Mercurial > repos > david-hoover > garbage1
changeset 22:d5e8dbe8072e draft
Uploaded
| author | david-hoover |
|---|---|
| date | Wed, 12 Sep 2012 18:10:34 -0400 |
| parents | 0a895e7c6d8e |
| children | 5aded99bf002 |
| files | README gatk2_wrapper.py indel_realigner.xml unified_genotyper.xml |
| diffstat | 4 files changed, 126 insertions(+), 1115 deletions(-) [+] |
line wrap: on
line diff
--- a/README Wed Sep 12 18:09:15 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,12 +0,0 @@ -The gatk2_sorted_picard_index.loc and gatk2_annotations.txt files must be -copied into the tool-data directory. The file tool_data_table_conf.xml must -be edited to include references to these two new files. - -Additionally, copies of or links to the GenomeAnalysisTK.jar and key file -must be made within the directory tool-data/shared/jars/gatk2. - - cd ${GALAXY_DATA_INDEX_DIR}/shared/jars - mkdir gatk2 - cd gatk2 - ln -s /path/to/wherever/GenomeAnalysisTK.jar . - ln -s /path/to/wherever/key.file gatk2_key_file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gatk2_wrapper.py Wed Sep 12 18:10:34 2012 -0400 @@ -0,0 +1,126 @@ +#!/usr/bin/env python +#David Hoover, based on gatk by Dan Blankenberg + +""" +A wrapper script for running the GenomeAnalysisTK.jar commands. +""" + +import sys, optparse, os, tempfile, subprocess, shutil +from binascii import unhexlify +from string import Template + +GALAXY_EXT_TO_GATK_EXT = { 'gatk_interval':'intervals', 'bam_index':'bam.bai', 'gatk_dbsnp':'dbSNP', 'picard_interval_list':'interval_list' } #items not listed here will use the galaxy extension as-is +GALAXY_EXT_TO_GATK_FILE_TYPE = GALAXY_EXT_TO_GATK_EXT #for now, these are the same, but could be different if needed +DEFAULT_GATK_PREFIX = "gatk_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 gatk_filename_from_galaxy( galaxy_filename, galaxy_ext, target_dir = None, prefix = None ): + suffix = GALAXY_EXT_TO_GATK_EXT.get( galaxy_ext, galaxy_ext ) + if prefix is None: + prefix = DEFAULT_GATK_PREFIX + if target_dir is None: + target_dir = os.getcwd() + gatk_filename = os.path.join( target_dir, "%s.%s" % ( prefix, suffix ) ) + os.symlink( galaxy_filename, gatk_filename ) + return gatk_filename + +def gatk_filetype_argument_substitution( argument, galaxy_ext ): + return argument % dict( file_type = GALAXY_EXT_TO_GATK_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 - GATK 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 index_bam_files( bam_filenames, tmp_dir ): + for bam_filename in bam_filenames: + bam_index_filename = "%s.bai" % bam_filename + if not os.path.exists( bam_index_filename ): + #need to index this bam file + stderr_name = tempfile.NamedTemporaryFile( prefix = "bam_index_stderr" ).name + command = 'samtools index %s %s' % ( bam_filename, bam_index_filename ) + proc = subprocess.Popen( args=command, shell=True, stderr=open( stderr_name, 'wb' ) ) + return_code = proc.wait() + if return_code: + for line in open( stderr_name ): + print >> sys.stderr, line + os.unlink( stderr_name ) #clean up + cleanup_before_exit( tmp_dir ) + raise Exception( "Error indexing BAM file" ) + os.unlink( stderr_name ) #clean up + +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 GATK, without any modification.' ) + parser.add_option( '-o', '--pass_through_options', dest='pass_through_options_encoded', action='append', type="string", help='These options are passed through directly to GATK, with decoding from binascii.unhexlify.' ) + parser.add_option( '-d', '--dataset', dest='datasets', action='append', type="string", nargs=4, help='"-argument" "original_filename" "galaxy_filetype" "name_prefix"' ) + parser.add_option( '', '--max_jvm_heap', dest='max_jvm_heap', action='store', type="string", default=None, help='If specified, the maximum java virtual machine heap size will be set to the provide value.' ) + parser.add_option( '', '--max_jvm_heap_fraction', dest='max_jvm_heap_fraction', action='store', type="int", default=None, help='If specified, the maximum java virtual machine heap size will be set to the provide value as a fraction of total physical memory.' ) + 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-gatk-' ) + if options.pass_through_options: + cmd = ' '.join( options.pass_through_options ) + else: + cmd = '' + if options.pass_through_options_encoded: + cmd = '%s %s' % ( cmd, ' '.join( map( unhexlify, options.pass_through_options_encoded ) ) ) + if options.max_jvm_heap is not None: + cmd = cmd.replace( 'java ', 'java -Xmx%s ' % ( options.max_jvm_heap ), 1 ) + elif options.max_jvm_heap_fraction is not None: + cmd = cmd.replace( 'java ', 'java -XX:DefaultMaxRAMFraction=%s -XX:+UseParallelGC ' % ( options.max_jvm_heap_fraction ), 1 ) + bam_filenames = [] + if options.datasets: + for ( dataset_arg, filename, galaxy_ext, prefix ) in options.datasets: + gatk_filename = gatk_filename_from_galaxy( filename, galaxy_ext, target_dir = tmp_dir, prefix = prefix ) + if dataset_arg: + cmd = '%s %s "%s"' % ( cmd, gatk_filetype_argument_substitution( dataset_arg, galaxy_ext ), gatk_filename ) + if galaxy_ext == "bam": + bam_filenames.append( gatk_filename ) + index_bam_files( bam_filenames, tmp_dir ) + #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="gatk-stderr-", dir=tmp_dir ) + + 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: + 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__()
--- a/indel_realigner.xml Wed Sep 12 18:09:15 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,492 +0,0 @@ -<tool id="gatk2_indel_realigner" name="Indel Realigner" version="0.0.1"> - <description>- perform local realignment</description> - <requirements> - <requirement type="package" version="2.1">gatk</requirement> - <requirement type="package">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 "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/GenomeAnalysisTK.jar" - -T "IndelRealigner" - -o "${output_bam}" - -et "NO_ET" -K "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/gatk2_key_file" ##ET no phone home - ##--num_threads 4 ##hard coded, for now - ##-log "${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 - -LOD "${lod_threshold}" - ${knowns_only} - ' - - #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.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}" "${reference_source.ref_file.ext}" "gatk_input" - #end if - ##end standard gatk options - ##start analysis specific options - -d "-targetIntervals" "${target_intervals}" "${target_intervals.ext}" "gatk_target_intervals" - -p ' - --disable_bam_indexing - ' - #if $analysis_param_type.analysis_param_type_selector == "advanced": - -p ' - --entropyThreshold "${analysis_param_type.entropy_threshold}" - ${analysis_param_type.simplify_bam} - --consensusDeterminationModel "${analysis_param_type.consensus_determination_model}" - --maxIsizeForMovement "${analysis_param_type.max_insert_size_for_movement}" - --maxPositionalMoveAllowed "${analysis_param_type.max_positional_move_allowed}" - --maxConsensuses "${analysis_param_type.max_consensuses}" - --maxReadsForConsensuses "${analysis_param_type.max_reads_for_consensuses}" - --maxReadsForRealignment "${analysis_param_type.max_reads_for_realignment}" - ${analysis_param_type.no_original_alignment_tags} - ' - #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> - <param name="target_intervals" type="data" format="gatk_interval,bed,picard_interval_list" label="Restrict realignment to provided intervals" help="-targetIntervals,--targetIntervals &lt;targetIntervals&gt;" /> - <repeat name="rod_bind" title="Binding for reference-ordered data" help="-known,--knownAlleles &lt;knownAlleles&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> - <param name="lod_threshold" type="float" value="5.0" label="LOD threshold above which the realigner will proceed to realign" help="-LOD,--LODThresholdForCleaning &lt;LODThresholdForCleaning&gt;" /> - <param name="knowns_only" type="boolean" checked="False" truevalue="-knownsOnly" falsevalue="" label="Use only known indels provided as RODs" help="-knownsOnly"/> - - <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"/> - - </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="entropy_threshold" type="float" value="0.15" label="percentage of mismatching base quality scores at a position to be considered having high entropy" help="-entropy,--entropyThreshold &lt;entropyThreshold&gt;" /> - <param name="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/> - <param name="consensus_determination_model" type="select" label="Consensus Determination Model" help="-model,--consensusDeterminationModel &lt;consensusDeterminationModel&gt;"> - <option value="KNOWNS_ONLY">KNOWNS_ONLY</option> - <option value="USE_READS" selected="True">USE_READS</option> - <option value="USE_SW">USE_SW</option> - </param> - <param name="max_insert_size_for_movement" type="integer" value="3000" label="Maximum insert size of read pairs that we attempt to realign" help="-maxIsize,--maxIsizeForMovement &lt;maxIsizeForMovement&gt;" /> - <param name="max_positional_move_allowed" type="integer" value="200" label="Maximum positional move in basepairs that a read can be adjusted during realignment" help="-maxPosMove,--maxPositionalMoveAllowed &lt;maxPositionalMoveAllowed&gt;" /> - <param name="max_consensuses" type="integer" value="30" label="Max alternate consensuses to try" help="-maxConsensuses,--maxConsensuses &lt;maxConsensuses&gt;" /> - <param name="max_reads_for_consensuses" type="integer" value="120" label="Max reads (chosen randomly) used for finding the potential alternate consensuses" help="-greedy,--maxReadsForConsensuses &lt;maxReadsForConsensuses&gt;" /> - <param name="max_reads_for_realignment" type="integer" value="20000" label="Max reads allowed at an interval for realignment" help="-maxReads,--maxReadsForRealignment &lt;maxReadsForRealignment&gt;" /> - <param name="no_original_alignment_tags" type="boolean" checked="False" truevalue="--noOriginalAlignmentTags" falsevalue="" label="Don't output the original cigar or alignment start tags for each realigned read in the output bam" help="-noTags,--noOriginalAlignmentTags"/> - </when> - </conditional> - </inputs> - <outputs> - <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (BAM)" /> - <data format="txt" name="output_log" label="${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="target_intervals" value="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.gatk_interval" ftype="gatk_interval" /> - <param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" /> - <param name="rod_bind_type_selector" value="snps" /> - <param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" /> - <param name="lod_threshold" value="5.0" /> - <param name="knowns_only" /> - <param name="gatk_param_type_selector" value="basic" /> - <param name="analysis_param_type_selector" value="advanced" /> - <param name="entropy_threshold" value="0.15" /> - <param name="simplify_bam" /> - <param name="consensus_determination_model" value="USE_SW" /> - <param name="max_insert_size_for_movement" value="3000" /> - <param name="max_positional_move_allowed" value="200" /> - <param name="max_consensuses" value="30" /> - <param name="max_reads_for_consensuses" value="120" /> - <param name="max_reads_for_realignment" value="20000" /> - <param name="no_original_alignment_tags" /> - <output name="output_bam" file="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" lines_diff="2" /> - <output name="output_log" file="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.log.contains" compare="contains" /> - </test> - </tests> - <help> -**What it does** - -Performs local realignment of reads based on misalignments due to the presence of indels. Unlike most mappers, this walker uses the full alignment context to determine whether an appropriate alternate reference (i.e. indel) exists and updates SAMRecords accordingly. - -For more information on local realignment around indels using the GATK, see this `tool specific page <http://www.broadinstitute.org/gsa/wiki/index.php/Local_realignment_around_indels>`_. - -To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3>`_. - -If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions>`_. - ------- - -**Inputs** - -GenomeAnalysisTK: IndelRealigner accepts an aligned BAM and a list of intervals to realign as input files. - - -**Outputs** - -The output is in the BAM format. - - -Go `here <http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK>`_ for details on GATK file formats. - -------- - -**Settings**:: - - targetIntervals intervals file output from RealignerTargetCreator - LODThresholdForCleaning LOD threshold above which the cleaner will clean - entropyThreshold percentage of mismatches at a locus to be considered having high entropy - out Output bam - bam_compression Compression level to use for writing BAM files - disable_bam_indexing Turn off on-the-fly creation of indices for output BAM files. - simplifyBAM If provided, output BAM files will be simplified to include just key reads for downstream variation discovery analyses (removing duplicates, PF-, non-primary reads), as well stripping all extended tags from the kept reads except the read group identifier - useOnlyKnownIndels Don't run 'Smith-Waterman' to generate alternate consenses; use only known indels provided as RODs for constructing the alternate references. - maxReadsInMemory max reads allowed to be kept in memory at a time by the SAMFileWriter. Keep it low to minimize memory consumption (but the tool may skip realignment on regions with too much coverage. If it is too low, it may generate errors during realignment); keep it high to maximize realignment (but make sure to give Java enough memory). - maxIsizeForMovement maximum insert size of read pairs that we attempt to realign - maxPositionalMoveAllowed maximum positional move in basepairs that a read can be adjusted during realignment - maxConsensuses max alternate consensuses to try (necessary to improve performance in deep coverage) - maxReadsForConsensuses max reads used for finding the alternate consensuses (necessary to improve performance in deep coverage) - maxReadsForRealignment max reads allowed at an interval for realignment; if this value is exceeded, realignment is not attempted and the reads are passed to the output file(s) as-is - noOriginalAlignmentTags Don't output the original cigar or alignment start tags for each realigned read in the output bam. - ------- - -**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>`_ - -If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.* - - </help> -</tool>
--- a/unified_genotyper.xml Wed Sep 12 18:09:15 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,611 +0,0 @@ -<tool id="gatk2_unified_genotyper" name="Unified Genotyper" version="0.0.1"> - <description>SNP and indel caller</description> - <requirements> - <requirement type="package" version="2.1">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}" - #for $i, $input_bam in enumerate( $reference_source.input_bams ): - -d "-I" "${input_bam.input_bam}" "${input_bam.input_bam.ext}" "gatk_input_${i}" - #if str( $input_bam.input_bam.metadata.bam_index ) != "None": - -d "" "${input_bam.input_bam.metadata.bam_index}" "bam_index" "gatk_input_${i}" ##hardcode galaxy ext type as bam_index - #end if - #end for - -p 'java - -jar "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/GenomeAnalysisTK.jar" - -T "UnifiedGenotyper" - --num_threads 4 ##hard coded, for now - --out "${output_vcf}" - --metrics_file "${output_metrics}" - -et "NO_ET" -K "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/gatk2_key_file" ##ET no phone home - ##-log "${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 - --genotype_likelihoods_model "${genotype_likelihoods_model}" - --standard_min_confidence_threshold_for_calling "${standard_min_confidence_threshold_for_calling}" - --standard_min_confidence_threshold_for_emitting "${standard_min_confidence_threshold_for_emitting}" - ' - #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( $rod_bind_name, -1 ) + 1 - -d "--dbsnp:${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.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 $analysis_param_type.analysis_param_type_selector == "advanced": - -p ' - --p_nonref_model "${analysis_param_type.p_nonref_model}" - --heterozygosity "${analysis_param_type.heterozygosity}" - --pcr_error_rate "${analysis_param_type.pcr_error_rate}" - --genotyping_mode "${analysis_param_type.genotyping_mode_type.genotyping_mode}" - #if str( $analysis_param_type.genotyping_mode_type.genotyping_mode ) == 'GENOTYPE_GIVEN_ALLELES': - --alleles "${analysis_param_type.genotyping_mode_type.input_alleles_rod}" - #end if - --output_mode "${analysis_param_type.output_mode}" - ${analysis_param_type.compute_SLOD} - --min_base_quality_score "${analysis_param_type.min_base_quality_score}" - --max_deletion_fraction "${analysis_param_type.max_deletion_fraction}" - --max_alternate_alleles "${analysis_param_type.max_alternate_alleles}" - --min_indel_count_for_genotyping "${analysis_param_type.min_indel_count_for_genotyping}" - --indel_heterozygosity "${analysis_param_type.indel_heterozygosity}" - --indelGapContinuationPenalty "${analysis_param_type.indelGapContinuationPenalty}" - --indelGapOpenPenalty "${analysis_param_type.indelGapOpenPenalty}" - --indelHaplotypeSize "${analysis_param_type.indelHaplotypeSize}" - ${analysis_param_type.doContextDependentGapPenalties} - #if str( $analysis_param_type.annotation ) != "None": - #for $annotation in str( $analysis_param_type.annotation.fields.gatk_value ).split( ','): - --annotation "${annotation}" - #end for - #end if - #for $additional_annotation in $analysis_param_type.additional_annotations: - --annotation "${additional_annotation.additional_annotation_name}" - #end for - #if str( $analysis_param_type.group ) != "None": - #for $group in str( $analysis_param_type.group ).split( ','): - --group "${group}" - #end for - #end if - #if str( $analysis_param_type.exclude_annotations ) != "None": - #for $annotation in str( $analysis_param_type.exclude_annotations.fields.gatk_value ).split( ','): - --excludeAnnotation "${annotation}" - #end for - #end if - ${analysis_param_type.multiallelic} - ' -## #if str( $analysis_param_type.snpEff_rod_bind_type.snpEff_rod_bind_type_selector ) == 'set_snpEff': -## -p '--annotation "SnpEff"' -## -d "--snpEffFile:${analysis_param_type.snpEff_rod_bind_type.snpEff_rod_name},%(file_type)s" "${analysis_param_type.snpEff_rod_bind_type.snpEff_input_rod}" "${analysis_param_type.snpEff_rod_bind_type.snpEff_input_rod.ext}" "input_snpEff_${analysis_param_type.snpEff_rod_bind_type.snpEff_rod_name}" -## #else: -## -p '--excludeAnnotation "SnpEff"' -## #end if - #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"> - <repeat name="input_bams" title="BAM file" min="1" help="-I,--input_file &lt;input_file&gt;"> - <param name="input_bam" type="data" format="bam" label="BAM file"> - <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> - </repeat> - <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"/> does not yet work in a repeat...--> - </options> - <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> - </param> - </when> - <when value="history"> <!-- FIX ME!!!! --> - <repeat name="input_bams" title="BAM file" min="1" help="-I,--input_file &lt;input_file&gt;"> - <param name="input_bam" type="data" format="bam" label="BAM file" > - </param> - </repeat> - <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;" /> - </when> - </conditional> - - <repeat name="rod_bind" title="Binding for reference-ordered data" help="-D,--dbsnp &lt;dbsnp&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> - - <param name="genotype_likelihoods_model" type="select" label="Genotype likelihoods calculation model to employ" help="-glm,--genotype_likelihoods_model &lt;genotype_likelihoods_model&gt;"> - <option value="BOTH" selected="True">BOTH</option> - <option value="SNP">SNP</option> - <option value="INDEL">INDEL</option> - </param> - - <param name="standard_min_confidence_threshold_for_calling" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called" help="-stand_call_conf,--standard_min_confidence_threshold_for_calling &lt;standard_min_confidence_threshold_for_calling&gt;" /> - <param name="standard_min_confidence_threshold_for_emitting" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)" help="-stand_emit_conf,--standard_min_confidence_threshold_for_emitting &lt;standard_min_confidence_threshold_for_emitting&gt;" /> - - - <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"/> - - </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="p_nonref_model" type="select" label="Non-reference probability calculation model to employ" help="-pnrm,--p_nonref_model &lt;p_nonref_model&gt;"> - <option value="EXACT" selected="True">EXACT</option> - <option value="GRID_SEARCH">GRID_SEARCH</option> - </param> - <param name="heterozygosity" type="float" value="1e-3" label="Heterozygosity value used to compute prior likelihoods for any locus" help="-hets,--heterozygosity &lt;heterozygosity&gt;" /> - <param name="pcr_error_rate" type="float" value="1e-4" label="The PCR error rate to be used for computing fragment-based likelihoods" help="-pcr_error,--pcr_error_rate &lt;pcr_error_rate&gt;" /> - <conditional name="genotyping_mode_type"> - <param name="genotyping_mode" type="select" label="How to determine the alternate allele to use for genotyping" help="-gt_mode,--genotyping_mode &lt;genotyping_mode&gt;"> - <option value="DISCOVERY" selected="True">DISCOVERY</option> - <option value="GENOTYPE_GIVEN_ALLELES">GENOTYPE_GIVEN_ALLELES</option> - </param> - <when value="DISCOVERY"> - <!-- Do nothing here --> - </when> - <when value="GENOTYPE_GIVEN_ALLELES"> - <param name="input_alleles_rod" type="data" format="vcf" label="Alleles ROD file" help="-alleles,--alleles &lt;alleles&gt;" /> - </when> - </conditional> - <param name="output_mode" type="select" label="Should we output confident genotypes (i.e. including ref calls) or just the variants?" help="-out_mode,--output_mode &lt;output_mode&gt;"> - <option value="EMIT_VARIANTS_ONLY" selected="True">EMIT_VARIANTS_ONLY</option> - <option value="EMIT_ALL_CONFIDENT_SITES">EMIT_ALL_CONFIDENT_SITES</option> - <option value="EMIT_ALL_SITES">EMIT_ALL_SITES</option> - </param> - <param name="compute_SLOD" type="boolean" truevalue="--computeSLOD" falsevalue="" label="Compute the SLOD" help="--computeSLOD" /> - <param name="min_base_quality_score" type="integer" value="17" label="Minimum base quality required to consider a base for calling" help="-mbq,--min_base_quality_score &lt;min_base_quality_score&gt;" /> - <param name="max_deletion_fraction" type="float" value="0.05" label="Maximum fraction of reads with deletions spanning this locus for it to be callable" help="to disable, set to < 0 or > 1 (-deletions,--max_deletion_fraction &lt;max_deletion_fraction&gt;)" /> - <param name="max_alternate_alleles" type="integer" value="5" label="Maximum number of alternate alleles to genotype" help="-maxAlleles,--max_alternate_alleles &lt;max_alternate_alleles&gt;" /> - <param name="min_indel_count_for_genotyping" type="integer" value="5" label="Minimum number of consensus indels required to trigger genotyping run" help="-minIndelCnt,--min_indel_count_for_genotyping &lt;min_indel_count_for_genotyping&gt;" /> - <param name="indel_heterozygosity" type="float" value="0.000125" label="Heterozygosity for indel calling" help="1.0/8000==0.000125 (-indelHeterozygosity,--indel_heterozygosity &lt;indel_heterozygosity&gt;)"/> - <param name="indelGapContinuationPenalty" type="float" value="10.0" label="Indel gap continuation penalty" help="--indelGapContinuationPenalty" /> - <param name="indelGapOpenPenalty" type="float" value="45.0" label="Indel gap open penalty" help="--indelGapOpenPenalty" /> - <param name="indelHaplotypeSize" type="integer" value="80" label="Indel haplotype size" help="--indelHaplotypeSize" /> - <param name="doContextDependentGapPenalties" type="boolean" truevalue="--doContextDependentGapPenalties" falsevalue="" label="Vary gap penalties by context" help="--doContextDependentGapPenalties" /> - <param name="annotation" type="select" multiple="True" display="checkboxes" label="Annotation Types" help="-A,--annotation &lt;annotation&gt;"> - <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs --> - <options from_data_table="gatk2_annotations"> - <filter type="multiple_splitter" column="tools_valid_for" separator=","/> - <filter type="static_value" value="UnifiedGenotyper" column="tools_valid_for"/> - </options> - </param> - <repeat name="additional_annotations" title="Additional annotation" help="-A,--annotation &lt;annotation&gt;"> - <param name="additional_annotation_name" type="text" value="" label="Annotation name" /> - </repeat> -<!-- - <conditional name="snpEff_rod_bind_type"> - <param name="snpEff_rod_bind_type_selector" type="select" label="Provide a snpEff reference-ordered data file"> - <option value="set_snpEff">Set snpEff</option> - <option value="exclude_snpEff" selected="True">Don't set snpEff</option> - </param> - <when value="exclude_snpEff"> - </when> - <when value="set_snpEff"> - <param name="snpEff_input_rod" type="data" format="vcf" label="ROD file" /> - <param name="snpEff_rod_name" type="hidden" value="snpEff" label="ROD Name"/> - </when> - </conditional> ---> - <param name="group" type="select" multiple="True" display="checkboxes" label="Annotation Interfaces/Groups" help="-G,--group &lt;group&gt;"> - <option value="RodRequiringAnnotation">RodRequiringAnnotation</option> - <option value="Standard">Standard</option> - <option value="Experimental">Experimental</option> - <option value="WorkInProgress">WorkInProgress</option> - <option value="RankSumTest">RankSumTest</option> - <!-- <option value="none">none</option> --> - </param> - <!-- <param name="family_string" type="text" value="" label="Family String"/> --> - <param name="exclude_annotations" type="select" multiple="True" display="checkboxes" label="Annotations to exclude" help="-XA,--excludeAnnotation &lt;excludeAnnotation&gt;" > - <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs --> - <options from_data_table="gatk2_annotations"> - <filter type="multiple_splitter" column="tools_valid_for" separator=","/> - <filter type="static_value" value="UnifiedGenotyper" column="tools_valid_for"/> - </options> - </param> - <param name="multiallelic" type="boolean" truevalue="--multiallelic" falsevalue="" label="Allow the discovery of multiple alleles (SNPs only)" help="--multiallelic" /> - </when> - </conditional> - </inputs> - <outputs> - <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (VCF)" /> - <data format="txt" name="output_metrics" label="${tool.name} on ${on_string} (metrics)" /> - <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> - </outputs> - <trackster_conf/> - <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="rod_bind_type_selector" value="dbsnp" /> - <param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" /> - <param name="standard_min_confidence_threshold_for_calling" value="0" /> - <param name="standard_min_confidence_threshold_for_emitting" value="4" /> - <param name="gatk_param_type_selector" value="basic" /> - <param name="analysis_param_type_selector" value="advanced" /> - <param name="genotype_likelihoods_model" value="BOTH" /> - <param name="p_nonref_model" value="EXACT" /> - <param name="heterozygosity" value="0.001" /> - <param name="pcr_error_rate" value="0.0001" /> - <param name="genotyping_mode" value="DISCOVERY" /> - <param name="output_mode" value="EMIT_ALL_CONFIDENT_SITES" /> - <param name="compute_SLOD" /> - <param name="min_base_quality_score" value="17" /> - <param name="max_deletion_fraction" value="-1" /> - <param name="min_indel_count_for_genotyping" value="2" /> - <param name="indel_heterozygosity" value="0.000125" /> - <param name="indelGapContinuationPenalty" value="10" /> - <param name="indelGapOpenPenalty" value="3" /> - <param name="indelHaplotypeSize" value="80" /> - <param name="doContextDependentGapPenalties" /> - <!-- <param name="annotation" value="" /> - <param name="group" value="" /> --> - <output name="output_vcf" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.vcf" lines_diff="4" /> - <output name="output_metrics" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.metrics" /> - <output name="output_log" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.log.contains" compare="contains" /> - </test> - </tests> - <help> -**What it does** - -A variant caller which unifies the approaches of several disparate callers. Works for single-sample and multi-sample data. The user can choose from several different incorporated calculation models. - -For more information on the GATK Unified Genotyper, see this `tool specific page <http://www.broadinstitute.org/gsa/wiki/index.php/Unified_genotyper>`_. - -To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3>`_. - -If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions>`_. - ------- - -**Inputs** - -GenomeAnalysisTK: UnifiedGenotyper accepts an aligned BAM input file. - - -**Outputs** - -The output is in VCF format. - - -Go `here <http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK>`_ for details on GATK file formats. - -------- - -**Settings**:: - - genotype_likelihoods_model Genotype likelihoods calculation model to employ -- BOTH is the default option, while INDEL is also available for calling indels and SNP is available for calling SNPs only (SNP|INDEL|BOTH) - p_nonref_model Non-reference probability calculation model to employ -- EXACT is the default option, while GRID_SEARCH is also available. (EXACT|GRID_SEARCH) - heterozygosity Heterozygosity value used to compute prior likelihoods for any locus - pcr_error_rate The PCR error rate to be used for computing fragment-based likelihoods - genotyping_mode Should we output confident genotypes (i.e. including ref calls) or just the variants? (DISCOVERY|GENOTYPE_GIVEN_ALLELES) - output_mode Should we output confident genotypes (i.e. including ref calls) or just the variants? (EMIT_VARIANTS_ONLY|EMIT_ALL_CONFIDENT_SITES|EMIT_ALL_SITES) - standard_min_confidence_threshold_for_calling The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called - standard_min_confidence_threshold_for_emitting The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold) - noSLOD If provided, we will not calculate the SLOD - min_base_quality_score Minimum base quality required to consider a base for calling - max_deletion_fraction Maximum fraction of reads with deletions spanning this locus for it to be callable [to disable, set to < 0 or > 1; default:0.05] - min_indel_count_for_genotyping Minimum number of consensus indels required to trigger genotyping run - indel_heterozygosity Heterozygosity for indel calling - indelGapContinuationPenalty Indel gap continuation penalty - indelGapOpenPenalty Indel gap open penalty - indelHaplotypeSize Indel haplotype size - doContextDependentGapPenalties Vary gap penalties by context - indel_recal_file Filename for the input covariates table recalibration .csv file - EXPERIMENTAL, DO NO USE - indelDebug Output indel debug info - out File to which variants should be written - annotation One or more specific annotations to apply to variant calls - group One or more classes/groups of annotations to apply to variant calls - ------- - -**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>`_ - -If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.* - - </help> -</tool>