Mercurial > repos > devteam > samtools_mpileup
changeset 4:c6fdfe3331d6 draft
Uploaded
| author | devteam |
|---|---|
| date | Tue, 21 Apr 2015 16:29:10 -0400 |
| parents | 973fea5b4bdf |
| children | aa0ef6f0ee89 |
| files | macros.xml samtools_mpileup.xml samtools_wrapper.py test-data/gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam test-data/phiX.bam test-data/phiX_1.bam test-data/samtools_mpileup_in_1.bam test-data/samtools_mpileup_out_1.log test-data/samtools_mpileup_out_1.pileup test-data/samtools_mpileup_out_2.log test-data/samtools_mpileup_out_2.vcf test-data/samtools_mpileup_out_3.log test-data/samtools_mpileup_out_4.log test-data/samtools_mpileup_out_4.vcf tool_dependencies.xml |
| diffstat | 15 files changed, 508 insertions(+), 293 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Tue Apr 21 16:29:10 2015 -0400 @@ -0,0 +1,70 @@ +<macros> + <xml name="requirements"> + <requirements> + <requirement type="package" version="1.2">samtools</requirement> + <yield/> + </requirements> + </xml> + <xml name="citations"> + <citations> + <citation type="bibtex"> + @misc{SAM_def, + title={Definition of SAM/BAM format}, + url = {https://samtools.github.io/hts-specs/SAMv1.pdf},} + </citation> + <citation type="doi">10.1093/bioinformatics/btp352</citation> + <citation type="doi">10.1093/bioinformatics/btr076</citation> + <citation type="doi">10.1093/bioinformatics/btr509</citation> + <citation type="bibtex"> + @misc{Danecek_et_al, + Author={Danecek, P., Schiffels, S., Durbin, R.}, + title={Multiallelic calling model in bcftools (-m)}, + url = {http://samtools.github.io/bcftools/call-m.pdf},} + </citation> + <citation type="bibtex"> + @misc{Durbin_VCQC, + Author={Durbin, R.}, + title={Segregation based metric for variant call QC}, + url = {http://samtools.github.io/bcftools/rd-SegBias.pdf},} + </citation> + <citation type="bibtex"> + @misc{Li_SamMath, + Author={Li, H.}, + title={Mathematical Notes on SAMtools Algorithms}, + url = {http://www.broadinstitute.org/gatk/media/docs/Samtools.pdf},} + </citation> + <citation type="bibtex"> + @misc{SamTools_github, + title={SAMTools GitHub page}, + url = {https://github.com/samtools/samtools},} + </citation> + </citations> + </xml> + <xml name="version_command"> + <version_command>samtools --version | head -n 1 | awk '{ print $2 }'</version_command> + </xml> + <xml name="stdio"> + <stdio> + <exit_code range="1:" level="fatal" description="Error" /> + </stdio> + </xml> + <token name="@no-chrom-options@"> +----- + +.. class:: warningmark + +**No options available? How to re-detect metadata** + +If you see a "No options available" within the "**Select references (chromosomes and contigs) you would like to restrict bam to**" drop down, you need to re-detect metadata for the dataset you are trying to process. To do this follow these steps: + +1. Click on the **pencil** icon adjacent to the dataset in the history +2. A new menu will appear in the center pane of the interface +3. Click **Datatype** tab +4. Set **New Type** to **BAM** +5. Click **Save** + +The medatada will be re-detected and you will be able to see the list of reference sequences in the "**Select references (chromosomes and contigs) you would like to restrict bam to**" drop-down. + + </token> + +</macros>
--- a/samtools_mpileup.xml Thu Mar 27 15:27:36 2014 -0400 +++ b/samtools_mpileup.xml Tue Apr 21 16:29:10 2015 -0400 @@ -1,213 +1,371 @@ -<tool id="samtools_mpileup" name="MPileup" version="0.0.3"> - <description>SNP and indel caller</description> - <requirements> - <requirement type="package" version="0.1.19">samtools</requirement> - </requirements> - <command interpreter="python">samtools_wrapper.py - -p 'samtools mpileup' - --stdout "${output_log}" +<tool id="samtools_mpileup" name="MPileup" version="2.0"> + <description>call variants</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <expand macro="stdio" /> + <expand macro="version_command" /> + <command> + <![CDATA[ + #if $reference_source.reference_source_selector == "history": + ln -s "${reference_source.ref_file}" && samtools faidx `basename "${reference_source.ref_file}"` && samtools mpileup + #else: + samtools mpileup + #end if #if $reference_source.reference_source_selector != "history": - -p '-f "${reference_source.ref_file.fields.path}"' + -f "${reference_source.ref_file.fields.path}" #else: - -d "-f" "${reference_source.ref_file}" "fa" "reference_input" + -f "${reference_source.ref_file}" #end if #for $i, $input_bam in enumerate( $reference_source.input_bams ): - -d " " "${input_bam.input_bam}" "${input_bam.input_bam.ext}" "bam_input_${i}" - -d "" "${input_bam.input_bam.metadata.bam_index}" "bam_index" "bam_input_${i}" ##hardcode galaxy ext type as bam_index + "${input_bam.input_bam}" #end for - -p ' #if str( $advanced_options.advanced_options_selector ) == "advanced": - ${advanced_options.skip_anomalous_read_pairs} + #if str( $advanced_options.filter_by_flags.filter_flags ) == "filter": + #if $advanced_options.filter_by_flags.require_flags: + --rf ${sum([int(flag) for flag in str($advanced_options.filter_by_flags.require_flags).split(',')])} + #end if + #if $advanced_options.filter_by_flags.exclude_flags: + --ff ${sum([int(flag) for flag in str($advanced_options.filter_by_flags.exclude_flags).split(',')])} + #end if + #end if + #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste": + -l "$pasted_regions" + #elif str( $advanced_options.limit_by_region.limit_by_regions ) == "history" + -l "$bed_regions" + #end if + #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste": + -G "$excluded_read_groups" + #elif str( $advanced_options.exclude_read_group.exclude_read_groups ) == "history" + -G "$read_groups" + #end if + ${advanced_options.skip_anomalous_read_pairs} ${advanced_options.disable_probabilistic_realignment} -C "${advanced_options.coefficient_for_downgrading}" -d "${advanced_options.max_reads_per_bam}" ${advanced_options.extended_BAQ_computation} - #if str( $advanced_options.position_list ) != 'None': - -l "${advanced_options.position_list}" - #end if -q "${advanced_options.minimum_mapping_quality}" -Q "${advanced_options.minimum_base_quality}" #if str( $advanced_options.region_string ): -r "${advanced_options.region_string}" #end if - ${advanced_options.output_per_sample_read_depth} - ${advanced_options.output_per_sample_strand_bias_p_value} + #end if #if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation': - ##-g or -u - -g - -e "${genotype_likelihood_computation_type.gap_extension_sequencing_error_probability}" - -h "${genotype_likelihood_computation_type.coefficient_for_modeling_homopolymer_errors}" + ## + + ${genotype_likelihood_computation_type.output_format} + ${genotype_likelihood_computation_type.compressed} + + #if str( $genotype_likelihood_computation_type.output_tags ) != "None": + -output-tags "${genotype_likelihood_computation_type.output_tags}" + #end if + #if str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'perform_indel_calling': + -o "${genotype_likelihood_computation_type.perform_indel_calling.gap_open_sequencing_error_probability}" + -e "${genotype_likelihood_computation_type.perform_indel_calling.gap_extension_sequencing_error_probability}" + -h "${genotype_likelihood_computation_type.perform_indel_calling.coefficient_for_modeling_homopolymer_errors}" -L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}" - #else: + -m "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_reads_for_indel_candidates}" + --open-prob "${genotype_likelihood_computation_type.perform_indel_calling.open_seq_error_probability}" + -F "${genotype_likelihood_computation_type.perform_indel_calling.minimum_gapped_read_fraction}" + ${genotype_likelihood_computation_type.perform_indel_calling.gapped_read_per_sample} + #if len( $genotype_likelihood_computation_type.perform_indel_calling.platform_list_repeat ): + -P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.perform_indel_calling.platform_list_repeat ] ) }" + #end if + #elif str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'do_not_perform_indel_calling': -I #end if - -o "${genotype_likelihood_computation_type.gap_open_sequencing_error_probability}" - #if len( $genotype_likelihood_computation_type.platform_list_repeat ): - -P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.platform_list_repeat ] ) }" - #end if + + + #else: + ${genotype_likelihood_computation_type.base_position_on_reads} + ${genotype_likelihood_computation_type.output_mapping_quality} #end if - > "${output_mpileup}" - ' - </command> - <inputs> - <conditional name="reference_source"> - <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> - <option value="cached">Locally cached</option> - <option value="history">History</option> - </param> - <when value="cached"> - <repeat name="input_bams" title="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." /> <!-- fixme!!! this needs to be a select --> - </param> - </repeat> - <param name="ref_file" type="select" label="Using reference genome"> - <options from_data_table="fasta_indexes"> - <!-- <filter type="data_meta" ref="input_bam" key="dbkey" column="1" /> does not yet work in a repeat...--> - </options> - </param> - </when> - <when value="history"> <!-- FIX ME!!!! --> - <repeat name="input_bams" title="BAM file" min="1"> - <param name="input_bam" type="data" format="bam" label="BAM file"> - <validator type="metadata" check="bam_index" message="Metadata missing, click the pencil icon in the history item and use the auto-detect feature to correct this issue." /> - </param> - </repeat> - <param name="ref_file" type="data" format="fasta" label="Using reference file" /> - </when> - </conditional> - - - <conditional name="genotype_likelihood_computation_type"> - <param name="genotype_likelihood_computation_type_selector" type="select" label="Genotype Likelihood Computation"> - <option value="perform_genotype_likelihood_computation">Perform genotype likelihood computation</option> - <option value="do_not_perform_genotype_likelihood_computation" selected="True">Do not perform genotype likelihood computation</option> - </param> - <when value="perform_genotype_likelihood_computation"> - <param name="gap_extension_sequencing_error_probability" type="integer" value="20" label="Phred-scaled gap extension sequencing error probability" /> - <param name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" label="Coefficient for modeling homopolymer errors." /> - <conditional name="perform_indel_calling"> - <param name="perform_indel_calling_selector" type="select" label="Perform INDEL calling"> - <option value="perform_indel_calling" selected="True">Perform INDEL calling</option> - <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option> + --output "$output_mpileup" 2> "$output_log" + ]]> + </command> + <inputs> + <conditional name="reference_source"> + <param label="Choose the source for the reference genome" name="reference_source_selector" type="select"> + <option value="cached">Use a built-in genome</option> + <option value="history">Use a genome from the history</option> + </param> + <when value="cached"> + <repeat min="1" name="input_bams" title="BAM file"> + <param format="bam" label="BAM file" name="input_bam" type="data"> + <validator type="unspecified_build" /> + <validator message="Sequences are not currently available for the specified build." metadata_column="1" metadata_name="dbkey" table_name="fasta_indexes" type="dataset_metadata_in_data_table" /> + </param> + </repeat> + <param label="Using reference genome" name="ref_file" type="select"> + <options from_data_table="fasta_indexes" /> + </param> + </when> + <when value="history"> + <repeat min="1" name="input_bams" title="BAM file"> + <param format="bam" label="BAM file" name="input_bam" type="data"> + <validator check="bam_index" message="Metadata missing, click the pencil icon in the history item and use the auto-detect feature to correct this issue." type="metadata" /> + </param> + </repeat> + <param format="fasta" label="Using reference genome" name="ref_file" type="data" /> + </when> + </conditional> + <conditional name="genotype_likelihood_computation_type"> + <param label="Genotype Likelihood Computation" name="genotype_likelihood_computation_type_selector" type="select"> + <option selected="True" value="perform_genotype_likelihood_computation">Perform genotype likelihood computation (--VCF, --BCF options)</option> + <option value="do_not_perform_genotype_likelihood_computation">Do not perform genotype likelihood computation (output pileup)</option> </param> - <when value="perform_indel_calling"> - <param name="skip_indel_calling_above_sample_depth" type="integer" value="250" label="Skip INDEL calling if the average per-sample depth is above" /> + <when value="perform_genotype_likelihood_computation"> + <param label="Choose the output format" name="output_format" type="select"> + <option value="--VCF">VCF</option> + <option value="--BCF">BCF</option> + </param> + <param checked="False" falsevalue="--uncompressed" label="Compress output" name="compressed" truevalue="" type="boolean" help="--incompressed; default=False"/> + <param name="output_tags" optional="True" type="select" multiple="True" display="checkboxes" label="Optional tags to output" help="--output-tags"> + <option value="DP">DP (Number of high-quality bases)</option> + <option value="DPR">DRP (Number of high-quality bases for each observed allele)</option> + <option value="DV">DV (Number of high-quality non-reference bases)</option> + <option value="DP4">DP4 (Number of high-quality ref-forward, ref-reverse, alt-forward and alt-reverse bases)</option> + <option value="INFO/DPR">INFO/DPR (Number of high-quality bases for each observed allele)</option> + <option value="SP">SP (Phred-scaled strand bias P-value)</option> + </param> + <conditional name="perform_indel_calling"> + <param label="Perform INDEL calling" name="perform_indel_calling_selector" type="select"> + <option selected="True" value="perform_indel_calling_def">Perform INDEL calling using default options</option> + <option value="perform_indel_calling">Perform INDEL calling and set advanced options</option> + <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option> + </param> + <when value="perform_indel_calling_def" /> + <when value="perform_indel_calling"> + <param label="Phred-scaled gap open sequencing error probability" name="gap_open_sequencing_error_probability" type="integer" value="40" help="--open-prob; Reducing this value leads to more indel calls; default=40"/> + <param label="Phred-scaled gap extension sequencing error probability" name="gap_extension_sequencing_error_probability" type="integer" value="20" help="--ext-prob; Reducing this value leads to longer indels. default=20"/> + <param label="Coefficient for modeling homopolymer errors." name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" help="--tandem-qual; default=100"/> + <param label="Skip INDEL calling if the average per-sample depth is above" name="skip_indel_calling_above_sample_depth" type="integer" value="250" help="--max-idepth; default=250"/> + <param label="Minimum gapped reads for indel candidates" name="minimum_gapped_reads_for_indel_candidates" type="integer" value="1" help="--min-ireads; default=1"/> + <param label="Phred-scaled gap open sequencing error probability" name="open_seq_error_probability" type="integer" value="40" help="--open-prob; Reducing this value leads to more indel calls; default=40"/> + <param label="Minimum fraction of gapped reads" name="minimum_gapped_read_fraction" type="float" value="0.002" help="--gap-frac; default=0.002"/> + <param checked="False" falsevalue="" label="Apply --min-ireads and --gap-frac values on a per-sample basis" name="gapped_read_per_sample" truevalue="-p" type="boolean" help="--per-sample-mF; by default both options are applied to reads pooled from all samples"/> + <repeat name="platform_list_repeat" title="Platform for INDEL candidates"> + <param label="Platform to use for INDEL candidates" name="platform_entry" type="text" value="" help="It is recommended to collect indel candidates from sequencing technologies that have low indel error rate such as ILLUMINA"/> + </repeat> + </when> + <when value="do_not_perform_indel_calling" /> + </conditional> + + </when> + <when value="do_not_perform_genotype_likelihood_computation"> + <param checked="False" falsevalue="" label="Output base positions on reads" name="base_position_on_reads" truevalue="-O" type="boolean" help="--output-BP"/> + <param checked="False" falsevalue="" label="Output mapping quality" name="output_mapping_quality" truevalue="-s" type="boolean" help="--output-MQ"/> </when> - <when value="do_not_perform_indel_calling" /> - </conditional> - <param name="gap_open_sequencing_error_probability" type="integer" value="40" label="Phred-scaled gap open sequencing error probability" /> - <repeat name="platform_list_repeat" title="Platform for INDEL candidates"> - <param name="platform_entry" type="text" value="" label="Platform to use for INDEL candidates" /> - </repeat> - </when> - <when value="do_not_perform_genotype_likelihood_computation"> - <!-- Do nothing here --> - </when> - </conditional> - <conditional name="advanced_options"> - <param name="advanced_options_selector" type="select" label="Set advanced options"> - <option value="basic" selected="True">Basic</option> - <option value="advanced">Advanced</option> - </param> - <when value="advanced"> - <param name="skip_anomalous_read_pairs" type="boolean" truevalue="-A" falsevalue="" checked="False" label="Do not skip anomalous read pairs in variant calling" /> - <param name="disable_probabilistic_realignment" type="boolean" truevalue="-B" falsevalue="" checked="False" label=" Disable probabilistic realignment for the computation of base alignment quality (BAQ)" /> - <param name="coefficient_for_downgrading" type="integer" value="0" label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" /> - <param name="max_reads_per_bam" type="integer" value="250" label="Max reads per BAM" /> - <param name="extended_BAQ_computation" type="boolean" truevalue="-E" falsevalue="" checked="False" label="Extended BAQ computation" /> - <param name="position_list" type="data" format="bed" label="List of regions or sites on which to operate" optional="True" /> - <param name="minimum_mapping_quality" type="integer" value="0" label="Minimum mapping quality for an alignment to be used" /> - <param name="minimum_base_quality" type="integer" value="13" label="Minimum base quality for a base to be considered" /> - <param name="region_string" type="text" value="" label="Only generate pileup in region" /> - <param name="output_per_sample_read_depth" type="boolean" truevalue="-D" falsevalue="" checked="False" label="Output per-sample read depth" /> - <param name="output_per_sample_strand_bias_p_value" type="boolean" truevalue="-S" falsevalue="" checked="False" label="Output per-sample Phred-scaled strand bias P-value" /> - </when> - <when value="basic" /> - </conditional> - </inputs> - <outputs> - <data format="pileup" name="output_mpileup" label="${tool.name} on ${on_string}"> - <change_format> - <when input="genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" format="bcf" /> - </change_format> - </data> - <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> - </outputs> - <tests> - <test> - <param name="reference_source_selector" value="history" /> - <param name="ref_file" value="phiX.fasta" ftype="fasta" /> - <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" /> - <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" /> - <param name="advanced_options_selector" value="basic" /> - <output name="output_mpileup" file="samtools/mpileup/samtools_mpileup_out_1.pileup" /> - <output name="output_log" file="samtools/mpileup/samtools_mpileup_out_1.log" /> - </test> - <test> - <param name="reference_source_selector" value="history" /> - <param name="ref_file" value="phiX.fasta" ftype="fasta" /> - <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" /> - <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" /> - <param name="gap_extension_sequencing_error_probability" value="20" /> - <param name="coefficient_for_modeling_homopolymer_errors" value="100" /> - <param name="perform_indel_calling_selector" value="perform_indel_calling" /> - <param name="skip_indel_calling_above_sample_depth" value="250" /> - <param name="gap_open_sequencing_error_probability" value="40" /> - <param name="platform_list_repeat" value="0" /> - <param name="advanced_options_selector" value="basic" /> - <output name="output_mpileup" file="samtools/mpileup/samtools_mpileup_out_2.bcf" /> - <output name="output_log" file="samtools/mpileup/samtools_mpileup_out_1.log" /> - </test> - </tests> - <help> + </conditional> + <conditional name="advanced_options"> + <param label="Set advanced options" name="advanced_options_selector" type="select"> + <option selected="True" value="basic">Basic</option> + <option value="advanced">Advanced</option> + </param> + <when value="advanced"> + <conditional name="filter_by_flags"> + <param label="Set filter by flags" name="filter_flags" type="select"> + <option selected="True" value="nofilter">Do not filter</option> + <option value="filter">Filter by flags to exclude or require</option> + </param> + <when value="filter"> + <param display="checkboxes" label="Require" multiple="True" name="require_flags" type="select" help="--incl-flags"> + <option value="1">Read is paired</option> + <option value="2">Read is mapped in a proper pair</option> + <option value="4">The read is unmapped</option> + <option value="8">The mate is unmapped</option> + <option value="16">Read strand</option> + <option value="32">Mate strand</option> + <option value="64">Read is the first in a pair</option> + <option value="128">Read is the second in a pair</option> + <option value="256">The alignment or this read is not primary</option> + <option value="512">The read fails platform/vendor quality checks</option> + <option value="1024">The read is a PCR or optical duplicate</option> + </param> + <param display="checkboxes" label="Exclude" multiple="True" name="exclude_flags" type="select" help="--excl-flags"> + <option value="1">Read is paired</option> + <option value="2">Read is mapped in a proper pair</option> + <option value="4">The read is unmapped</option> + <option value="8">The mate is unmapped</option> + <option value="16">Read strand</option> + <option value="32">Mate strand</option> + <option value="64">Read is the first in a pair</option> + <option value="128">Read is the second in a pair</option> + <option value="256">The alignment or this read is not primary</option> + <option value="512">The read fails platform/vendor quality checks</option> + <option value="1024">The read is a PCR or optical duplicate</option> + </param> + </when> + <when value="nofilter" /> + </conditional> + <conditional name="limit_by_region"> + <param label="Select regions to call" name="limit_by_regions" type="select"> + <option selected="True" value="no_limit">Do not limit</option> + <option value="history">From an uploaded BED file (--positions)</option> + <option value="paste">Paste a list of regions or BED (--region)</option> + </param> + <when value="history"> + <param format="bed" label="BED file" name="bed_regions" type="data" help="--positions"> + <validator type="dataset_ok_validator" /> + </param> + </when> + <when value="paste"> + <param area="true" help="Paste a list of regions in BED format or as a list of chromosomes and positions" label="Regions" name="region_paste" size="10x35" type="text"/> + </when> + <when value="no_limit" /> + </conditional> + <conditional name="exclude_read_group"> + <param label="Select read groups to exclude" name="exclude_read_groups" type="select" help="--exclude-RG"> + <option selected="True" value="no_limit">Do not exclude</option> + <option value="history">From an uploaded text file</option> + <option value="paste">Paste a list of read groups</option> + </param> + <when value="history"> + <param format="txt" label="Text file" name="read_groups" type="data"> + <validator type="dataset_ok_validator" /> + </param> + </when> + <when value="paste"> + <param area="true" help="Paste a list of read groups" label="Read groups" name="group_paste" size="10x35" type="text" /> + </when> + <when value="no_limit" /> + </conditional> + <param checked="False" falsevalue="" label="Disable read-pair overlap detection" name="ignore_overlaps" truevalue="-x" type="boolean" help="--ignore-overlaps"/> + <param checked="False" falsevalue="" label="Do not skip anomalous read pairs in variant calling" name="skip_anomalous_read_pairs" truevalue="-A" type="boolean" help="--count-orphans"/> + <param checked="False" falsevalue="" label="Disable probabilistic realignment for the computation of base alignment quality (BAQ)" name="disable_probabilistic_realignment" truevalue="-B" type="boolean" help="--no-BAQ; BAQ is the Phred-scaled probability of a read base being misaligned. Applying this option greatly helps to reduce false SNPs caused by misalignments"/> + <param label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" name="coefficient_for_downgrading" type="integer" value="0" help="--adjust-MQ; Given a read with a phred-scaled probability q of being generated from the mapped position, the new mapping quality is about sqrt((INT-q)/INT)*INT. A zero value disables this functionality; if enabled, the recommended value for BWA is 50. default=0"/> + <param label="Max reads per BAM" max="1024" min="1" name="max_reads_per_bam" type="integer" value="250" help="--max-depth; default=250"/> + <param checked="False" falsevalue="" label="Redo BAQ computation" name="extended_BAQ_computation" truevalue="-E" type="boolean" help="--redo-BAQ; ignore existing BQ tags"/> + <param label="Minimum mapping quality for an alignment to be used" name="minimum_mapping_quality" type="integer" value="0" help="-min-MQ; default=0"/> + <param label="Minimum base quality for a base to be considered" name="minimum_base_quality" type="integer" value="13" help="--min-BQ; default=13"/> + </when> + <when value="basic" /> + </conditional> + </inputs> + <outputs> + <data format="pileup" label="${tool.name} on ${on_string}" name="output_mpileup"> + <change_format> + <when format="bcf" input="genotype_likelihood_computation_type.output_format" value="--BCF" /> + <when format="vcf" input="genotype_likelihood_computation_type.output_format" value="--VCF" /> + </change_format> + </data> + <data format="txt" label="${tool.name} on ${on_string} (log)" name="output_log" /> + </outputs> + <tests> + <test> + <param name="reference_source_selector" value="history" /> + <param ftype="fasta" name="ref_file" value="phiX.fasta" /> + <param ftype="bam" name="input_bam" value="samtools_mpileup_in_1.bam" /> + <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" /> + <param name="advanced_options_selector" value="basic" /> + <param name="base_position_on_reads" value="true" /> + <param name="output_mapping_quality" value="true" /> + <output file="samtools_mpileup_out_1.pileup" name="output_mpileup" /> + <output file="samtools_mpileup_out_1.log" name="output_log" /> + </test> + <test> + <param name="reference_source_selector" value="history" /> + <param ftype="fasta" name="ref_file" value="phiX.fasta" /> + <param ftype="bam" name="input_bam" value="phiX.bam" /> + <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" /> + <param name="gap_extension_sequencing_error_probability" value="20" /> + <param name="coefficient_for_modeling_homopolymer_errors" value="100" /> + <param name="perform_indel_calling_selector" value="perform_indel_calling" /> + <param name="skip_indel_calling_above_sample_depth" value="250" /> + <param name="gap_open_sequencing_error_probability" value="40" /> + <param name="platform_list_repeat" value="0" /> + <param name="advanced_options_selector" value="basic" /> + <param name="genotype_likelihood_computation_type|output_format" value="VCF" /> + <output file="samtools_mpileup_out_2.vcf" ftype="vcf" lines_diff="8" name="output_mpileup" /> + <output file="samtools_mpileup_out_2.log" name="output_log" /> + </test> + </tests> + <help> +<![CDATA[ **What it does** - Generate BCF or pileup for one or multiple BAM files. Alignment records are grouped by sample identifiers in @RG header lines. If sample identifiers are absent, each input file is regarded as one sample. +Report variants for one or multiple BAM files. Alignment records are grouped by sample identifiers in @RG header lines. If sample identifiers are absent, each input file is regarded as one sample. ------ -**Settings**:: +**Input options**:: + + -6, --illumina1.3+ quality is in the Illumina-1.3+ encoding + -A, --count-orphans do not discard anomalous read pairs + -b, --bam-list FILE list of input BAM filenames, one per line + -B, --no-BAQ disable BAQ (per-Base Alignment Quality) + -C, --adjust-MQ INT adjust mapping quality; recommended:50, disable:0 [0] + -d, --max-depth INT max per-BAM depth; avoids excessive memory usage [250] + -E, --redo-BAQ recalculate BAQ on the fly, ignore existing BQs + -f, --fasta-ref FILE faidx indexed reference sequence file + -G, --exclude-RG FILE exclude read groups listed in FILE + -l, --positions FILE skip unlisted positions (chr pos) or regions (BED) + -q, --min-MQ INT skip alignments with mapQ smaller than INT [0] + -Q, --min-BQ INT skip bases with baseQ/BAQ smaller than INT [13] + -r, --region REG region in which pileup is generated + -R, --ignore-RG ignore RG tags (one BAM = one sample) + --rf, --incl-flags STR|INT required flags: skip reads with mask bits unset [] + --ff, --excl-flags STR|INT filter flags: skip reads with mask bits set + [UNMAP,SECONDARY,QCFAIL,DUP] + -x, --ignore-overlaps disable read-pair overlap detection + +**Output options**:: + + -o, --output FILE write output to FILE [standard output] + -g, --BCF generate genotype likelihoods in BCF format + -v, --VCF generate genotype likelihoods in VCF format + +**Output options for mpileup format** (without -g/-v):: + + -O, --output-BP output base positions on reads + -s, --output-MQ output mapping quality + +**Output options for genotype likelihoods** (when -g/-v is used):: + + -t, --output-tags LIST optional tags to output: DP,DPR,DV,DP4,INFO/DPR,SP [] + -u, --uncompressed generate uncompressed VCF/BCF output + +**SNP/INDEL genotype likelihoods options** (effective with -g/-v):: - Input Options: - -6 Assume the quality is in the Illumina 1.3+ encoding. - -A Do not skip anomalous read pairs in variant calling. - -B Disable probabilistic realignment for the computation of base alignment quality (BAQ). BAQ is the Phred-scaled probability of a read base being misaligned. Applying this option greatly helps to reduce false SNPs caused by misalignments. - -b FILE List of input BAM files, one file per line [null] - -C INT Coefficient for downgrading mapping quality for reads containing excessive mismatches. Given a read with a phred-scaled probability q of being generated from the mapped position, the new mapping quality is about sqrt((INT-q)/INT)*INT. A zero value disables this functionality; if enabled, the recommended value for BWA is 50. [0] - -d INT At a position, read maximally INT reads per input BAM. [250] - -E Extended BAQ computation. This option helps sensitivity especially for MNPs, but may hurt specificity a little bit. - -f FILE The faidx-indexed reference file in the FASTA format. The file can be optionally compressed by razip. [null] - -l FILE BED or position list file containing a list of regions or sites where pileup or BCF should be generated [null] - -q INT Minimum mapping quality for an alignment to be used [0] - -Q INT Minimum base quality for a base to be considered [13] - -r STR Only generate pileup in region STR [all sites] - Output Options: - - -D Output per-sample read depth - -g Compute genotype likelihoods and output them in the binary call format (BCF). - -S Output per-sample Phred-scaled strand bias P-value - -u Similar to -g except that the output is uncompressed BCF, which is preferred for piping. - - Options for Genotype Likelihood Computation (for -g or -u): - - -e INT Phred-scaled gap extension sequencing error probability. Reducing INT leads to longer indels. [20] - -h INT Coefficient for modeling homopolymer errors. Given an l-long homopolymer run, the sequencing error of an indel of size s is modeled as INT*s/l. [100] - -I Do not perform INDEL calling - -L INT Skip INDEL calling if the average per-sample depth is above INT. [250] - -o INT Phred-scaled gap open sequencing error probability. Reducing INT leads to more indel calls. [40] - -P STR Comma dilimited list of platforms (determined by @RG-PL) from which indel candidates are obtained. It is recommended to collect indel candidates from sequencing technologies that have low indel error rate such as ILLUMINA. [all] + -e, --ext-prob INT Phred-scaled gap extension seq error probability [20] + -F, --gap-frac FLOAT minimum fraction of gapped reads [0.002] + -h, --tandem-qual INT coefficient for homopolymer errors [100] + -I, --skip-indels do not perform indel calling + -L, --max-idepth INT maximum per-sample depth for INDEL calling [250] + -m, --min-ireads INT minimum number gapped reads for indel candidates [1] + -o, --open-prob INT Phred-scaled gap open seq error probability [40] + -p, --per-sample-mF apply -m and -F per-sample for increased sensitivity + -P, --platforms STR comma separated list of platforms for indels [all] ------- - -**Citation** - -For the underlying tool, please cite `Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, Marth G, Abecasis G, Durbin R; 1000 Genome Project Data Processing Subgroup. The Sequence Alignment/Map format and SAMtools. Bioinformatics. 2009 Aug 15;25(16):2078-9. <http://www.ncbi.nlm.nih.gov/pubmed/19505943>`_ - -If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.* - - </help> +**Notes**: Assuming diploid individuals. +]]> + </help> + <configfiles> + <configfile name="excluded_read_groups"> +<![CDATA[ +#set pasted_data = '' +#if str( $advanced_options.advanced_options_selector ) == "advanced": + #if str( $advanced_options.exclude_read_group.exclude_read_groups ) == "paste": + #set pasted_data = '\t'.join( str( $advanced_options.exclude_read_group['read_groups'] ).split() ) + #end if +#end if +${pasted_data} +]]> + </configfile> + <configfile name="pasted_regions"> +<![CDATA[ +#set pasted_data = '' +#if str( $advanced_options.advanced_options_selector ) == "advanced": + #if str( $advanced_options.limit_by_region.limit_by_regions ) == "paste": + #set pasted_data = '\t'.join( str( $advanced_options.limit_by_region['region_paste'] ).split() ) + #end if +#end if +${pasted_data} +]]> + </configfile> + </configfiles> + <expand macro="citations" /> </tool>
--- a/samtools_wrapper.py Thu Mar 27 15:27:36 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,110 +0,0 @@ -#!/usr/bin/env python -#Dan Blankenberg - -""" -A wrapper script for running SAMTools commands. -""" - -import sys, optparse, os, tempfile, subprocess, shutil -from string import Template - -GALAXY_EXT_TO_SAMTOOLS_EXT = { 'bam_index':'bam.bai', } #items not listed here will use the galaxy extension as-is -GALAXY_EXT_TO_SAMTOOLS_FILE_TYPE = GALAXY_EXT_TO_SAMTOOLS_EXT #for now, these are the same, but could be different if needed -DEFAULT_SAMTOOLS_PREFIX = "SAMTools_file" -CHUNK_SIZE = 2**20 #1mb - - -def cleanup_before_exit( tmp_dir ): - if tmp_dir and os.path.exists( tmp_dir ): - shutil.rmtree( tmp_dir ) - -def SAMTOOLS_filename_from_galaxy( galaxy_filename, galaxy_ext, target_dir = None, prefix = None ): - suffix = GALAXY_EXT_TO_SAMTOOLS_EXT.get( galaxy_ext, galaxy_ext ) - if prefix is None: - prefix = DEFAULT_SAMTOOLS_PREFIX - if target_dir is None: - target_dir = os.getcwd() - SAMTools_filename = os.path.join( target_dir, "%s.%s" % ( prefix, suffix ) ) - os.symlink( galaxy_filename, SAMTools_filename ) - return SAMTools_filename - -def SAMTOOLS_filetype_argument_substitution( argument, galaxy_ext ): - return argument % dict( file_type = GALAXY_EXT_TO_SAMTOOLS_FILE_TYPE.get( galaxy_ext, galaxy_ext ) ) - -def open_file_from_option( filename, mode = 'rb' ): - if filename: - return open( filename, mode = mode ) - return None - -def html_report_from_directory( html_out, dir ): - html_out.write( '<html>\n<head>\n<title>Galaxy - SAMTOOLS Output</title>\n</head>\n<body>\n<p/>\n<ul>\n' ) - for fname in sorted( os.listdir( dir ) ): - html_out.write( '<li><a href="%s">%s</a></li>\n' % ( fname, fname ) ) - html_out.write( '</ul>\n</body>\n</html>\n' ) - -def __main__(): - #Parse Command Line - parser = optparse.OptionParser() - parser.add_option( '-p', '--pass_through', dest='pass_through_options', action='append', type="string", help='These options are passed through directly to SAMTOOLS, without any modification.' ) - parser.add_option( '-d', '--dataset', dest='datasets', action='append', type="string", nargs=4, help='"-argument" "original_filename" "galaxy_filetype" "name_prefix"' ) - parser.add_option( '', '--stdout', dest='stdout', action='store', type="string", default=None, help='If specified, the output of stdout will be written to this file.' ) - parser.add_option( '', '--stderr', dest='stderr', action='store', type="string", default=None, help='If specified, the output of stderr will be written to this file.' ) - parser.add_option( '', '--html_report_from_directory', dest='html_report_from_directory', action='append', type="string", nargs=2, help='"Target HTML File" "Directory"') - (options, args) = parser.parse_args() - - tmp_dir = tempfile.mkdtemp( prefix='tmp-SAMTOOLS-' ) - - #set up stdout and stderr output options - stdout = open_file_from_option( options.stdout, mode = 'wb' ) - stderr = open_file_from_option( options.stderr, mode = 'wb' ) - #if no stderr file is specified, we'll use our own - if stderr is None: - stderr = tempfile.NamedTemporaryFile( prefix="SAMTOOLS-stderr-", dir=tmp_dir ) - - if options.pass_through_options: - cmd = ' '.join( options.pass_through_options ) - else: - cmd = '' - return_code = None - if options.datasets: - for ( dataset_arg, filename, galaxy_ext, prefix ) in options.datasets: - SAMTools_filename = SAMTOOLS_filename_from_galaxy( filename, galaxy_ext, target_dir = tmp_dir, prefix = prefix ) - if dataset_arg: - if '>' in cmd: - cmd = cmd.replace( '>', ' %s "%s" >' % ( SAMTOOLS_filetype_argument_substitution( dataset_arg, galaxy_ext ), SAMTools_filename ), 1 ) - else: - cmd = '%s %s "%s"' % ( cmd, SAMTOOLS_filetype_argument_substitution( dataset_arg, galaxy_ext ), SAMTools_filename ) - #auto index fasta files: - if galaxy_ext == 'fa': - index_cmd = 'samtools faidx %s' % ( SAMTools_filename ) - proc = subprocess.Popen( args=index_cmd, stdout=stdout, stderr=stderr, shell=True, cwd=tmp_dir ) - return_code = proc.wait() - if return_code: - break - if return_code is None or not return_code: - proc = subprocess.Popen( args=cmd, stdout=stdout, stderr=stderr, shell=True, cwd=tmp_dir ) - return_code = proc.wait() - if return_code: - stderr_target = sys.stderr - else: - if stdout: - stderr_target = stdout - else: - stderr_target = sys.stdout - stderr.flush() - stderr.seek(0) - while True: - chunk = stderr.read( CHUNK_SIZE ) - if chunk: - stderr_target.write( chunk ) - else: - break - stderr.close() - #generate html reports - if options.html_report_from_directory: - for ( html_filename, html_dir ) in options.html_report_from_directory: - html_report_from_directory( open( html_filename, 'wb' ), html_dir ) - - cleanup_before_exit( tmp_dir ) - -if __name__=="__main__": __main__()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/samtools_mpileup_out_1.log Tue Apr 21 16:29:10 2015 -0400 @@ -0,0 +1,3 @@ +[fai_load] build FASTA index. +[mpileup] 1 samples in 1 input files +<mpileup> Set max per-file depth to 8000
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/samtools_mpileup_out_1.pileup Tue Apr 21 16:29:10 2015 -0400 @@ -0,0 +1,43 @@ +phiX174 1411 A 0 1 +phiX174 1412 G 0 2,1,1 +phiX174 1413 C 0 3,2,2,1,1 +phiX174 1414 G 0 4,3,3,2,2,1 +phiX174 1415 C 0 5,4,4,3,3,2,1 +phiX174 1416 C 0 6,5,5,4,4,3,2,1 +phiX174 1417 G 0 7,6,6,5,5,4,3,2,1 +phiX174 1418 T 0 8,7,7,6,6,5,4,3,2,1 +phiX174 1419 G 0 9,8,8,7,7,6,5,4,3,2 +phiX174 1420 G 0 10,9,9,8,8,7,6,5,4,3 +phiX174 1421 A 0 11,10,10,9,9,8,7,6,5,4 +phiX174 1422 T 0 12,11,11,10,10,9,8,7,6,5 +phiX174 1423 G 0 13,12,12,11,11,10,9,8,7,6 +phiX174 1424 C 0 14,13,13,12,12,11,10,9,8,7 +phiX174 1425 C 0 15,14,14,13,13,12,11,10,9,8 +phiX174 1426 T 0 16,15,15,14,14,13,12,11,10,9 +phiX174 1427 G 0 17,16,16,15,15,14,13,12,11,10 +phiX174 1428 A 0 18,17,17,16,16,15,14,13,12,11 +phiX174 1429 C 0 19,18,18,17,17,16,15,14,13,12 +phiX174 1430 C 0 20,19,19,18,18,17,16,15,14,13 +phiX174 1431 G 0 21,20,20,19,19,18,17,16,15,14 +phiX174 1432 T 0 22,21,21,20,20,19,18,17,16,15 +phiX174 1433 A 0 23,22,22,21,21,20,19,18,17,16 +phiX174 1434 C 0 24,23,23,22,22,21,20,19,18,17 +phiX174 1435 C 0 25,24,24,23,23,22,21,20,19,18 +phiX174 1436 G 0 26,25,25,24,24,23,22,21,20,19 +phiX174 1437 A 0 27,26,26,25,25,24,23,22,21,20 +phiX174 1438 G 0 28,27,27,26,26,25,24,23,22,21 +phiX174 1439 G 0 29,28,28,27,27,26,25,24,23,22 +phiX174 1440 C 0 30,29,29,28,28,27,26,25,24,23 +phiX174 1441 T 0 31,30,30,29,29,28,27,26,25,24 +phiX174 1442 A 0 32,31,31,30,30,29,28,27,26,25 +phiX174 1443 A 0 33,32,32,31,31,30,29,28,27,26 +phiX174 1444 C 0 34,33,33,32,32,31,30,29,28,27 +phiX174 1445 C 0 34,33,34,32,33,32,31,30,29,28 +phiX174 1446 C 0 35,34,35,33,34,33,32,31,30,29 +phiX174 1447 T 0 36,35,36,34,35,34,33,32,31,30 +phiX174 1448 A 0 36,35,36,35,34,33,32,31 +phiX174 1449 A 0 36,36,35,34,33,32 +phiX174 1450 T 0 36,35,34,33 +phiX174 1451 G 0 36,35,34 +phiX174 1452 A 0 36,35 +phiX174 1453 G 0 36
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/samtools_mpileup_out_2.log Tue Apr 21 16:29:10 2015 -0400 @@ -0,0 +1,3 @@ +[fai_load] build FASTA index. +[mpileup] 1 samples in 1 input files +<mpileup> Set max per-file depth to 8000
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/samtools_mpileup_out_2.vcf Tue Apr 21 16:29:10 2015 -0400 @@ -0,0 +1,22 @@ +##fileformat=VCFv4.2 +##FILTER=<ID=PASS,Description="All filters passed"> +##samtoolsVersion=1.1+htslib-1.1 +##samtoolsCommand=samtools mpileup --VCF --uncompressed -f /tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_735.dat -g -e 20 -h 100 -L 250 -m 1 --open-prob 40 -F 0.002 -e 40 --output /tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_736.dat /tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_734.dat +##reference=file:///tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_735.dat +##contig=<ID=phiX174,length=5386> +##ALT=<ID=X,Description="Represents allele(s) other than observed."> +##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL."> +##INFO=<ID=IDV,Number=1,Type=Integer,Description="Maximum number of reads supporting an indel"> +##INFO=<ID=IMF,Number=1,Type=Float,Description="Maximum fraction of reads supporting an indel"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Raw read depth"> +##INFO=<ID=VDB,Number=1,Type=Float,Description="Variant Distance Bias for filtering splice-site artefacts in RNA-seq data (bigger is better)",Version="3"> +##INFO=<ID=RPB,Number=1,Type=Float,Description="Mann-Whitney U test of Read Position Bias (bigger is better)"> +##INFO=<ID=MQB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality Bias (bigger is better)"> +##INFO=<ID=BQB,Number=1,Type=Float,Description="Mann-Whitney U test of Base Quality Bias (bigger is better)"> +##INFO=<ID=MQSB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality vs Strand Bias (bigger is better)"> +##INFO=<ID=SGB,Number=1,Type=Float,Description="Segregation based metric."> +##INFO=<ID=MQ0F,Number=1,Type=Float,Description="Fraction of MQ0 reads (smaller is better)"> +##INFO=<ID=I16,Number=16,Type=Float,Description="Auxiliary tag used for calling, see description of bcf_callret1_t in bam2bcf.h"> +##INFO=<ID=QS,Number=R,Type=Float,Description="Auxiliary tag used for calling"> +##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods"> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT /tmp/tmpId8vOP/tmp3bubIE/database/files/000/dataset_734.dat
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/samtools_mpileup_out_3.log Tue Apr 21 16:29:10 2015 -0400 @@ -0,0 +1,2 @@ +[mpileup] 1 samples in 1 input files +<mpileup> Set max per-file depth to 8000
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/samtools_mpileup_out_4.log Tue Apr 21 16:29:10 2015 -0400 @@ -0,0 +1,2 @@ +[mpileup] 1 samples in 1 input files +<mpileup> Set max per-file depth to 8000
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/samtools_mpileup_out_4.vcf Tue Apr 21 16:29:10 2015 -0400 @@ -0,0 +1,22 @@ +##fileformat=VCFv4.2 +##FILTER=<ID=PASS,Description="All filters passed"> +##samtoolsVersion=1.1+htslib-1.1 +##samtoolsCommand=samtools mpileup --VCF --uncompressed -f /var/galaxy/workspace/CleanGalaxy/tool-data/phiX/sam_indexes/phiX/phiX.fa -C 0 -d 200 -E -q 0 -Q 43 -g -e 20 -h 100 -L 250 -m 1 --open-prob 40 -F 0.002 -e 40 --output /tmp/tmp5TzrZC/tmpDtGVov/database/files/000/dataset_756.dat /tmp/tmp5TzrZC/tmpDtGVov/database/files/000/dataset_755.dat +##reference=file:///var/galaxy/workspace/CleanGalaxy/tool-data/phiX/sam_indexes/phiX/phiX.fa +##contig=<ID=phiX174,length=5386> +##ALT=<ID=X,Description="Represents allele(s) other than observed."> +##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL."> +##INFO=<ID=IDV,Number=1,Type=Integer,Description="Maximum number of reads supporting an indel"> +##INFO=<ID=IMF,Number=1,Type=Float,Description="Maximum fraction of reads supporting an indel"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Raw read depth"> +##INFO=<ID=VDB,Number=1,Type=Float,Description="Variant Distance Bias for filtering splice-site artefacts in RNA-seq data (bigger is better)",Version="3"> +##INFO=<ID=RPB,Number=1,Type=Float,Description="Mann-Whitney U test of Read Position Bias (bigger is better)"> +##INFO=<ID=MQB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality Bias (bigger is better)"> +##INFO=<ID=BQB,Number=1,Type=Float,Description="Mann-Whitney U test of Base Quality Bias (bigger is better)"> +##INFO=<ID=MQSB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality vs Strand Bias (bigger is better)"> +##INFO=<ID=SGB,Number=1,Type=Float,Description="Segregation based metric."> +##INFO=<ID=MQ0F,Number=1,Type=Float,Description="Fraction of MQ0 reads (smaller is better)"> +##INFO=<ID=I16,Number=16,Type=Float,Description="Auxiliary tag used for calling, see description of bcf_callret1_t in bam2bcf.h"> +##INFO=<ID=QS,Number=R,Type=Float,Description="Auxiliary tag used for calling"> +##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods"> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT /tmp/tmp5TzrZC/tmpDtGVov/database/files/000/dataset_755.dat
--- a/tool_dependencies.xml Thu Mar 27 15:27:36 2014 -0400 +++ b/tool_dependencies.xml Tue Apr 21 16:29:10 2015 -0400 @@ -1,6 +1,6 @@ <?xml version="1.0"?> <tool_dependency> - <package name="samtools" version="0.1.19"> - <repository changeset_revision="1ef76f8d8e52" name="package_samtools_0_1_19" owner="devteam" toolshed="http://toolshed.g2.bx.psu.edu" /> + <package name="samtools" version="1.2"> + <repository changeset_revision="6eea04363026" name="package_samtools_1_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> </package> </tool_dependency>