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