1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/3097eedaf60b/ changeset: 3097eedaf60b user: dan date: 2012-02-01 17:25:18 summary: Add a new complete FreeBayes tool configuration. affected #: 4 files diff -r a372c3970447dd0caf123db7c3047d372bfb8092 -r 3097eedaf60b515fceae5d26639f8f4621099040 test-data/variant_detection/freebayes/freebayes_out_1.output_trace --- /dev/null +++ b/test-data/variant_detection/freebayes/freebayes_out_1.output_trace @@ -0,0 +1,8 @@ +phiX174,1411,allele,phiX174,phiX174,A,60,100 +phiX174,1412,allele,phiX174,phiX174,G,60,100 +phiX174,1413,allele,phiX174,phiX174,C,60,100 +phiX174,1414,allele,phiX174,phiX174,G,60,100 +phiX174,1415,allele,phiX174,phiX174,C,60,100 +phiX174,1416,allele,phiX174,phiX174,C,60,100 +phiX174,1417,allele,phiX174,phiX174,G,60,100 +phiX174,1418,allele,phiX174,phiX174,T,60,100 diff -r a372c3970447dd0caf123db7c3047d372bfb8092 -r 3097eedaf60b515fceae5d26639f8f4621099040 test-data/variant_detection/freebayes/freebayes_out_1.vcf.contains --- /dev/null +++ b/test-data/variant_detection/freebayes/freebayes_out_1.vcf.contains @@ -0,0 +1,2 @@ +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT A + diff -r a372c3970447dd0caf123db7c3047d372bfb8092 -r 3097eedaf60b515fceae5d26639f8f4621099040 tool_conf.xml.sample --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -415,6 +415,9 @@ <tool file="gatk/variant_eval.xml" /><tool file="gatk/variant_combine.xml" /></section> + <section name="NGS: Variant Detection" id="variant_detection"> + <tool file="variant_detection/freebayes.xml" /> + </section><section name="NGS: Peak Calling" id="peak_calling"><tool file="peak_calling/macs_wrapper.xml" /><tool file="peak_calling/sicer_wrapper.xml" /> diff -r a372c3970447dd0caf123db7c3047d372bfb8092 -r 3097eedaf60b515fceae5d26639f8f4621099040 tools/variant_detection/freebayes.xml --- /dev/null +++ b/tools/variant_detection/freebayes.xml @@ -0,0 +1,655 @@ +<?xml version="1.0"?> +<tool id="freebayes" name="FreeBayes" version="0.0.1"> + <requirements> + <requirement type="package" version="0.9.4">freebayes</requirement> + <requirement type="package">samtools</requirement> + </requirements> + <description> - Bayesian genetic variant detector</description> + <command> + ##set up input files + #set $reference_fasta_filename = "localref.fa" + #if str( $reference_source.reference_source_selector ) == "history": + ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" && + samtools faidx "${reference_fasta_filename}" 2>&1 || echo "Error running samtools faidx for FreeBayes" >&2 && + #else: + #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) + #end if + #for $bam_count, $input_bam in enumerate( $reference_source.input_bams ): + ln -s "${input_bam.input_bam}" "localbam_${bam_count}.bam" && + ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" && + #end for + ##finished setting up inputs + + ##start FreeBayes commandline + freebayes + #for $bam_count, $input_bam in enumerate( $reference_source.input_bams ): + --bam "localbam_${bam_count}.bam" + #end for + --fasta-reference "${reference_fasta_filename}" + + ##outputs + --vcf "${output_vcf}" + --trace "${output_trace}" + --failed-alleles "${output_failed_alleles_bed}" + + ##advanced options + #if str( $options_type.options_type_selector ) == "advanced": + ##additional inputs + #if str( $options_type.target_limit_type.target_limit_type_selector ) == "limit_by_target_file": + --targets "${options_type.target_limit_type.input_target_bed}" + #elif str( $options_type.target_limit_type.target_limit_type_selector ) == "limit_by_region": + --region "${options_type.target_limit_type.region_chromosome}:${options_type.target_limit_type.region_start}..${options_type.target_limit_type.region_end}" + #end if + #if $options_type.input_sample_file: + --samples "${options_type.input_sample_file}" + #end if + #if $options_type.input_populations_file: + --populations "${options_type.input_populations_file}" + #end if + #if $options_type.input_cnv_map_bed: + --cnv-map "${options_type.input_cnv_map_bed}" + #end if + #if str( $options_type.input_variant_type.input_variant_type_selector ) == "provide_vcf": + --variant-input "${options_type.input_variant_type.input_variant_vcf}" + ${options_type.input_variant_type.only_use_input_alleles} + #end if + + ##reporting + #if str( $options_type.section_reporting_type.section_reporting_type_selector ) == "set": + --pvar "${options_type.section_reporting_type.pvar}" + ${options_type.section_reporting_type.show_reference_repeats} + #end if + + ##population model + #if str( $options_type.section_population_model_type.section_population_model_type_selector ) == "set": + --theta "${options_type.section_population_model_type.theta}" + --ploidy "${options_type.section_population_model_type.ploidy}" + ${options_type.section_population_model_type.pooled} + #end if + + ##reference allele + #if str( $options_type.use_reference_allele_type.use_reference_allele_type_selector ) == "include_reference_allele": + --use-reference-allele + ${options_type.use_reference_allele_type.diploid_reference} + --reference-quality "${options_type.use_reference_allele_type.reference_quality_mq},${options_type.use_reference_allele_type.reference_quality_bq}" + #end if + + ##allele scope + #if str( $options_type.section_allele_scope_type.section_allele_scope_type_selector ) == "set": + ${options_type.section_allele_scope_type.no_snps} + ${options_type.section_allele_scope_type.no_indels} + ${options_type.section_allele_scope_type.no_mnps} + ${options_type.section_allele_scope_type.no_complex} + --use-best-n-alleles "${options_type.section_allele_scope_type.use_best_n_alleles}" + #if $options_type.section_allele_scope_type.max_complex_gap: + --max-complex-gap "${options_type.section_allele_scope_type.max_complex_gap}" + #end if + #end if + + ##indel realignment + ${options_type.left_align_indels} + + ##input filters + #if str( $options_type.section_input_filters_type.section_input_filters_type_selector ) == "set": + ${options_type.section_input_filters_type.use_duplicate_reads} + #if str( $options_type.section_input_filters_type.no_filter_type.no_filter_type_selector ) == "apply_filters": + --min-mapping-quality "${options_type.section_input_filters_type.no_filter_type.min_mapping_quality}" + --min-base-quality "${options_type.section_input_filters_type.no_filter_type.min_base_quality}" + --min-supporting-quality "${options_type.section_input_filters_type.no_filter_type.min_supporting_quality_mq},${options_type.section_input_filters_type.no_filter_type.min_supporting_quality_bq}" + #else: + --no-filters + #end if + --mismatch-base-quality-threshold "${options_type.section_input_filters_type.mismatch_base_quality_threshold}" + #if $options_type.section_input_filters_type.read_mismatch_limit: + --read-mismatch-limit "${options_type.section_input_filters_type.read_mismatch_limit}" + #end if + --read-max-mismatch-fraction "${options_type.section_input_filters_type.read_max_mismatch_fraction}" + #if $options_type.section_input_filters_type.read_snp_limit: + --read-snp-limit "${options_type.section_input_filters_type.read_snp_limit}" + #end if + #if $options_type.section_input_filters_type.read_indel_limit: + --read-indel-limit "${options_type.section_input_filters_type.read_indel_limit}" + #end if + --indel-exclusion-window "${options_type.section_input_filters_type.indel_exclusion_window}" + --min-alternate-fraction "${options_type.section_input_filters_type.min_alternate_fraction}" + --min-alternate-count "${options_type.section_input_filters_type.min_alternate_count}" + --min-alternate-qsum "${options_type.section_input_filters_type.min_alternate_qsum}" + --min-alternate-total "${options_type.section_input_filters_type.min_alternate_total}" + --min-coverage "${options_type.section_input_filters_type.min_coverage}" + #end if + + ##bayesian priors + #if str( $options_type.section_bayesian_priors_type.section_bayesian_priors_type_selector ) == "set": + ${options_type.section_bayesian_priors_type.no_ewens_priors} + ${options_type.section_bayesian_priors_type.no_population_priors} + ${options_type.section_bayesian_priors_type.hwe_priors} + #end if + + ##observation prior expectations + #if str( $options_type.section_observation_prior_expectations_type.section_observation_prior_expectations_type_selector ) == "set": + ${options_type.section_observation_prior_expectations_type.binomial_obs_priors} + ${options_type.section_observation_prior_expectations_type.allele_balance_priors} + #end if + + ##algorithmic features + #if str( $options_type.section_algorithmic_features_type.section_algorithmic_features_type_selector ) == "set": + --site-selection-max-iterations "${options_type.section_algorithmic_features_type.site_selection_max_iterations}" + --genotyping-max-iterations "${options_type.section_algorithmic_features_type.genotyping_max_iterations}" + --genotyping-max-banddepth "${options_type.section_algorithmic_features_type.genotyping_max_banddepth}" + --posterior-integration-limits "${options_type.section_algorithmic_features_type.posterior_integration_limits_n},${options_type.section_algorithmic_features_type.posterior_integration_limits_m}" + ${options_type.section_algorithmic_features_type.no_permute} + ${options_type.section_algorithmic_features_type.exclude_unobserved_genotypes} + #if $options_type.section_algorithmic_features_type.genotype_variant_threshold: + --genotype-variant-threshold "${options_type.section_algorithmic_features_type.genotype_variant_threshold}" + #end if + ${options_type.section_algorithmic_features_type.use_mapping_quality} + --read-dependence-factor "${options_type.section_algorithmic_features_type.read_dependence_factor}" + ${options_type.section_algorithmic_features_type.no_marginals} + #end if + + #end if + </command> + <inputs> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> + <option value="cached">Locally cached</option> + <option value="history">History</option> + </param> + <when value="cached"> + <repeat name="input_bams" title="Sample BAM file" min="1"> + <param name="input_bam" type="data" format="bam" label="BAM file"> + <validator type="unspecified_build" /> + <validator type="dataset_metadata_in_data_table" table_name="sam_fa_indexes" metadata_name="dbkey" metadata_column="value" message="Sequences are not currently available for the specified build." /> + </param> + </repeat> + <param name="ref_file" type="select" label="Using reference genome"> + <options from_data_table="sam_fa_indexes"> + <!-- <filter type="sam_fa_indexes" key="dbkey" ref="input_bam" column="value"/> does not yet work in a repeat...--> + </options> + <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> + </param> + </when> + <when value="history"><!-- FIX ME!!!! --> + <repeat name="input_bams" title="Sample BAM file" min="1"> + <param name="input_bam" type="data" format="bam" label="BAM file" /> + </repeat> + <param name="ref_file" type="data" format="fasta" label="Using reference file" /> + </when> + </conditional> + + <conditional name="options_type"> + <param name="options_type_selector" type="select" label="Basic or Advanced options"> + <option value="basic" selected="True">Basic</option> + <option value="advanced">Advanced</option> + </param> + <when value="basic"> + <!-- Do nothing here --> + </when> + <when value="advanced"> + + <!-- input and output --> + <conditional name="target_limit_type"> + <param name="target_limit_type_selector" type="select" label="Limit analysis to listed targets"> + <option value="do_not_limit" selected="True">Do not limit</option> + <option value="limit_by_target_file">Limit by target file</option> + <option value="limit_by_region">Limit to region</option> + </param> + <when value="do_not_limit"> + <!-- Do nothing here --> + </when> + <when value="limit_by_target_file"> + <param name="input_target_bed" type="data" format="bed" label="Limit analysis to targets listed in the BED-format FILE." /> + </when> + <when value="limit_by_region"> + <param name="region_chromosome" type="text" label="Region Chromosome" value="" /><!--only once? --> + <param name="region_start" type="integer" label="Region Start" value="" /> + <param name="region_end" type="integer" label="Region End" value="" /> + </when> + </conditional> + <param name="input_sample_file" type="data" format="txt" label="Limit analysis to samples listed (one per line) in the FILE" optional="True" /> + <param name="input_populations_file" type="data" format="txt" label="Populations File" optional="True" /> + <param name="input_cnv_map_bed" type="data" format="bed" label="Read a copy number map from the BED file FILE" optional="True" /> + <conditional name="input_variant_type"> + <param name="input_variant_type_selector" type="select" label="Provide variants file"> + <option value="do_not_provide" selected="True">Do not provide</option> + <option value="provide_vcf">Provide VCF file</option> + </param> + <when value="do_not_provide"> + <!-- Do nothing here --> + </when> + <when value="provide_vcf"> + <param name="input_variant_vcf" type="data" format="vcf" label="Use variants reported in VCF file as input to the algorithm" /> + <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" /> + </when> + </conditional> + + + <!-- reporting --> + <conditional name="section_reporting_type"> + <param name="section_reporting_type_selector" type="select" label="Set Reporting options"> + <option value="do_not_set" selected="True">Do not set</option> + <option value="set">Set</option> + </param> + <when value="do_no_set"> + <!-- do nothing here --> + </when> + <when value="set"> + <param name="pvar" type="float" label="Report sites if the probability that there is a polymorphism at the site is greater" value="0.0001" /> + <param name="show_reference_repeats" type="boolean" truevalue="--show-reference-repeats" falsevalue="" checked="False" label="Calculate and show information about reference repeats" /> + </when> + </conditional> + + + <!-- population model --> + <conditional name="section_population_model_type"> + <param name="section_population_model_type_selector" type="select" label="Set population model options"> + <option value="do_not_set" selected="True">Do not set</option> + <option value="set">Set</option> + </param> + <when value="do_no_set"> + <!-- do nothing here --> + </when> + <when value="set"> + <param name="theta" type="float" label="expected mutation rate or pairwise nucleotide diversity among the population" value="0.001" help="This serves as the single parameter to the Ewens Sampling Formula prior model"/> + <param name="ploidy" type="integer" label="default ploidy for the analysis" value="2" /> + <param name="pooled" type="boolean" truevalue="--pooled" falsevalue="" checked="False" label="Assume that samples result from pooled sequencing" help="When using this flag, set --ploidy to the number of alleles in each sample." /> + </when> + </conditional> + + <!-- reference allele --> + <conditional name="use_reference_allele_type"> + <param name="use_reference_allele_type_selector" type="select" label="Include the reference allele in the analysis"> + <option value="do_not_include_reference_allele" selected="True">Do not include</option> + <option value="include_reference_allele">Include</option> + </param> + <when value="do_not_include_reference_allele"> + <!-- Do nothing here --> + </when> + <when value="include_reference_allele"> + <param name="diploid_reference" type="boolean" truevalue="--diploid-reference" falsevalue="" checked="False" label="Treat reference as diploid" /> + <param name="reference_quality_mq" type="integer" label="Assign mapping quality" value="100" /> + <param name="reference_quality_bq" type="integer" label="Assign base quality" value="60" /> + </when> + </conditional> + + <!-- allele scope --> + <conditional name="section_allele_scope_type"> + <param name="section_allele_scope_type_selector" type="select" label="Set allele scope options"> + <option value="do_not_set" selected="True">Do not set</option> + <option value="set">Set</option> + </param> + <when value="do_no_set"> + <!-- do nothing here --> + </when> + <when value="set"> + <param name="no_snps" type="boolean" truevalue="--no-snps" falsevalue="" checked="False" label="Ignore SNP alleles" /> + <param name="no_indels" type="boolean" truevalue="--no-indels" falsevalue="" checked="False" label="Ignore insertion and deletion alleles" /> + <param name="no_mnps" type="boolean" truevalue="--no-mnps" falsevalue="" checked="False" label="Ignore multi-nuceotide polymorphisms, MNPs" /> + <param name="no_complex" type="boolean" truevalue="--no-complex" falsevalue="" checked="False" label="Ignore complex events (composites of other classes)" /> + <param name="use_best_n_alleles" type="integer" label="Evaluate only the best N SNP alleles" value="0" min="0" help="Ranked by sum of supporting quality scores; Set to 0 to use all" /> + <param name="max_complex_gap" type="integer" label="Allow complex alleles with contiguous embedded matches of up to this length" value="" optional="True"/> + </when> + </conditional> + + <!-- indel realignment --> + <param name="left_align_indels" type="boolean" truevalue="--left-align-indels" falsevalue="" checked="False" label="Left-realign and merge gaps embedded in reads" /> + + <!-- input filters --> + <conditional name="section_input_filters_type"> + <param name="section_input_filters_type_selector" type="select" label="Set input filters options"> + <option value="do_not_set" selected="True">Do not set</option> + <option value="set">Set</option> + </param> + <when value="do_no_set"> + <!-- do nothing here --> + </when> + <when value="set"> + <param name="use_duplicate_reads" type="boolean" truevalue="--use-duplicate-reads" falsevalue="" checked="False" label="Include duplicate-marked alignments in the analysis" /> + <conditional name="no_filter_type"> + <param name="no_filter_type_selector" type="select" label="Apply filters"> + <option value="apply_filters" selected="True">Apply</option> + <option value="no_filters">Do not apply</option> + </param> + <when value="no_filters"> + <!-- Do nothing here --><!-- no-filters --> + </when> + <when value="apply_filters"> + <param name="min_mapping_quality" type="integer" label="Exclude alignments from analysis if they have a mapping quality less than" value="30" /> + <param name="min_base_quality" type="integer" label="Exclude alleles from analysis if their supporting base quality less than" value="20" /> + <param name="min_supporting_quality_mq" type="integer" label="In order to consider an alternate allele, at least one supporting alignment must have mapping quality" value="0" /> + <param name="min_supporting_quality_bq" type="integer" label="In order to consider an alternate allele, at least one supporting alignment must have base quality" value="0" /> + </when> + </conditional> + <param name="mismatch_base_quality_threshold" type="integer" label="Count mismatches toward read-mismatch-limit if the base quality of the mismatch is >=" value="10" /> + <param name="read_mismatch_limit" type="integer" label="Exclude reads with more than N mismatches where each mismatch has base quality >= mismatch-base-quality-threshold" value="" optional="True" /> + <param name="read_max_mismatch_fraction" type="float" label="Exclude reads with more than N [0,1] fraction of mismatches where each mismatch has base quality >= mismatch-base-quality-threshold" value="1.0" /> + <param name="read_snp_limit" type="integer" label="Exclude reads with more than N base mismatches, ignoring gaps with quality >= mismatch-base-quality-threshold" value="" optional="True" /> + <param name="read_indel_limit" type="integer" label="Exclude reads with more than N separate gaps" value="" optional="True" /> + <param name="indel_exclusion_window" type="integer" label="Ignore portions of alignments this many bases from a putative insertion or deletion allele" value="0" /> + <param name="min_alternate_fraction" type="float" label="Require at least this fraction of observations supporting an alternate allele within a single individual in the in order to evaluate the position" value="0" /> + <param name="min_alternate_count" type="integer" label="Require at least this count of observations supporting an alternate allele within a single individual in order to evaluate the position" value="1" /> + <param name="min_alternate_qsum" type="integer" label="Require at least this sum of quality of observations supporting an alternate allele within a single individual in order to evaluate the position" value="0" /> + <param name="min_alternate_total" type="integer" label="Require at least this count of observations supporting an alternate allele within the total population in order to use the allele in analysis" value="1" /> + <param name="min_coverage" type="integer" label="Require at least this coverage to process a site" value="0" /> + </when> + </conditional> + + + <!-- bayesian priors --> + <conditional name="section_bayesian_priors_type"> + <param name="section_bayesian_priors_type_selector" type="select" label="Set bayesian priors options"> + <option value="do_not_set" selected="True">Do not set</option> + <option value="set">Set</option> + </param> + <when value="do_no_set"> + <!-- do nothing here --> + </when> + <when value="set"> + <param name="no_ewens_priors" type="boolean" truevalue="--no-ewens-priors" falsevalue="" checked="False" label="Turns off the Ewens' Sampling Formula component of the priors" /> + <param name="no_population_priors" type="boolean" truevalue="--no-population-priors" falsevalue="" checked="False" label="No population priors" help="Equivalent to --pooled --no-ewens-priors" /> + <param name="hwe_priors" type="boolean" truevalue="--hwe-priors" falsevalue="" checked="False" label="Use the probability of the combination arising under HWE given the allele frequency as estimated by observation frequency" /> + </when> + </conditional> + + <!-- observation prior expectations --> + <conditional name="section_observation_prior_expectations_type"> + <param name="section_observation_prior_expectations_type_selector" type="select" label="Set observation prior expectations options"> + <option value="do_not_set" selected="True">Do not set</option> + <option value="set">Set</option> + </param> + <when value="do_no_set"> + <!-- do nothing here --> + </when> + <when value="set"> + <param name="binomial_obs_priors" type="boolean" truevalue="--binomial-obs-priors" falsevalue="" checked="False" label="Incorporate expectations about osbervations into the priors, Uses read placement probability, strand balance probability, and read position (5'-3') probability" /> + <param name="allele_balance_priors" type="boolean" truevalue="--allele-balance-priors" falsevalue="" checked="False" label="Use aggregate probability of observation balance between alleles as a component of the priors. Best for observations with minimal inherent reference bias" /> + </when> + </conditional> + + + <!-- algorithmic features --> + <conditional name="section_algorithmic_features_type"> + <param name="section_algorithmic_features_type_selector" type="select" label="Set algorithmic features options"> + <option value="do_not_set" selected="True">Do not set</option> + <option value="set">Set</option> + </param> + <when value="do_no_set"> + <!-- do nothing here --> + </when> + <when value="set"> + <param name="site_selection_max_iterations" type="integer" label="Uses hill-climbing algorithm to search posterior space for N iterations to determine if the site should be evaluated." value="5" help="Set to 0 to prevent use of this algorithm for site selection, and to a low integer for improvide site selection at a slight performance penalty" /> + <param name="genotyping_max_iterations" type="integer" label="Iterate no more than N times during genotyping step" value="25" /> + <param name="genotyping_max_banddepth" type="integer" label="Integrate no deeper than the Nth best genotype by likelihood when genotyping" value="6" /> + <param name="posterior_integration_limits_n" type="integer" label="Posteriror integration limit N" help="Integrate all genotype combinations in our posterior space which include no more than N samples with their Mth best data likelihood." value="1" /> + <param name="posterior_integration_limits_m" type="integer" label="Posteriror integration limit M" help="Integrate all genotype combinations in our posterior space which include no more than N samples with their Mth best data likelihood." value="3" /> + <param name="no_permute" type="boolean" truevalue="--no-permute" falsevalue="" checked="False" label="Do not scale prior probability of genotype combination given allele frequency by the number of permutations of included genotypes" /> + <param name="exclude_unobserved_genotypes" type="boolean" truevalue="--exclude-unobserved-genotypes" falsevalue="" checked="False" label="Skip sample genotypings for which the sample has no supporting reads" /> + <param name="genotype_variant_threshold" 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" value="" optional="True" /> + <param name="use_mapping_quality" type="boolean" truevalue="--use-mapping-quality" falsevalue="" checked="False" label="Use mapping quality of alleles when calculating data likelihoods" /> + <param name="read_dependence_factor" type="float" label="Incorporate non-independence of reads by scaling successive observations by this factor during data likelihood calculations" value="0.9" /> + <param name="no_marginals" type="boolean" truevalue="--no-marginals" falsevalue="" checked="False" label="Do not calculate the marginal probability of genotypes. Saves time and improves scaling performance in large populations" /> + </when> + </conditional> + + + </when> + </conditional> + + </inputs> + <outputs> + <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (variants)" /> + <data format="txt" name="output_trace" label="${tool.name} on ${on_string} (trace)" /> + <data format="bed" name="output_failed_alleles_bed" label="${tool.name} on ${on_string} (failed alleles)" /> + </outputs> + <tests> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" ftype="fasta" value="phiX.fasta"/> + <param name="input_bam" ftype="bam" value="gatk/fake_phiX_reads_1.bam"/> + <param name="options_type_selector" value="basic"/> + <output name="output_vcf" file="variant_detection/freebayes/freebayes_out_1.vcf.contains" compare="contains"/> + <output name="output_trace" file="variant_detection/freebayes/freebayes_out_1.output_trace" /> + <output name="output_failed_alleles_bed" file="empty_file.dat" /> + </test> + </tests> + <help> +**What it does** + +This tool uses FreeBayes to call SNPS given a reference sequence and a BAM alignment file. + +FreeBayes is a high-performance, flexible, and open-source Bayesian genetic variant detector. It operates on BAM alignment files, which are produced by most contemporary short-read aligners. + +In addition to substantial performance improvements over its predecessors (PolyBayes, GigaBayes, and BamBayes), it expands the scope of SNP and small-indel variant calling to populations of individuals with heterogeneous copy number. FreeBayes is currently under active development. + +Go `here <http://bioinformatics.bc.edu/marthlab/FreeBayes>`_ for details on FreeBayes. + +------ + +**Inputs** + +FreeBayes accepts an input aligned BAM file. + + +**Outputs** + +The output is in the VCF format. + +------- + +**Settings**:: + + input and output: + + -b --bam FILE Add FILE to the set of BAM files to be analyzed. + -c --stdin Read BAM input on stdin. + -v --vcf FILE Output VCF-format results to FILE. + -f --fasta-reference FILE + Use FILE as the reference sequence for analysis. + An index file (FILE.fai) will be created if none exists. + If neither --targets nor --region are specified, FreeBayes + will analyze every position in this reference. + -t --targets FILE + Limit analysis to targets listed in the BED-format FILE. + -r --region <chrom>:<start_position>..<end_position> + Limit analysis to the specified region, 0-base coordinates, + end_position not included (same as BED format). + -s --samples FILE + Limit analysis to samples listed (one per line) in the FILE. + By default FreeBayes will analyze all samples in its input + BAM files. + --populations FILE + 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. + -A --cnv-map FILE + 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. + -L --trace FILE Output an algorithmic trace to FILE. + --failed-alleles FILE + Write a BED file of the analyzed positions which do not + pass --pvar to FILE. + -@ --variant-input VCF + Use variants reported in VCF file as input to the algorithm. + A report will be generated for every record in the VCF file. + -l --only-use-input-alleles + Only provide variant calls and genotype likelihoods for sites + and alleles which are provided in the VCF input, and provide + output in the VCF for all input alleles, not just those which + have support in the data. + + reporting: + + -P --pvar N Report sites if the probability that there is a polymorphism + at the site is greater than N. default: 0.0001 + -_ --show-reference-repeats + Calculate and show information about reference repeats in + the VCF output. + + population model: + + -T --theta N The expected mutation rate or pairwise nucleotide diversity + among the population under analysis. This serves as the + single parameter to the Ewens Sampling Formula prior model + default: 0.001 + -p --ploidy N Sets the default ploidy for the analysis to N. default: 2 + -J --pooled Assume that samples result from pooled sequencing. + When using this flag, set --ploidy to the number of + alleles in each sample. + + reference allele: + + -Z --use-reference-allele + This flag includes the reference allele in the analysis as + if it is another sample from the same population. + -H --diploid-reference + If using the reference sequence as a sample (-Z), + treat it as diploid. default: false (reference is haploid) + --reference-quality MQ,BQ + Assign mapping quality of MQ to the reference allele at each + site and base quality of BQ. default: 100,60 + + allele scope: + + -I --no-snps Ignore SNP alleles. + -i --no-indels Ignore insertion and deletion alleles. + -X --no-mnps Ignore multi-nuceotide polymorphisms, MNPs. + -u --no-complex Ignore complex events (composites of other classes). + -n --use-best-n-alleles N + Evaluate only the best N SNP alleles, ranked by sum of + supporting quality scores. (Set to 0 to use all; default: all) + -E --max-complex-gap N + Allow complex alleles with contiguous embedded matches of up + to this length. + + indel realignment: + + -O --left-align-indels + Left-realign and merge gaps embedded in reads. default: false + + input filters: + + -4 --use-duplicate-reads + Include duplicate-marked alignments in the analysis. + default: exclude duplicates + -m --min-mapping-quality Q + Exclude alignments from analysis if they have a mapping + quality less than Q. default: 30 + -q --min-base-quality Q + Exclude alleles from analysis if their supporting base + quality is less than Q. default: 20 + -R --min-supporting-quality MQ,BQ + In order to consider an alternate allele, at least one supporting + alignment must have mapping quality MQ, and one supporting + allele must have base quality BQ. default: 0,0, unset + -Q --mismatch-base-quality-threshold Q + Count mismatches toward --read-mismatch-limit if the base + quality of the mismatch is >= Q. default: 10 + -U --read-mismatch-limit N + Exclude reads with more than N mismatches where each mismatch + has base quality >= mismatch-base-quality-threshold. + default: ~unbounded + -z --read-max-mismatch-fraction N + Exclude reads with more than N [0,1] fraction of mismatches where + each mismatch has base quality >= mismatch-base-quality-threshold + default: 1.0 + -$ --read-snp-limit N + Exclude reads with more than N base mismatches, ignoring gaps + with quality >= mismatch-base-quality-threshold. + default: ~unbounded + -e --read-indel-limit N + Exclude reads with more than N separate gaps. + default: ~unbounded + -0 --no-filters Do not use any input base and mapping quality filters + Equivalent to -m 0 -q 0 -R 0 -S 0 + -x --indel-exclusion-window + Ignore portions of alignments this many bases from a + putative insertion or deletion allele. default: 0 + -F --min-alternate-fraction N + Require at least this fraction of observations supporting + an alternate allele within a single individual in the + in order to evaluate the position. default: 0.0 + -C --min-alternate-count N + Require at least this count of observations supporting + an alternate allele within a single individual in order + to evaluate the position. default: 1 + -3 --min-alternate-qsum N + Require at least this sum of quality of observations supporting + an alternate allele within a single individual in order + to evaluate the position. default: 0 + -G --min-alternate-total N + Require at least this count of observations supporting + an alternate allele within the total population in order + to use the allele in analysis. default: 1 + -! --min-coverage N + Require at least this coverage to process a site. default: 0 + + bayesian priors: + + -Y --no-ewens-priors + Turns off the Ewens' Sampling Formula component of the priors. + -k --no-population-priors + Equivalent to --pooled --no-ewens-priors + -w --hwe-priors Use the probability of the combination arising under HWE given + the allele frequency as estimated by observation frequency. + + observation prior expectations: + + -V --binomial-obs-priors + Incorporate expectations about osbervations into the priors, + Uses read placement probability, strand balance probability, + and read position (5'-3') probability. + -a --allele-balance-priors + Use aggregate probability of observation balance between alleles + as a component of the priors. Best for observations with minimal + inherent reference bias. + + algorithmic features: + + -M --site-selection-max-iterations N + Uses hill-climbing algorithm to search posterior space for N + iterations to determine if the site should be evaluated. Set to 0 + to prevent use of this algorithm for site selection, and + to a low integer for improvide site selection at a slight + performance penalty. default: 5. + -B --genotyping-max-iterations N + Iterate no more than N times during genotyping step. default: 25. + --genotyping-max-banddepth N + Integrate no deeper than the Nth best genotype by likelihood when + genotyping. default: 6. + -W --posterior-integration-limits N,M + Integrate all genotype combinations in our posterior space + which include no more than N samples with their Mth best + data likelihood. default: 1,3. + -K --no-permute + Do not scale prior probability of genotype combination given allele + frequency by the number of permutations of included genotypes. + -N --exclude-unobserved-genotypes + Skip sample genotypings for which the sample has no supporting reads. + -S --genotype-variant-threshold N + 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. default: ~unbounded + -j --use-mapping-quality + Use mapping quality of alleles when calculating data likelihoods. + -D --read-dependence-factor N + Incorporate non-independence of reads by scaling successive + observations by this factor during data likelihood + calculations. default: 0.9 + -= --no-marginals + Do not calculate the marginal probability of genotypes. Saves + time and improves scaling performance in large populations. + + +------ + +**Citation** + +For the underlying tool, please cite `FreeBayes <http://bioinformatics.bc.edu/marthlab/FreeBayes>`_. + +If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.* + + </help> +</tool> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.