Mercurial > repos > jjohnson > gatk2
view realigner_target_creator.xml @ 29:c511aa6f93da draft
Temporarily use my own copy of samtools until cross dependency support is in release
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Tue, 19 Feb 2013 20:59:51 -0600 |
| parents | 6ef8eb568700 |
| children | 76f8ca47b810 |
line wrap: on
line source
<tool id="gatk2_realigner_target_creator" name="Realigner Target Creator" version="0.0.5"> <description>for use in local realignment</description> <requirements> <requirement type="package" version="2.3">gatk</requirement> <requirement type="package" version="0.1.18">samtools</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py --max_jvm_heap_fraction "1" --stdout "${output_log}" -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input" #if str( $reference_source.input_bam.metadata.bam_index ) != "None": -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index #end if -p 'java -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" -T "RealignerTargetCreator" -o "${output_interval}" \$GATK2_SITE_OPTIONS \$GATK2_NUM_THREADS ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home ##--num_threads 4 ##hard coded, for now ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout #if $reference_source.reference_source_selector != "history": -R "${reference_source.ref_file.fields.path}" #end if ' #set $rod_binding_names = dict() #for $rod_binding in $rod_bind: #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom': #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name #else #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector #end if #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1 -d "-known:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}" #end for ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": #for $pedigree in $gatk_param_type.pedigree: -p '--pedigree "${pedigree.pedigree_file}"' #end for #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: -p '--pedigreeString "${pedigree_string.pedigree_string}"' #end for -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) #for $name, $param in $read_filter.read_filter_type.iteritems(): #if $name not in [ "__current_case__", "read_filter_type_selector" ]: #if hasattr( $param.input, 'truevalue' ): ${param} #else: --${name} "${param}" #end if #end if #end for ' #end for #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ): -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}" #end for #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ): -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"' #end if -p ' --baq "${gatk_param_type.baq}" --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}" ${gatk_param_type.use_original_qualities} --defaultBaseQualities "${gatk_param_type.default_base_qualities}" --validation_strictness "${gatk_param_type.validation_strictness}" --interval_merging "${gatk_param_type.interval_merging}" ${gatk_param_type.disable_experimental_low_memory_sharding} ${gatk_param_type.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file": -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}" #else -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"' #end if #end for #end if #if $reference_source.reference_source_selector == "history": -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input" #end if ##end standard gatk options ##start analysis specific options #if $analysis_param_type.analysis_param_type_selector == "advanced": -p ' --minReadsAtLocus "${analysis_param_type.minReadsAtLocus}" --windowSize "${analysis_param_type.windowSize}" --mismatchFraction "${analysis_param_type.mismatchFraction}" --maxIntervalSize "${analysis_param_type.maxIntervalSize}" ' #end if </command> <inputs> <conditional name="reference_source"> <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> <option value="cached">Locally cached</option> <option value="history">History</option> </param> <when value="cached"> <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &lt;input_file&gt;"> <validator type="unspecified_build" /> <validator type="dataset_metadata_in_data_table" table_name="gatk2_picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select --> </param> <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &lt;reference_sequence&gt;" > <options from_data_table="gatk2_picard_indexes"> <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> </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 file" help="-I,--input_file &lt;input_file&gt;" /> <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;"> <options> <filter type="data_meta" key="dbkey" ref="input_bam" /> </options> </param> </when> </conditional> <repeat name="rod_bind" title="Binding for reference-ordered data" help="-known,--known &lt;known&gt;"> <conditional name="rod_bind_type"> <param name="rod_bind_type_selector" type="select" label="Binding Type"> <option value="dbsnp" selected="True">dbSNP</option> <option value="snps">SNPs</option> <option value="indels">INDELs</option> <option value="custom">Custom</option> </param> <when value="dbsnp"> <param name="input_rod" type="data" format="vcf" label="ROD file" /> </when> <when value="snps"> <param name="input_rod" type="data" format="vcf" label="ROD file" /> </when> <when value="indels"> <param name="input_rod" type="data" format="vcf" label="ROD file" /> </when> <when value="custom"> <param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/> <param name="input_rod" type="data" format="vcf" label="ROD file" /> </when> </conditional> </repeat> <conditional name="gatk_param_type"> <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options"> <option value="basic" selected="True">Basic</option> <option value="advanced">Advanced</option> </param> <when value="basic"> <!-- Do nothing here --> </when> <when value="advanced"> <repeat name="pedigree" title="Pedigree file" help="-ped,--pedigree &lt;pedigree&gt;"> <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples"/> </repeat> <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &lt;pedigreeString&gt;"> <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/> </repeat> <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information" help="-pedValidationType,--pedigreeValidationType &lt;pedigreeValidationType&gt;"> <option value="STRICT" selected="True">STRICT</option> <option value="SILENT">SILENT</option> </param> <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &lt;read_filter&gt;"> <conditional name="read_filter_type"> <param name="read_filter_type_selector" type="select" label="Read Filter Type"> <option value="BadCigar">BadCigar</option> <option value="BadMate">BadMate</option> <option value="DuplicateRead">DuplicateRead</option> <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option> <option value="MalformedRead">MalformedRead</option> <option value="MappingQuality">MappingQuality</option> <option value="MappingQualityUnavailable">MappingQualityUnavailable</option> <option value="MappingQualityZero">MappingQualityZero</option> <option value="MateSameStrand">MateSameStrand</option> <option value="MaxInsertSize">MaxInsertSize</option> <option value="MaxReadLength" selected="True">MaxReadLength</option> <option value="MissingReadGroup">MissingReadGroup</option> <option value="NoOriginalQualityScores">NoOriginalQualityScores</option> <option value="NotPrimaryAlignment">NotPrimaryAlignment</option> <option value="Platform454">Platform454</option> <option value="Platform">Platform</option> <option value="PlatformUnit">PlatformUnit</option> <option value="ReadGroupBlackList">ReadGroupBlackList</option> <option value="ReadName">ReadName</option> <option value="ReadStrand">ReadStrand</option> <option value="ReassignMappingQuality">ReassignMappingQuality</option> <option value="Sample">Sample</option> <option value="SingleReadGroup">SingleReadGroup</option> <option value="UnmappedRead">UnmappedRead</option> </param> <when value="BadCigar"> <!-- no extra options --> </when> <when value="BadMate"> <!-- no extra options --> </when> <when value="DuplicateRead"> <!-- no extra options --> </when> <when value="FailsVendorQualityCheck"> <!-- no extra options --> </when> <when value="MalformedRead"> <!-- no extra options --> </when> <when value="MappingQuality"> <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/> </when> <when value="MappingQualityUnavailable"> <!-- no extra options --> </when> <when value="MappingQualityZero"> <!-- no extra options --> </when> <when value="MateSameStrand"> <!-- no extra options --> </when> <when value="MaxInsertSize"> <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/> </when> <when value="MaxReadLength"> <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/> </when> <when value="MissingReadGroup"> <!-- no extra options --> </when> <when value="NoOriginalQualityScores"> <!-- no extra options --> </when> <when value="NotPrimaryAlignment"> <!-- no extra options --> </when> <when value="Platform454"> <!-- no extra options --> </when> <when value="Platform"> <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/> </when> <when value="PlatformUnit"> <!-- no extra options --> </when> <when value="ReadGroupBlackList"> <!-- no extra options --> </when> <when value="ReadName"> <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/> </when> <when value="ReadStrand"> <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/> </when> <when value="ReassignMappingQuality"> <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/> </when> <when value="Sample"> <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/> </when> <when value="SingleReadGroup"> <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/> </when> <when value="UnmappedRead"> <!-- no extra options --> </when> </conditional> </repeat> <repeat name="input_interval_repeat" title="Operate on Genomic intervals" help="-L,--intervals &lt;intervals&gt;"> <param name="input_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" /> </repeat> <repeat name="input_exclude_interval_repeat" title="Exclude Genomic intervals" help="-XL,--excludeIntervals &lt;excludeIntervals&gt;"> <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" /> </repeat> <param name="interval_set_rule" type="select" label="Interval set rule" help="-isr,--interval_set_rule &lt;interval_set_rule&gt;"> <option value="UNION" selected="True">UNION</option> <option value="INTERSECTION">INTERSECTION</option> </param> <conditional name="downsampling_type"> <param name="downsampling_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="-dt,--downsampling_type &lt;downsampling_type&gt;"> <option value="NONE" selected="True">NONE</option> <option value="ALL_READS">ALL_READS</option> <option value="BY_SAMPLE">BY_SAMPLE</option> </param> <when value="NONE"> <!-- no more options here --> </when> <when value="ALL_READS"> <conditional name="downsample_to_type"> <param name="downsample_to_type_selector" type="select" label="Downsample method"> <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option> <option value="downsample_to_coverage">Downsample by Coverage</option> </param> <when value="downsample_to_fraction"> <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &lt;downsample_to_fraction&gt;"/> </when> <when value="downsample_to_coverage"> <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &lt;downsample_to_coverage&gt;"/> </when> </conditional> </when> <when value="BY_SAMPLE"> <conditional name="downsample_to_type"> <param name="downsample_to_type_selector" type="select" label="Downsample method"> <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option> <option value="downsample_to_coverage">Downsample by Coverage</option> </param> <when value="downsample_to_fraction"> <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &lt;downsample_to_fraction&gt;"/> </when> <when value="downsample_to_coverage"> <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &lt;downsample_to_coverage&gt;"/> </when> </conditional> </when> </conditional> <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine" help="-baq,--baq &lt;baq&gt;"> <option value="OFF" selected="True">OFF</option> <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option> <option value="RECALCULATE">RECALCULATE</option> </param> <param name="baq_gap_open_penalty" type="float" label="BAQ gap open penalty (Phred Scaled)" value="40" help="Default value is 40. 30 is perhaps better for whole genome call sets. -baqGOP,--baqGapOpenPenalty &lt;baqGapOpenPenalty&gt;" /> <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" help="-OQ,--useOriginalQualities" /> <param name="default_base_qualities" type="integer" label="Value to be used for all base quality scores, when some are missing" value="-1" help="-DBQ,--defaultBaseQualities &lt;defaultBaseQualities&gt;"/> <param name="validation_strictness" type="select" label="How strict should we be with validation" help="-S,--validation_strictness &lt;validation_strictness&gt;"> <option value="STRICT" selected="True">STRICT</option> <option value="LENIENT">LENIENT</option> <option value="SILENT">SILENT</option> <!-- <option value="DEFAULT_STRINGENCY">DEFAULT_STRINGENCY</option> listed in docs, but not valid value...--> </param> <param name="interval_merging" type="select" label="Interval merging rule" help="-im,--interval_merging &lt;interval_merging&gt;"> <option value="ALL" selected="True">ALL</option> <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option> </param> <repeat name="read_group_black_list_repeat" title="Read group black list" help="-rgbl,--read_group_black_list &lt;read_group_black_list&gt;"> <conditional name="read_group_black_list_type"> <param name="read_group_black_list_type_selector" type="select" label="Type of reads read group black list"> <option value="file" selected="True">Filters in file</option> <option value="text">Specify filters as a string</option> </param> <when value="file"> <param name="read_group_black_list" type="data" format="txt" label="Read group black list file" /> </when> <when value="text"> <param name="read_group_black_list" type="text" value="tag:string" label="Read group black list tag:string" /> </when> </conditional> </repeat> <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/> <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/> <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional> <conditional name="analysis_param_type"> <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> <option value="basic" selected="True">Basic</option> <option value="advanced">Advanced</option> </param> <when value="basic"> <!-- Do nothing here --> </when> <when value="advanced"> <param name="windowSize" type="integer" value="10" label="Window size for calculating entropy or SNP clusters (windowSize)" help="-window,--windowSize &lt;windowSize&gt;" /> <param name="mismatchFraction" type="float" value="0.15" label="Fraction of base qualities needing to mismatch for a position to have high entropy (mismatchFraction)" help="to disable set to <= 0 or > 1 (-mismatch,--mismatchFraction &lt;mismatchFraction&gt;)"/> <param name="minReadsAtLocus" type="integer" value="4" label="Minimum reads at a locus to enable using the entropy calculation (minReadsAtLocus)" help="-minReads,--minReadsAtLocus &lt;minReadsAtLocus&gt;" /> <param name="maxIntervalSize" type="integer" value="500" label="Maximum interval size" help="-maxInterval,--maxIntervalSize &lt;maxIntervalSize&gt;" /> </when> </conditional> </inputs> <outputs> <data format="gatk_interval" name="output_interval" label="${tool.name} on ${on_string} (GATK intervals)" /> <data format="txt" name="output_log" label="${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/fake_phiX_reads_1.bam" ftype="bam" /> <param name="rod_bind_type_selector" value="dbsnp" /> <param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" /> <param name="gatk_param_type_selector" value="basic" /> <param name="analysis_param_type_selector" value="advanced" /> <param name="windowSize" value="10" /> <param name="mismatchFraction" value="0.15" /> <param name="minReadsAtLocus" value="4" /> <param name="maxIntervalSize" value="500" /> <output name="output_interval" file="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.gatk_interval" /> <output name="output_log" file="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.log.contains" compare="contains"/> </test> </tests> <help> **What it does** Emits intervals for the Local Indel Realigner to target for cleaning. Ignores 454 reads, MQ0 reads, and reads with consecutive indel operators in the CIGAR string. For more information on local realignment around indels using the GATK, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_indels_RealignerTargetCreator.html>`_. To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gatk/guide/topic?name=best-practices>`_. If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gatk/guide/topic?name=faqs>`_. ------ **Inputs** GenomeAnalysisTK: RealignerTargetCreator accepts an aligned BAM input file. **Outputs** The output is in GATK Interval format. Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. ------- **Settings**:: windowSize window size for calculating entropy or SNP clusters mismatchFraction fraction of base qualities needing to mismatch for a position to have high entropy; to disable set to <= 0 or > 1 minReadsAtLocus minimum reads at a locus to enable using the entropy calculation maxIntervalSize maximum interval size ------ **Citation** For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. <http://www.ncbi.nlm.nih.gov/pubmed/21478889>`_ Please also site `McKenna A, Hanna M, Banks E, Sivachenko A, Cibulskis K, Kernytsky A, Garimella K, Altshuler D, Gabriel S, Daly M, DePristo MA (2010). The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data. Genome Res. 20:1297-303. Epub 2010 Jul 19. <http://www.ncbi.nlm.nih.gov/pubmed/20644199>`_ If you use this tool in Galaxy, please cite `Blankenberg D, Von Kuster G, Coraor N, Ananda G, Lazarus R, Mangan M, Nekrutenko A, Taylor J. Galaxy: a web-based genome analysis tool for experimentalists. Curr Protoc Mol Biol. 2010 Jan;Chapter 19:Unit 19.10.1-21. <http://www.ncbi.nlm.nih.gov/pubmed/20069535>`_ </help> </tool>