# HG changeset patch
# User urgi-team
# Date 1447163491 18000
# Node ID 874dd6c0fcde779df4f2bf762404a6a40ace6719
Uploaded
diff -r 000000000000 -r 874dd6c0fcde freebayes4workflow.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/freebayes4workflow.xml Tue Nov 10 08:51:31 2015 -0500
@@ -0,0 +1,851 @@
+
+
+
+ freebayes
+ samtools
+
+ - bayesian genetic variant detector
+
+ ##set up input files
+
+ #set $reference_fasta_filename = "localref.fa"
+
+ #if str( $reference_source.reference_source_selector ) == "history":
+ ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" &&
+ samtools faidx "${reference_fasta_filename}" 2>&1 || echo "Error running samtools faidx for FreeBayes" >&2 &&
+ #else:
+ #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path )
+ #end if
+
+ #for $bam_count, $input_bam in enumerate( $input_bams ):
+ ln -s "${input_bam.input_bam}" "localbam_${bam_count}.bam" &&
+ ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" &&
+ #end for
+
+ ## 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" &&
+ #end if
+
+ ##finished setting up inputs
+
+ ##COMMAND LINE STARTS HERE
+
+ freebayes
+ #for $bam_count, $input_bam in enumerate( $input_bams ):
+ --bam "localbam_${bam_count}.bam"
+ #end for
+ --fasta-reference "${reference_fasta_filename}"
+
+ ##outputs
+ #if str( $rename_output.rename_output_selector ) == "noRename":
+ --vcf ${output_vcf_default}
+ #elif str( $rename_output.rename_output_selector ) == "firstBAM":
+ --vcf "${output_vcf_firstBAM}"
+ #elif str( $rename_output.rename_output_selector ) == "providedName":
+ --vcf "${output_vcf_rename}"
+ #end if
+
+ #if str( $target_limit_type.target_limit_type_selector ) == "limit_by_target_file":
+ --targets "${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}"
+ #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
+
+ #elif str( $options_type.options_type_selector ) == "simple_w_filters":
+
+ --standard-filters
+ --min-coverage "${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
+
+ #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}"
+
+## 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:
+
+ #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
+
+ ${options_type.optional_inputs.report_monomorphic}
+
+ #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
+
+ ${options_type.optional_inputs.report_monomorphic}
+
+ #if str( $options_type.reporting.reporting_selector ) == "True":
+ --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}"
+ ${options_type.population_model.J}
+ ${options_type.population_model.K}
+
+ #end if
+
+## REFERENCE ALLELE
+
+ #if str( $options_type.reference_allele.reference_allele_selector ) == "True":
+ ${options_type.reference_allele.Z}
+ --reference-quality "${options_type.reference_allele.reference_quality}"
+ #end if
+
+## ALLELE SCOPE
+
+ #if str( $options_type.allele_scope.allele_scope_selector ) == "True":
+ ${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}"
+ ${options_type.allele_scope.no_partial_observations}
+ #end if
+
+## REALIGNMENT
+
+ ${options_type.O}
+
+##INPUT FILTERS
+
+ #if str( $options_type.input_filters.input_filters_selector ) == "True":
+ ${options_type.input_filters.use_duplicate_reads}
+ -m "${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 "${options_type.input_filters.mismatch_filters.read_snp_limit}"
+ #end if
+
+ -e "${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}"
+ #end if
+
+## POPULATION AND MAPPABILITY PRIORS
+
+ #if str( $options_type.population_mappability_priors.population_mappability_priors_selector ) == "True":
+ ${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}"
+ ${$options_type.genotype_likelihoods.experimental_gls}
+ --prob-contamination "${$options_type.genotype_likelihoods.prob_contamination}"
+ #end if
+
+## ALGORITHMIC FEATURES
+
+ #if str( $options_type.algorithmic_features.algorithmic_features_selector ) == "True":
+ ${options_type.algorithmic_features.report_genotype_likelihood_max}
+ -B "${options_type.algorithmic_features.B}"
+ --genotyping-max-banddepth "${options_type.algorithmic_features.genotyping_max_banddepth}"
+ -W "${options_type.algorithmic_features.W}"
+ ${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}"
+ #end if
+
+ ${options_type.algorithmic_features.j}
+ ${options_type.algorithmic_features.H}
+ -D "${options_type.algorithmic_features.D}"
+ ${options_type.algorithmic_features.genotype_qualities}
+ #end if
+ #end if
+
+
+ #silent sys.stderr.write("!!!! Cheetah Template Variables !!!!\n")
+ #for k,v in $searchList[2].items()
+ #silent sys.stderr.write(" %s = %s\n" % (str(k), str(v) ))
+ #end for
+ #silent sys.stderr.write("!!!! end-of-list !!!!\n")
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ ( rename_output['rename_output_selector'] == 'noRename' )
+
+
+ ( rename_output['rename_output_selector'] == 'firstBAM' )
+
+
+ ( rename_output['rename_output_selector'] == 'providedName' )
+
+
+ ( 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
+
+
+ ( 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
+
+
+
+
+
+
+**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
+
+This tool is a fork of Freebayes revision 22 (99684adf84de)
+
+------
+
+**Description**
+
+Privided BAM file(s) and a reference. FreeBayes will provide VCF output on standard out describing SNPs, indels, and complex variants in samples in the input alignments.
+
+By default, FreeBayes will consider variants supported by at least 2 observations in a single sample (-C) and also by at least 20% of the reads from a single sample (-F). These settings are suitable to low to high depth sequencing in haploid and diploid samples, but users working with polyploid or pooled samples may wish to adjust them depending on the characteristics of their sequencing data.
+
+FreeBayes is capable of calling variant haplotypes shorter than a read length where multiple polymorphisms segregate on the same read. The maximum distance between polymorphisms phased in this way is determined by the --max-complex-gap, which defaults to 3bp. In practice, this can comfortably be set to half the read length.
+
+Ploidy may be set to any level (-p), but by default all samples are assumed to be diploid. FreeBayes can model per-sample and per-region variation in copy-number (-A) using a copy-number variation map.
+
+FreeBayes can act as a frequency-based pooled caller and describe variants and haplotypes in terms of observation frequency rather than called genotypes. To do so, use --pooled-continuous and set input filters to a suitable level. Allele observation counts will be described by AO and RO fields in the VCF output.
+
+-------
+
+**Galaxy-specific options**
+
+Galaxy allows six levels of control over FreeBayes options provided by **Choose parameter selection level** menu option. These are:
+
+ 1. *Simple diploid calling*: The simples possible FreeBayes application. Equvalent of using FreeBayes with only a BAM input and no other parameter options.
+ 2. *Simple diploid calling with filtering and coverage*: Same as #1 plus two additional options: -0 (standard filters: --min-mapping-quality 30 --min-base-quality 20 --min-supporting-allele-qsum 0 --genotype-varinat-threshold 0) and --min-coverage.
+ 3. *Frequency-based pooled calling*: This is equivalent to using FreeBayes with the following options: --haplotype-length 0 --min-alternate-count 1 --min-alternate-fraction 0 --pooled-continuous --report-monomorphic. This is the best choice for calling varinats in mixtures such as viral, bacterial, or organellar genomes.
+ 4. *Frequency-based pooled calling with filtering and coverage*: Same as #3 but adds -0 and --min-coverage like in #2.
+ 5. *Complete list of all options*: Gives you full control by exposing all FreeBayes options as Galaxy widgets.
+
+-----
+
+**FreeBayes options**
+
+.. class:: infomark
+
+Note that each Galaxy parameter widget corresponding to command line flags listed below:
+
+Input and output::
+
+ -t --targets FILE
+ Limit analysis to targets listed in the BED-format FILE.
+ -r --region chrom:start_position-end_position
+ Limit analysis to the specified region, 0-base coordinates,
+ end_position included. Either '-' or '..' maybe used as a separator.
+ -s --samples FILE
+ Limit analysis to samples listed (one per line) in the FILE.
+ By default FreeBayes will analyze all samples in its input
+ BAM files.
+ --populations FILE
+ Each line of FILE should list a sample and a population which
+ it is part of. The population-based bayesian inference model
+ will then be partitioned on the basis of the populations.
+ -A --cnv-map FILE
+ Read a copy number map from the BED file FILE, which has
+ the format:
+ reference sequence, start, end, sample name, copy number
+ ... for each region in each sample which does not have the
+ default copy number as set by --ploidy.
+ --trace FILE Output an algorithmic trace to FILE.
+ --failed-alleles FILE
+ Write a BED file of the analyzed positions which do not
+ pass --pvar to FILE.
+ -@ --variant-input VCF
+ Use variants reported in VCF file as input to the algorithm.
+ Variants in this file will be treated as putative variants
+ even if there is not enough support in the data to pass
+ input filters.
+ -l --only-use-input-alleles
+ Only provide variant calls and genotype likelihoods for sites
+ and alleles which are provided in the VCF input, and provide
+ output in the VCF for all input alleles, not just those which
+ have support in the data.
+ --haplotype-basis-alleles VCF
+ When specified, only variant alleles provided in this input
+ VCF will be used for the construction of complex or haplotype
+ alleles.
+ --report-all-haplotype-alleles
+ At sites where genotypes are made over haplotype alleles,
+ provide information about all alleles in output, not only
+ those which are called.
+ --report-monomorphic
+ Report even loci which appear to be monomorphic, and report all
+ considered alleles, even those which are not in called genotypes.
+ Loci which do not have any potential alternates have '.' for ALT.
+
+Reporting::
+
+ -P --pvar N Report sites if the probability that there is a polymorphism
+ at the site is greater than N. default: 0.0. Note that post-
+ filtering is generally recommended over the use of this parameter.
+
+Population model::
+
+ -T --theta N The expected mutation rate or pairwise nucleotide diversity
+ among the population under analysis. This serves as the
+ single parameter to the Ewens Sampling Formula prior model
+ default: 0.001
+ -p --ploidy N Sets the default ploidy for the analysis to N. default: 2
+ -J --pooled-discrete
+ Assume that samples result from pooled sequencing.
+ 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.
+ -K --pooled-continuous
+ Output all alleles which pass input filters, regardles of
+ genotyping outcome or model.
+
+Reference allele::
+
+ -Z --use-reference-allele
+ This flag includes the reference allele in the analysis as
+ if it is another sample from the same population.
+ --reference-quality MQ,BQ
+ Assign mapping quality of MQ to the reference allele at each
+ site and base quality of BQ. default: 100,60
+
+Allele scope::
+
+ -I --no-snps Ignore SNP alleles.
+ -i --no-indels Ignore insertion and deletion alleles.
+ -X --no-mnps Ignore multi-nuceotide polymorphisms, MNPs.
+ -u --no-complex Ignore complex events (composites of other classes).
+ -n --use-best-n-alleles N
+ Evaluate only the best N SNP alleles, ranked by sum of
+ supporting quality scores. (Set to 0 to use all; default: all)
+ -E --max-complex-gap N
+ --haplotype-length N
+ Allow haplotype calls with contiguous embedded matches of up
+ to this length. (default: 3)
+ --min-repeat-size N
+ When assembling observations across repeats, require the total repeat
+ length at least this many bp. (default: 5)
+ --min-repeat-entropy N
+ To detect interrupted repeats, build across sequence until it has
+ entropy > N bits per bp. (default: 0, off)
+ --no-partial-observations
+ Exclude observations which do not fully span the dynamically-determined
+ detection window. (default, use all observations, dividing partial
+ support across matching haplotypes when generating haplotypes.)
+
+Indel realignment::
+
+ -O --dont-left-align-indels
+ Turn off left-alignment of indels, which is enabled by default.
+
+Input filters::
+
+ -4 --use-duplicate-reads
+ Include duplicate-marked alignments in the analysis.
+ default: exclude duplicates marked as such in alignments
+ -m --min-mapping-quality Q
+ Exclude alignments from analysis if they have a mapping
+ quality less than Q. default: 1
+ -q --min-base-quality Q
+ Exclude alleles from analysis if their supporting base
+ quality is less than Q. default: 0
+ -R --min-supporting-allele-qsum Q
+ Consider any allele in which the sum of qualities of supporting
+ observations is at least Q. default: 0
+ -Y --min-supporting-mapping-qsum Q
+ Consider any allele in which and the sum of mapping qualities of
+ supporting reads is at least Q. default: 0
+ -Q --mismatch-base-quality-threshold Q
+ Count mismatches toward --read-mismatch-limit if the base
+ quality of the mismatch is >= Q. default: 10
+ -U --read-mismatch-limit N
+ Exclude reads with more than N mismatches where each mismatch
+ has base quality >= mismatch-base-quality-threshold.
+ default: ~unbounded
+ -z --read-max-mismatch-fraction N
+ Exclude reads with more than N [0,1] fraction of mismatches where
+ each mismatch has base quality >= mismatch-base-quality-threshold
+ default: 1.0
+ -$ --read-snp-limit N
+ Exclude reads with more than N base mismatches, ignoring gaps
+ with quality >= mismatch-base-quality-threshold.
+ default: ~unbounded
+ -e --read-indel-limit N
+ Exclude reads with more than N separate gaps.
+ default: ~unbounded
+ -0 --standard-filters Use stringent input base and mapping quality filters
+ Equivalent to -m 30 -q 20 -R 0 -S 0
+ -F --min-alternate-fraction N
+ Require at least this fraction of observations supporting
+ an alternate allele within a single individual in the
+ in order to evaluate the position. default: 0.2
+ -C --min-alternate-count N
+ Require at least this count of observations supporting
+ an alternate allele within a single individual in order
+ to evaluate the position. default: 2
+ -3 --min-alternate-qsum N
+ Require at least this sum of quality of observations supporting
+ an alternate allele within a single individual in order
+ to evaluate the position. default: 0
+ -G --min-alternate-total N
+ Require at least this count of observations supporting
+ an alternate allele within the total population in order
+ to use the allele in analysis. default: 1
+ -! --min-coverage N
+ Require at least this coverage to process a site. default: 0
+
+Population priors::
+
+ -k --no-population-priors
+ Equivalent to --pooled-discrete --hwe-priors-off and removal of
+ Ewens Sampling Formula component of priors.
+
+Mappability priors::
+
+ -w --hwe-priors-off
+ Disable estimation of the probability of the combination
+ arising under HWE given the allele frequency as estimated
+ by observation frequency.
+ -V --binomial-obs-priors-off
+ Disable incorporation of prior expectations about observations.
+ Uses read placement probability, strand balance probability,
+ and read position (5'-3') probability.
+ -a --allele-balance-priors-off
+ Disable use of aggregate probability of observation balance between alleles
+ as a component of the priors.
+
+Genotype likelihoods::
+
+ --observation-bias FILE
+ Read length-dependent allele observation biases from FILE.
+ The format is [length] [alignment efficiency relative to reference]
+ where the efficiency is 1 if there is no relative observation bias.
+ --base-quality-cap Q
+ Limit estimated observation quality by capping base quality at Q.
+ --experimental-gls
+ Generate genotype likelihoods using 'effective base depth' metric
+ qual = 1-BaseQual * 1-MapQual. Incorporate partial observations.
+ This is the default when contamination estimates are provided.
+ Optimized for diploid samples.
+ --prob-contamination F
+ An estimate of contamination to use for all samples. default: 10e-9
+ --contamination-estimates FILE
+ A file containing per-sample estimates of contamination, such as
+ those generated by VerifyBamID. The format should be:
+ sample p(read=R|genotype=AR) p(read=A|genotype=AA)
+ Sample '*' can be used to set default contamination estimates.
+
+Algorithmic features::
+
+ --report-genotype-likelihood-max
+ Report genotypes using the maximum-likelihood estimate provided
+ from genotype likelihoods.
+ -B --genotyping-max-iterations N
+ Iterate no more than N times during genotyping step. default: 1000.
+ --genotyping-max-banddepth N
+ Integrate no deeper than the Nth best genotype by likelihood when
+ genotyping. default: 6.
+ -W --posterior-integration-limits N,M
+ Integrate all genotype combinations in our posterior space
+ which include no more than N samples with their Mth best
+ data likelihood. default: 1,3.
+ -N --exclude-unobserved-genotypes
+ Skip sample genotypings for which the sample has no supporting reads.
+ -S --genotype-variant-threshold N
+ Limit posterior integration to samples where the second-best
+ genotype likelihood is no more than log(N) from the highest
+ genotype likelihood for the sample. default: ~unbounded
+ -j --use-mapping-quality
+ Use mapping quality of alleles when calculating data likelihoods.
+ -H --harmonic-indel-quality
+ Use a weighted sum of base qualities around an indel, scaled by the
+ distance from the indel. By default use a minimum BQ in flanking sequence.
+ -D --read-dependence-factor N
+ Incorporate non-independence of reads by scaling successive
+ observations by this factor during data likelihood
+ calculations. default: 0.9
+ -= --genotype-qualities
+ Calculate the marginal probability of genotypes and report as GQ in
+ each sample field in the VCF output.
+
+
+------
+
+**Citation**
+
+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.
+
+
+
+
+ @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},
+}
+
+
diff -r 000000000000 -r 874dd6c0fcde tool-data/fasta_indexes.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/fasta_indexes.loc.sample Tue Nov 10 08:51:31 2015 -0500
@@ -0,0 +1,29 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of Samtools indexed sequences data files. You will need
+#to create these data files and then create a fasta_indexes.loc file
+#similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The fasta_indexes.loc
+#file has this format (white space characters are TAB characters):
+#
+#
+#
+#So, for example, if you had hg19 Canonical indexed stored in
+#
+# /depot/data2/galaxy/hg19/sam/,
+#
+#then the fasta_indexes.loc entry would look like this:
+#
+#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /depot/data2/galaxy/hg19/sam/hg19canon.fa
+#
+#and your /depot/data2/galaxy/hg19/sam/ directory
+#would contain hg19canon.fa and hg19canon.fa.fai files.
+#
+#Your fasta_indexes.loc file should include an entry per line for
+#each index set you have stored. The file in the path does actually
+#exist, but it should never be directly used. Instead, the name serves
+#as a prefix for the index file. For example:
+#
+#hg18canon hg18 Human (Homo sapiens): hg18 Canonical /depot/data2/galaxy/hg18/sam/hg18canon.fa
+#hg18full hg18 Human (Homo sapiens): hg18 Full /depot/data2/galaxy/hg18/sam/hg18full.fa
+#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /depot/data2/galaxy/hg19/sam/hg19canon.fa
+#hg19full hg19 Human (Homo sapiens): hg19 Full /depot/data2/galaxy/hg19/sam/hg19full.fa
diff -r 000000000000 -r 874dd6c0fcde tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Tue Nov 10 08:51:31 2015 -0500
@@ -0,0 +1,8 @@
+
+
+
+