mercurial > repos > devteam > freebayes
annotate freebayes.xml @ 20:8fb829f953d6 draft
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
| author | devteam |
|---|---|
| date | Tue, 21 Jul 2015 15:29:21 -0400 |
| parents | 4c80a1387285 |
| children | 978760187fe2 |
| rev | line source |
|---|---|
| 13 | 1 <?xml version="1.0"?> |
| 17 | 2 <tool id="freebayes" name="FreeBayes" version="0.4"> |
| 13 | 3 <requirements> |
| 17 | 4 <requirement type="package" version="0_9_20_b040236">freebayes</requirement> |
| 13 | 5 <requirement type="package" version="0.1.18">samtools</requirement> |
| 6 </requirements> | |
| 16 | 7 <description> - bayesian genetic variant detector</description> |
| 13 | 8 <command> |
| 9 ##set up input files | |
| 10 | |
| 11 #set $reference_fasta_filename = "localref.fa" | |
| 12 | |
| 13 #if str( $reference_source.reference_source_selector ) == "history": | |
| 14 ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" && | |
| 15 samtools faidx "${reference_fasta_filename}" 2>&1 || echo "Error running samtools faidx for FreeBayes" >&2 && | |
| 16 #else: | |
| 17 #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) | |
| 18 #end if | |
| 19 | |
| 20 #for $bam_count, $input_bam in enumerate( $reference_source.input_bams ): | |
| 21 ln -s "${input_bam.input_bam}" "localbam_${bam_count}.bam" && | |
| 22 ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" && | |
| 23 #end for | |
| 24 | |
| 25 ## Tabixize optional input_varinat_vcf file (for --variant-input option) | |
| 26 | |
| 16 | 27 #if ( str( $options_type.options_type_selector ) == 'cline' or str( $options_type.options_type_selector ) == 'full' ) and $options_type.optional_inputs.optional_inputs_selector and str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf": |
| 28 ln -s "${options_type.optional_inputs.input_variant_type.input_variant_vcf}" "input_variant_vcf.vcf.gz" && | |
| 29 ln -s "${Tabixized_input}" "input_variant_vcf.vcf.gz.tbi" && | |
| 13 | 30 #end if |
| 31 | |
| 32 ##finished setting up inputs | |
| 33 | |
| 34 ##COMMAND LINE STARTS HERE | |
| 35 | |
| 36 freebayes | |
| 37 #for $bam_count, $input_bam in enumerate( $reference_source.input_bams ): | |
| 38 --bam "localbam_${bam_count}.bam" | |
| 39 #end for | |
| 40 --fasta-reference "${reference_fasta_filename}" | |
| 41 | |
| 42 ##outputs | |
| 43 --vcf "${output_vcf}" | |
| 44 | |
| 45 #if str( $target_limit_type.target_limit_type_selector ) == "limit_by_target_file": | |
| 46 --targets "${target_limit_type.input_target_bed}" | |
| 47 #elif str( $target_limit_type.target_limit_type_selector ) == "limit_by_region": | |
| 48 --region "${target_limit_type.region_chromosome}:${target_limit_type.region_start}..${target_limit_type.region_end}" | |
| 49 #end if | |
| 50 | |
| 51 ##advanced options | |
| 52 #if str( $options_type.options_type_selector ) == "simple": | |
| 53 ##do nothing as command like build up to this point is sufficinet for simple diploid calling | |
| 54 | |
| 55 #elif str( $options_type.options_type_selector ) == "simple_w_filters": | |
| 56 | |
| 57 --standard-filters | |
| 58 --min-coverage "${options_type.min_coverage}" | |
| 59 | |
| 60 #elif str( $options_type.options_type_selector ) == "naive": | |
| 61 | |
| 62 --haplotype-length 0 | |
| 63 --min-alternate-count 1 | |
| 64 --min-alternate-fraction 0 | |
| 65 --pooled-continuous | |
| 66 --report-monomorphic | |
| 67 | |
| 68 #elif str( $options_type.options_type_selector ) == "naive_w_filters": | |
| 69 | |
| 70 --haplotype-length 0 | |
| 71 --min-alternate-count 1 | |
| 72 --min-alternate-fraction 0 | |
| 73 --pooled-continuous | |
| 74 --report-monomorphic | |
| 75 --standard-filters | |
| 76 --min-coverage "${options_type.min_coverage}" | |
| 16 | 77 |
| 78 ## Command line direct text entry is not allowed at this time for security reasons | |
| 13 | 79 |
| 80 #elif str( $options_type.options_type_selector ) == "full": | |
| 81 | |
| 17 | 82 #if $options_type.optional_inputs.optional_inputs_selector: |
| 83 | |
| 84 #if $options_type.optional_inputs.output_trace_option: | |
| 85 --trace "${output_trace}" | |
| 86 #end if | |
| 87 | |
| 88 #if $options_type.optional_inputs.output_failed_alleles_option: | |
| 89 --failed-alleles "${output_failed_alleles_bed}" | |
| 90 #end if | |
| 91 | |
| 92 #if $options_type.optional_inputs.samples: | |
| 93 --samples "${options_type.optional_inputs.samples}" | |
| 94 #end if | |
| 95 | |
| 96 #if $options_type.optional_inputs.populations: | |
| 97 --populations "${options_type.optional_inputs.populations}" | |
| 98 #end if | |
| 99 | |
| 100 #if $options_type.optional_inputs.A: | |
| 101 --cnv-map "${options_type.optional_inputs.A}" | |
| 102 #end if | |
| 103 | |
| 104 #if str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf": | |
| 105 --variant-input "input_variant_vcf.vcf.gz" ## input_variant_vcf.vcf.gz is symlinked to a galaxy-generated dataset in "Tabixize optional input_varinat_vcf file" section of the command line above | |
| 106 ${options_type.optional_inputs.input_variant_type.only_use_input_alleles} | |
| 107 #end if | |
| 108 | |
| 109 #if $options_type.optional_inputs.haplotype_basis_alleles: | |
| 110 --haplotype-basis-alleles "${options_type.optional_inputs.haplotype_basis_alleles}" | |
| 111 #end if | |
| 112 | |
| 113 #if $options_type.optional_inputs.observation_bias: | |
| 114 --observation-bias "${options_type.optional_inputs.observation_bias}" | |
| 115 #end if | |
| 116 | |
| 117 #if $options_type.optional_inputs.contamination_estimates: | |
| 118 --contamination-estimates "${options_type.optional_inputs.contamination_estimates}" | |
| 119 #end if | |
| 120 | |
| 121 #end if | |
| 13 | 122 |
| 123 ## REPORTING | |
|
20
8fb829f953d6
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
17
diff
changeset
|
124 |
|
8fb829f953d6
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
17
diff
changeset
|
125 ${options_type.optional_inputs.report_monomorphic} |
|
8fb829f953d6
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
17
diff
changeset
|
126 |
| 13 | 127 #if str( $options_type.reporting.reporting_selector ) == "True": |
| 128 --pvar ${options_type.reporting.pvar} | |
| 129 #end if | |
| 130 | |
| 131 ## POPULATION MODEL | |
| 132 | |
| 133 #if str( $options_type.population_model.population_model_selector ) == "True": | |
| 134 --theta "${options_type.population_model.T}" | |
| 135 --ploidy "${options_type.population_model.P}" | |
| 136 ${options_type.population_model.J} | |
| 137 ${options_type.population_model.K} | |
| 138 | |
| 139 #end if | |
| 140 | |
| 141 ## REFERENCE ALLELE | |
| 142 | |
| 143 #if str( $options_type.reference_allele.reference_allele_selector ) == "True": | |
| 144 ${options_type.reference_allele.Z} | |
| 145 --reference-quality "${options_type.reference_allele.reference_quality}" | |
| 146 #end if | |
| 147 | |
| 148 ## ALLELE SCOPE | |
| 149 | |
| 150 #if str( $options_type.allele_scope.allele_scope_selector ) == "True": | |
| 151 ${options_type.allele_scope.I} | |
| 152 ${options_type.allele_scope.i} | |
| 153 ${options_type.allele_scope.X} | |
| 154 ${options_type.allele_scope.u} | |
| 155 -n "${options_type.allele_scope.n}" | |
| 156 --haplotype-length "${options_type.allele_scope.haplotype_length}" | |
| 15 | 157 --min-repeat-size "${options_type.allele_scope.min_repeat_length}" |
| 13 | 158 --min-repeat-entropy "${options_type.allele_scope.min_repeat_entropy}" |
| 159 ${options_type.allele_scope.no_partial_observations} | |
| 160 #end if | |
| 161 | |
| 162 ## REALIGNMENT | |
| 163 | |
| 164 ${options_type.O} | |
| 165 | |
| 166 ##INPUT FILTERS | |
| 167 | |
| 168 #if str( $options_type.input_filters.input_filters_selector ) == "True": | |
| 169 ${options_type.input_filters.use_duplicate_reads} | |
| 170 -m "${options_type.input_filters.m}" | |
| 171 -q "${options_type.input_filters.q}" | |
| 172 -R "${options_type.input_filters.R}" | |
| 173 -Y "${options_type.input_filters.Y}" | |
| 174 | |
| 175 #if str( $options_type.input_filters.mismatch_filters.mismatch_filters_selector ) == "True": | |
| 176 -Q "${options_type.input_filters.mismatch_filters.Q}" | |
| 177 -U "${options_type.input_filters.mismatch_filters.U}" | |
| 178 -z "${options_type.input_filters.mismatch_filters.z}" | |
| 179 --read-snp-limit "${options_type.input_filters.mismatch_filters.read_snp_limit}" | |
| 180 #end if | |
| 181 | |
| 182 -e "${options_type.input_filters.e}" | |
| 183 -F "${options_type.input_filters.F}" | |
| 184 -C "${options_type.input_filters.C}" | |
| 185 --min-alternate-qsum "${options_type.input_filters.min_alternate_qsum}" | |
| 186 -G "${options_type.input_filters.G}" | |
| 187 --min-coverage "${options_type.input_filters.min_coverage}" | |
| 188 #end if | |
| 189 | |
| 190 ## POPULATION AND MAPPABILITY PRIORS | |
| 191 | |
| 192 #if str( $options_type.population_mappability_priors.population_mappability_priors_selector ) == "True": | |
| 193 ${options_type.population_mappability_priors.k} | |
| 194 ${options_type.population_mappability_priors.w} | |
| 195 ${options_type.population_mappability_priors.V} | |
| 196 ${options_type.population_mappability_priors.a} | |
| 197 #end if | |
| 198 | |
| 199 ## GENOTYPE LIKELIHOODS | |
| 200 | |
| 201 #if str( $options_type.genotype_likelihoods.genotype_likelihoods_selector ) == "True": | |
| 202 --base-quality-cap "${$options_type.genotype_likelihoods.base_quality_cap}" | |
| 203 ${$options_type.genotype_likelihoods.experimental_gls} | |
| 15 | 204 --prob-contamination "${$options_type.genotype_likelihoods.prob_contamination}" |
| 13 | 205 #end if |
| 206 | |
| 207 ## ALGORITHMIC FEATURES | |
| 208 | |
| 209 #if str( $options_type.algorithmic_features.algorithmic_features_selector ) == "True": | |
| 15 | 210 ${options_type.algorithmic_features.report_genotype_likelihood_max} |
| 13 | 211 -B "${options_type.algorithmic_features.B}" |
| 212 --genotyping-max-banddepth "${options_type.algorithmic_features.genotyping_max_banddepth}" | |
| 213 -W "${options_type.algorithmic_features.W}" | |
| 214 ${options_type.algorithmic_features.N} | |
| 215 | |
| 216 #if str( $options_type.algorithmic_features.genotype_variant_threshold.genotype_variant_threshold_selector ) == "True": | |
| 217 -S "${options_type.algorithmic_features.genotype_variant_threshold.S}" | |
| 218 #end if | |
| 219 | |
| 220 ${options_type.algorithmic_features.j} | |
| 221 ${options_type.algorithmic_features.H} | |
| 222 -D "${options_type.algorithmic_features.D}" | |
| 223 ${options_type.algorithmic_features.genotype_qualities} | |
| 224 #end if | |
| 225 #end if | |
| 226 | |
| 227 </command> | |
| 228 | |
| 229 <inputs> | |
| 230 <conditional name="reference_source"> | |
| 231 <param name="reference_source_selector" type="select" label="Load reference genome from"> | |
| 232 <option value="cached">Local cache</option> | |
| 233 <option value="history">History</option> | |
| 234 </param> | |
| 235 <when value="cached"> | |
| 236 <repeat name="input_bams" title="Sample BAM file" min="1"> | |
| 237 <param name="input_bam" type="data" format="bam" label="BAM file"> | |
| 238 <validator type="unspecified_build" /> | |
| 16 | 239 <validator type="dataset_metadata_in_data_table" table_name="fasta_indexes" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." /> |
| 13 | 240 </param> |
| 241 </repeat> | |
| 16 | 242 |
| 13 | 243 <param name="ref_file" type="select" label="Using reference genome"> |
| 16 | 244 <options from_data_table="fasta_indexes"></options> |
| 13 | 245 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> |
| 246 </param> | |
| 247 </when> | |
| 248 <when value="history"> <!-- FIX ME!!!! --> | |
| 249 <repeat name="input_bams" title="Sample BAM file" min="1"> | |
| 250 <param name="input_bam" type="data" format="bam" label="BAM file" /> | |
| 251 </repeat> | |
| 16 | 252 <param name="ref_file" type="data" format="fasta" label="Use the following dataset as the reference sequence" help="You can upload a FASTA sequence to the history and use it as reference" /> |
| 13 | 253 </when> |
| 254 </conditional> | |
| 255 | |
| 256 <conditional name="target_limit_type"> | |
| 257 <param name="target_limit_type_selector" type="select" label="Limit variant calling to a set of regions?" help="Sets --targets or --region options"> | |
| 258 <option value="do_not_limit" selected="True">Do not limit</option> | |
| 259 <option value="limit_by_target_file">Limit by target file</option> | |
| 260 <option value="limit_by_region">Limit to region</option> | |
| 261 </param> | |
| 262 <when value="do_not_limit"> | |
| 263 <!-- Do nothing here --> | |
| 264 </when> | |
| 265 <when value="limit_by_target_file"> | |
| 266 <param name="input_target_bed" type="data" format="bed" label="Limit analysis to targets listed in the BED-format FILE." help="-t --targets"/> | |
| 267 </when> | |
| 268 <when value="limit_by_region"> | |
| 269 <param name="region_chromosome" type="text" label="Region Chromosome" value="" help="-r --region"/> <!--only once? --> | |
| 270 <param name="region_start" type="integer" label="Region Start" value="" /> | |
| 271 <param name="region_end" type="integer" label="Region End" value="" /> | |
| 272 </when> | |
| 273 </conditional> | |
| 274 | |
| 275 <conditional name="options_type"> | |
| 276 <param name="options_type_selector" type="select" label="Choose parameter selection level" help="Select how much control over the freebayes run you need" > | |
| 277 <option value="simple" selected="True">1:Simple diploid calling</option> | |
| 278 <option value="simple_w_filters">2:Simple diploid calling with filtering and coverage</option> | |
| 279 <option value="naive">3:Frequency-based pooled calling</option> | |
| 280 <option value="naive_w_filters">4:Frequency-based pooled calling with filtering and coverage</option> | |
| 281 <option value="full">5:Complete list of all options</option> | |
| 16 | 282 <!-- We will not alloow command line text boxes at this time |
| 13 | 283 <option value="cline">6:Input parameters on the command line</option> |
| 16 | 284 --> |
| 13 | 285 </param> |
| 286 <when value="full"> | |
| 17 | 287 |
| 288 <conditional name="optional_inputs"> | |
| 289 <param name="optional_inputs_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Do you want to provide additional inputs?" help="Sets --samples, --populations, --cnv-map, --trace, --failed-alleles, --varinat-input, --only-use-input-alleles, --haplotype-basis-alleles, --report-all-haplotype-alleles, --report-monomorphic options, --observation-bias, and --contamination-estimates" /> | |
| 290 <when value="set"> | |
| 291 <param name="output_failed_alleles_option" type="boolean" truevalue="--failed-alleles" falsevalue="" checked="False" label="Write out failed alleles file" help="--failed-alleles" /> | |
| 292 <param name="output_trace_option" type="boolean" truevalue="--trace" falsevalue="" checked="False" label="Write out algorithm trace file" help="--trace"/> | |
| 293 <param name="samples" type="data" format="txt" label="Limit analysis to samples listed (one per line) in the FILE" optional="True" help="-s --samples; default=By default FreeBayes will analyze all samples in its input BAM files"/> | |
| 294 <param name="populations" type="data" format="txt" label="Populations File" optional="True" help="--populations; default=False. Each line of FILE should list a sample and a population which it is part of. The population-based bayesian inference model will then be partitioned on the basis of the populations" /> | |
| 295 <param name="A" type="data" format="bed" label="Read a copy number map from the BED file FILE" optional="True" help="-A --cnv-map; default=copy number is set to as specified by --ploidy. Read a copy number map from the BED file FILE, which has the format: reference sequence, start, end, sample name, copy number ... for each region in each sample which does not have the default copy number as set by --ploidy."/> | |
| 296 <conditional name="input_variant_type"> | |
| 297 <param name="input_variant_type_selector" type="select" label="Provide variants file"> | |
| 298 <option value="do_not_provide" selected="True">Do not provide</option> | |
| 299 <option value="provide_vcf">Provide VCF file</option> | |
| 300 </param> | |
| 301 <when value="do_not_provide"> | |
| 302 <!-- Do nothing here --> | |
| 303 </when> | |
| 304 <when value="provide_vcf"> | |
| 305 <param name="input_variant_vcf" type="data" format="vcf_bgzip" label="Use variants reported in VCF file as input to the algorithm"> | |
| 306 <conversion name="Tabixized_input" type="tabix" /> | |
| 307 </param> | |
| 308 <param name="only_use_input_alleles" type="boolean" truevalue="--only-use-input-alleles" falsevalue="" checked="False" label="Only provide variant calls and genotype likelihoods for sites in VCF" /> | |
| 309 </when> | |
| 310 </conditional> | |
| 311 <param name="haplotype_basis_alleles" type="data" format="vcf" label="Only use variant alleles provided in this input VCF for the construction of complex or haplotype alleles" optional="True" help="--haplotype-basis-alleles" /> | |
| 312 <param name="report_monomorphic" type="boolean" truevalue="--report-monomorphic" falsevalue="" checked="False" label="Report even loci which appear to be monomorphic, and report all considered alleles, even those which are not in called genotypes." help="--report-monomorphic " /> | |
| 313 <param name="observation_bias" optional="True" type="data" format="tabular" label="Load read length-dependent allele observation biases from" help="--observation-bias; The format is [length] [alignment efficiency relative to reference] where the efficiency is 1 if there is no relative observation bias" /> | |
| 314 <param name="contamination_estimates" optional="True" type="data" format="tabular" label="Upload per-sample estimates of contamination from" help="--contamination-estimates; The format should be: sample p(read=R|genotype=AR) p(read=A|genotype=AA) Sample '*' can be used to set default contamination estimates." /> | |
| 315 </when> | |
| 316 <when value="do_not_set"> | |
| 317 <!-- do nothing --> | |
| 318 </when> | |
| 319 </conditional> | |
| 13 | 320 |
| 321 <!-- reporting --> | |
| 322 | |
| 323 <conditional name="reporting"> | |
| 324 <param name="reporting_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set reporting option?" help="Sets -P --pvar option" /> | |
| 325 <when value="set"> | |
| 326 <param name="pvar" type="float" value="0.0" label="Report sites if the probability that there is a polymorphism at the site is greater than" help="-P --pvar; default=0.0. Note that post-filtering is generally recommended over the use of this parameter. " /> | |
| 327 </when> | |
| 328 <when value="do_not_set"> | |
| 329 <!-- do nothing --> | |
| 330 </when> | |
| 331 </conditional> | |
| 332 | |
| 333 <!-- population model --> | |
| 334 | |
| 335 <conditional name="population_model"> | |
| 336 <param name="population_model_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set population model?" help="Sets --theta, --ploidy, --pooled-discrete, and --pooled-continuous options " /> | |
| 337 <when value="set"> | |
| 338 <param name="T" type="float" value="0.001" label="The expected mutation rate or pairwise nucleotide diversity among the population under analysis" help="-T --theta; default = 0.001. This serves as the single parameter to the Ewens Sampling Formula prior model." /> | |
| 339 <param name="P" type="integer" value="2" label="Set ploidy for the analysis" help="-p --ploidy; default=2" /> | |
| 340 <param name="J" type="boolean" truevalue="-J" falsevalue="" checked="False" label="Assume that samples result from pooled sequencing" help="-J --pooled-discrete; default=False. Model pooled samples using discrete genotypes across pools. When using this flag, set --ploidy to the number of alleles in each sample or use the --cnv-map to define per-sample ploidy." /> | |
| 341 <param name="K" type="boolean" truevalue="-K" falsevalue="" checked="False" label="Output all alleles which pass input filters, regardles of genotyping outcome or model" help="-K, --poled-continuous; default=False. " /> | |
| 342 </when> | |
| 343 <when value="do_not_set"> | |
| 344 <!-- do nothing --> | |
| 345 </when> | |
| 346 </conditional> | |
| 347 | |
| 348 <!-- reference allele --> | |
| 349 | |
| 350 <conditional name="reference_allele"> | |
| 351 <param name="reference_allele_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Use reference allele?" help="Sets --use-reference-allele and --reference-quality options " /> | |
| 352 <when value="set"> | |
| 353 <param name="Z" type="boolean" truevalue="-Z" falsevalue="" checked="False" label="Include the reference allele in the analysis as if it is another sample from the same population" help="-Z --use-reference-allele; default=False" /> | |
| 354 <param name="reference_quality" type="text" size="8" value="100,60" label="Assign mapping quality of MQ (100) to the reference allele at each site and base quality of BQ (60)" help="--reference-quality; default=100,60 " /> | |
| 355 </when> | |
| 356 <when value="do_not_set"> | |
| 357 <!-- do nothing --> | |
| 358 </when> | |
| 359 </conditional> | |
| 360 | |
| 361 <!-- allelic scope --> | |
| 362 | |
| 363 <conditional name="allele_scope"> | |
| 15 | 364 <param name="allele_scope_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set allelic scope?" help="Sets -I, i, -X, -u, -n, --haplotype-length, --min-repeat-size, --min-repeat-entropy, and --no-partial-observations options " /> |
| 13 | 365 <when value="set"> |
| 366 <param name="I" type="boolean" truevalue="-I" falsevalue="" checked="False" label="Ignore SNP alleles" help="-I --no-snps; default=False" /> | |
| 367 <param name="i" type="boolean" truevalue="-i" falsevalue="" checked="False" label="Ignore indels alleles" help="-i --no-indels; default=False" /> | |
| 368 <param name="X" type="boolean" truevalue="-X" falsevalue="" checked="False" label="Ignore multi-nucleotide polymorphisms, MNPs" help="-X --no-mnps; default=False" /> | |
| 369 <param name="u" type="boolean" truevalue="-u" falsevalue="" checked="False" label="Ignore complex events (composites of other classes)." help="-u --no-complex; default=False" /> | |
| 370 <param name="n" type="integer" value="0" label="How many best SNP alleles to evaluate" help="-n --use-best-n-alleles; default=0 (all). Alleles are ranked by the sum of supporting quality scores. Set to 0 to evaluate all" /> | |
| 15 | 371 <param name="haplotype_length" type="integer" value="3" label="Allow haplotype calls with contiguous embedded matches of up to (nucleotides)" help="-E --max-complex-gap --haplotype-length; default=3." /> |
| 372 <param name="min_repeat_length" type="integer" value="5" label="When assembling observations across repeats, require the total repeat length at least this many bp" help="--min-repeat-size; default=5." /> | |
| 373 <param name="min_repeat_entropy" type="integer" value="0" label="To detect interrupted repeats, build across sequence until it has entropy > (bits per bp)" help="--min-repeat-entropy; default=0 (off)." /> | |
| 13 | 374 <param name="no_partial_observations" type="boolean" truevalue="--no-partial-observations" falsevalue="" checked="False" label="Exclude observations which do not fully span the dynamically-determined detection window" help="--no-partial-observations; default=use all observations, dividing partial support across matching haplotypes when generating haplotypes. " /> |
| 375 </when> | |
| 376 <when value="do_not_set"> | |
| 377 <!-- do nothing --> | |
| 378 </when> | |
| 379 </conditional> | |
| 380 | |
| 381 <!-- indel realignment --> | |
| 382 | |
| 383 <param name="O" type="boolean" truevalue="-O" falsevalue="" checked="False" label="Turn off left-alignment of indels?" help="-O --dont-left-align-indels; default=False (do left align). " /> | |
| 384 | |
| 385 <!-- input filters --> | |
| 386 | |
| 387 <conditional name="input_filters"> | |
| 388 <param name="input_filters_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set input filters?" help="Sets -4, -m, -q, -R, -Y, -Q, -U, -z, -$, -e, -0, -F, -C, -3, -G, and -! options " /> | |
| 389 <when value="set"> | |
| 390 <param name="use_duplicate_reads" type="boolean" truevalue="--use-duplicate-reads" falsevalue="" checked="False" label="Include duplicate-marked alignments in the analysis." help="-4 --use-duplicate-reads; default=False (exclude duplicates marked as such in alignments)." /> | |
| 391 <param name="m" type="integer" value="1" label="Exclude alignments from analysis if they have a mapping quality less than" help="-m --min-mapping-quality; default=1" /> | |
| 392 <param name="q" type="integer" value="0" label="Exclude alleles from analysis if their supporting base quality less than" help="-q --min-base-quality; default=0" /> | |
| 393 <param name="R" type="integer" value="0" label="Consider any allele in which the sum of qualities of supporting observations is at least" help="-R --min-supporting-allele-qsum; default=0" /> | |
| 394 <param name="Y" type="integer" value="0" label="Consider any allele in which and the sum of mapping qualities of supporting reads is at least" help="-Y --min-supporting-mapping-qsum; default=0" /> | |
| 395 <conditional name="mismatch_filters"> | |
| 396 <param name="mismatch_filters_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Perform mismatch filtering?" help="Sets -Q, -U, -z, and $ options" /> | |
| 397 <when value="set"> | |
| 398 <param name="Q" type="integer" value="10" label="Count mismatches toward -U (option below) if the base quality of the mismatch is >=" help="-Q --mismatch-base-quality-threshold; default=10" /> | |
| 399 <param name="U" type="integer" value="1000" optional="True" label="Exclude reads with more than N mismatches where each mismatch has base quality >= Q (option above)" help="-U --read-mismatch-limit; default=~unbound" /> | |
| 400 <param name="z" type="float" value="1.0" min="0.0" max="1.0" label="Exclude reads with more than N [0,1] fraction of mismatches where each mismatch has base quality >= Q (second option above)" help="-z --read-max-mismatch-fraction; default=1.0" /> | |
| 401 <param name="read_snp_limit" type="integer" value="1000" label="Exclude reads with more than N base mismatches, ignoring gaps with quality >= Q (third option abobe)" help="-$amp; --read-snp-limit N " /> | |
| 402 </when> | |
| 403 <when value="do_not_set"> | |
| 404 <!-- do nothing --> | |
| 405 </when> | |
| 406 </conditional> | |
| 407 <param name="e" type="integer" value="1000" label="Exclude reads with more than this number of separate gaps" help="-e --read-snp-limit; default=~unbounded" /> | |
| 408 <param name="standard_filters" type="boolean" truevalue="-0" falsevalue="" checked="False" label="Use stringent input base and mapping quality filters" help="-0 --standard-filters; default=False. Equivalent to -m 30 -q 20 -R 0 -S 0" /> | |
| 409 <param name="F" type="float" value="0.2" label="Require at least this fraction of observations supporting an alternate allele within a single individual in the in order to evaluate the position" help="-F --min-alternate-fraction; default=0.2" /> | |
| 410 <param name="C" type="integer" value="2" label="Require at least this count of observations supporting an alternate allele within a single individual in order to evaluate the position" help="-C --min-alternate-count; default=2" /> | |
| 411 <param name="min_alternate_qsum" type="integer" value="0" label="Require at least this sum of quality of observations supporting an alternate allele within a single individual in order to evaluate the position" help="-3 --min-alternate-qsum; default=0" /> | |
| 412 <param name="G" type="integer" value="1" label="Require at least this count of observations supporting an alternate allele within the total population in order to use the allele in analysis" help="-G --min-alternate-total N; default=1" /> | |
| 413 <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " /> | |
| 414 </when> | |
| 415 <when value="do_not_set"> | |
| 416 <!-- do nothing --> | |
| 417 </when> | |
| 418 </conditional> | |
| 419 | |
| 420 <!-- population and mappability priors --> | |
| 421 | |
| 422 <conditional name="population_mappability_priors"> | |
| 423 <param name="population_mappability_priors_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set population and mappability priors?" help="Sets -k, -w, -V, and -a options " /> | |
| 424 <when value="set"> | |
| 425 <param name="k" type="boolean" truevalue="-k" falsevalue="" checked="False" label="No population priors" help="-k --no-population-priors; default=False. Equivalent to --pooled-discrete --hwe-priors-off and removal of Ewens Sampling Formula component of priors." /> | |
| 426 <param name="w" type="boolean" truevalue="-w" falsevalue="" checked="False" label="Disable estimation of the probability of the combination arising under HWE given the allele frequency as estimated by observation frequency" help="-w --hwe-priors-off; default=False" /> | |
| 427 <param name="V" type="boolean" truevalue="-V" falsevalue="" checked="False" label="Disable incorporation of prior expectations about observations" help="-V --binomial-obs-priors-off; default=False. Uses read placement probability, strand balance probability, and read position (5''-3'') probability." /> | |
| 428 <param name="a" type="boolean" truevalue="-a" falsevalue="" checked="False" label="isable use of aggregate probability of observation balance between alleles as a component of the priors" help="-a --allele-balance-priors-off; default=False " /> | |
| 429 </when> | |
| 430 <when value="do_not_set"> | |
| 431 <!-- do nothing --> | |
| 432 </when> | |
| 433 </conditional> | |
| 434 | |
| 435 <!-- genotype likelihoods --> | |
| 436 | |
| 437 <conditional name="genotype_likelihoods"> | |
| 438 <param name="genotype_likelihoods_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Tweak genotype likelihoods?" help="Sets --base-quality-cap, --experimental-gls, and --prob-contamination options. " /> | |
| 439 <when value="set"> | |
| 440 <param name="base_quality_cap" type="integer" value="0" label="Limit estimated observation quality by capping base quality at" help="--base-quality-cap" /> | |
| 441 <param name="experimental_gls" type="boolean" truevalue="--experimental-gls" falsevalue="" checked="False" label="Generate genotype likelihoods using 'effective base depth' metric qual = 1-BaseQual * 1-MapQual" help="--experimental-gls; Incorporate partial observations. This is the default when contamination estimates are provided. Optimized for diploid samples." /> | |
| 442 <param name="prob_contamination" type="float" value="10e-9" label="An estimate of contamination to use for all samples. " help="--prob-contamination; default=10e-9." /> | |
| 443 </when> | |
| 444 <when value="do_not_set"> | |
| 445 <!-- do nothing --> | |
| 446 </when> | |
| 447 </conditional> | |
| 448 | |
| 449 <!-- algorithmic features --> | |
| 450 | |
| 451 <conditional name="algorithmic_features"> | |
| 15 | 452 <param name="algorithmic_features_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Tweak algorithmic features?" help="Sets --report-genotypes-likelihood-max, -B, --genotyping-max-banddepth, -W, -N, S, -j, -H, -D, -= options " /> |
| 13 | 453 <when value="set"> |
| 454 <param name="report_genotype_likelihood_max" type="boolean" truevalue="--report-genotype-likelihood-max" falsevalue="" checked="False" label="Report genotypes using the maximum-likelihood estimate provided from genotype likelihoods." help="--report-genotype-likelihood-max; default=False" /> | |
| 455 <param name="B" type="integer" value="1000" label="Iterate no more than N times during genotyping step" help="-B --genotyping-max-iterations; default=1000." /> | |
| 456 <param name="genotyping_max_banddepth" type="integer" value="6" label="Integrate no deeper than the Nth best genotype by likelihood when genotyping" help="--genotyping-max-banddepth; default=6" /> | |
| 457 <param name="W" type="text" size="8" value="1,3" label="Integrate all genotype combinations in our posterior space which include no more than N (1) samples with their Mth (3) best data likelihood" help="-W --posterior-integration-limits; default=1,3" /> | |
| 458 <param name="N" type="boolean" truevalue="--exclude-unobserved-genotypes" falsevalue="" checked="False" label="Skip sample genotypings for which the sample has no supporting reads" help="-N --exclude-unobserved-genotypes; default=False" /> | |
| 459 <conditional name="genotype_variant_threshold"> | |
| 460 <param name="genotype_variant_threshold_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Do you want to to limit posterior integration" help="-S --genotype-variant-threshold" /> | |
| 461 <when value="do_not_set"> | |
| 462 <!-- do nothing --> | |
| 463 </when> | |
| 464 <when value="set"> | |
| 465 <param name="S" value="" type="integer" label="Limit posterior integration to samples where the second-best genotype likelihood is no more than log(N) from the highest genotype likelihood for the sample." help="-S --genotype-variant-threshold; default=~unbounded" /> | |
| 466 </when> | |
| 467 </conditional> | |
| 468 <param name="j" type="boolean" truevalue="-j" falsevalue="" checked="False" label="Use mapping quality of alleles when calculating data likelihoods" help="-j --use-mapping-quality; default=False" /> | |
| 469 <param name="H" type="boolean" truevalue="-H" falsevalue="" checked="False" label="Use a weighted sum of base qualities around an indel, scaled by the distance from the indel" help="-H --harmonic-indel-quality; default=use a minimum Base Quality in flanking sequence." /> | |
| 470 <param name="D" type="float" value="0.9" label="Incorporate non-independence of reads by scaling successive observations by this factor during data likelihood calculations" help="-D --read-dependence-factor; default=0.9." /> | |
| 471 <param name="genotype_qualities" type="boolean" truevalue="--genotype-qualities" falsevalue="" checked="False" label="Calculate the marginal probability of genotypes and report as GQ in each sample field in the VCF output" help="-= --genotype-qualities; default=False " /> | |
| 472 </when> | |
| 473 <when value="do_not_set"> | |
| 474 <!-- do nothing --> | |
| 475 </when> | |
| 476 </conditional> | |
| 477 </when> | |
| 478 <when value="simple"> | |
| 479 <!-- do nothing --> | |
| 480 </when> | |
| 481 <when value="simple_w_filters"> | |
| 482 <!-- add standard-filters to command line --> | |
| 483 <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " /> | |
| 484 </when> | |
| 485 <when value="naive"> | |
| 486 <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic --> | |
| 487 </when> | |
| 488 <when value="naive_w_filters"> | |
| 489 <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic standard-filters--> | |
| 490 <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " /> | |
| 491 </when> | |
| 492 </conditional> | |
| 493 | |
| 494 </inputs> | |
| 17 | 495 |
| 13 | 496 <outputs> |
| 497 <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (variants)" /> | |
| 498 <data format="bed" name="output_failed_alleles_bed" label="${tool.name} on ${on_string} (failed alleles)"> | |
| 499 <filter>( options_type['options_type_selector'] == 'cline' or options_type['options_type_selector'] == 'full' ) and options_type['optional_inputs']['optional_inputs_selector'] is True and options_type['optional_inputs']['output_failed_alleles_option'] is True</filter> | |
| 500 </data> | |
| 501 <data format="txt" name="output_trace" label="${tool.name} on ${on_string} (trace)"> | |
| 502 <filter>( options_type['options_type_selector'] == 'cline' or options_type['options_type_selector'] == 'full' ) and options_type['optional_inputs']['optional_inputs_selector'] is True and options_type['optional_inputs']['output_trace_option'] is True</filter> | |
| 503 </data> | |
| 504 </outputs> | |
| 505 <tests> | |
| 506 <test> | |
| 507 <param name="reference_source_selector" value="history" /> | |
| 508 <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/> | |
| 509 <param name="input_bam" ftype="bam" value="freebayes-phix174.bam"/> | |
| 510 <param name="options_type_selector" value="simple"/> | |
| 511 <output name="output_vcf" file="freebayes-phix174-test1.vcf" compare="contains"/> | |
| 512 </test> | |
| 17 | 513 <test> |
| 514 <param name="reference_source_selector" value="history" /> | |
| 515 <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/> | |
| 516 <param name="input_bam" ftype="bam" value="freebayes-phix174.bam"/> | |
| 517 <param name="options_type_selector" value="naive_w_filters"/> | |
| 518 <param name="min_coverage" value="14"/> | |
| 519 <output name="output_vcf" file="freebayes-phix174-test2.vcf" compare="contains"/> | |
| 520 </test> | |
| 13 | 521 </tests> |
| 522 <stdio> | |
| 523 <exit_code range="1:" /> | |
| 524 </stdio> | |
| 525 <help> | |
| 526 **What it does** | |
| 527 | |
| 528 FreeBayes is a Bayesian genetic variant detector designed to find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms), indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and complex events (composite insertion and substitution events) smaller than the length of a short-read sequencing alignment. | |
| 529 | |
| 530 See https://github.com/ekg/freebayes for details on FreeBayes. | |
| 531 | |
| 17 | 532 This Galaxy instance of FreeBayes corresponds to release 0.9.20 |
| 13 | 533 |
| 534 ------ | |
| 535 | |
| 536 **Description** | |
| 537 | |
| 538 Privided BAM file(s) and a reference. FreeBayes will provide VCF output on standard out describing SNPs, indels, and complex variants in samples in the input alignments. | |
| 539 | |
| 540 By default, FreeBayes will consider variants supported by at least 2 observations in a single sample (-C) and also by at least 20% of the reads from a single sample (-F). These settings are suitable to low to high depth sequencing in haploid and diploid samples, but users working with polyploid or pooled samples may wish to adjust them depending on the characteristics of their sequencing data. | |
| 541 | |
| 542 FreeBayes is capable of calling variant haplotypes shorter than a read length where multiple polymorphisms segregate on the same read. The maximum distance between polymorphisms phased in this way is determined by the --max-complex-gap, which defaults to 3bp. In practice, this can comfortably be set to half the read length. | |
| 543 | |
| 544 Ploidy may be set to any level (-p), but by default all samples are assumed to be diploid. FreeBayes can model per-sample and per-region variation in copy-number (-A) using a copy-number variation map. | |
| 545 | |
| 546 FreeBayes can act as a frequency-based pooled caller and describe variants and haplotypes in terms of observation frequency rather than called genotypes. To do so, use --pooled-continuous and set input filters to a suitable level. Allele observation counts will be described by AO and RO fields in the VCF output. | |
| 547 | |
| 548 ------- | |
| 549 | |
| 550 **Galaxy-specific options** | |
| 551 | |
| 552 Galaxy allows six levels of control over FreeBayes options provided by **Choose parameter selection level** menu option. These are: | |
| 553 | |
| 554 1. *Simple diploid calling*: The simples possible FreeBayes application. Equvalent of using FreeBayes with only a BAM input and no other parameter options. | |
| 555 2. *Simple diploid calling with filtering and coverage*: Same as #1 plus two additional options: -0 (standard filters: --min-mapping-quality 30 --min-base-quality 20 --min-supporting-allele-qsum 0 --genotype-varinat-threshold 0) and --min-coverage. | |
| 556 3. *Frequency-based pooled calling*: This is equivalent to using FreeBayes with the following options: --haplotype-length 0 --min-alternate-count 1 --min-alternate-fraction 0 --pooled-continuous --report-monomorphic. This is the best choice for calling varinats in mixtures such as viral, bacterial, or organellar genomes. | |
| 557 4. *Frequency-based pooled calling with filtering and coverage*: Same as #3 but adds -0 and --min-coverage like in #2. | |
| 558 5. *Complete list of all options*: Gives you full control by exposing all FreeBayes options as Galaxy widgets. | |
| 559 | |
| 560 ----- | |
| 561 | |
| 562 **FreeBayes options** | |
| 563 | |
| 564 .. class:: infomark | |
| 565 | |
| 566 Note that each Galaxy parameter widget corresponding to command line flags listed below: | |
| 567 | |
| 568 Input and output:: | |
| 569 | |
| 570 -t --targets FILE | |
| 571 Limit analysis to targets listed in the BED-format FILE. | |
| 572 -r --region chrom:start_position-end_position | |
| 573 Limit analysis to the specified region, 0-base coordinates, | |
| 574 end_position included. Either '-' or '..' maybe used as a separator. | |
| 575 -s --samples FILE | |
| 576 Limit analysis to samples listed (one per line) in the FILE. | |
| 577 By default FreeBayes will analyze all samples in its input | |
| 578 BAM files. | |
| 579 --populations FILE | |
| 580 Each line of FILE should list a sample and a population which | |
| 581 it is part of. The population-based bayesian inference model | |
| 582 will then be partitioned on the basis of the populations. | |
| 583 -A --cnv-map FILE | |
| 584 Read a copy number map from the BED file FILE, which has | |
| 585 the format: | |
| 586 reference sequence, start, end, sample name, copy number | |
| 587 ... for each region in each sample which does not have the | |
| 588 default copy number as set by --ploidy. | |
| 589 --trace FILE Output an algorithmic trace to FILE. | |
| 590 --failed-alleles FILE | |
| 591 Write a BED file of the analyzed positions which do not | |
| 592 pass --pvar to FILE. | |
| 593 -@ --variant-input VCF | |
| 594 Use variants reported in VCF file as input to the algorithm. | |
| 595 Variants in this file will be treated as putative variants | |
| 596 even if there is not enough support in the data to pass | |
| 597 input filters. | |
| 598 -l --only-use-input-alleles | |
| 599 Only provide variant calls and genotype likelihoods for sites | |
| 600 and alleles which are provided in the VCF input, and provide | |
| 601 output in the VCF for all input alleles, not just those which | |
| 602 have support in the data. | |
| 603 --haplotype-basis-alleles VCF | |
| 604 When specified, only variant alleles provided in this input | |
| 605 VCF will be used for the construction of complex or haplotype | |
| 606 alleles. | |
| 607 --report-all-haplotype-alleles | |
| 608 At sites where genotypes are made over haplotype alleles, | |
| 609 provide information about all alleles in output, not only | |
| 610 those which are called. | |
| 611 --report-monomorphic | |
| 612 Report even loci which appear to be monomorphic, and report all | |
| 613 considered alleles, even those which are not in called genotypes. | |
| 614 Loci which do not have any potential alternates have '.' for ALT. | |
| 615 | |
| 616 Reporting:: | |
| 617 | |
| 618 -P --pvar N Report sites if the probability that there is a polymorphism | |
| 619 at the site is greater than N. default: 0.0. Note that post- | |
| 620 filtering is generally recommended over the use of this parameter. | |
| 621 | |
| 622 Population model:: | |
| 623 | |
| 624 -T --theta N The expected mutation rate or pairwise nucleotide diversity | |
| 625 among the population under analysis. This serves as the | |
| 626 single parameter to the Ewens Sampling Formula prior model | |
| 627 default: 0.001 | |
| 628 -p --ploidy N Sets the default ploidy for the analysis to N. default: 2 | |
| 629 -J --pooled-discrete | |
| 630 Assume that samples result from pooled sequencing. | |
| 631 Model pooled samples using discrete genotypes across pools. | |
| 632 When using this flag, set --ploidy to the number of | |
| 633 alleles in each sample or use the --cnv-map to define | |
| 634 per-sample ploidy. | |
| 635 -K --pooled-continuous | |
| 636 Output all alleles which pass input filters, regardles of | |
| 637 genotyping outcome or model. | |
| 638 | |
| 639 Reference allele:: | |
| 640 | |
| 641 -Z --use-reference-allele | |
| 642 This flag includes the reference allele in the analysis as | |
| 643 if it is another sample from the same population. | |
| 644 --reference-quality MQ,BQ | |
| 645 Assign mapping quality of MQ to the reference allele at each | |
| 646 site and base quality of BQ. default: 100,60 | |
| 647 | |
| 648 Allele scope:: | |
| 649 | |
| 650 -I --no-snps Ignore SNP alleles. | |
| 651 -i --no-indels Ignore insertion and deletion alleles. | |
| 652 -X --no-mnps Ignore multi-nuceotide polymorphisms, MNPs. | |
| 653 -u --no-complex Ignore complex events (composites of other classes). | |
| 654 -n --use-best-n-alleles N | |
| 655 Evaluate only the best N SNP alleles, ranked by sum of | |
| 656 supporting quality scores. (Set to 0 to use all; default: all) | |
| 657 -E --max-complex-gap N | |
| 658 --haplotype-length N | |
| 659 Allow haplotype calls with contiguous embedded matches of up | |
| 660 to this length. (default: 3) | |
| 15 | 661 --min-repeat-size N |
| 13 | 662 When assembling observations across repeats, require the total repeat |
| 663 length at least this many bp. (default: 5) | |
| 664 --min-repeat-entropy N | |
| 665 To detect interrupted repeats, build across sequence until it has | |
| 666 entropy > N bits per bp. (default: 0, off) | |
| 667 --no-partial-observations | |
| 668 Exclude observations which do not fully span the dynamically-determined | |
| 669 detection window. (default, use all observations, dividing partial | |
| 670 support across matching haplotypes when generating haplotypes.) | |
| 671 | |
| 672 Indel realignment:: | |
| 673 | |
| 674 -O --dont-left-align-indels | |
| 675 Turn off left-alignment of indels, which is enabled by default. | |
| 676 | |
| 677 Input filters:: | |
| 678 | |
| 679 -4 --use-duplicate-reads | |
| 680 Include duplicate-marked alignments in the analysis. | |
| 681 default: exclude duplicates marked as such in alignments | |
| 682 -m --min-mapping-quality Q | |
| 683 Exclude alignments from analysis if they have a mapping | |
| 684 quality less than Q. default: 1 | |
| 685 -q --min-base-quality Q | |
| 686 Exclude alleles from analysis if their supporting base | |
| 687 quality is less than Q. default: 0 | |
| 688 -R --min-supporting-allele-qsum Q | |
| 689 Consider any allele in which the sum of qualities of supporting | |
| 690 observations is at least Q. default: 0 | |
| 691 -Y --min-supporting-mapping-qsum Q | |
| 692 Consider any allele in which and the sum of mapping qualities of | |
| 693 supporting reads is at least Q. default: 0 | |
| 694 -Q --mismatch-base-quality-threshold Q | |
| 695 Count mismatches toward --read-mismatch-limit if the base | |
| 696 quality of the mismatch is >= Q. default: 10 | |
| 697 -U --read-mismatch-limit N | |
| 698 Exclude reads with more than N mismatches where each mismatch | |
| 699 has base quality >= mismatch-base-quality-threshold. | |
| 700 default: ~unbounded | |
| 701 -z --read-max-mismatch-fraction N | |
| 702 Exclude reads with more than N [0,1] fraction of mismatches where | |
| 703 each mismatch has base quality >= mismatch-base-quality-threshold | |
| 704 default: 1.0 | |
| 705 -$ --read-snp-limit N | |
| 706 Exclude reads with more than N base mismatches, ignoring gaps | |
| 707 with quality >= mismatch-base-quality-threshold. | |
| 708 default: ~unbounded | |
| 709 -e --read-indel-limit N | |
| 710 Exclude reads with more than N separate gaps. | |
| 711 default: ~unbounded | |
| 712 -0 --standard-filters Use stringent input base and mapping quality filters | |
| 713 Equivalent to -m 30 -q 20 -R 0 -S 0 | |
| 714 -F --min-alternate-fraction N | |
| 715 Require at least this fraction of observations supporting | |
| 716 an alternate allele within a single individual in the | |
| 717 in order to evaluate the position. default: 0.2 | |
| 718 -C --min-alternate-count N | |
| 719 Require at least this count of observations supporting | |
| 720 an alternate allele within a single individual in order | |
| 721 to evaluate the position. default: 2 | |
| 722 -3 --min-alternate-qsum N | |
| 723 Require at least this sum of quality of observations supporting | |
| 724 an alternate allele within a single individual in order | |
| 725 to evaluate the position. default: 0 | |
| 726 -G --min-alternate-total N | |
| 727 Require at least this count of observations supporting | |
| 728 an alternate allele within the total population in order | |
| 729 to use the allele in analysis. default: 1 | |
| 730 -! --min-coverage N | |
| 731 Require at least this coverage to process a site. default: 0 | |
| 732 | |
| 733 Population priors:: | |
| 734 | |
| 735 -k --no-population-priors | |
| 736 Equivalent to --pooled-discrete --hwe-priors-off and removal of | |
| 737 Ewens Sampling Formula component of priors. | |
| 738 | |
| 739 Mappability priors:: | |
| 740 | |
| 741 -w --hwe-priors-off | |
| 742 Disable estimation of the probability of the combination | |
| 743 arising under HWE given the allele frequency as estimated | |
| 744 by observation frequency. | |
| 745 -V --binomial-obs-priors-off | |
| 746 Disable incorporation of prior expectations about observations. | |
| 747 Uses read placement probability, strand balance probability, | |
| 748 and read position (5'-3') probability. | |
| 749 -a --allele-balance-priors-off | |
| 750 Disable use of aggregate probability of observation balance between alleles | |
| 751 as a component of the priors. | |
| 752 | |
| 753 Genotype likelihoods:: | |
| 754 | |
| 755 --observation-bias FILE | |
| 756 Read length-dependent allele observation biases from FILE. | |
| 757 The format is [length] [alignment efficiency relative to reference] | |
| 758 where the efficiency is 1 if there is no relative observation bias. | |
| 759 --base-quality-cap Q | |
| 760 Limit estimated observation quality by capping base quality at Q. | |
| 761 --experimental-gls | |
| 762 Generate genotype likelihoods using 'effective base depth' metric | |
| 763 qual = 1-BaseQual * 1-MapQual. Incorporate partial observations. | |
| 764 This is the default when contamination estimates are provided. | |
| 765 Optimized for diploid samples. | |
| 766 --prob-contamination F | |
| 767 An estimate of contamination to use for all samples. default: 10e-9 | |
| 768 --contamination-estimates FILE | |
| 769 A file containing per-sample estimates of contamination, such as | |
| 770 those generated by VerifyBamID. The format should be: | |
| 771 sample p(read=R|genotype=AR) p(read=A|genotype=AA) | |
| 772 Sample '*' can be used to set default contamination estimates. | |
| 773 | |
| 774 Algorithmic features:: | |
| 775 | |
| 776 --report-genotype-likelihood-max | |
| 777 Report genotypes using the maximum-likelihood estimate provided | |
| 778 from genotype likelihoods. | |
| 779 -B --genotyping-max-iterations N | |
| 780 Iterate no more than N times during genotyping step. default: 1000. | |
| 781 --genotyping-max-banddepth N | |
| 782 Integrate no deeper than the Nth best genotype by likelihood when | |
| 783 genotyping. default: 6. | |
| 784 -W --posterior-integration-limits N,M | |
| 785 Integrate all genotype combinations in our posterior space | |
| 786 which include no more than N samples with their Mth best | |
| 787 data likelihood. default: 1,3. | |
| 788 -N --exclude-unobserved-genotypes | |
| 789 Skip sample genotypings for which the sample has no supporting reads. | |
| 790 -S --genotype-variant-threshold N | |
| 791 Limit posterior integration to samples where the second-best | |
| 792 genotype likelihood is no more than log(N) from the highest | |
| 793 genotype likelihood for the sample. default: ~unbounded | |
| 794 -j --use-mapping-quality | |
| 795 Use mapping quality of alleles when calculating data likelihoods. | |
| 796 -H --harmonic-indel-quality | |
| 797 Use a weighted sum of base qualities around an indel, scaled by the | |
| 798 distance from the indel. By default use a minimum BQ in flanking sequence. | |
| 799 -D --read-dependence-factor N | |
| 800 Incorporate non-independence of reads by scaling successive | |
| 801 observations by this factor during data likelihood | |
| 802 calculations. default: 0.9 | |
| 803 -= --genotype-qualities | |
| 804 Calculate the marginal probability of genotypes and report as GQ in | |
| 805 each sample field in the VCF output. | |
| 806 | |
| 807 | |
| 808 ------ | |
| 809 | |
| 810 **Citation** | |
| 811 | |
| 812 For the underlying tool, please cite `Erik Garrison and Gabor Marth. Haplotype-based variant detection from short-read sequencing <http://arxiv.org/abs/1207.3907>`_. | |
| 813 | |
| 814 The initial version of the wrapper was produced by Dan Blankenberg and upgraded by Anton Nekrutenko. | |
| 815 | |
| 816 </help> | |
| 16 | 817 |
| 818 <citations> | |
| 819 <citation type="bibtex">@misc{1207.3907, | |
| 820 Author = {Erik Garrison}, | |
| 821 Title = {Haplotype-based variant detection from short-read sequencing}, | |
| 822 Year = {2012}, | |
| 823 Eprint = {arXiv:1207.3907}, | |
| 824 url = {http://arxiv.org/abs/1207.3907}, | |
| 825 }</citation> | |
| 826 </citations> | |
| 13 | 827 </tool> |