Galaxy |

Changeset 13:2dd40b601766 (2014-06-20)

Previous changeset 12:aaf568580946 (2014-06-20) Next changeset 14:443ccd9208a0 (2014-06-20)

Commit message:
Uploaded

added:
freebayes.xml

diff -r aaf568580946 -r 2dd40b601766 freebayes.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/freebayes.xml Fri Jun 20 17:18:49 2014 -0400

[

b'@@ -0,0 +1,839 @@\n+<?xml version="1.0"?>\n+<tool id="freebayes" name="FreeBayes" version="freebayes-0.9.14">\n+ <requirements>\n+ <requirement type="package" version="freebayes-0.9.14_8a407cf5f4">freebayes</requirement>\n+ <requirement type="package" version="0.1.18">samtools</requirement>\n+ </requirements>\n+ <description> - Bayesian genetic variant detector</description>\n+ <command>\n+ ##set up input files\n+\n+ #set $reference_fasta_filename = "localref.fa"\n+ \n+ #if str( $reference_source.reference_source_selector ) == "history":\n+ ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" &&\n+ samtools faidx "${reference_fasta_filename}" 2>&1 || echo "Error running samtools faidx for FreeBayes" >&2 &&\n+ #else:\n+ #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path )\n+ #end if\n+ \n+ #for $bam_count, $input_bam in enumerate( $reference_source.input_bams ):\n+ ln -s "${input_bam.input_bam}" "localbam_${bam_count}.bam" &&\n+ ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" &&\n+ #end for\n+ \n+ ## Tabixize optional input_varinat_vcf file (for --variant-input option)\n+ \n+ #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( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf":\n+ ln -s "${options_type.optional_inputs.input_variant_type.input_variant_vcf}" input_variant_vcf.vcf.gz &&\n+ ln -s "${Tabixized_input}" input_variant_vcf.vcf.gz.tbi &&\n+ #end if\n+ \n+ ##finished setting up inputs\n+ \n+ ##COMMAND LINE STARTS HERE\n+ \n+ freebayes\n+ #for $bam_count, $input_bam in enumerate( $reference_source.input_bams ):\n+ --bam "localbam_${bam_count}.bam"\n+ #end for\n+ --fasta-reference "${reference_fasta_filename}"\n+ \n+ ##outputs\n+ --vcf "${output_vcf}"\n+ \n+ #if str( $target_limit_type.target_limit_type_selector ) == "limit_by_target_file":\n+ --targets "${target_limit_type.input_target_bed}"\n+ #elif str( $target_limit_type.target_limit_type_selector ) == "limit_by_region":\n+ --region "${target_limit_type.region_chromosome}:${target_limit_type.region_start}..${target_limit_type.region_end}"\n+ #end if\n+ \n+ ##advanced options\n+ #if str( $options_type.options_type_selector ) == "simple":\n+ ##do nothing as command like build up to this point is sufficinet for simple diploid calling\n+ \n+ #elif str( $options_type.options_type_selector ) == "simple_w_filters":\n+ \n+ --standard-filters\n+ --min-coverage "${options_type.min_coverage}"\n+ \n+ #elif str( $options_type.options_type_selector ) == "naive":\n+ \n+ --haplotype-length 0\n+ --min-alternate-count 1\n+ --min-alternate-fraction 0\n+ --pooled-continuous\n+ --report-monomorphic\n+ \n+ #elif str( $options_type.options_type_selector ) == "naive_w_filters":\n+\n+ --haplotype-length 0\n+ --min-alternate-count 1\n+ --min-alternate-fraction 0\n+ --pooled-continuous\n+ --report-monomorphic\n+ --standard-filters\n+ --min-coverage "${options_type.min_coverage}"\n+ \n+ #elif str( $options_type.options_type_selector ) == "cline":\n+ \n+ ${options_type.cline}\n+ \n+ @optional_inputs_outputs@\n+ \n+ #elif str( $options_type.options_type_selector ) == "full":\n+ \n+##optional inputs and outputs\n+ \n+ @optional_inputs_outputs@\n+ \n+## REPORTING\n+ \n+ #if str( $options_type.reporting.reporting_selector ) == "True":\n+ --pvar ${options_type.reporting.pvar}\n+ #end if\n+ \n+## POPULATION MODEL\n+\n+ #if str( $options_type.population_model.population_model_selector ) == "True":\n+ --theta'..b"e combination\n+ arising under HWE given the allele frequency as estimated\n+ by observation frequency.\n+ -V --binomial-obs-priors-off\n+ Disable incorporation of prior expectations about observations.\n+ Uses read placement probability, strand balance probability,\n+ and read position (5'-3') probability.\n+ -a --allele-balance-priors-off\n+ Disable use of aggregate probability of observation balance between alleles\n+ as a component of the priors.\n+\n+Genotype likelihoods::\n+\n+ --observation-bias FILE\n+ Read length-dependent allele observation biases from FILE.\n+ The format is [length] [alignment efficiency relative to reference]\n+ where the efficiency is 1 if there is no relative observation bias.\n+ --base-quality-cap Q\n+ Limit estimated observation quality by capping base quality at Q.\n+ --experimental-gls\n+ Generate genotype likelihoods using 'effective base depth' metric\n+ qual = 1-BaseQual * 1-MapQual. Incorporate partial observations.\n+ This is the default when contamination estimates are provided.\n+ Optimized for diploid samples.\n+ --prob-contamination F\n+ An estimate of contamination to use for all samples. default: 10e-9\n+ --contamination-estimates FILE\n+ A file containing per-sample estimates of contamination, such as\n+ those generated by VerifyBamID. The format should be:\n+ sample p(read=R|genotype=AR) p(read=A|genotype=AA)\n+ Sample '*' can be used to set default contamination estimates.\n+\n+Algorithmic features::\n+\n+ --report-genotype-likelihood-max\n+ Report genotypes using the maximum-likelihood estimate provided\n+ from genotype likelihoods.\n+ -B --genotyping-max-iterations N\n+ Iterate no more than N times during genotyping step. default: 1000.\n+ --genotyping-max-banddepth N\n+ Integrate no deeper than the Nth best genotype by likelihood when\n+ genotyping. default: 6.\n+ -W --posterior-integration-limits N,M\n+ Integrate all genotype combinations in our posterior space\n+ which include no more than N samples with their Mth best\n+ data likelihood. default: 1,3.\n+ -N --exclude-unobserved-genotypes\n+ Skip sample genotypings for which the sample has no supporting reads.\n+ -S --genotype-variant-threshold N\n+ Limit posterior integration to samples where the second-best\n+ genotype likelihood is no more than log(N) from the highest\n+ genotype likelihood for the sample. default: ~unbounded\n+ -j --use-mapping-quality\n+ Use mapping quality of alleles when calculating data likelihoods.\n+ -H --harmonic-indel-quality\n+ Use a weighted sum of base qualities around an indel, scaled by the\n+ distance from the indel. By default use a minimum BQ in flanking sequence.\n+ -D --read-dependence-factor N\n+ Incorporate non-independence of reads by scaling successive\n+ observations by this factor during data likelihood\n+ calculations. default: 0.9\n+ -= --genotype-qualities\n+ Calculate the marginal probability of genotypes and report as GQ in\n+ each sample field in the VCF output.\n+\n+\n+------\n+\n+**Citation**\n+\n+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>`_.\n+\n+The initial version of the wrapper was produced by Dan Blankenberg and upgraded by Anton Nekrutenko.\n+\n+ </help>\n+</tool>\n"