Mercurial > repos > devteam > freebayes

comparison freebayes.xml @ 13:2dd40b601766 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Fri, 20 Jun 2014 17:18:49 -0400
parents
children 59731e950e23
comparison
equal deleted inserted replaced
12:aaf568580946 13:2dd40b601766
1 <?xml version="1.0"?>
2 <tool id="freebayes" name="FreeBayes" version="freebayes-0.9.14">
3 <requirements>
4 <requirement type="package" version="freebayes-0.9.14_8a407cf5f4">freebayes</requirement>
5 <requirement type="package" version="0.1.18">samtools</requirement>
6 </requirements>
7 <description> - Bayesian genetic variant detector</description>
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}" "${reference_fasta_filename}" &amp;&amp;
15 samtools faidx "${reference_fasta_filename}" 2&gt;&amp;1 || echo "Error running samtools faidx for FreeBayes" &gt;&amp;2 &amp;&amp;
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_${bam_count}.bam" &amp;&amp;
22 ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" &amp;&amp;
23 #end for
24
25 ## Tabixize optional input_varinat_vcf file (for --variant-input option)
26
27 #if ( str( $options_type.options_type_selector ) == 'cline' or str( $options_type.options_type_selector ) == 'full' ) and str( $options_type.optional_inputs.optional_inputs_selector ) == 'set' 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 &amp;&amp;
29 ln -s "${Tabixized_input}" input_variant_vcf.vcf.gz.tbi &amp;&amp;
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}"
77
78 #elif str( $options_type.options_type_selector ) == "cline":
79
80 ${options_type.cline}
81
82 @optional_inputs_outputs@
83
84 #elif str( $options_type.options_type_selector ) == "full":
85
86 ##optional inputs and outputs
87
88 @optional_inputs_outputs@
89
90 ## REPORTING
91
92 #if str( $options_type.reporting.reporting_selector ) == "True":
93 --pvar ${options_type.reporting.pvar}
94 #end if
95
96 ## POPULATION MODEL
97
98 #if str( $options_type.population_model.population_model_selector ) == "True":
99 --theta "${options_type.population_model.T}"
100 --ploidy "${options_type.population_model.P}"
101 ${options_type.population_model.J}
102 ${options_type.population_model.K}
103
104 #end if
105
106 ## REFERENCE ALLELE
107
108 #if str( $options_type.reference_allele.reference_allele_selector ) == "True":
109 ${options_type.reference_allele.Z}
110 --reference-quality "${options_type.reference_allele.reference_quality}"
111 #end if
112
113 ## ALLELE SCOPE
114
115 #if str( $options_type.allele_scope.allele_scope_selector ) == "True":
116 ${options_type.allele_scope.I}
117 ${options_type.allele_scope.i}
118 ${options_type.allele_scope.X}
119 ${options_type.allele_scope.u}
120 -n "${options_type.allele_scope.n}"
121 --haplotype-length "${options_type.allele_scope.haplotype_length}"
122 --min-repeat-length "${options_type.allele_scope.min_repeat_length}"
123 --min-repeat-entropy "${options_type.allele_scope.min_repeat_entropy}"
124 ${options_type.allele_scope.no_partial_observations}
125 #end if
126
127 ## REALIGNMENT
128
129 ${options_type.O}
130
131 ##INPUT FILTERS
132
133 #if str( $options_type.input_filters.input_filters_selector ) == "True":
134 ${options_type.input_filters.use_duplicate_reads}
135 -m "${options_type.input_filters.m}"
136 -q "${options_type.input_filters.q}"
137 -R "${options_type.input_filters.R}"
138 -Y "${options_type.input_filters.Y}"
139
140 #if str( $options_type.input_filters.mismatch_filters.mismatch_filters_selector ) == "True":
141 -Q "${options_type.input_filters.mismatch_filters.Q}"
142 -U "${options_type.input_filters.mismatch_filters.U}"
143 -z "${options_type.input_filters.mismatch_filters.z}"
144 --read-snp-limit "${options_type.input_filters.mismatch_filters.read_snp_limit}"
145 #end if
146
147 -e "${options_type.input_filters.e}"
148 -F "${options_type.input_filters.F}"
149 -C "${options_type.input_filters.C}"
150 --min-alternate-qsum "${options_type.input_filters.min_alternate_qsum}"
151 -G "${options_type.input_filters.G}"
152 --min-coverage "${options_type.input_filters.min_coverage}"
153 #end if
154
155 ## POPULATION AND MAPPABILITY PRIORS
156
157 #if str( $options_type.population_mappability_priors.population_mappability_priors_selector ) == "True":
158 ${options_type.population_mappability_priors.k}
159 ${options_type.population_mappability_priors.w}
160 ${options_type.population_mappability_priors.V}
161 ${options_type.population_mappability_priors.a}
162 #end if
163
164 ## GENOTYPE LIKELIHOODS
165
166 #if str( $options_type.genotype_likelihoods.genotype_likelihoods_selector ) == "True":
167 --base-quality-cap "${$options_type.genotype_likelihoods.base_quality_cap}"
168 ${$options_type.genotype_likelihoods.experimental_gls}
169 --prob_contamination "${$options_type.genotype_likelihoods.prob_contamination}"
170 #end if
171
172 ## ALGORITHMIC FEATURES
173
174 #if str( $options_type.algorithmic_features.algorithmic_features_selector ) == "True":
175 v
176 -B "${options_type.algorithmic_features.B}"
177 --genotyping-max-banddepth "${options_type.algorithmic_features.genotyping_max_banddepth}"
178 -W "${options_type.algorithmic_features.W}"
179 ${options_type.algorithmic_features.N}
180
181 #if str( $options_type.algorithmic_features.genotype_variant_threshold.genotype_variant_threshold_selector ) == "True":
182 -S "${options_type.algorithmic_features.genotype_variant_threshold.S}"
183 #end if
184
185 ${options_type.algorithmic_features.j}
186 ${options_type.algorithmic_features.H}
187 -D "${options_type.algorithmic_features.D}"
188 ${options_type.algorithmic_features.genotype_qualities}
189 #end if
190 #end if
191
192 </command>
193
194 <macros>
195 <token name="@optional_inputs_outputs@">
196 ## This token gets injected in commane in two instances: when options_type.options_type_selector == "full" and "cline"
197
198 #if $options_type.optional_inputs.optional_inputs_selector:
199
200 #if $options_type.optional_inputs.output_trace_option:
201 --trace "${output_trace}"
202 #end if
203
204 #if $options_type.optional_inputs.output_failed_alleles_option:
205 --failed-alleles "${output_failed_alleles_bed}"
206 #end if
207
208 #if $options_type.optional_inputs.samples:
209 --samples "${options_type.optional_inputs.samples}"
210 #end if
211
212 #if $options_type.optional_inputs.populations:
213 --populations "${options_type.optional_inputs.populations}"
214 #end if
215
216 #if $options_type.optional_inputs.A:
217 --cnv-map "${options_type.optional_inputs.A}"
218 #end if
219
220 #if str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf":
221 --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
222 ${options_type.optional_inputs.input_variant_type.only_use_input_alleles}
223 #end if
224
225 #if $options_type.optional_inputs.haplotype_basis_alleles:
226 --haplotype-basis-alleles "${options_type.optional_inputs.haplotype_basis_alleles}"
227 #end if
228
229 #if $options_type.optional_inputs.observation_bias:
230 --observation-bias "${options_type.optional_inputs.observation_bias}"
231 #end if
232
233 #if $options_type.optional_inputs.contamination_estimates:
234 --contamination-estimates "${options_type.optional_inputs.contamination_estimates}"
235 #end if
236
237 #end if
238 </token>
239 <xml name="optional_file_inputs">
240 <conditional name="optional_inputs">
241 <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" />
242 <when value="set">
243 <param name="output_failed_alleles_option" type="boolean" truevalue="--failed-alleles" falsevalue="" checked="False" label="Write out failed alleles file" help="--failed-alleles" />
244 <param name="output_trace_option" type="boolean" truevalue="--trace" falsevalue="" checked="False" label="Write out algorithm trace file" help="--trace"/>
245 <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"/>
246 <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" />
247 <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."/>
248 <conditional name="input_variant_type">
249 <param name="input_variant_type_selector" type="select" label="Provide variants file">
250 <option value="do_not_provide" selected="True">Do not provide</option>
251 <option value="provide_vcf">Provide VCF file</option>
252 </param>
253 <when value="do_not_provide">
254 <!-- Do nothing here -->
255 </when>
256 <when value="provide_vcf">
257 <param name="input_variant_vcf" type="data" format="vcf_bgzip" label="Use variants reported in VCF file as input to the algorithm">
258 <conversion name="Tabixized_input" type="tabix" />
259 </param>
260 <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" />
261 </when>
262 </conditional>
263 <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" />
264 <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 " />
265 <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" />
266 <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." />
267 </when>
268 <when value="do_not_set">
269 <!-- do nothing -->
270 </when>
271 </conditional>
272 </xml>
273 </macros>
274
275 <inputs>
276 <conditional name="reference_source">
277 <param name="reference_source_selector" type="select" label="Load reference genome from">
278 <option value="cached">Local cache</option>
279 <option value="history">History</option>
280 </param>
281 <when value="cached">
282 <repeat name="input_bams" title="Sample BAM file" min="1">
283 <param name="input_bam" type="data" format="bam" label="BAM file">
284 <validator type="unspecified_build" />
285 <validator type="dataset_metadata_in_data_table" table_name="sam_fa_indexes" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." />
286 </param>
287 </repeat>
288 <param name="ref_file" type="select" label="Using reference genome">
289 <options from_data_table="sam_fa_indexes">
290 <!-- <filter type="sam_fa_indexes" key="dbkey" ref="input_bam" column="value"/> does not yet work in a repeat...-->
291 </options>
292 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
293 </param>
294 </when>
295 <when value="history"> <!-- FIX ME!!!! -->
296 <repeat name="input_bams" title="Sample BAM file" min="1">
297 <param name="input_bam" type="data" format="bam" label="BAM file" />
298 </repeat>
299 <param name="ref_file" type="data" format="fasta" label="Use the folloing dataset as the reference sequence" help="You can upload a FASTA sequence to the history and use it as reference" />
300 </when>
301 </conditional>
302
303 <conditional name="target_limit_type">
304 <param name="target_limit_type_selector" type="select" label="Limit variant calling to a set of regions?" help="Sets --targets or --region options">
305 <option value="do_not_limit" selected="True">Do not limit</option>
306 <option value="limit_by_target_file">Limit by target file</option>
307 <option value="limit_by_region">Limit to region</option>
308 </param>
309 <when value="do_not_limit">
310 <!-- Do nothing here -->
311 </when>
312 <when value="limit_by_target_file">
313 <param name="input_target_bed" type="data" format="bed" label="Limit analysis to targets listed in the BED-format FILE." help="-t --targets"/>
314 </when>
315 <when value="limit_by_region">
316 <param name="region_chromosome" type="text" label="Region Chromosome" value="" help="-r --region"/> <!--only once? -->
317 <param name="region_start" type="integer" label="Region Start" value="" />
318 <param name="region_end" type="integer" label="Region End" value="" />
319 </when>
320 </conditional>
321
322 <conditional name="options_type">
323 <param name="options_type_selector" type="select" label="Choose parameter selection level" help="Select how much control over the freebayes run you need" >
324 <option value="simple" selected="True">1:Simple diploid calling</option>
325 <option value="simple_w_filters">2:Simple diploid calling with filtering and coverage</option>
326 <option value="naive">3:Frequency-based pooled calling</option>
327 <option value="naive_w_filters">4:Frequency-based pooled calling with filtering and coverage</option>
328 <option value="full">5:Complete list of all options</option>
329 <option value="cline">6:Input parameters on the command line</option>
330 </param>
331 <when value="full">
332
333 <expand macro="optional_file_inputs" /> <!-- see macros section -->
334
335 <!-- reporting -->
336
337 <conditional name="reporting">
338 <param name="reporting_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set reporting option?" help="Sets -P --pvar option" />
339 <when value="set">
340 <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. " />
341 </when>
342 <when value="do_not_set">
343 <!-- do nothing -->
344 </when>
345 </conditional>
346
347 <!-- population model -->
348
349 <conditional name="population_model">
350 <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 " />
351 <when value="set">
352 <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." />
353 <param name="P" type="integer" value="2" label="Set ploidy for the analysis" help="-p --ploidy; default=2" />
354 <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." />
355 <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. " />
356 </when>
357 <when value="do_not_set">
358 <!-- do nothing -->
359 </when>
360 </conditional>
361
362 <!-- reference allele -->
363
364 <conditional name="reference_allele">
365 <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 " />
366 <when value="set">
367 <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" />
368 <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 " />
369 </when>
370 <when value="do_not_set">
371 <!-- do nothing -->
372 </when>
373 </conditional>
374
375 <!-- allelic scope -->
376
377 <conditional name="allele_scope">
378 <param name="allele_scope_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set allelic scope?" help="Sets -I, i, -X, -u, -n, -E, --haplotype-length, --min-repeat-length, --min-repeat-entropy, and --no-partial-observations options " />
379 <when value="set">
380 <param name="I" type="boolean" truevalue="-I" falsevalue="" checked="False" label="Ignore SNP alleles" help="-I --no-snps; default=False" />
381 <param name="i" type="boolean" truevalue="-i" falsevalue="" checked="False" label="Ignore indels alleles" help="-i --no-indels; default=False" />
382 <param name="X" type="boolean" truevalue="-X" falsevalue="" checked="False" label="Ignore multi-nucleotide polymorphisms, MNPs" help="-X --no-mnps; default=False" />
383 <param name="u" type="boolean" truevalue="-u" falsevalue="" checked="False" label="Ignore complex events (composites of other classes)." help="-u --no-complex; default=False" />
384 <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" />
385 <param name="haplotype_length" type="integer" value="3" label="Allow haplotype calls with contiguous embedded matches of up to (nucleotides)" help="--haplotype-length; default=3." />
386 <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-length; default=5." />
387 <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-entrpy; default=0 (off)." />
388 <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. " />
389 </when>
390 <when value="do_not_set">
391 <!-- do nothing -->
392 </when>
393 </conditional>
394
395 <!-- indel realignment -->
396
397 <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). " />
398
399 <!-- input filters -->
400
401 <conditional name="input_filters">
402 <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, -&#36;, -e, -0, -F, -C, -3, -G, and -&#33; options " />
403 <when value="set">
404 <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)." />
405 <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" />
406 <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" />
407 <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" />
408 <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" />
409 <conditional name="mismatch_filters">
410 <param name="mismatch_filters_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Perform mismatch filtering?" help="Sets -Q, -U, -z, and &#36; options" />
411 <when value="set">
412 <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" />
413 <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" />
414 <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" />
415 <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 " />
416 </when>
417 <when value="do_not_set">
418 <!-- do nothing -->
419 </when>
420 </conditional>
421 <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" />
422 <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" />
423 <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" />
424 <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" />
425 <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" />
426 <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" />
427 <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " />
428 </when>
429 <when value="do_not_set">
430 <!-- do nothing -->
431 </when>
432 </conditional>
433
434 <!-- population and mappability priors -->
435
436 <conditional name="population_mappability_priors">
437 <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 " />
438 <when value="set">
439 <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." />
440 <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" />
441 <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&#39;'-3&#39;') probability." />
442 <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 " />
443 </when>
444 <when value="do_not_set">
445 <!-- do nothing -->
446 </when>
447 </conditional>
448
449 <!-- genotype likelihoods -->
450
451 <conditional name="genotype_likelihoods">
452 <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. " />
453 <when value="set">
454 <param name="base_quality_cap" type="integer" value="0" label="Limit estimated observation quality by capping base quality at" help="--base-quality-cap" />
455 <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." />
456 <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." />
457 </when>
458 <when value="do_not_set">
459 <!-- do nothing -->
460 </when>
461 </conditional>
462
463 <!-- algorithmic features -->
464
465 <conditional name="algorithmic_features">
466 <param name="algorithmic_features_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Tweak agrithmic features?" help="Sets --report-genotypes-likelihood-max, -B, --genotyping-max-banddepth, -W, -N, S, -j, -H, -D, -= options " />
467 <when value="set">
468 <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" />
469 <param name="B" type="integer" value="1000" label="Iterate no more than N times during genotyping step" help="-B --genotyping-max-iterations; default=1000." />
470 <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" />
471 <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" />
472 <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" />
473 <conditional name="genotype_variant_threshold">
474 <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" />
475 <when value="do_not_set">
476 <!-- do nothing -->
477 </when>
478 <when value="set">
479 <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" />
480 </when>
481 </conditional>
482 <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" />
483 <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." />
484 <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." />
485 <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 " />
486 </when>
487 <when value="do_not_set">
488 <!-- do nothing -->
489 </when>
490 </conditional>
491 </when>
492 <when value="simple">
493 <!-- do nothing -->
494 </when>
495 <when value="simple_w_filters">
496 <!-- add standard-filters to command line -->
497 <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " />
498 </when>
499 <when value="naive">
500 <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic -->
501 </when>
502 <when value="naive_w_filters">
503 <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic standard-filters-->
504 <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " />
505 </when>
506 <when value="cline">
507
508 <expand macro="optional_file_inputs" /> <!-- see macros section -->
509
510 <param name="cline" size="60" type="text" value="-m 20 -q 30" label="Type command line tags here" help="All paremeters that DO NOT involve filenames can be typed here. Use &quot;Do you want to provide additional inputs?&quot; section above to control input and output files. For full syntax check help section below">
511 <sanitizer>
512 <valid initial="string.printable">
513 <remove value="&apos;"/>
514 </valid>
515 <mapping initial="none">
516 <add source="&apos;" target="__sq__"/>
517 </mapping>
518 </sanitizer>
519 </param>
520 </when>
521
522 </conditional>
523
524 </inputs>
525 <outputs>
526 <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (variants)" />
527 <data format="bed" name="output_failed_alleles_bed" label="${tool.name} on ${on_string} (failed alleles)">
528 <filter>( options_type['options_type_selector'] == 'cline' or options_type['options_type_selector'] == 'full' ) and options_type['optional_inputs']['optional_inputs_selector'] is True and options_type['optional_inputs']['output_failed_alleles_option'] is True</filter>
529 </data>
530 <data format="txt" name="output_trace" label="${tool.name} on ${on_string} (trace)">
531 <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>
532 </data>
533 </outputs>
534 <tests>
535 <test>
536 <param name="reference_source_selector" value="history" />
537 <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/>
538 <param name="input_bam" ftype="bam" value="freebayes-phix174.bam"/>
539 <param name="options_type_selector" value="simple"/>
540 <output name="output_vcf" file="freebayes-phix174-test1.vcf" compare="contains"/>
541 </test>
542 </tests>
543 <stdio>
544 <exit_code range="1:" />
545 </stdio>
546 <help>
547 **What it does**
548
549 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.
550
551 See https://github.com/ekg/freebayes for details on FreeBayes.
552
553 This Galaxy instance of FreeBayes corresponds to release 8a407cf5f4416b5eba5bf27ca80144cd5e75bb80
554
555 ------
556
557 **Description**
558
559 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.
560
561 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.
562
563 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.
564
565 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.
566
567 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.
568
569 -------
570
571 **Galaxy-specific options**
572
573 Galaxy allows six levels of control over FreeBayes options provided by **Choose parameter selection level** menu option. These are:
574
575 1. *Simple diploid calling*: The simples possible FreeBayes application. Equvalent of using FreeBayes with only a BAM input and no other parameter options.
576 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.
577 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.
578 4. *Frequency-based pooled calling with filtering and coverage*: Same as #3 but adds -0 and --min-coverage like in #2.
579 5. *Complete list of all options*: Gives you full control by exposing all FreeBayes options as Galaxy widgets.
580 6. *Input parameters on the command line*: Similar to the choice above but for those who does not like clicking. Here options can be directly typed into a text box.
581
582 -----
583
584 **FreeBayes options**
585
586 .. class:: infomark
587
588 Note that each Galaxy parameter widget corresponding to command line flags listed below:
589
590 Input and output::
591
592 -t --targets FILE
593 Limit analysis to targets listed in the BED-format FILE.
594 -r --region chrom:start_position-end_position
595 Limit analysis to the specified region, 0-base coordinates,
596 end_position included. Either '-' or '..' maybe used as a separator.
597 -s --samples FILE
598 Limit analysis to samples listed (one per line) in the FILE.
599 By default FreeBayes will analyze all samples in its input
600 BAM files.
601 --populations FILE
602 Each line of FILE should list a sample and a population which
603 it is part of. The population-based bayesian inference model
604 will then be partitioned on the basis of the populations.
605 -A --cnv-map FILE
606 Read a copy number map from the BED file FILE, which has
607 the format:
608 reference sequence, start, end, sample name, copy number
609 ... for each region in each sample which does not have the
610 default copy number as set by --ploidy.
611 --trace FILE Output an algorithmic trace to FILE.
612 --failed-alleles FILE
613 Write a BED file of the analyzed positions which do not
614 pass --pvar to FILE.
615 -@ --variant-input VCF
616 Use variants reported in VCF file as input to the algorithm.
617 Variants in this file will be treated as putative variants
618 even if there is not enough support in the data to pass
619 input filters.
620 -l --only-use-input-alleles
621 Only provide variant calls and genotype likelihoods for sites
622 and alleles which are provided in the VCF input, and provide
623 output in the VCF for all input alleles, not just those which
624 have support in the data.
625 --haplotype-basis-alleles VCF
626 When specified, only variant alleles provided in this input
627 VCF will be used for the construction of complex or haplotype
628 alleles.
629 --report-all-haplotype-alleles
630 At sites where genotypes are made over haplotype alleles,
631 provide information about all alleles in output, not only
632 those which are called.
633 --report-monomorphic
634 Report even loci which appear to be monomorphic, and report all
635 considered alleles, even those which are not in called genotypes.
636 Loci which do not have any potential alternates have '.' for ALT.
637
638 Reporting::
639
640 -P --pvar N Report sites if the probability that there is a polymorphism
641 at the site is greater than N. default: 0.0. Note that post-
642 filtering is generally recommended over the use of this parameter.
643
644 Population model::
645
646 -T --theta N The expected mutation rate or pairwise nucleotide diversity
647 among the population under analysis. This serves as the
648 single parameter to the Ewens Sampling Formula prior model
649 default: 0.001
650 -p --ploidy N Sets the default ploidy for the analysis to N. default: 2
651 -J --pooled-discrete
652 Assume that samples result from pooled sequencing.
653 Model pooled samples using discrete genotypes across pools.
654 When using this flag, set --ploidy to the number of
655 alleles in each sample or use the --cnv-map to define
656 per-sample ploidy.
657 -K --pooled-continuous
658 Output all alleles which pass input filters, regardles of
659 genotyping outcome or model.
660
661 Reference allele::
662
663 -Z --use-reference-allele
664 This flag includes the reference allele in the analysis as
665 if it is another sample from the same population.
666 --reference-quality MQ,BQ
667 Assign mapping quality of MQ to the reference allele at each
668 site and base quality of BQ. default: 100,60
669
670 Allele scope::
671
672 -I --no-snps Ignore SNP alleles.
673 -i --no-indels Ignore insertion and deletion alleles.
674 -X --no-mnps Ignore multi-nuceotide polymorphisms, MNPs.
675 -u --no-complex Ignore complex events (composites of other classes).
676 -n --use-best-n-alleles N
677 Evaluate only the best N SNP alleles, ranked by sum of
678 supporting quality scores. (Set to 0 to use all; default: all)
679 -E --max-complex-gap N
680 --haplotype-length N
681 Allow haplotype calls with contiguous embedded matches of up
682 to this length. (default: 3)
683 --min-repeat-length N
684 When assembling observations across repeats, require the total repeat
685 length at least this many bp. (default: 5)
686 --min-repeat-entropy N
687 To detect interrupted repeats, build across sequence until it has
688 entropy > N bits per bp. (default: 0, off)
689 --no-partial-observations
690 Exclude observations which do not fully span the dynamically-determined
691 detection window. (default, use all observations, dividing partial
692 support across matching haplotypes when generating haplotypes.)
693
694 Indel realignment::
695
696 -O --dont-left-align-indels
697 Turn off left-alignment of indels, which is enabled by default.
698
699 Input filters::
700
701 -4 --use-duplicate-reads
702 Include duplicate-marked alignments in the analysis.
703 default: exclude duplicates marked as such in alignments
704 -m --min-mapping-quality Q
705 Exclude alignments from analysis if they have a mapping
706 quality less than Q. default: 1
707 -q --min-base-quality Q
708 Exclude alleles from analysis if their supporting base
709 quality is less than Q. default: 0
710 -R --min-supporting-allele-qsum Q
711 Consider any allele in which the sum of qualities of supporting
712 observations is at least Q. default: 0
713 -Y --min-supporting-mapping-qsum Q
714 Consider any allele in which and the sum of mapping qualities of
715 supporting reads is at least Q. default: 0
716 -Q --mismatch-base-quality-threshold Q
717 Count mismatches toward --read-mismatch-limit if the base
718 quality of the mismatch is >= Q. default: 10
719 -U --read-mismatch-limit N
720 Exclude reads with more than N mismatches where each mismatch
721 has base quality >= mismatch-base-quality-threshold.
722 default: ~unbounded
723 -z --read-max-mismatch-fraction N
724 Exclude reads with more than N [0,1] fraction of mismatches where
725 each mismatch has base quality >= mismatch-base-quality-threshold
726 default: 1.0
727 -$ --read-snp-limit N
728 Exclude reads with more than N base mismatches, ignoring gaps
729 with quality >= mismatch-base-quality-threshold.
730 default: ~unbounded
731 -e --read-indel-limit N
732 Exclude reads with more than N separate gaps.
733 default: ~unbounded
734 -0 --standard-filters Use stringent input base and mapping quality filters
735 Equivalent to -m 30 -q 20 -R 0 -S 0
736 -F --min-alternate-fraction N
737 Require at least this fraction of observations supporting
738 an alternate allele within a single individual in the
739 in order to evaluate the position. default: 0.2
740 -C --min-alternate-count N
741 Require at least this count of observations supporting
742 an alternate allele within a single individual in order
743 to evaluate the position. default: 2
744 -3 --min-alternate-qsum N
745 Require at least this sum of quality of observations supporting
746 an alternate allele within a single individual in order
747 to evaluate the position. default: 0
748 -G --min-alternate-total N
749 Require at least this count of observations supporting
750 an alternate allele within the total population in order
751 to use the allele in analysis. default: 1
752 -! --min-coverage N
753 Require at least this coverage to process a site. default: 0
754
755 Population priors::
756
757 -k --no-population-priors
758 Equivalent to --pooled-discrete --hwe-priors-off and removal of
759 Ewens Sampling Formula component of priors.
760
761 Mappability priors::
762
763 -w --hwe-priors-off
764 Disable estimation of the probability of the combination
765 arising under HWE given the allele frequency as estimated
766 by observation frequency.
767 -V --binomial-obs-priors-off
768 Disable incorporation of prior expectations about observations.
769 Uses read placement probability, strand balance probability,
770 and read position (5'-3') probability.
771 -a --allele-balance-priors-off
772 Disable use of aggregate probability of observation balance between alleles
773 as a component of the priors.
774
775 Genotype likelihoods::
776
777 --observation-bias FILE
778 Read length-dependent allele observation biases from FILE.
779 The format is [length] [alignment efficiency relative to reference]
780 where the efficiency is 1 if there is no relative observation bias.
781 --base-quality-cap Q
782 Limit estimated observation quality by capping base quality at Q.
783 --experimental-gls
784 Generate genotype likelihoods using 'effective base depth' metric
785 qual = 1-BaseQual * 1-MapQual. Incorporate partial observations.
786 This is the default when contamination estimates are provided.
787 Optimized for diploid samples.
788 --prob-contamination F
789 An estimate of contamination to use for all samples. default: 10e-9
790 --contamination-estimates FILE
791 A file containing per-sample estimates of contamination, such as
792 those generated by VerifyBamID. The format should be:
793 sample p(read=R|genotype=AR) p(read=A|genotype=AA)
794 Sample '*' can be used to set default contamination estimates.
795
796 Algorithmic features::
797
798 --report-genotype-likelihood-max
799 Report genotypes using the maximum-likelihood estimate provided
800 from genotype likelihoods.
801 -B --genotyping-max-iterations N
802 Iterate no more than N times during genotyping step. default: 1000.
803 --genotyping-max-banddepth N
804 Integrate no deeper than the Nth best genotype by likelihood when
805 genotyping. default: 6.
806 -W --posterior-integration-limits N,M
807 Integrate all genotype combinations in our posterior space
808 which include no more than N samples with their Mth best
809 data likelihood. default: 1,3.
810 -N --exclude-unobserved-genotypes
811 Skip sample genotypings for which the sample has no supporting reads.
812 -S --genotype-variant-threshold N
813 Limit posterior integration to samples where the second-best
814 genotype likelihood is no more than log(N) from the highest
815 genotype likelihood for the sample. default: ~unbounded
816 -j --use-mapping-quality
817 Use mapping quality of alleles when calculating data likelihoods.
818 -H --harmonic-indel-quality
819 Use a weighted sum of base qualities around an indel, scaled by the
820 distance from the indel. By default use a minimum BQ in flanking sequence.
821 -D --read-dependence-factor N
822 Incorporate non-independence of reads by scaling successive
823 observations by this factor during data likelihood
824 calculations. default: 0.9
825 -= --genotype-qualities
826 Calculate the marginal probability of genotypes and report as GQ in
827 each sample field in the VCF output.
828
829
830 ------
831
832 **Citation**
833
834 For the underlying tool, please cite `Erik Garrison and Gabor Marth. Haplotype-based variant detection from short-read sequencing &lt;http://arxiv.org/abs/1207.3907&gt;`_.
835
836 The initial version of the wrapper was produced by Dan Blankenberg and upgraded by Anton Nekrutenko.
837
838 </help>
839 </tool>