Mercurial > repos > devteam > freebayes
changeset 4:c171daf263dd draft
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/freebayes commit cf4a70e780f104bc724323912b3b87fb37f887dd
| author | devteam |
|---|---|
| date | Sun, 25 Sep 2016 09:48:11 -0400 |
| parents | 9f3d6c3098ac |
| children | 0f44dd2e7fe3 |
| files | freebayes.xml leftalign.xml test-data/freebayes-phix174-test1.vcf test-data/freebayes-phix174-test2.vcf test-data/freebayes-phix174-test3.vcf test-data/freebayes-phix174-test4.vcf tool_dependencies.xml |
| diffstat | 7 files changed, 1005 insertions(+), 599 deletions(-) [+] |
line wrap: on
line diff
--- a/freebayes.xml Mon Nov 09 11:37:39 2015 -0500 +++ b/freebayes.xml Sun Sep 25 09:48:11 2016 -0400 @@ -1,537 +1,674 @@ -<?xml version="1.0"?> -<tool id="freebayes" name="FreeBayes" version="0.4.1"> - <requirements> - <requirement type="package" version="0_9_20_b040236">freebayes</requirement> - <requirement type="package" version="0.1.18">samtools</requirement> - </requirements> - <description> - bayesian genetic variant detector</description> - <command> +<tool id="freebayes" name="FreeBayes" version="1.0.2.29--1"> + <description> - bayesian genetic variant detector</description> + <requirements> + <requirement type="package" version="1.0.2.29">freebayes</requirement> + <requirement type="package" version="0.1.19">samtools</requirement> + <requirement type="package" version="4.1.3">gawk</requirement> + <requirement type="package" version="20160622">parallel</requirement> + </requirements> + <stdio> + <exit_code range="1:" /> + </stdio> + <command> +<![CDATA[ ##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 && + 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_${bam_count}.bam.bai" && + ln -s "${input_bam}" "b_${bam_count}.bam" && + ln -s "${input_bam.metadata.bam_index}" "b_${bam_count}.bam.bai" && #end for - + ## Tabixize optional input_varinat_vcf file (for --variant-input option) - - #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( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf": - ln -s "${options_type.optional_inputs.input_variant_type.input_variant_vcf}" "input_variant_vcf.vcf.gz" && - ln -s "${Tabixized_input}" "input_variant_vcf.vcf.gz.tbi" && + #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( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf": + ln -s "${options_type.optional_inputs.input_variant_type.input_variant_vcf}" "input_variant_vcf.vcf.gz" && + ln -s "${Tabixized_input}" "input_variant_vcf.vcf.gz.tbi" && #end if - - ##finished setting up inputs - - ##COMMAND LINE STARTS HERE - - freebayes + #for $bam_count, $input_bam in enumerate( $reference_source.input_bams ): - --bam "localbam_${bam_count}.bam" + samtools view -H b_${bam_count}.bam | grep "^@SQ" | cut -f 2- | awk '{ gsub("^SN:","",$1); gsub("^LN:","",$2); print $1"\t0\t"$2; }' >> regions_all.bed && #end for - --fasta-reference "${reference_fasta_filename}" - - ##outputs - --vcf "${output_vcf}" - + + sort -u regions_all.bed > regions_uniq.bed && + ## split into even small chunks, this has some disatvantages and will not be used for the moment + ## bedtools makewindows -b regions_uniq.bed -w 10000000 -s 9990000 > regions.bed && + + mkdir vcf_output && + mkdir failed_alleles && + mkdir trace && + + ## Finished setting up inputs + + for i in `cat regions_uniq.bed | awk '{print $1":"$2".."$3}'`; + do + + echo " + + ## COMMAND LINE STARTS HERE + + freebayes + + --region '\$i' + + #for $bam_count, $input_bam in enumerate( $reference_source.input_bams ): + --bam 'b_${bam_count}.bam' + #end for + --fasta-reference '${reference_fasta_filename}' + + ## Outputs + --vcf './vcf_output/part_\$i.vcf' + #if str( $target_limit_type.target_limit_type_selector ) == "limit_by_target_file": - --targets "${target_limit_type.input_target_bed}" + --targets '${target_limit_type.input_target_bed}' #elif str( $target_limit_type.target_limit_type_selector ) == "limit_by_region": - --region "${target_limit_type.region_chromosome}:${target_limit_type.region_start}..${target_limit_type.region_end}" + --region '${target_limit_type.region_chromosome}:${target_limit_type.region_start}..${target_limit_type.region_end}' #end if - + ##advanced options #if str( $options_type.options_type_selector ) == "simple": - ##do nothing as command like build up to this point is sufficinet for simple diploid calling - + ##do nothing as command like build up to this point is sufficinet for simple diploid calling + #elif str( $options_type.options_type_selector ) == "simple_w_filters": - - --standard-filters - --min-coverage "${options_type.min_coverage}" - + --standard-filters + --min-coverage '${options_type.min_coverage}' #elif str( $options_type.options_type_selector ) == "naive": - - --haplotype-length 0 - --min-alternate-count 1 - --min-alternate-fraction 0 - --pooled-continuous - --report-monomorphic - + --haplotype-length 0 + --min-alternate-count 1 + --min-alternate-fraction 0 + --pooled-continuous + --report-monomorphic #elif str( $options_type.options_type_selector ) == "naive_w_filters": + --haplotype-length 0 + --min-alternate-count 1 + --min-alternate-fraction 0 + --pooled-continuous + --report-monomorphic + --standard-filters + --min-coverage '${options_type.min_coverage}' - --haplotype-length 0 - --min-alternate-count 1 - --min-alternate-fraction 0 - --pooled-continuous - --report-monomorphic - --standard-filters - --min-coverage "${options_type.min_coverage}" - -## Command line direct text entry is not allowed at this time for security reasons - + ## Command line direct text entry is not allowed at this time for security reasons #elif str( $options_type.options_type_selector ) == "full": - - #if $options_type.optional_inputs.optional_inputs_selector: - - ${options_type.optional_inputs.report_monomorphic} - - #if $options_type.optional_inputs.output_trace_option: - --trace "${output_trace}" - #end if - - #if $options_type.optional_inputs.output_failed_alleles_option: - --failed-alleles "${output_failed_alleles_bed}" - #end if - - #if $options_type.optional_inputs.samples: - --samples "${options_type.optional_inputs.samples}" - #end if - - #if $options_type.optional_inputs.populations: - --populations "${options_type.optional_inputs.populations}" - #end if - - #if $options_type.optional_inputs.A: - --cnv-map "${options_type.optional_inputs.A}" - #end if - - #if str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf": - --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 - ${options_type.optional_inputs.input_variant_type.only_use_input_alleles} - #end if - - #if $options_type.optional_inputs.haplotype_basis_alleles: - --haplotype-basis-alleles "${options_type.optional_inputs.haplotype_basis_alleles}" - #end if - - #if $options_type.optional_inputs.observation_bias: - --observation-bias "${options_type.optional_inputs.observation_bias}" - #end if - - #if $options_type.optional_inputs.contamination_estimates: - --contamination-estimates "${options_type.optional_inputs.contamination_estimates}" - #end if - + #if str( $options_type.optional_inputs.optional_inputs_selector ) == 'set': + ${options_type.optional_inputs.report_monomorphic} + + #if $options_type.optional_inputs.output_trace_option: + --trace ./trace/part_'\$i'.txt + #end if + #if $options_type.optional_inputs.output_failed_alleles_option: + --failed-alleles ./failed_alleles/part_'\$i'.bed + #end if + #if $options_type.optional_inputs.samples: + --samples '${options_type.optional_inputs.samples}' + #end if + #if $options_type.optional_inputs.populations: + --populations '${options_type.optional_inputs.populations}' + #end if + #if $options_type.optional_inputs.A: + --cnv-map '${options_type.optional_inputs.A}' + #end if + #if str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf": + --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 + ${options_type.optional_inputs.input_variant_type.only_use_input_alleles} + #end if + #if $options_type.optional_inputs.haplotype_basis_alleles: + --haplotype-basis-alleles '${options_type.optional_inputs.haplotype_basis_alleles}' + #end if + #if $options_type.optional_inputs.observation_bias: + --observation-bias '${options_type.optional_inputs.observation_bias}' + #end if + #if $options_type.optional_inputs.contamination_estimates: + --contamination-estimates '${options_type.optional_inputs.contamination_estimates}' + #end if #end if - -## REPORTING - - #if str( $options_type.reporting.reporting_selector ) == "True": + ## REPORTING + #if str( $options_type.reporting.reporting_selector ) == "set": --pvar ${options_type.reporting.pvar} #end if - -## POPULATION MODEL - - #if str( $options_type.population_model.population_model_selector ) == "True": - --theta "${options_type.population_model.T}" - --ploidy "${options_type.population_model.P}" + ## POPULATION MODEL + #if str( $options_type.population_model.population_model_selector ) == "set": + --theta '${options_type.population_model.T}' + --ploidy '${options_type.population_model.P}' ${options_type.population_model.J} ${options_type.population_model.K} - #end if - -## REFERENCE ALLELE - - #if str( $options_type.reference_allele.reference_allele_selector ) == "True": + + ## REFERENCE ALLELE + #if str( $options_type.reference_allele.reference_allele_selector ) == "set": ${options_type.reference_allele.Z} - --reference-quality "${options_type.reference_allele.reference_quality}" + --reference-quality '${options_type.reference_allele.reference_quality}' #end if - -## ALLELE SCOPE - - #if str( $options_type.allele_scope.allele_scope_selector ) == "True": + + ## ALLELE SCOPE + #if str( $options_type.allele_scope.allele_scope_selector ) == "set": ${options_type.allele_scope.I} ${options_type.allele_scope.i} ${options_type.allele_scope.X} ${options_type.allele_scope.u} - -n "${options_type.allele_scope.n}" - --haplotype-length "${options_type.allele_scope.haplotype_length}" - --min-repeat-size "${options_type.allele_scope.min_repeat_length}" - --min-repeat-entropy "${options_type.allele_scope.min_repeat_entropy}" + -n '${options_type.allele_scope.n}' + --haplotype-length '${options_type.allele_scope.haplotype_length}' + --min-repeat-size '${options_type.allele_scope.min_repeat_length}' + --min-repeat-entropy '${options_type.allele_scope.min_repeat_entropy}' ${options_type.allele_scope.no_partial_observations} #end if - -## REALIGNMENT - + + ## REALIGNMENT ${options_type.O} - -##INPUT FILTERS - #if str( $options_type.input_filters.input_filters_selector ) == "True": + ##INPUT FILTERS + #if str( $options_type.input_filters.input_filters_selector ) == "set": ${options_type.input_filters.use_duplicate_reads} - -m "${options_type.input_filters.m}" - -q "${options_type.input_filters.q}" - -R "${options_type.input_filters.R}" - -Y "${options_type.input_filters.Y}" - - #if str( $options_type.input_filters.mismatch_filters.mismatch_filters_selector ) == "True": - -Q "${options_type.input_filters.mismatch_filters.Q}" - -U "${options_type.input_filters.mismatch_filters.U}" - -z "${options_type.input_filters.mismatch_filters.z}" - --read-snp-limit "${options_type.input_filters.mismatch_filters.read_snp_limit}" + -m '${options_type.input_filters.m}' + -q '${options_type.input_filters.q}' + -R '${options_type.input_filters.R}' + -Y '${options_type.input_filters.Y}' + + #if str( $options_type.input_filters.mismatch_filters.mismatch_filters_selector ) == "set": + -Q '${options_type.input_filters.mismatch_filters.Q}' + -U '${options_type.input_filters.mismatch_filters.U}' + -z '${options_type.input_filters.mismatch_filters.z}' + --read-snp-limit '${options_type.input_filters.mismatch_filters.read_snp_limit}' #end if - - -e "${options_type.input_filters.e}" - -F "${options_type.input_filters.F}" - -C "${options_type.input_filters.C}" + + -e '${options_type.input_filters.e}' + -F '${options_type.input_filters.F}' + -C '${options_type.input_filters.C}' --min-alternate-qsum "${options_type.input_filters.min_alternate_qsum}" - -G "${options_type.input_filters.G}" - --min-coverage "${options_type.input_filters.min_coverage}" + -G '${options_type.input_filters.G}' + --min-coverage '${options_type.input_filters.min_coverage}' #end if - -## POPULATION AND MAPPABILITY PRIORS - - #if str( $options_type.population_mappability_priors.population_mappability_priors_selector ) == "True": + + ## POPULATION AND MAPPABILITY PRIORS + #if str( $options_type.population_mappability_priors.population_mappability_priors_selector ) == "set": ${options_type.population_mappability_priors.k} ${options_type.population_mappability_priors.w} ${options_type.population_mappability_priors.V} ${options_type.population_mappability_priors.a} #end if - -## GENOTYPE LIKELIHOODS - - #if str( $options_type.genotype_likelihoods.genotype_likelihoods_selector ) == "True": - --base-quality-cap "${$options_type.genotype_likelihoods.base_quality_cap}" + + ## GENOTYPE LIKELIHOODS + #if str( $options_type.genotype_likelihoods.genotype_likelihoods_selector ) == "set": + --base-quality-cap '${$options_type.genotype_likelihoods.base_quality_cap}' ${$options_type.genotype_likelihoods.experimental_gls} - --prob-contamination "${$options_type.genotype_likelihoods.prob_contamination}" + --prob-contamination '${$options_type.genotype_likelihoods.prob_contamination}' #end if - -## ALGORITHMIC FEATURES - - #if str( $options_type.algorithmic_features.algorithmic_features_selector ) == "True": + + ## ALGORITHMIC FEATURES + #if str( $options_type.algorithmic_features.algorithmic_features_selector ) == "set": ${options_type.algorithmic_features.report_genotype_likelihood_max} - -B "${options_type.algorithmic_features.B}" - --genotyping-max-banddepth "${options_type.algorithmic_features.genotyping_max_banddepth}" - -W "${options_type.algorithmic_features.W}" + -B '${options_type.algorithmic_features.B}' + --genotyping-max-banddepth '${options_type.algorithmic_features.genotyping_max_banddepth}' + -W '${options_type.algorithmic_features.W}' ${options_type.algorithmic_features.N} - - #if str( $options_type.algorithmic_features.genotype_variant_threshold.genotype_variant_threshold_selector ) == "True": - -S "${options_type.algorithmic_features.genotype_variant_threshold.S}" + + #if str( $options_type.algorithmic_features.genotype_variant_threshold.genotype_variant_threshold_selector ) == "set": + -S '${options_type.algorithmic_features.genotype_variant_threshold.S}' #end if - + ${options_type.algorithmic_features.j} ${options_type.algorithmic_features.H} - -D "${options_type.algorithmic_features.D}" + -D '${options_type.algorithmic_features.D}' ${options_type.algorithmic_features.genotype_qualities} #end if #end if - - </command> - - <inputs> - <conditional name="reference_source"> - <param name="reference_source_selector" type="select" label="Load reference genome from"> - <option value="cached">Local cache</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="fasta_indexes" metadata_name="dbkey" metadata_column="1" 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="fasta_indexes"></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="Use the following dataset as the reference sequence" help="You can upload a FASTA sequence to the history and use it as reference" /> - </when> - </conditional> - - <conditional name="target_limit_type"> - <param name="target_limit_type_selector" type="select" label="Limit variant calling to a set of regions?" help="Sets --targets or --region options"> - <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." help="-t --targets"/> - </when> - <when value="limit_by_region"> - <param name="region_chromosome" type="text" label="Region Chromosome" value="" help="-r --region"/> <!--only once? --> - <param name="region_start" type="integer" label="Region Start" value="" /> - <param name="region_end" type="integer" label="Region End" value="" /> - </when> - </conditional> - - <conditional name="options_type"> - <param name="options_type_selector" type="select" label="Choose parameter selection level" help="Select how much control over the freebayes run you need" > - <option value="simple" selected="True">1:Simple diploid calling</option> - <option value="simple_w_filters">2:Simple diploid calling with filtering and coverage</option> - <option value="naive">3:Frequency-based pooled calling</option> - <option value="naive_w_filters">4:Frequency-based pooled calling with filtering and coverage</option> - <option value="full">5:Complete list of all options</option> - <!-- We will not alloow command line text boxes at this time - <option value="cline">6:Input parameters on the command line</option> - --> - </param> - <when value="full"> - - <conditional name="optional_inputs"> - <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" /> - <when value="set"> - <param name="output_failed_alleles_option" type="boolean" truevalue="--failed-alleles" falsevalue="" checked="False" label="Write out failed alleles file" help="--failed-alleles" /> - <param name="output_trace_option" type="boolean" truevalue="--trace" falsevalue="" checked="False" label="Write out algorithm trace file" help="--trace"/> - <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"/> - <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" /> - <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."/> - <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_bgzip" label="Use variants reported in VCF file as input to the algorithm"> - <conversion name="Tabixized_input" type="tabix" /> - </param> - <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> - <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" /> - <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 " /> - <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" /> - <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." /> - </when> - <when value="do_not_set"> - <!-- do nothing --> - </when> - </conditional> - - <!-- reporting --> - - <conditional name="reporting"> - <param name="reporting_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set reporting option?" help="Sets -P --pvar option" /> - <when value="set"> - <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. " /> - </when> - <when value="do_not_set"> - <!-- do nothing --> - </when> - </conditional> - - <!-- population model --> - - <conditional name="population_model"> - <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 " /> - <when value="set"> - <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." /> - <param name="P" type="integer" value="2" label="Set ploidy for the analysis" help="-p --ploidy; default=2" /> - <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." /> - <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. " /> - </when> - <when value="do_not_set"> - <!-- do nothing --> - </when> - </conditional> + + "; + done > freebayes_commands.sh && + cat freebayes_commands.sh | parallel --no-notice -j \${GALAXY_SLOTS:-1} && + + ## make VCF header + + grep "^#" "./vcf_output/part_\$i.vcf" > header.txt && + + for i in `cat regions_uniq.bed | awk '{print $1":"$2".."$3}'`; + do + ## if this fails then it bails out the script + cat "./vcf_output/part_\$i.vcf" | grep -v "^#" || true + ; + done | sort -k1,1 -k2,2n -k5,5 -u | cat header.txt - > "${output_vcf}" - <!-- reference allele --> + #if str( $options_type.options_type_selector ) == "full": + #if str( $options_type.optional_inputs.optional_inputs_selector ) == 'set': + #if $options_type.optional_inputs.output_failed_alleles_option: + && + for i in `cat regions.bed | awk '{print $1":"$2".."$3}'`; + do + cat "./failed_alleles/part_\$i.bed" + ; + done > '${output_failed_alleles_bed}' + #end if - <conditional name="reference_allele"> - <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 " /> - <when value="set"> - <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" /> - <param name="reference_quality" type="text" 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 " /> - </when> - <when value="do_not_set"> - <!-- do nothing --> - </when> - </conditional> - - <!-- allelic scope --> + #if $options_type.optional_inputs.output_trace_option: + && + for i in `cat regions.bed | awk '{print $1":"$2".."$3}'`; + do + cat './trace/part_\$i.txt' + ; + done > '${output_trace}' + #end if + #end if + #end if +]]> + </command> - <conditional name="allele_scope"> - <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 " /> - <when value="set"> - <param name="I" type="boolean" truevalue="-I" falsevalue="" checked="False" label="Ignore SNP alleles" help="-I --no-snps; default=False" /> - <param name="i" type="boolean" truevalue="-i" falsevalue="" checked="False" label="Ignore indels alleles" help="-i --no-indels; default=False" /> - <param name="X" type="boolean" truevalue="-X" falsevalue="" checked="False" label="Ignore multi-nucleotide polymorphisms, MNPs" help="-X --no-mnps; default=False" /> - <param name="u" type="boolean" truevalue="-u" falsevalue="" checked="False" label="Ignore complex events (composites of other classes)." help="-u --no-complex; default=False" /> - <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" /> - <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." /> - <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." /> - <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)." /> - <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. " /> - </when> - <when value="do_not_set"> - <!-- do nothing --> - </when> - </conditional> - - <!-- indel realignment --> - - <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). " /> - - <!-- input filters --> - - <conditional name="input_filters"> - <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 " /> - <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." help="-4 --use-duplicate-reads; default=False (exclude duplicates marked as such in alignments)." /> - <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" /> - <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" /> - <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" /> - <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" /> - <conditional name="mismatch_filters"> - <param name="mismatch_filters_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Perform mismatch filtering?" help="Sets -Q, -U, -z, and $ options" /> - <when value="set"> - <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" /> - <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" /> - <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" /> - <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 " /> + <inputs> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Load reference genome from"> + <option value="cached">Local cache</option> + <option value="history">History</option> + </param> + <when value="cached"> + <param name="input_bams" type="data" format="bam" multiple="True" label="BAM file"> + <validator type="unspecified_build" /> + <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." /> + </param> + <param name="ref_file" type="select" label="Using reference genome"> + <options from_data_table="fasta_indexes"></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="do_not_set"> - <!-- do nothing --> + <when value="history"> <!-- FIX ME!!!! --> + <param name="input_bams" type="data" format="bam" multiple="True" label="BAM file" /> + <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" /> + </when> + </conditional> + <conditional name="target_limit_type"> + <param name="target_limit_type_selector" type="select" label="Limit variant calling to a set of regions?" help="Sets --targets or --region options"> + <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." help="-t --targets"/> + </when> + <when value="limit_by_region"> + <param name="region_chromosome" type="text" label="Region Chromosome" value="" help="-r --region"/> <!--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="e" type="integer" value="1000" label="Exclude reads with more than this number of separate gaps" help="-e --read-snp-limit; default=~unbounded" /> - <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" /> - <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" /> - <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" /> - <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" /> - <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" /> - <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " /> - </when> - <when value="do_not_set"> - <!-- do nothing --> - </when> - </conditional> - - <!-- population and mappability priors --> - - <conditional name="population_mappability_priors"> - <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 " /> - <when value="set"> - <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." /> - <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" /> - <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." /> - <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 " /> - </when> - <when value="do_not_set"> - <!-- do nothing --> - </when> - </conditional> - - <!-- genotype likelihoods --> - - <conditional name="genotype_likelihoods"> - <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. " /> - <when value="set"> - <param name="base_quality_cap" type="integer" value="0" label="Limit estimated observation quality by capping base quality at" help="--base-quality-cap" /> - <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." /> - <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." /> - </when> - <when value="do_not_set"> - <!-- do nothing --> - </when> - </conditional> - - <!-- algorithmic features --> - - <conditional name="algorithmic_features"> - <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 " /> - <when value="set"> - <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" /> - <param name="B" type="integer" value="1000" label="Iterate no more than N times during genotyping step" help="-B --genotyping-max-iterations; default=1000." /> - <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" /> - <param name="W" type="text" 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" /> - <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" /> - <conditional name="genotype_variant_threshold"> - <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" /> - <when value="do_not_set"> - <!-- do nothing --> - </when> - <when value="set"> - <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" /> - </when> </conditional> - <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" /> - <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." /> - <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." /> - <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 " /> - </when> - <when value="do_not_set"> - <!-- do nothing --> - </when> - </conditional> - </when> - <when value="simple"> - <!-- do nothing --> - </when> - <when value="simple_w_filters"> - <!-- add standard-filters to command line --> - <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " /> - </when> - <when value="naive"> - <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic --> - </when> - <when value="naive_w_filters"> - <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic standard-filters--> - <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " /> - </when> -</conditional> - - </inputs> - - <outputs> - <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (variants)" /> - <data format="bed" name="output_failed_alleles_bed" label="${tool.name} on ${on_string} (failed alleles)"> - <filter>( options_type['options_type_selector'] == 'cline' or options_type['options_type_selector'] == 'full' ) and options_type['optional_inputs']['optional_inputs_selector'] is True and options_type['optional_inputs']['output_failed_alleles_option'] is True</filter> - </data> - <data format="txt" name="output_trace" label="${tool.name} on ${on_string} (trace)"> - <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> - </data> - </outputs> - <tests> - <test> - <param name="reference_source_selector" value="history" /> - <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/> - <param name="input_bam" ftype="bam" value="freebayes-phix174.bam"/> - <param name="options_type_selector" value="simple"/> - <output name="output_vcf" file="freebayes-phix174-test1.vcf" compare="contains"/> - </test> - <test> - <param name="reference_source_selector" value="history" /> - <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/> - <param name="input_bam" ftype="bam" value="freebayes-phix174.bam"/> - <param name="options_type_selector" value="naive_w_filters"/> - <param name="min_coverage" value="14"/> - <output name="output_vcf" file="freebayes-phix174-test2.vcf" compare="contains"/> - </test> - </tests> - <stdio> - <exit_code range="1:" /> - </stdio> - <help> + <conditional name="options_type"> + <param name="options_type_selector" type="select" label="Choose parameter selection level" help="Select how much control over the freebayes run you need" > + <option value="simple" selected="True">1:Simple diploid calling</option> + <option value="simple_w_filters">2:Simple diploid calling with filtering and coverage</option> + <option value="naive">3:Frequency-based pooled calling</option> + <option value="naive_w_filters">4:Frequency-based pooled calling with filtering and coverage</option> + <option value="full">5:Complete list of all options</option> + <!-- We will not alloow command line text boxes at this time + <option value="cline">6:Input parameters on the command line</option> + --> + </param> + <when value="full"> + <conditional name="optional_inputs"> + <param name="optional_inputs_selector" type="select" label="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"> + <option value="do_not_set" selected="true">Do not provide additional inputs</option> + <option value="set">Provide additional inputs</option> + </param> + <when value="set"> + <param name="output_failed_alleles_option" type="boolean" truevalue="--failed-alleles" falsevalue="" checked="False" + label="Write out failed alleles file" help="--failed-alleles" /> + <param name="output_trace_option" type="boolean" truevalue="--trace" falsevalue="" checked="False" + label="Write out algorithm trace file" help="--trace"/> + <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"/> + <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" /> + <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."/> + <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_bgzip" label="Use variants reported in VCF file as input to the algorithm"> + <conversion name="Tabixized_input" type="tabix" /> + </param> + <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> + <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" /> + <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 " /> + <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" /> + <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." /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + <!-- reporting --> + <conditional name="reporting"> + <param name="reporting_selector" type="select" label="Reporting options" help="Sets -P --pvar option"> + <option value="do_not_set" selected="True">Use defaults</option> + <option value="set">Set reporting options</option> + </param> + <when value="set"> + <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. " /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + <!-- population model --> + <conditional name="population_model"> + <param name="population_model_selector" type="select" label="Population model options" + help="Sets --theta, --ploidy, --pooled-discrete, and --pooled-continuous options " > + <option value="do_not_set" selected="true">Use defaults</option> + <option value="set">Set population model options</option> + </param> + <when value="set"> + <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." /> + <param name="P" type="integer" value="2" label="Set ploidy for the analysis" help="-p --ploidy; default=2" /> + <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." /> + <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." /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + <!-- reference allele --> + <conditional name="reference_allele"> + <param name="reference_allele_selector" type="select" label="Reference allele options" + help="Sets --use-reference-allele and --reference-quality options."> + <option value="do_not_set" selected="true">Use defaults</option> + <option value="set">Set reference allele options</option> + </param> + <when value="set"> + <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" /> + <param name="reference_quality" type="text" 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 " /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + <!-- allelic scope --> + <conditional name="allele_scope"> + <param name="allele_scope_selector" type="select" label="Allelic scope options" + help="Sets -I, i, -X, -u, -n, --haplotype-length, --min-repeat-size, --min-repeat-entropy, and --no-partial-observations options."> + <option value="do_not_set" selected="true">Use defaults</option> + <option value="set">Set alleic scope options</option> + </param> + <when value="set"> + <param name="I" type="boolean" truevalue="-I" falsevalue="" checked="False" label="Ignore SNP alleles" help="-I --no-snps; default=False" /> + <param name="i" type="boolean" truevalue="-i" falsevalue="" checked="False" label="Ignore indels alleles" help="-i --no-indels; default=False" /> + <param name="X" type="boolean" truevalue="-X" falsevalue="" checked="False" label="Ignore multi-nucleotide polymorphisms, MNPs" help="-X --no-mnps; default=False" /> + <param name="u" type="boolean" truevalue="-u" falsevalue="" checked="False" label="Ignore complex events (composites of other classes)." + help="-u --no-complex; default=False" /> + <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" /> + <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." /> + <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." /> + <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)." /> + <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." /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + <!-- indel realignment --> + <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)." /> + <!-- input filters --> + <conditional name="input_filters"> + <param name="input_filters_selector" type="select" label="Input filters" + help="Sets -4, -m, -q, -R, -Y, -Q, -U, -z, -$, -e, -0, -F, -C, -3, -G, and -! options."> + <option value="do_not_set" selected="true">No input filters (default)</option> + <option value="set">Set input filters</option> + </param> + <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." + help="-4 --use-duplicate-reads; default=False (exclude duplicates marked as such in alignments)." /> + <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" /> + <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" /> + <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" /> + <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" /> + <conditional name="mismatch_filters"> + <param name="mismatch_filters_selector" type="select" label="Mismatch filters" + help="Sets -Q, -U, -z, and $ options"> + <option value="do_not_set" selected="true">No mismatch filters (default)</option> + <option value="set">Set mismatch filters</option> + </param> + <when value="set"> + <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" /> + <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" /> + <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" /> + <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 " /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + <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" /> + <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" /> + <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" /> + <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" /> + <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" /> + <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" /> + <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" + help="-! --min-coverage; default=0 " /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + <!-- population and mappability priors --> + <conditional name="population_mappability_priors"> + <param name="population_mappability_priors_selector" type="select" label="Population and mappability priors" + help="Sets -k, -w, -V, and -a options."> + <option value="do_not_set" selected="true">Use defaults</option> + <option value="set">Set population and mappability priors</option> + </param> + <when value="set"> + <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." /> + <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" /> + <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." /> + <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 " /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + <!-- genotype likelihoods --> + <conditional name="genotype_likelihoods"> + <param name="genotype_likelihoods_selector" type="select" label="Genotype likelihood options" + help="Sets --base-quality-cap, --experimental-gls, and --prob-contamination options."> + <option value="do_not_set" selected="true">Use defaults</option> + <option value="set">Set genotype likelihood options</option> + </param> + <when value="set"> + <param name="base_quality_cap" type="integer" value="0" label="Limit estimated observation quality by capping base quality at" help="--base-quality-cap" /> + <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." /> + <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." /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + <!-- algorithmic features --> + <conditional name="algorithmic_features"> + <param name="algorithmic_features_selector" type="select" label="Algorithmic features" + help="Sets --report-genotypes-likelihood-max, -B, --genotyping-max-banddepth, -W, -N, S, -j, -H, -D, -= options"> + <option value="do_not_set" selected="true">Use defaults</option> + <option value="set">Set algorithmic features</option> + </param> + <when value="set"> + <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" /> + <param name="B" type="integer" value="1000" label="Iterate no more than N times during genotyping step" + help="-B --genotyping-max-iterations; default=1000." /> + <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" /> + <param name="W" type="text" 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" /> + <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" /> + <conditional name="genotype_variant_threshold"> + <param name="genotype_variant_threshold_selector" type="select" + label="Limit posterior integration" + help="-S --genotype-variant-threshold"> + <option value="do_not_set" selected="true">Do not limit posterior integration</option> + <option value="set">Set posterior integration limit</option> + </param> + <when value="do_not_set"> + <!-- do nothing --> + </when> + <when value="set"> + <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" /> + </when> + </conditional> + <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" /> + <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." /> + <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." /> + <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 " /> + </when> + <when value="do_not_set"> + <!-- do nothing --> + </when> + </conditional> + </when> + <when value="simple"> + <!-- do nothing --> + </when> + <when value="simple_w_filters"> + <!-- add standard-filters to command line --> + <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " /> + </when> + <when value="naive"> + <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic --> + </when> + <when value="naive_w_filters"> + <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic standard-filters--> + <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0 " /> + </when> + </conditional> + </inputs> + <outputs> + <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (variants)" /> + <data format="bed" name="output_failed_alleles_bed" label="${tool.name} on ${on_string} (failed alleles)"> + <filter>( options_type['options_type_selector'] == 'cline' or options_type['options_type_selector'] == 'full' ) and options_type['optional_inputs']['optional_inputs_selector'] == 'set' and options_type['optional_inputs']['output_failed_alleles_option'] is True</filter> + </data> + <data format="txt" name="output_trace" label="${tool.name} on ${on_string} (trace)"> + <filter>( options_type['options_type_selector'] == 'cline' or options_type['options_type_selector'] == 'full' ) and options_type['optional_inputs']['optional_inputs_selector'] == 'set' and options_type['optional_inputs']['output_trace_option'] is True</filter> + </data> + </outputs> + <tests> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/> + <param name="input_bams" ftype="bam" value="freebayes-phix174.bam"/> + <param name="options_type_selector" value="simple"/> + <output name="output_vcf" file="freebayes-phix174-test1.vcf" compare="contains"/> + </test> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/> + <param name="input_bams" ftype="bam" value="freebayes-phix174.bam"/> + <param name="options_type_selector" value="naive_w_filters"/> + <param name="min_coverage" value="14"/> + <output name="output_vcf" file="freebayes-phix174-test2.vcf" compare="contains"/> + </test> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/> + <param name="input_bams" ftype="bam" value="freebayes-phix174.bam"/> + <param name="options_type_selector" value="naive_w_filters"/> + <param name="min_coverage" value="14"/> + <output name="output_vcf" file="freebayes-phix174-test3.vcf" compare="contains"/> + </test> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/> + <param name="input_bams" ftype="bam" value="freebayes-phix174.bam"/> + <param name="options_type_selector" value="full"/> + <param name="population_model_selector" value="set"/> + <param name="P" value="1"/> + <output name="output_vcf" file="freebayes-phix174-test4.vcf" compare="contains"/> + </test> + </tests> + <help> **What it does** 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. See https://github.com/ekg/freebayes for details on FreeBayes. -This Galaxy instance of FreeBayes corresponds to release 0.9.20 - ------ **Description** @@ -813,16 +950,16 @@ 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>`_. The initial version of the wrapper was produced by Dan Blankenberg and upgraded by Anton Nekrutenko. +TNG was developed by Bjoern Gruening - </help> - - <citations> - <citation type="bibtex">@misc{1207.3907, + </help> + <citations> + <citation type="bibtex">@misc{1207.3907, Author = {Erik Garrison}, Title = {Haplotype-based variant detection from short-read sequencing}, Year = {2012}, Eprint = {arXiv:1207.3907}, url = {http://arxiv.org/abs/1207.3907}, }</citation> - </citations> + </citations> </tool>
--- a/leftalign.xml Mon Nov 09 11:37:39 2015 -0500 +++ b/leftalign.xml Sun Sep 25 09:48:11 2016 -0400 @@ -1,85 +1,83 @@ <?xml version="1.0"?> -<tool id="bamleftalign" name="BamLeftAlign" version="0.4"> - <requirements> - <requirement type="package" version="0_9_20_b040236">freebayes</requirement> - <requirement type="package" version="0.1.18">samtools</requirement> - </requirements> - <description> indels in BAM datasets</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 leftalign" >&2 && - #else: - #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) - #end if +<tool id="bamleftalign" name="BamLeftAlign" version="1.0.2.29"> + <description> indels in BAM datasets</description> + <requirements> + <requirement type="package" version="1.0.2.29">freebayes</requirement> + <requirement type="package" version="0.1.19">samtools</requirement> + </requirements> + <stdio> + <exit_code range="1:" /> + </stdio> + <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 leftalign" >&2 && + #else: + #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) + #end if - ##finished setting up inputs - - ##start leftalign commandline - samtools view -bh "${input_bam}" | bamleftalign - --fasta-reference "${reference_fasta_filename}" - -c - --max-iterations "${iterations}" - ##outputs - > "${output_bam}" - </command> - <inputs> - <conditional name="reference_source"> - <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> - <option value="cached">Locally cached</option> - <option value="history">History</option> - </param> - <when value="cached"> - <param name="input_bam" type="data" format="bam" label="Select BAM dataset to leftalign"> - <validator type="unspecified_build" /> - <validator type="dataset_metadata_in_data_table" table_name="fasta_indexes" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." /> + ##finished setting up inputs + + ##start leftalign commandline + samtools view -bh "${input_bam}" | bamleftalign + --fasta-reference "${reference_fasta_filename}" + -c + --max-iterations "${iterations}" + ##outputs + > "${output_bam}" + </command> + <inputs> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> + <option value="cached">Locally cached</option> + <option value="history">History</option> </param> - <param name="ref_file" type="select" label="Using reference genome"> - <options from_data_table="fasta_indexes"></options> - <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> - </param> - </when> - <when value="history"> - <param name="input_bam" type="data" format="bam" label="BAM dataset to re-align" /> - <param name="ref_file" type="data" format="fasta" label="Using reference file" /> - </when> - </conditional> - <param name="iterations" type="integer" value="5" label="Maximum number of iterations" help="Iterate the left-realignment no more than this many times" /> - </inputs> - <outputs> - <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (alignments)" /> - </outputs> - <tests> - <test> - <param name="reference_source_selector" value="history" /> - <param name="ref_file" ftype="fasta" value="leftalign.fa"/> - <param name="input_bam" ftype="bam" value="left-align-input.bam"/> - <param name="iterations" value="5"/> - <output name="output_bam" file="left-align-output.bam" /> - </test> - </tests> - <stdio> - <exit_code range="1:" /> - </stdio> - <help> + <when value="cached"> + <param name="input_bam" type="data" format="bam" label="Select BAM dataset to leftalign"> + <validator type="unspecified_build" /> + <validator type="dataset_metadata_in_data_table" table_name="fasta_indexes" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." /> + </param> + <param name="ref_file" type="select" label="Using reference genome"> + <options from_data_table="fasta_indexes"></options> + <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> + </param> + </when> + <when value="history"> + <param name="input_bam" type="data" format="bam" label="BAM dataset to re-align" /> + <param name="ref_file" type="data" format="fasta" label="Using reference file" /> + </when> + </conditional> + <param name="iterations" type="integer" value="5" label="Maximum number of iterations" help="Iterate the left-realignment no more than this many times" /> + </inputs> + <outputs> + <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (alignments)" /> + </outputs> + <tests> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" ftype="fasta" value="leftalign.fa"/> + <param name="input_bam" ftype="bam" value="left-align-input.bam"/> + <param name="iterations" value="5"/> + <output name="output_bam" file="left-align-output.bam" /> + </test> + </tests> + <help> When calling indels, it is important to homogenize the positional distribution of insertions and deletions in the input by using left realignment. Left realignment will place all indels in homopolymer and microsatellite repeats at the same position, provided that doing so does not introduce mismatches between the read and reference other than the indel. This method is computationally inexpensive and handles the most common classes of alignment inconsistency. This is leftalign utility from FreeBayes package developed and maintained by Erik Garrison (https://github.com/ekg/freebayes). - </help> - - <citations> - <citation type="bibtex"> - @misc{1207.3907, - Author = {Erik Garrison}, - Title = {Haplotype-based variant detection from short-read sequencing}, - Year = {2012}, - Eprint = {arXiv:1207.3907}, - url = {http://arxiv.org/abs/1207.3907} - } - </citation> - </citations> - + </help> + <citations> + <citation type="bibtex"> + @misc{1207.3907, + Author = {Erik Garrison}, + Title = {Haplotype-based variant detection from short-read sequencing}, + Year = {2012}, + Eprint = {arXiv:1207.3907}, + url = {http://arxiv.org/abs/1207.3907} + } + </citation> + </citations> </tool>
--- a/test-data/freebayes-phix174-test1.vcf Mon Nov 09 11:37:39 2015 -0500 +++ b/test-data/freebayes-phix174-test1.vcf Sun Sep 25 09:48:11 2016 -0400 @@ -1,26 +1,85 @@ -phiX174 311 . A G 6.48411 . AB=0.222222;ABP=9.04217;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=7.35324;EPPR=5.80219;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=33.5714;NS=1;NUMALT=1;ODDS=1.23853;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=70;QR=478;RO=7;RPL=0;RPP=7.35324;RPPR=3.32051;RPR=2;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=5;SRP=5.80219;SRR=2;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:9:7:478:2:70:-5.49703,0,-42.5499 -phiX174 374 . T G 30.6931 . AB=0.5;ABP=3.0103;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=4;DPB=4;DPRA=0;EPP=7.35324;EPPR=7.35324;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=25;NS=1;NUMALT=1;ODDS=7.0665;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=75;QR=141;RO=2;RPL=1;RPP=3.0103;RPPR=7.35324;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=0;SRP=7.35324;SRR=2;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:4:2:141:2:75:-6.69903,0,-12.969 -phiX174 913 . A C 13.1703 . AB=0.4;ABP=3.44459;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=3.0103;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=29;NS=1;NUMALT=1;ODDS=2.98318;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=58;QR=171;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=3;SRP=9.52472;SRR=0;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:5:3:171:2:58:-5.00485,0,-15.4549 -phiX174 1205 . A C 2.30262 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=7.35324;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=34;NS=1;NUMALT=1;ODDS=0.357718;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=67;QR=456;RO=8;RPL=2;RPP=7.35324;RPPR=7.35324;RPR=0;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=7.35324;SRR=6;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/0:10:8:456:2:67:-5.00791,0,-40.2529 -phiX174 1245 . G T 6.48411 . AB=0.222222;ABP=9.04217;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=7.35324;EPPR=3.32051;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=28.4286;NS=1;NUMALT=1;ODDS=1.23853;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=70;QR=389;RO=7;RPL=2;RPP=7.35324;RPPR=3.32051;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=0;SRP=18.2106;SRR=7;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:9:7:389:2:70:-5.49703,0,-34.4127 -phiX174 1249 . T G 15.3287 . AB=0.222222;ABP=9.04217;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=3.0103;EPPR=3.32051;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=30.1429;NS=1;NUMALT=1;ODDS=3.4998;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=74;QR=464;RO=7;RPL=1;RPP=3.0103;RPPR=5.80219;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=5.80219;SRR=5;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:9:7:464:2:74:-5.87703,0,-41.2699 -phiX174 1445 . C A 24.4745 . AB=0.285714;ABP=5.80219;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=7;DPB=7;DPRA=0;EPP=7.35324;EPPR=6.91895;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=32.2;NS=1;NUMALT=1;ODDS=5.63189;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=76;QR=273;RO=5;RPL=1;RPP=3.0103;RPPR=6.91895;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=2;SRP=3.44459;SRR=3;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:7:5:273:2:76:-6.43501,0,-24.331 -phiX174 1577 . A C 4.06305 . AB=0.222222;ABP=9.04217;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=7.35324;EPPR=3.32051;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=35.2857;NS=1;NUMALT=1;ODDS=0.437365;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=60;QR=460;RO=7;RPL=1;RPP=3.0103;RPPR=10.7656;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=4;SRP=3.32051;SRR=3;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:9:7:460:2:60:-4.54703,0,-40.9042 -phiX174 1631 . T G 2.719 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=4.09604;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=28;NS=1;NUMALT=1;ODDS=0.138972;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=68;QR=500;RO=8;RPL=0;RPP=7.35324;RPPR=3.0103;RPR=2;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=3;SRP=4.09604;SRR=5;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/0:10:8:500:2:68:-5.10291,0,-44.2679 -phiX174 1772 . T G 2.16317 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=3.0103;EPPR=3.32051;GTI=0;LEN=1;MEANALT=2;MQM=31;MQMR=31.8571;NS=1;NUMALT=1;ODDS=0.437618;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=59;QR=425;RO=7;RPL=1;RPP=3.0103;RPPR=3.32051;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=1;SRP=10.7656;SRR=6;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/0:10:7:425:2:59:-4.16703,0,-37.3833 -phiX174 1945 . T G 11.7103 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=3.0103;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=37;NS=1;NUMALT=1;ODDS=2.62656;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=59;QR=263;RO=4;RPL=1;RPP=3.0103;RPPR=5.18177;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=3.0103;SRR=2;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:6:4:263:2:59:-4.97491,0,-23.6974 -phiX174 2230 . T G 1.61813 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=35.5;NS=1;NUMALT=1;ODDS=0.795209;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=65;QR=491;RO=8;RPL=0;RPP=7.35324;RPPR=4.09604;RPR=2;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=3;SRP=4.09604;SRR=5;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/0:10:8:491:2:65:-4.81791,0,-43.4467 -phiX174 2699 . C A 31.6424 . AB=0.5;ABP=3.0103;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=4;DPB=4;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=37;NS=1;NUMALT=1;ODDS=7.28525;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=76;QR=109;RO=2;RPL=1;RPP=3.0103;RPPR=3.0103;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=0;SRP=7.35324;SRR=2;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:4:2:109:2:76:-6.79403,0,-9.92903 -phiX174 2722 . T G 21.5364 . AB=0.4;ABP=3.44459;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=7.35324;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=33;NS=1;NUMALT=1;ODDS=4.95189;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=67;QR=150;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=0;SRP=9.52472;SRR=3;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:5:3:150:2:67:-5.85985,0,-13.4949 -phiX174 2814 . T G 8.81714 . AB=0.4;ABP=3.44459;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=3.0103;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=33;NS=1;NUMALT=1;ODDS=1.88946;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=53;QR=135;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=0;SRP=9.52472;SRR=3;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:5:3:135:2:53:-4.52985,0,-12.0949 -phiX174 2828 . T G 37.7173 . AB=0.25;ABP=7.35324;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=8;DPB=8;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=31;NS=1;NUMALT=1;ODDS=8.68456;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=100;QR=348;RO=6;RPL=0;RPP=7.35324;RPPR=4.45795;RPR=2;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=1;SRP=8.80089;SRR=5;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:8:6:348:2:100:-8.53892,0,-30.9389 -phiX174 2983 . T G 12.2712 . AB=0.4;ABP=3.44459;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=3.0103;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=33;NS=1;NUMALT=1;ODDS=2.76444;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=57;QR=150;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=3.73412;SRR=1;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:5:3:150:2:57:-4.90985,0,-13.4949 -phiX174 3110 . T C 34.4848 . AB=0.333333;ABP=5.18177;AC=1;AF=0.5;AN=2;AO=3;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=3.73412;EPPR=4.45795;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=35;NS=1;NUMALT=1;ODDS=7.94006;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=94;QR=361;RO=6;RPL=0;RPP=9.52472;RPPR=3.0103;RPR=3;RUN=1;SAF=1;SAP=3.73412;SAR=2;SRF=1;SRP=8.80089;SRR=5;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:9:6:361:3:94:-7.98834,0,-32.3067 -phiX174 3155 . T G 23.5283 . AB=0.285714;ABP=5.80219;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=7;DPB=7;DPRA=0;EPP=3.0103;EPPR=3.44459;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=29.8;NS=1;NUMALT=1;ODDS=5.41314;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=75;QR=299;RO=5;RPL=1;RPP=3.0103;RPPR=3.44459;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=4;SRP=6.91895;SRR=1;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:7:5:299:2:75:-6.34001,0,-26.723 -phiX174 3325 . A C 5.77196 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=7.35324;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=31;NS=1;NUMALT=1;ODDS=1.02152;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=58;QR=284;RO=4;RPL=2;RPP=7.35324;RPPR=3.0103;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=3;SRP=5.18177;SRR=1;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:6:4:284:2:58:-4.87991,0,-25.6399 -phiX174 3418 . A C 0.61163 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=34;NS=1;NUMALT=1;ODDS=1.88894;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=60;QR=526;RO=8;RPL=2;RPP=7.35324;RPPR=4.09604;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=5;SRP=4.09604;SRR=3;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/0:10:8:526:2:60:-4.34291,0,-46.6404 -phiX174 3729 . C T 8.03017 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=7.35324;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=37;NS=1;NUMALT=1;ODDS=1.67776;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=61;QR=232;RO=4;RPL=2;RPP=7.35324;RPPR=5.18177;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=0;SRP=11.6962;SRR=4;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:6:4:232:2:61:-5.16491,0,-20.8299 -phiX174 4031 . T G 23.4861 . AB=0.25;ABP=7.35324;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=8;DPB=8;DPRA=0;EPP=7.35324;EPPR=4.45795;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=27;NS=1;NUMALT=1;ODDS=5.40338;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=85;QR=322;RO=6;RPL=2;RPP=7.35324;RPPR=8.80089;RPR=0;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=3;SRP=3.0103;SRR=3;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:8:6:322:2:85:-7.11392,0,-28.5556 -phiX174 4502 . A C 8.30185 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=3.0103;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=37;NS=1;NUMALT=1;ODDS=1.75158;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=55;QR=284;RO=4;RPL=1;RPP=3.0103;RPPR=11.6962;RPR=1;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=3;SRP=5.18177;SRR=1;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:6:4:284:2:55:-4.59491,0,-25.6399 -phiX174 4558 . C G 6.48999 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=28;NS=1;NUMALT=1;ODDS=1.24027;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=59;QR=204;RO=4;RPL=2;RPP=7.35324;RPPR=11.6962;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=2;SRP=3.0103;SRR=2;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:6:4:204:2:59:-4.97491,0,-18.2399 -phiX174 4655 . T G 21.8853 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=3.0103;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=37;NS=1;NUMALT=1;ODDS=5.03277;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=70;QR=193;RO=4;RPL=1;RPP=3.0103;RPPR=3.0103;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=0;SRP=11.6962;SRR=4;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/1:6:4:193:2:70:-6.01991,0,-17.2224 +##fileformat=VCFv4.1 +##reference=localref.fa +##contig=<ID=phiX174,length=5386> +##phasing=none +##commandline="freebayes --region phiX174:0..5386 --bam b_0.bam --fasta-reference localref.fa --vcf ./vcf_output/part_phiX174:0..5386.vcf" +##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of samples with data"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus"> +##INFO=<ID=DPB,Number=1,Type=Float,Description="Total read depth per bp at the locus; bases in reads overlapping / bases in haplotype"> +##INFO=<ID=AC,Number=A,Type=Integer,Description="Total number of alternate alleles in called genotypes"> +##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes"> +##INFO=<ID=AF,Number=A,Type=Float,Description="Estimated allele frequency in the range (0,1]"> +##INFO=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count, with partial observations recorded fractionally"> +##INFO=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observations, with partial observations recorded fractionally"> +##INFO=<ID=PRO,Number=1,Type=Float,Description="Reference allele observation count, with partial observations recorded fractionally"> +##INFO=<ID=PAO,Number=A,Type=Float,Description="Alternate allele observations, with partial observations recorded fractionally"> +##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred"> +##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred"> +##INFO=<ID=PQR,Number=1,Type=Float,Description="Reference allele quality sum in phred for partial observations"> +##INFO=<ID=PQA,Number=A,Type=Float,Description="Alternate allele quality sum in phred for partial observations"> +##INFO=<ID=SRF,Number=1,Type=Integer,Description="Number of reference observations on the forward strand"> +##INFO=<ID=SRR,Number=1,Type=Integer,Description="Number of reference observations on the reverse strand"> +##INFO=<ID=SAF,Number=A,Type=Integer,Description="Number of alternate observations on the forward strand"> +##INFO=<ID=SAR,Number=A,Type=Integer,Description="Number of alternate observations on the reverse strand"> +##INFO=<ID=SRP,Number=1,Type=Float,Description="Strand balance probability for the reference allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SRF and SRR given E(SRF/SRR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=SAP,Number=A,Type=Float,Description="Strand balance probability for the alternate allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SAF and SAR given E(SAF/SAR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous"> +##INFO=<ID=ABP,Number=A,Type=Float,Description="Allele balance probability at heterozygous sites: Phred-scaled upper-bounds estimate of the probability of observing the deviation between ABR and ABA given E(ABR/ABA) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RUN,Number=A,Type=Integer,Description="Run length: the number of consecutive repeats of the alternate allele in the reference genome"> +##INFO=<ID=RPP,Number=A,Type=Float,Description="Read Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RPPR,Number=1,Type=Float,Description="Read Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RPL,Number=A,Type=Float,Description="Reads Placed Left: number of reads supporting the alternate balanced to the left (5') of the alternate allele"> +##INFO=<ID=RPR,Number=A,Type=Float,Description="Reads Placed Right: number of reads supporting the alternate balanced to the right (3') of the alternate allele"> +##INFO=<ID=EPP,Number=A,Type=Float,Description="End Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=EPPR,Number=1,Type=Float,Description="End Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=DPRA,Number=A,Type=Float,Description="Alternate allele depth ratio. Ratio between depth in samples with each called alternate allele and those without."> +##INFO=<ID=ODDS,Number=1,Type=Float,Description="The log odds ratio of the best genotype combination to the second-best."> +##INFO=<ID=GTI,Number=1,Type=Integer,Description="Number of genotyping iterations required to reach convergence or bailout."> +##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex."> +##INFO=<ID=CIGAR,Number=A,Type=String,Description="The extended CIGAR representation of each alternate allele, with the exception that '=' is replaced by 'M' to ease VCF parsing. Note that INDEL alleles do not have the first matched base (which is provided by default, per the spec) referred to by the CIGAR."> +##INFO=<ID=NUMALT,Number=1,Type=Integer,Description="Number of unique non-reference alleles in called genotypes at this position."> +##INFO=<ID=MEANALT,Number=A,Type=Float,Description="Mean number of unique non-reference allele observations per sample with the corresponding alternate alleles."> +##INFO=<ID=LEN,Number=A,Type=Integer,Description="allele length"> +##INFO=<ID=MQM,Number=A,Type=Float,Description="Mean mapping quality of observed alternate alleles"> +##INFO=<ID=MQMR,Number=1,Type=Float,Description="Mean mapping quality of observed reference alleles"> +##INFO=<ID=PAIRED,Number=A,Type=Float,Description="Proportion of observed alternate alleles which are supported by properly paired read fragments"> +##INFO=<ID=PAIREDR,Number=1,Type=Float,Description="Proportion of observed reference alleles which are supported by properly paired read fragments"> +##INFO=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block."> +##INFO=<ID=END,Number=1,Type=Integer,Description="Last position (inclusive) in gVCF output record."> +##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype"> +##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality, the Phred-scaled marginal (or unconditional) probability of the called genotype"> +##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy"> +##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth"> +##FORMAT=<ID=DPR,Number=A,Type=Integer,Description="Number of observation for each allele"> +##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count"> +##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations"> +##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count"> +##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations"> +##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block."> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT unknown +phiX174 311 . A G 0.00392026 . AB=0.222222;ABP=9.04217;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=7.35324;EPPR=5.80219;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=33.5714;NS=1;NUMALT=1;ODDS=7.0097;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=70;QR=478;RO=7;RPL=0;RPP=7.35324;RPPR=3.32051;RPR=2;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=5;SRP=5.80219;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:9:9,2:7:478:2:70:-1.91487,0,-18.7749 +phiX174 374 . T G 23.3387 . AB=0.5;ABP=3.0103;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=4;DPB=4;DPRA=0;EPP=7.35324;EPPR=7.35324;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=25;NS=1;NUMALT=1;ODDS=1.58025;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=75;QR=141;RO=2;RPL=1;RPP=3.0103;RPPR=7.35324;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=0;SRP=7.35324;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:4:4,2:2:141:2:75:-5.19433,0,-3.54586 +phiX174 913 . A C 1.83104 . AB=0.4;ABP=3.44459;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=3.0103;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=29;NS=1;NUMALT=1;ODDS=0.651489;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=58;QR=171;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=3;SRP=9.52472;SRR=0;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:5:5,2:3:171:2:58:-3.42633,0,-6.47921 +phiX174 1205 . A C 0.00388031 . AB=0.2;ABP=10.8276;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=7.35324;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=34;NS=1;NUMALT=1;ODDS=7.01995;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=67;QR=456;RO=8;RPL=2;RPP=7.35324;RPPR=7.35324;RPR=0;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=7.35324;SRR=6;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:10:10,2:8:456:2:67:-2.11454,0,-21.3383 +phiX174 1245 . G T 0.0324554 . AB=0.222222;ABP=9.04217;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=7.35324;EPPR=3.32051;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=28.4286;NS=1;NUMALT=1;ODDS=4.8927;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=70;QR=389;RO=7;RPL=2;RPP=7.35324;RPPR=3.32051;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=0;SRP=18.2106;SRR=7;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:9:9,2:7:389:2:70:-2.83427,0,-14.5618 +phiX174 1249 . T G 0.0166698 . AB=0.222222;ABP=9.04217;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=3.0103;EPPR=3.32051;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=30.1429;NS=1;NUMALT=1;ODDS=5.56079;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=74;QR=464;RO=7;RPL=1;RPP=3.0103;RPPR=5.80219;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=5.80219;SRR=5;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:9:9,2:7:464:2:74:-1.94207,0,-16.5662 +phiX174 1445 . C A 0.147157 . AB=0.285714;ABP=5.80219;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=7;DPB=7;DPRA=0;EPP=7.35324;EPPR=6.91895;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=32.2;NS=1;NUMALT=1;ODDS=3.36782;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=76;QR=273;RO=5;RPL=1;RPP=3.0103;RPPR=6.91895;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=2;SRP=3.44459;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:7:7,2:5:273:2:76:-2.52649,0,-12.4911 +phiX174 1577 . A C 0.0123232 . AB=0.222222;ABP=9.04217;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=7.35324;EPPR=3.32051;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=35.2857;NS=1;NUMALT=1;ODDS=5.8634;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=60;QR=460;RO=7;RPL=1;RPP=3.0103;RPPR=10.7656;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=4;SRP=3.32051;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:9:9,2:7:460:2:60:-1.81064,0,-19.8257 +phiX174 1631 . T G 0.00100612 . AB=0.2;ABP=10.8276;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=4.09604;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=28;NS=1;NUMALT=1;ODDS=8.3701;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=68;QR=500;RO=8;RPL=0;RPP=7.35324;RPPR=3.0103;RPR=2;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=3;SRP=4.09604;SRR=5;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:10:10,2:8:500:2:68:-1.52818,0,-17.3788 +phiX174 1772 . T G 0.0180574 . AB=0.2;ABP=10.8276;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=3.0103;EPPR=3.32051;GTI=0;LEN=1;MEANALT=2;MQM=31;MQMR=31.8571;NS=1;NUMALT=1;ODDS=5.48067;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=59;QR=425;RO=7;RPL=1;RPP=3.0103;RPPR=3.32051;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=1;SRP=10.7656;SRR=6;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:10:10,2:7:425:2:59:-1.97686,0,-17.3816 +phiX174 1945 . T G 1.01422 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=3.0103;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=37;NS=1;NUMALT=1;ODDS=1.3354;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=59;QR=263;RO=4;RPL=1;RPP=3.0103;RPPR=5.18177;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=3.0103;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:6:6,2:4:263:2:59:-3.25425,0,-11.8637 +phiX174 2230 . T G 0.00507157 . AB=0.2;ABP=10.8276;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=35.5;NS=1;NUMALT=1;ODDS=6.75207;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=65;QR=491;RO=8;RPL=0;RPP=7.35324;RPPR=4.09604;RPR=2;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=3;SRP=4.09604;SRR=5;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:10:10,2:8:491:2:65:-2.23088,0,-22.3591 +phiX174 2699 . C A 2.04855 . AB=0.5;ABP=3.0103;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=4;DPB=4;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=37;NS=1;NUMALT=1;ODDS=0.517362;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=76;QR=109;RO=2;RPL=1;RPP=3.0103;RPPR=3.0103;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=0;SRP=7.35324;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:4:4,2:2:109:2:76:-3.4054,0,-5.58455 +phiX174 2722 . T G 1.01772 . AB=0.4;ABP=3.44459;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=7.35324;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=33;NS=1;NUMALT=1;ODDS=1.33197;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=67;QR=150;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=0;SRP=9.52472;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:5:5,2:3:150:2:67:-3.1308,0,-7.62253 +phiX174 2814 . T G 0.509494 . AB=0.4;ABP=3.44459;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=3.0103;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=33;NS=1;NUMALT=1;ODDS=2.08698;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=53;QR=135;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=0;SRP=9.52472;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:5:5,2:3:135:2:53:-2.80291,0,-6.73807 +phiX174 2828 . T G 0.160629 . AB=0.25;ABP=7.35324;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=8;DPB=8;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=31;NS=1;NUMALT=1;ODDS=3.27866;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=100;QR=348;RO=6;RPL=0;RPP=7.35324;RPPR=4.45795;RPR=2;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=1;SRP=8.80089;SRR=5;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:8:8,2:6:348:2:100:-3.34336,0,-13.6819 +phiX174 2983 . T G 1.55467 . AB=0.4;ABP=3.44459;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=3.0103;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=33;NS=1;NUMALT=1;ODDS=0.843116;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=57;QR=150;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=3.73412;SRR=1;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:5:5,2:3:150:2:57:-3.34311,0,-7.61298 +phiX174 3110 . T C 1.16857 . AB=0.333333;ABP=5.18177;AC=1;AF=0.5;AN=2;AO=3;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=3.73412;EPPR=4.45795;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=35;NS=1;NUMALT=1;ODDS=1.17522;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=94;QR=361;RO=6;RPL=0;RPP=9.52472;RPPR=3.0103;RPR=3;RUN=1;SAF=1;SAP=3.73412;SAR=2;SRF=1;SRP=8.80089;SRR=5;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:9:9,3:6:361:3:94:-4.02963,0,-16.4039 +phiX174 3155 . T G 5.42491 . AB=0.285714;ABP=5.80219;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=7;DPB=7;DPRA=0;EPP=3.0103;EPPR=3.44459;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=29.8;NS=1;NUMALT=1;ODDS=0.911202;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=75;QR=299;RO=5;RPL=1;RPP=3.0103;RPPR=3.44459;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=4;SRP=6.91895;SRR=1;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:7:7,2:5:299:2:75:-4.38484,0,-11.5688 +phiX174 3325 . A C 0.0705175 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=7.35324;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=31;NS=1;NUMALT=1;ODDS=4.11232;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=58;QR=284;RO=4;RPL=2;RPP=7.35324;RPPR=3.0103;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=3;SRP=5.18177;SRR=1;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:6:6,2:4:284:2:58:-2.65031,0,-9.66348 +phiX174 3418 . A C 0.000937887 . AB=0.2;ABP=10.8276;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=34;NS=1;NUMALT=1;ODDS=8.44033;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=60;QR=526;RO=8;RPL=2;RPP=7.35324;RPPR=4.09604;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=5;SRP=4.09604;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:10:10,2:8:526:2:60:-1.49768,0,-21.0207 +phiX174 3729 . C T 0.274997 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=7.35324;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=37;NS=1;NUMALT=1;ODDS=2.72772;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=61;QR=232;RO=4;RPL=2;RPP=7.35324;RPPR=5.18177;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=0;SRP=11.6962;SRR=4;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:6:6,2:4:232:2:61:-3.25163,0,-11.7007 +phiX174 4031 . T G 0.0784807 . AB=0.25;ABP=7.35324;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=8;DPB=8;DPRA=0;EPP=7.35324;EPPR=4.45795;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=27;NS=1;NUMALT=1;ODDS=4.00441;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=85;QR=322;RO=6;RPL=2;RPP=7.35324;RPPR=8.80089;RPR=0;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=3;SRP=3.0103;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:8:8,2:6:322:2:85:-3.02817,0,-11.6802 +phiX174 4502 . A C 0.232919 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=3.0103;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=37;NS=1;NUMALT=1;ODDS=2.89868;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=55;QR=284;RO=4;RPL=1;RPP=3.0103;RPPR=11.6962;RPR=1;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=3;SRP=5.18177;SRR=1;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:6:6,2:4:284:2:55:-2.57533,0,-11.8832 +phiX174 4558 . C G 0.076247 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=28;NS=1;NUMALT=1;ODDS=4.03372;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=59;QR=204;RO=4;RPL=2;RPP=7.35324;RPPR=11.6962;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=2;SRP=3.0103;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:6:6,2:4:204:2:59:-2.68445,0,-8.4362 +phiX174 4655 . T G 0.399408 . AB=0.333333;ABP=4.45795;AC=1;AF=0.5;AN=2;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=3.0103;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=37;NS=1;NUMALT=1;ODDS=2.33999;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=70;QR=193;RO=4;RPL=1;RPP=3.0103;RPPR=3.0103;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=0;SRP=11.6962;SRR=4;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/1:6:6,2:4:193:2:70:-2.81796,0,-11.1489
--- a/test-data/freebayes-phix174-test2.vcf Mon Nov 09 11:37:39 2015 -0500 +++ b/test-data/freebayes-phix174-test2.vcf Sun Sep 25 09:48:11 2016 -0400 @@ -1,19 +1,78 @@ -phiX174 1134 . A . 1.75185e-15 . DP=14;DPB=14;EPPR=3.0103;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=916;RO=14;RPPR=8.59409 GT:DP:RO:QR:AO:QA:GL 0/0:14:14:916:.:.:0 -phiX174 1135 . C . 1.75538e-15 . DP=14;DPB=14;EPPR=3.63072;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=957;RO=14;RPPR=5.49198 GT:DP:RO:QR:AO:QA:GL 0/0:14:14:957:.:.:0 -phiX174 1136 . G . 1.75185e-15 . DP=14;DPB=14;EPPR=8.59409;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=919;RO=14;RPPR=3.0103 GT:DP:RO:QR:AO:QA:GL 0/0:14:14:919:.:.:0 -phiX174 1137 . C . 1.75349e-15 . DP=14;DPB=14;EPPR=5.49198;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=927;RO=14;RPPR=3.63072 GT:DP:RO:QR:AO:QA:GL 0/0:14:14:927:.:.:0 -phiX174 1138 . C . 1.75538e-15 . DP=14;DPB=14;EPPR=3.63072;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=876;RO=14;RPPR=5.49198 GT:DP:RO:QR:AO:QA:GL 0/0:14:14:876:.:.:0 -phiX174 1139 . G . 1.75538e-15 . DP=14;DPB=14;EPPR=3.63072;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=946;RO=14;RPPR=5.49198 GT:DP:RO:QR:AO:QA:GL 0/0:14:14:946:.:.:0 -phiX174 1140 . T . 6.10945e-16 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=927;RO=15;RPPR=4.31318 GT:DP:RO:QR:AO:QA:GL 0/0:15:15:927:.:.:0 -phiX174 1141 . T G 0.000113755 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=1;CIGAR=1X;DP=15;DPB=15;DPRA=0;EPP=5.18177;EPPR=3.63072;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=37;NS=1;NUMALT=1;ODDS=10.55;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=50;QR=880;RO=14;RPL=0;RPP=5.18177;RPPR=5.49198;RPR=1;RUN=1;SAF=0;SAP=5.18177;SAR=1;SRF=5;SRP=5.49198;SRR=9;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/0:15:14:880:1:50:-1.66064,0,-76.4892 -phiX174 1142 . G . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1082;RO=16;RPPR=3.55317 GT:DP:RO:QR:AO:QA:GL 0/0:16:16:1082:.:.:0 -phiX174 1143 . G . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1029;RO=16;RPPR=3.55317 GT:DP:RO:QR:AO:QA:GL 0/0:16:16:1029:.:.:0 -phiX174 1144 . C . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1114;RO=16;RPPR=3.55317 GT:DP:RO:QR:AO:QA:GL 0/0:16:16:1114:.:.:0 -phiX174 1145 . G . 6.0859e-16 . DP=15;DPB=15;EPPR=6.62942;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1042;RO=15;RPPR=3.15506 GT:DP:RO:QR:AO:QA:GL 0/0:15:15:1042:.:.:0 -phiX174 1146 . C . 6.0859e-16 . DP=15;DPB=15;EPPR=6.62942;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1058;RO=15;RPPR=3.15506 GT:DP:RO:QR:AO:QA:GL 0/0:15:15:1058:.:.:0 -phiX174 1147 . T . 6.10945e-16 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=999;RO=15;RPPR=4.31318 GT:DP:RO:QR:AO:QA:GL 0/0:15:15:999:.:.:0 -phiX174 1148 . C . 6.10945e-16 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1003;RO=15;RPPR=4.31318 GT:DP:RO:QR:AO:QA:GL 0/0:15:15:1003:.:.:0 -phiX174 1149 . T C 7.90879e-06 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=1;CIGAR=1X;DP=14;DPB=14;DPRA=0;EPP=5.18177;EPPR=3.17734;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=37;NS=1;NUMALT=1;ODDS=13.2161;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=33;QR=830;RO=13;RPL=0;RPP=5.18177;RPPR=7.18621;RPR=1;RUN=1;SAF=0;SAP=5.18177;SAR=1;SRF=5;SRP=4.51363;SRR=8;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/0:14:13:830:1:33:-0.231708,0,-72.2702 -phiX174 1151 . C T 5.70134e-07 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=1;CIGAR=1X;DP=15;DPB=15;DPRA=0;EPP=5.18177;EPPR=8.59409;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=37;NS=1;NUMALT=1;ODDS=15.8459;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=27;QR=946;RO=14;RPL=1;RPP=5.18177;RPPR=3.0103;RPR=0;RUN=1;SAF=1;SAP=5.18177;SAR=0;SRF=3;SRP=12.937;SRR=11;TYPE=snp GT:DP:RO:QR:AO:QA:GL 0/0:15:14:946:1:27:0,-0.639359,-83.1157 -phiX174 1152 . G . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=993;RO=16;RPPR=5.18177 GT:DP:RO:QR:AO:QA:GL 0/0:16:16:993:.:.:0 -phiX174 1153 . T . 0 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=880;RO=15;RPPR=4.31318 GT:DP:RO:QR:AO:QA:GL 0/0:15:15:880:.:.:0 +##fileformat=VCFv4.1 +##reference=localref.fa +##contig=<ID=phiX174,length=5386> +##phasing=none +##commandline="freebayes --region phiX174:0..5386 --bam b_0.bam --fasta-reference localref.fa --vcf ./vcf_output/part_phiX174:0..5386.vcf --haplotype-length 0 --min-alternate-count 1 --min-alternate-fraction 0 --pooled-continuous --report-monomorphic --standard-filters --min-coverage 14" +##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of samples with data"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus"> +##INFO=<ID=DPB,Number=1,Type=Float,Description="Total read depth per bp at the locus; bases in reads overlapping / bases in haplotype"> +##INFO=<ID=AC,Number=A,Type=Integer,Description="Total number of alternate alleles in called genotypes"> +##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes"> +##INFO=<ID=AF,Number=A,Type=Float,Description="Estimated allele frequency in the range (0,1]"> +##INFO=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count, with partial observations recorded fractionally"> +##INFO=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observations, with partial observations recorded fractionally"> +##INFO=<ID=PRO,Number=1,Type=Float,Description="Reference allele observation count, with partial observations recorded fractionally"> +##INFO=<ID=PAO,Number=A,Type=Float,Description="Alternate allele observations, with partial observations recorded fractionally"> +##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred"> +##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred"> +##INFO=<ID=PQR,Number=1,Type=Float,Description="Reference allele quality sum in phred for partial observations"> +##INFO=<ID=PQA,Number=A,Type=Float,Description="Alternate allele quality sum in phred for partial observations"> +##INFO=<ID=SRF,Number=1,Type=Integer,Description="Number of reference observations on the forward strand"> +##INFO=<ID=SRR,Number=1,Type=Integer,Description="Number of reference observations on the reverse strand"> +##INFO=<ID=SAF,Number=A,Type=Integer,Description="Number of alternate observations on the forward strand"> +##INFO=<ID=SAR,Number=A,Type=Integer,Description="Number of alternate observations on the reverse strand"> +##INFO=<ID=SRP,Number=1,Type=Float,Description="Strand balance probability for the reference allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SRF and SRR given E(SRF/SRR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=SAP,Number=A,Type=Float,Description="Strand balance probability for the alternate allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SAF and SAR given E(SAF/SAR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous"> +##INFO=<ID=ABP,Number=A,Type=Float,Description="Allele balance probability at heterozygous sites: Phred-scaled upper-bounds estimate of the probability of observing the deviation between ABR and ABA given E(ABR/ABA) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RUN,Number=A,Type=Integer,Description="Run length: the number of consecutive repeats of the alternate allele in the reference genome"> +##INFO=<ID=RPP,Number=A,Type=Float,Description="Read Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RPPR,Number=1,Type=Float,Description="Read Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RPL,Number=A,Type=Float,Description="Reads Placed Left: number of reads supporting the alternate balanced to the left (5') of the alternate allele"> +##INFO=<ID=RPR,Number=A,Type=Float,Description="Reads Placed Right: number of reads supporting the alternate balanced to the right (3') of the alternate allele"> +##INFO=<ID=EPP,Number=A,Type=Float,Description="End Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=EPPR,Number=1,Type=Float,Description="End Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=DPRA,Number=A,Type=Float,Description="Alternate allele depth ratio. Ratio between depth in samples with each called alternate allele and those without."> +##INFO=<ID=ODDS,Number=1,Type=Float,Description="The log odds ratio of the best genotype combination to the second-best."> +##INFO=<ID=GTI,Number=1,Type=Integer,Description="Number of genotyping iterations required to reach convergence or bailout."> +##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex."> +##INFO=<ID=CIGAR,Number=A,Type=String,Description="The extended CIGAR representation of each alternate allele, with the exception that '=' is replaced by 'M' to ease VCF parsing. Note that INDEL alleles do not have the first matched base (which is provided by default, per the spec) referred to by the CIGAR."> +##INFO=<ID=NUMALT,Number=1,Type=Integer,Description="Number of unique non-reference alleles in called genotypes at this position."> +##INFO=<ID=MEANALT,Number=A,Type=Float,Description="Mean number of unique non-reference allele observations per sample with the corresponding alternate alleles."> +##INFO=<ID=LEN,Number=A,Type=Integer,Description="allele length"> +##INFO=<ID=MQM,Number=A,Type=Float,Description="Mean mapping quality of observed alternate alleles"> +##INFO=<ID=MQMR,Number=1,Type=Float,Description="Mean mapping quality of observed reference alleles"> +##INFO=<ID=PAIRED,Number=A,Type=Float,Description="Proportion of observed alternate alleles which are supported by properly paired read fragments"> +##INFO=<ID=PAIREDR,Number=1,Type=Float,Description="Proportion of observed reference alleles which are supported by properly paired read fragments"> +##INFO=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block."> +##INFO=<ID=END,Number=1,Type=Integer,Description="Last position (inclusive) in gVCF output record."> +##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype"> +##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality, the Phred-scaled marginal (or unconditional) probability of the called genotype"> +##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy"> +##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth"> +##FORMAT=<ID=DPR,Number=A,Type=Integer,Description="Number of observation for each allele"> +##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count"> +##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations"> +##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count"> +##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations"> +##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block."> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT unknown +phiX174 1134 . A . 0 . DP=14;DPB=14;EPPR=3.0103;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=916;RO=14;RPPR=8.59409 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:916:.:.:0 +phiX174 1135 . C . 0 . DP=14;DPB=14;EPPR=3.63072;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=957;RO=14;RPPR=5.49198 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:957:.:.:0 +phiX174 1136 . G . 0 . DP=14;DPB=14;EPPR=8.59409;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=919;RO=14;RPPR=3.0103 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:919:.:.:0 +phiX174 1137 . C . 0 . DP=14;DPB=14;EPPR=5.49198;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=927;RO=14;RPPR=3.63072 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:927:.:.:0 +phiX174 1138 . C . 0 . DP=14;DPB=14;EPPR=3.63072;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=876;RO=14;RPPR=5.49198 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:876:.:.:0 +phiX174 1139 . G . 0 . DP=14;DPB=14;EPPR=3.63072;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=946;RO=14;RPPR=5.49198 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:946:.:.:0 +phiX174 1140 . T . 0 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=927;RO=15;RPPR=4.31318 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:927:.:.:0 +phiX174 1141 . T G 3.61953e-07 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=1;CIGAR=1X;DP=15;DPB=15;DPRA=0;EPP=5.18177;EPPR=3.63072;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=37;NS=1;NUMALT=1;ODDS=16.3003;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=50;QR=880;RO=14;RPL=0;RPP=5.18177;RPPR=5.49198;RPR=1;RUN=1;SAF=0;SAP=5.18177;SAR=1;SRF=5;SRP=5.49198;SRR=9;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15,1:14:880:1:50:0,-0.836684,-42.5367 +phiX174 1142 . G . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1082;RO=16;RPPR=3.55317 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:16:16:16:1082:.:.:0 +phiX174 1143 . G . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1029;RO=16;RPPR=3.55317 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:16:16:16:1029:.:.:0 +phiX174 1144 . C . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1114;RO=16;RPPR=3.55317 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:16:16:16:1114:.:.:0 +phiX174 1145 . G . 0 . DP=15;DPB=15;EPPR=6.62942;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1042;RO=15;RPPR=3.15506 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:1042:.:.:0 +phiX174 1146 . C . 0 . DP=15;DPB=15;EPPR=6.62942;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1058;RO=15;RPPR=3.15506 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:1058:.:.:0 +phiX174 1147 . T . 0 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=999;RO=15;RPPR=4.31318 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:999:.:.:0 +phiX174 1148 . C . 0 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1003;RO=15;RPPR=4.31318 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:1003:.:.:0 +phiX174 1149 . T C 4.04114e-07 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=1;CIGAR=1X;DP=14;DPB=14;DPRA=0;EPP=5.18177;EPPR=3.17734;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=37;NS=1;NUMALT=1;ODDS=16.1901;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=33;QR=830;RO=13;RPL=0;RPP=5.18177;RPPR=7.18621;RPR=1;RUN=1;SAF=0;SAP=5.18177;SAR=1;SRF=5;SRP=4.51363;SRR=8;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14,1:13:830:1:33:0,-1.0599,-39.8344 +phiX174 1151 . C T 3.45599e-08 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=1;CIGAR=1X;DP=15;DPB=15;DPRA=0;EPP=5.18177;EPPR=8.59409;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=37;NS=1;NUMALT=1;ODDS=18.6491;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=27;QR=946;RO=14;RPL=1;RPP=5.18177;RPPR=3.0103;RPR=0;RUN=1;SAF=1;SAP=5.18177;SAR=0;SRF=3;SRP=12.937;SRR=11;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15,1:14:946:1:27:0,-1.85676,-43.833 +phiX174 1152 . G . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=993;RO=16;RPPR=5.18177 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:16:16:16:993:.:.:0 +phiX174 1153 . T . 3.38668e-15 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=880;RO=15;RPPR=4.31318 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:880:.:.:0
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/freebayes-phix174-test3.vcf Sun Sep 25 09:48:11 2016 -0400 @@ -0,0 +1,78 @@ +##fileformat=VCFv4.1 +##reference=localref.fa +##contig=<ID=phiX174,length=5386> +##phasing=none +##commandline="freebayes --region phiX174:0..5386 --bam b_0.bam --fasta-reference localref.fa --vcf ./vcf_output/part_phiX174:0..5386.vcf --haplotype-length 0 --min-alternate-count 1 --min-alternate-fraction 0 --pooled-continuous --report-monomorphic --standard-filters --min-coverage 14" +##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of samples with data"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus"> +##INFO=<ID=DPB,Number=1,Type=Float,Description="Total read depth per bp at the locus; bases in reads overlapping / bases in haplotype"> +##INFO=<ID=AC,Number=A,Type=Integer,Description="Total number of alternate alleles in called genotypes"> +##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes"> +##INFO=<ID=AF,Number=A,Type=Float,Description="Estimated allele frequency in the range (0,1]"> +##INFO=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count, with partial observations recorded fractionally"> +##INFO=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observations, with partial observations recorded fractionally"> +##INFO=<ID=PRO,Number=1,Type=Float,Description="Reference allele observation count, with partial observations recorded fractionally"> +##INFO=<ID=PAO,Number=A,Type=Float,Description="Alternate allele observations, with partial observations recorded fractionally"> +##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred"> +##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred"> +##INFO=<ID=PQR,Number=1,Type=Float,Description="Reference allele quality sum in phred for partial observations"> +##INFO=<ID=PQA,Number=A,Type=Float,Description="Alternate allele quality sum in phred for partial observations"> +##INFO=<ID=SRF,Number=1,Type=Integer,Description="Number of reference observations on the forward strand"> +##INFO=<ID=SRR,Number=1,Type=Integer,Description="Number of reference observations on the reverse strand"> +##INFO=<ID=SAF,Number=A,Type=Integer,Description="Number of alternate observations on the forward strand"> +##INFO=<ID=SAR,Number=A,Type=Integer,Description="Number of alternate observations on the reverse strand"> +##INFO=<ID=SRP,Number=1,Type=Float,Description="Strand balance probability for the reference allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SRF and SRR given E(SRF/SRR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=SAP,Number=A,Type=Float,Description="Strand balance probability for the alternate allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SAF and SAR given E(SAF/SAR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous"> +##INFO=<ID=ABP,Number=A,Type=Float,Description="Allele balance probability at heterozygous sites: Phred-scaled upper-bounds estimate of the probability of observing the deviation between ABR and ABA given E(ABR/ABA) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RUN,Number=A,Type=Integer,Description="Run length: the number of consecutive repeats of the alternate allele in the reference genome"> +##INFO=<ID=RPP,Number=A,Type=Float,Description="Read Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RPPR,Number=1,Type=Float,Description="Read Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RPL,Number=A,Type=Float,Description="Reads Placed Left: number of reads supporting the alternate balanced to the left (5') of the alternate allele"> +##INFO=<ID=RPR,Number=A,Type=Float,Description="Reads Placed Right: number of reads supporting the alternate balanced to the right (3') of the alternate allele"> +##INFO=<ID=EPP,Number=A,Type=Float,Description="End Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=EPPR,Number=1,Type=Float,Description="End Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=DPRA,Number=A,Type=Float,Description="Alternate allele depth ratio. Ratio between depth in samples with each called alternate allele and those without."> +##INFO=<ID=ODDS,Number=1,Type=Float,Description="The log odds ratio of the best genotype combination to the second-best."> +##INFO=<ID=GTI,Number=1,Type=Integer,Description="Number of genotyping iterations required to reach convergence or bailout."> +##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex."> +##INFO=<ID=CIGAR,Number=A,Type=String,Description="The extended CIGAR representation of each alternate allele, with the exception that '=' is replaced by 'M' to ease VCF parsing. Note that INDEL alleles do not have the first matched base (which is provided by default, per the spec) referred to by the CIGAR."> +##INFO=<ID=NUMALT,Number=1,Type=Integer,Description="Number of unique non-reference alleles in called genotypes at this position."> +##INFO=<ID=MEANALT,Number=A,Type=Float,Description="Mean number of unique non-reference allele observations per sample with the corresponding alternate alleles."> +##INFO=<ID=LEN,Number=A,Type=Integer,Description="allele length"> +##INFO=<ID=MQM,Number=A,Type=Float,Description="Mean mapping quality of observed alternate alleles"> +##INFO=<ID=MQMR,Number=1,Type=Float,Description="Mean mapping quality of observed reference alleles"> +##INFO=<ID=PAIRED,Number=A,Type=Float,Description="Proportion of observed alternate alleles which are supported by properly paired read fragments"> +##INFO=<ID=PAIREDR,Number=1,Type=Float,Description="Proportion of observed reference alleles which are supported by properly paired read fragments"> +##INFO=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block."> +##INFO=<ID=END,Number=1,Type=Integer,Description="Last position (inclusive) in gVCF output record."> +##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype"> +##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality, the Phred-scaled marginal (or unconditional) probability of the called genotype"> +##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy"> +##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth"> +##FORMAT=<ID=DPR,Number=A,Type=Integer,Description="Number of observation for each allele"> +##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count"> +##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations"> +##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count"> +##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations"> +##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block."> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT unknown +phiX174 1134 . A . 0 . DP=14;DPB=14;EPPR=3.0103;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=916;RO=14;RPPR=8.59409 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:916:.:.:0 +phiX174 1135 . C . 0 . DP=14;DPB=14;EPPR=3.63072;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=957;RO=14;RPPR=5.49198 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:957:.:.:0 +phiX174 1136 . G . 0 . DP=14;DPB=14;EPPR=8.59409;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=919;RO=14;RPPR=3.0103 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:919:.:.:0 +phiX174 1137 . C . 0 . DP=14;DPB=14;EPPR=5.49198;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=927;RO=14;RPPR=3.63072 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:927:.:.:0 +phiX174 1138 . C . 0 . DP=14;DPB=14;EPPR=3.63072;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=876;RO=14;RPPR=5.49198 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:876:.:.:0 +phiX174 1139 . G . 0 . DP=14;DPB=14;EPPR=3.63072;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=946;RO=14;RPPR=5.49198 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14:14:946:.:.:0 +phiX174 1140 . T . 0 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=927;RO=15;RPPR=4.31318 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:927:.:.:0 +phiX174 1141 . T G 3.61953e-07 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=1;CIGAR=1X;DP=15;DPB=15;DPRA=0;EPP=5.18177;EPPR=3.63072;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=37;NS=1;NUMALT=1;ODDS=16.3003;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=50;QR=880;RO=14;RPL=0;RPP=5.18177;RPPR=5.49198;RPR=1;RUN=1;SAF=0;SAP=5.18177;SAR=1;SRF=5;SRP=5.49198;SRR=9;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15,1:14:880:1:50:0,-0.836684,-42.5367 +phiX174 1142 . G . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1082;RO=16;RPPR=3.55317 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:16:16:16:1082:.:.:0 +phiX174 1143 . G . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1029;RO=16;RPPR=3.55317 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:16:16:16:1029:.:.:0 +phiX174 1144 . C . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1114;RO=16;RPPR=3.55317 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:16:16:16:1114:.:.:0 +phiX174 1145 . G . 0 . DP=15;DPB=15;EPPR=6.62942;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1042;RO=15;RPPR=3.15506 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:1042:.:.:0 +phiX174 1146 . C . 0 . DP=15;DPB=15;EPPR=6.62942;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1058;RO=15;RPPR=3.15506 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:1058:.:.:0 +phiX174 1147 . T . 0 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=999;RO=15;RPPR=4.31318 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:999:.:.:0 +phiX174 1148 . C . 0 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=1003;RO=15;RPPR=4.31318 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:1003:.:.:0 +phiX174 1149 . T C 4.04114e-07 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=1;CIGAR=1X;DP=14;DPB=14;DPRA=0;EPP=5.18177;EPPR=3.17734;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=37;NS=1;NUMALT=1;ODDS=16.1901;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=33;QR=830;RO=13;RPL=0;RPP=5.18177;RPPR=7.18621;RPR=1;RUN=1;SAF=0;SAP=5.18177;SAR=1;SRF=5;SRP=4.51363;SRR=8;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/0:14:14,1:13:830:1:33:0,-1.0599,-39.8344 +phiX174 1151 . C T 3.45599e-08 . AB=0;ABP=0;AC=0;AF=0;AN=2;AO=1;CIGAR=1X;DP=15;DPB=15;DPRA=0;EPP=5.18177;EPPR=8.59409;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=37;NS=1;NUMALT=1;ODDS=18.6491;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=27;QR=946;RO=14;RPL=1;RPP=5.18177;RPPR=3.0103;RPR=0;RUN=1;SAF=1;SAP=5.18177;SAR=0;SRF=3;SRP=12.937;SRR=11;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15,1:14:946:1:27:0,-1.85676,-43.833 +phiX174 1152 . G . 0 . DP=16;DPB=16;EPPR=5.18177;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=993;RO=16;RPPR=5.18177 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:16:16:16:993:.:.:0 +phiX174 1153 . T . 3.38668e-15 . DP=15;DPB=15;EPPR=4.31318;GTI=0;MQMR=37;NS=1;NUMALT=0;ODDS=0;PAIREDR=0;PQR=0;PRO=0;QR=880;RO=15;RPPR=4.31318 GT:DP:DPR:RO:QR:AO:QA:GL 0/0:15:15:15:880:.:.:0
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/freebayes-phix174-test4.vcf Sun Sep 25 09:48:11 2016 -0400 @@ -0,0 +1,84 @@ +##fileformat=VCFv4.1 +##reference=localref.fa +##contig=<ID=phiX174,length=5386> +##phasing=none +##commandline="freebayes --region phiX174:0..5386 --bam b_0.bam --fasta-reference localref.fa --vcf ./vcf_output/part_phiX174:0..5386.vcf --theta 0.001 --ploidy 1" +##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of samples with data"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Total read depth at the locus"> +##INFO=<ID=DPB,Number=1,Type=Float,Description="Total read depth per bp at the locus; bases in reads overlapping / bases in haplotype"> +##INFO=<ID=AC,Number=A,Type=Integer,Description="Total number of alternate alleles in called genotypes"> +##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes"> +##INFO=<ID=AF,Number=A,Type=Float,Description="Estimated allele frequency in the range (0,1]"> +##INFO=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count, with partial observations recorded fractionally"> +##INFO=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observations, with partial observations recorded fractionally"> +##INFO=<ID=PRO,Number=1,Type=Float,Description="Reference allele observation count, with partial observations recorded fractionally"> +##INFO=<ID=PAO,Number=A,Type=Float,Description="Alternate allele observations, with partial observations recorded fractionally"> +##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred"> +##INFO=<ID=QA,Number=A,Type=Integer,Description="Alternate allele quality sum in phred"> +##INFO=<ID=PQR,Number=1,Type=Float,Description="Reference allele quality sum in phred for partial observations"> +##INFO=<ID=PQA,Number=A,Type=Float,Description="Alternate allele quality sum in phred for partial observations"> +##INFO=<ID=SRF,Number=1,Type=Integer,Description="Number of reference observations on the forward strand"> +##INFO=<ID=SRR,Number=1,Type=Integer,Description="Number of reference observations on the reverse strand"> +##INFO=<ID=SAF,Number=A,Type=Integer,Description="Number of alternate observations on the forward strand"> +##INFO=<ID=SAR,Number=A,Type=Integer,Description="Number of alternate observations on the reverse strand"> +##INFO=<ID=SRP,Number=1,Type=Float,Description="Strand balance probability for the reference allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SRF and SRR given E(SRF/SRR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=SAP,Number=A,Type=Float,Description="Strand balance probability for the alternate allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SAF and SAR given E(SAF/SAR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=AB,Number=A,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous"> +##INFO=<ID=ABP,Number=A,Type=Float,Description="Allele balance probability at heterozygous sites: Phred-scaled upper-bounds estimate of the probability of observing the deviation between ABR and ABA given E(ABR/ABA) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RUN,Number=A,Type=Integer,Description="Run length: the number of consecutive repeats of the alternate allele in the reference genome"> +##INFO=<ID=RPP,Number=A,Type=Float,Description="Read Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RPPR,Number=1,Type=Float,Description="Read Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=RPL,Number=A,Type=Float,Description="Reads Placed Left: number of reads supporting the alternate balanced to the left (5') of the alternate allele"> +##INFO=<ID=RPR,Number=A,Type=Float,Description="Reads Placed Right: number of reads supporting the alternate balanced to the right (3') of the alternate allele"> +##INFO=<ID=EPP,Number=A,Type=Float,Description="End Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=EPPR,Number=1,Type=Float,Description="End Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality"> +##INFO=<ID=DPRA,Number=A,Type=Float,Description="Alternate allele depth ratio. Ratio between depth in samples with each called alternate allele and those without."> +##INFO=<ID=ODDS,Number=1,Type=Float,Description="The log odds ratio of the best genotype combination to the second-best."> +##INFO=<ID=GTI,Number=1,Type=Integer,Description="Number of genotyping iterations required to reach convergence or bailout."> +##INFO=<ID=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex."> +##INFO=<ID=CIGAR,Number=A,Type=String,Description="The extended CIGAR representation of each alternate allele, with the exception that '=' is replaced by 'M' to ease VCF parsing. Note that INDEL alleles do not have the first matched base (which is provided by default, per the spec) referred to by the CIGAR."> +##INFO=<ID=NUMALT,Number=1,Type=Integer,Description="Number of unique non-reference alleles in called genotypes at this position."> +##INFO=<ID=MEANALT,Number=A,Type=Float,Description="Mean number of unique non-reference allele observations per sample with the corresponding alternate alleles."> +##INFO=<ID=LEN,Number=A,Type=Integer,Description="allele length"> +##INFO=<ID=MQM,Number=A,Type=Float,Description="Mean mapping quality of observed alternate alleles"> +##INFO=<ID=MQMR,Number=1,Type=Float,Description="Mean mapping quality of observed reference alleles"> +##INFO=<ID=PAIRED,Number=A,Type=Float,Description="Proportion of observed alternate alleles which are supported by properly paired read fragments"> +##INFO=<ID=PAIREDR,Number=1,Type=Float,Description="Proportion of observed reference alleles which are supported by properly paired read fragments"> +##INFO=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block."> +##INFO=<ID=END,Number=1,Type=Integer,Description="Last position (inclusive) in gVCF output record."> +##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype"> +##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality, the Phred-scaled marginal (or unconditional) probability of the called genotype"> +##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype Likelihood, log10-scaled likelihoods of the data given the called genotype for each possible genotype generated from the reference and alternate alleles given the sample ploidy"> +##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth"> +##FORMAT=<ID=DPR,Number=A,Type=Integer,Description="Number of observation for each allele"> +##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count"> +##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations"> +##FORMAT=<ID=AO,Number=A,Type=Integer,Description="Alternate allele observation count"> +##FORMAT=<ID=QA,Number=A,Type=Integer,Description="Sum of quality of the alternate observations"> +##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block."> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT unknown +phiX174 311 . A G 5.72946e-15 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=7.35324;EPPR=5.80219;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=33.5714;NS=1;NUMALT=1;ODDS=38.0687;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=70;QR=478;RO=7;RPL=0;RPP=7.35324;RPPR=3.32051;RPR=2;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=5;SRP=5.80219;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:9:9,2:7:478:2:70:0,-16.86 +phiX174 374 . T G 22.5297 . AB=0;ABP=0;AC=1;AF=1;AN=1;AO=2;CIGAR=1X;DP=4;DPB=4;DPRA=0;EPP=7.35324;EPPR=7.35324;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=25;NS=1;NUMALT=1;ODDS=5.18205;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=75;QR=141;RO=2;RPL=1;RPP=3.0103;RPPR=7.35324;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=0;SRP=7.35324;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 1:4:4,2:2:141:2:75:-1.64847,0 +phiX174 913 . A C 0.0136501 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=3.0103;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=29;NS=1;NUMALT=1;ODDS=5.76099;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=58;QR=171;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=3;SRP=9.52472;SRR=0;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:5:5,2:3:171:2:58:0,-3.05287 +phiX174 1205 . A C 6.98431e-15 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=7.35324;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=34;NS=1;NUMALT=1;ODDS=41.7843;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=67;QR=456;RO=8;RPL=2;RPP=7.35324;RPPR=7.35324;RPR=0;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=7.35324;SRR=6;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:10:10,2:8:456:2:67:0,-19.2238 +phiX174 1245 . G T 2.17569e-10 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=7.35324;EPPR=3.32051;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=28.4286;NS=1;NUMALT=1;ODDS=23.7171;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=70;QR=389;RO=7;RPL=2;RPP=7.35324;RPPR=3.32051;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=0;SRP=18.2106;SRR=7;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:9:9,2:7:389:2:70:0,-11.7275 +phiX174 1249 . T G 9.08243e-14 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=3.0103;EPPR=3.32051;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=30.1429;NS=1;NUMALT=1;ODDS=31.5341;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=74;QR=464;RO=7;RPL=1;RPP=3.0103;RPPR=5.80219;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=5.80219;SRR=5;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:9:9,2:7:464:2:74:0,-14.6241 +phiX174 1445 . C A 3.85961e-09 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=7;DPB=7;DPRA=0;EPP=7.35324;EPPR=6.91895;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=32.2;NS=1;NUMALT=1;ODDS=20.8413;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=76;QR=273;RO=5;RPL=1;RPP=3.0103;RPPR=6.91895;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=2;SRP=3.44459;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:7:7,2:5:273:2:76:0,-9.96463 +phiX174 1577 . A C 7.60962e-15 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=9;DPB=9;DPRA=0;EPP=7.35324;EPPR=3.32051;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=35.2857;NS=1;NUMALT=1;ODDS=38.7543;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=60;QR=460;RO=7;RPL=1;RPP=3.0103;RPPR=10.7656;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=4;SRP=3.32051;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:9:9,2:7:460:2:60:0,-18.0151 +phiX174 1631 . T G 8.14828e-15 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=4.09604;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=28;NS=1;NUMALT=1;ODDS=36.3199;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=68;QR=500;RO=8;RPL=0;RPP=7.35324;RPPR=3.0103;RPR=2;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=3;SRP=4.09604;SRR=5;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:10:10,2:8:500:2:68:0,-15.8506 +phiX174 1772 . T G 2.89903e-14 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=3.0103;EPPR=3.32051;GTI=0;LEN=1;MEANALT=2;MQM=31;MQMR=31.8571;NS=1;NUMALT=1;ODDS=32.7439;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=59;QR=425;RO=7;RPL=1;RPP=3.0103;RPPR=3.32051;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=1;SRP=10.7656;SRR=6;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:10:10,2:7:425:2:59:0,-15.4048 +phiX174 1945 . T G 2.84647e-08 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=3.0103;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=37;NS=1;NUMALT=1;ODDS=18.8432;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=59;QR=263;RO=4;RPL=1;RPP=3.0103;RPPR=5.18177;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=3.0103;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:6:6,2:4:263:2:59:0,-8.60945 +phiX174 2230 . T G 2.38869e-15 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=35.5;NS=1;NUMALT=1;ODDS=46.1694;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=65;QR=491;RO=8;RPL=0;RPP=7.35324;RPPR=4.09604;RPR=2;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=3;SRP=4.09604;SRR=5;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:10:10,2:8:491:2:65:0,-20.1282 +phiX174 2699 . C A 0.0286554 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=4;DPB=4;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=37;NS=1;NUMALT=1;ODDS=5.01766;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=76;QR=109;RO=2;RPL=1;RPP=3.0103;RPPR=3.0103;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=0;SRP=7.35324;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:4:4,2:2:109:2:76:0,-2.17914 +phiX174 2722 . T G 0.000497664 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=7.35324;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=33;NS=1;NUMALT=1;ODDS=9.07408;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=67;QR=150;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=1;SAP=3.0103;SAR=1;SRF=0;SRP=9.52472;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:5:5,2:3:150:2:67:0,-4.49173 +phiX174 2814 . T G 0.00179241 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=3.0103;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=33;NS=1;NUMALT=1;ODDS=7.79254;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=53;QR=135;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=0;SRP=9.52472;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:5:5,2:3:135:2:53:0,-3.93517 +phiX174 2828 . T G 4.53266e-10 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=8;DPB=8;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=31;NS=1;NUMALT=1;ODDS=22.9831;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=100;QR=348;RO=6;RPL=0;RPP=7.35324;RPPR=4.45795;RPR=2;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=1;SRP=8.80089;SRR=5;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:8:8,2:6:348:2:100:0,-10.3385 +phiX174 2983 . T G 0.000276493 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=5;DPB=5;DPRA=0;EPP=3.0103;EPPR=3.73412;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=33;NS=1;NUMALT=1;ODDS=9.66185;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=57;QR=150;RO=3;RPL=1;RPP=3.0103;RPPR=3.73412;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=2;SRP=3.73412;SRR=1;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:5:5,2:3:150:2:57:0,-4.26987 +phiX174 3155 . T G 1.16474e-06 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=7;DPB=7;DPRA=0;EPP=3.0103;EPPR=3.44459;GTI=0;LEN=1;MEANALT=1;MQM=37;MQMR=29.8;NS=1;NUMALT=1;ODDS=15.1316;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=75;QR=299;RO=5;RPL=1;RPP=3.0103;RPPR=3.44459;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=4;SRP=6.91895;SRR=1;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:7:7,2:5:299:2:75:0,-7.18392 +phiX174 3325 . A C 2.80881e-07 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=7.35324;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=31;NS=1;NUMALT=1;ODDS=16.5539;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=58;QR=284;RO=4;RPL=2;RPP=7.35324;RPPR=3.0103;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=3;SRP=5.18177;SRR=1;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:6:6,2:4:284:2:58:0,-7.01317 +phiX174 3418 . A C 0 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=10;DPB=10;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=34;NS=1;NUMALT=1;ODDS=44.7759;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=60;QR=526;RO=8;RPL=2;RPP=7.35324;RPPR=4.09604;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=5;SRP=4.09604;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:10:10,2:8:526:2:60:0,-19.523 +phiX174 3729 . C T 6.17726e-08 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=7.35324;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=37;NS=1;NUMALT=1;ODDS=18.0684;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=61;QR=232;RO=4;RPL=2;RPP=7.35324;RPPR=5.18177;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=0;SRP=11.6962;SRR=4;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:6:6,2:4:232:2:61:0,-8.44905 +phiX174 4031 . T G 2.20192e-08 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=8;DPB=8;DPRA=0;EPP=7.35324;EPPR=4.45795;GTI=0;LEN=1;MEANALT=1;MQM=31;MQMR=27;NS=1;NUMALT=1;ODDS=19.0999;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=85;QR=322;RO=6;RPL=2;RPP=7.35324;RPPR=8.80089;RPR=0;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=3;SRP=3.0103;SRR=3;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:8:8,2:6:322:2:85:0,-8.65207 +phiX174 4502 . A C 3.4202e-08 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=3.0103;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=37;NS=1;NUMALT=1;ODDS=18.6595;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=55;QR=284;RO=4;RPL=1;RPP=3.0103;RPPR=11.6962;RPR=1;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=3;SRP=5.18177;SRR=1;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:6:6,2:4:284:2:55:0,-9.30785 +phiX174 4558 . C G 1.36745e-05 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=7.35324;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=28;NS=1;NUMALT=1;ODDS=12.6685;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=59;QR=204;RO=4;RPL=2;RPP=7.35324;RPPR=11.6962;RPR=0;RUN=1;SAF=2;SAP=7.35324;SAR=0;SRF=2;SRP=3.0103;SRR=2;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:6:6,2:4:204:2:59:0,-5.75175 +phiX174 4655 . T G 1.44134e-07 . AB=0;ABP=0;AC=0;AF=0;AN=1;AO=2;CIGAR=1X;DP=6;DPB=6;DPRA=0;EPP=3.0103;EPPR=3.0103;GTI=0;LEN=1;MEANALT=1;MQM=25;MQMR=37;NS=1;NUMALT=1;ODDS=17.2211;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=70;QR=193;RO=4;RPL=1;RPP=3.0103;RPPR=3.0103;RPR=1;RUN=1;SAF=0;SAP=7.35324;SAR=2;SRF=0;SRP=11.6962;SRR=4;TYPE=snp GT:DP:DPR:RO:QR:AO:QA:GL 0:6:6,2:4:193:2:70:0,-8.33095
--- a/tool_dependencies.xml Mon Nov 09 11:37:39 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,9 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="freebayes" version="0_9_20_b040236"> - <repository changeset_revision="4fe037b74be9" name="package_freebayes_0_9_20_b040236" owner="devteam" toolshed="https://testtoolshed.g2.bx.psu.edu" /> - </package> - <package name="samtools" version="0.1.18"> - <repository changeset_revision="c0f72bdba484" name="package_samtools_0_1_18" owner="devteam" toolshed="https://testtoolshed.g2.bx.psu.edu" /> - </package> -</tool_dependency>