Mercurial > repos > jjohnson > gatk2
view base_recalibrator.xml @ 37:dd9f8ea2b718 draft
unified_genotyper - indelGap penalty param need to be integer values
author | Jim Johnson <jj@umn.edu> |
---|---|
date | Fri, 01 Mar 2013 12:43:41 -0600 |
parents | 14d47237bb0a |
children |
line wrap: on
line source
<tool id="gatk2_base_recalibrator" name="Base Recalibrator" version="0.0.7"> <description>on BAM files</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 "BaseRecalibrator" \$GATK2_SITE_OPTIONS \$GATK2_CPU_THREADS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/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 #if str($input_recal) != 'None': --BQSR "${input_recal}" #end if --out "${output_recal}" ${standard_covs} #if str( $covariates ) != "None": #for $cov in str( $covariates ).split( ',' ): -cov "${cov}" #end for #end if #if $plot_pdf: --plot_pdf_file $output_pdf #end if ' #set $snp_dataset_provided = False #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 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'dbsnp': #set $snp_dataset_provided = True #end if #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1 -d "--knownSites:${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}"' #set default_read_filters = ['DuplicateRead','FailsVendorQualityCheck','NotPrimaryAlignment','MappingQualityZero','MalformedRead','MappingQualityUnavailable','UnmappedRead'] #for $read_filter in $gatk_param_type.read_filter: -p ' #if $read_filter.read_filter_type.read_filter_type_selector not in $default_read_filters: --read_filter "${read_filter.read_filter_type.read_filter_type_selector}" #end if ###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 str( $reference_source.reference_source_selector ) == "history": -d "-R" "${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 ' #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set": --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}" #end if #if str( $analysis_param_type.default_platform ) != "default": --default_platform "${analysis_param_type.default_platform}" #end if #if str( $analysis_param_type.force_read_group_type.force_read_group_type_selector ) == "set": --force_read_group "${analysis_param_type.force_read_group_type.force_read_group}" #end if #if str( $analysis_param_type.force_platform ) != "default": --force_platform "${analysis_param_type.force_platform}" #end if ${analysis_param_type.exception_if_no_tile} #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set": #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default": --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}" #end if #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default": --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}" #end if #end if --window_size_nqs "${analysis_param_type.window_size_nqs}" --homopolymer_nback "${analysis_param_type.homopolymer_nback}" ' #end if #if not $snp_dataset_provided: -p '--run_without_dbsnp_potentially_ruining_quality' #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="input_recal" type="data" format="gatk_report" optional="true" label="Covariates table recalibration file" help="-BQSR,--BQSR &lt;recal_file&gt;" > <help>The input covariates table file which enables on-the-fly base quality score recalibration. Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool. Please be aware that one should only run recalibration with the covariates file created on the same input bam(s). </help> </param> <param name="standard_covs" type="boolean" truevalue="" falsevalue="--no_standard_covs" checked="false" label="Do not use the standard set of covariates in addition to the ones selected" help="--no_standard_covs/-noStandard" /> <param name="covariates" type="select" multiple="True" display="checkboxes" label="Covariates to be used in the recalibration" help="-cov,--covariate &lt;covariate&gt;" > <!-- might we want to load the available covariates from an external configuration file, since additional ones can be added to local installs? --> <option value="ReadGroupCovariate" /> <option value="QualityScoreCovariate" /> <option value="CycleCovariate" /> <option value="ContextCovariate" /> <!-- covariates below were pulled from list option --> <option value="HomopolymerCovariate" /> <option value="GCContentCovariate" /> <option value="MappingQualityCovariate" /> <option value="MinimumNQSCovariate" /> <option value="PositionCovariate" /> <option value="PrimerRoundCovariate" /> <option value="TileCovariate" /> </param> <repeat name="rod_bind" title="Binding for reference-ordered data" help="-knownSites,--knownSites &lt;knownSites&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="mask">Mask</option> <option value="custom">Custom</option> </param> <when value="dbsnp"> <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> </when> <when value="snps"> <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> </when> <when value="indels"> <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> </when> <when value="mask"> <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" 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,gatk_dbsnp,bed" label="ROD file" /> </when> </conditional> </repeat> <param name="plot_pdf" type="boolean" truevalue="--plot_pdf_file" falsevalue="" checked="False" label="Output recalibration plots pdf"/> <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"> <param name="filter_mismatching_base_and_quals" type="boolean" truevalue="--filter_mismatching_base_and_quals" falsevalue="" checked="false" label="filter out the reads with mismatching number of bases and base qualities" help="filter out the mismatch reads instead of quitting with an error"/> </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"> <conditional name="default_read_group_type"> <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group"> <option value="default" selected="True">Don't Set</option> <option value="set">Set</option> </param> <when value="default"> <!-- do nothing here --> </when> <when value="set"> <param name="default_read_group" type="text" value="Unknown" label="If a read has no read group then default to the provided String"/> </when> </conditional> <param name="default_platform" type="select" label="Set default Platform" help="--default_platform"> <option value="default" selected="True">Don't Set</option> <option value="illumina">illumina</option> <option value="454">454</option> <option value="solid">solid</option> </param> <conditional name="force_read_group_type"> <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group"> <option value="default" selected="True">Don't Force</option> <option value="set">Force</option> </param> <when value="default"> <!-- do nothing here --> </when> <when value="set"> <param name="force_read_group" type="text" value="Unknown" label="If provided, the read group ID of EVERY read will be forced to be the provided String."/> </when> </conditional> <param name="force_platform" type="select" label="Force Platform" help="--force_platform"> <option value="default" selected="True">Don't Force</option> <option value="illumina">illumina</option> <option value="454">454</option> <option value="solid">solid</option> </param> <param name="exception_if_no_tile" type="boolean" checked="False" truevalue="--exception_if_no_tile" falsevalue="" label="Throw an exception when no tile can be found" help="--exception_if_no_tile"/> <conditional name="solid_options_type"> <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options"> <option value="default" selected="True">Don't Set</option> <option value="set">Set</option> </param> <when value="default"> <!-- do nothing here --> </when> <when value="set"> <param name="solid_recal_mode" type="select" label="How should we recalibrate solid bases in which the reference was inserted" help="-sMode,--solid_recal_mode &lt;solid_recal_mode&gt;"> <option value="default" selected="True">Don't set</option> <option value="DO_NOTHING">DO_NOTHING</option> <option value="SET_Q_ZERO">SET_Q_ZERO</option> <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option> <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option> </param> <param name="solid_nocall_strategy" type="select" label="Behavior of the recalibrator when it encounters no calls" help="-solid_nocall_strategy,--solid_nocall_strategy &lt;solid_nocall_strategy&gt;"> <option value="default" selected="True">Don't set</option> <option value="THROW_EXCEPTION">THROW_EXCEPTION</option> <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option> <option value="PURGE_READ">PURGE_READ</option> </param> </when> </conditional> <param name="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate" help="window_size_nqs"/> <param name="homopolymer_nback" type="integer" value="7" label="number of previous bases to look at in HomopolymerCovariate" help="-nback,--homopolymer_nback &lt;homopolymer_nback&gt;" /> </when> </conditional> </inputs> <outputs> <data format="gatk_report" name="output_recal" label="${tool.name} on ${on_string} (Covariate File)" /> <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> <data format="pdf" name="output_pdf" label="${tool.name} on ${on_string} (plot_pdf_file)"> <filter>plot_pdf == True</filter> </data> </outputs> <tests> <test> <param name="reference_source_selector" value="history" /> <param name="ref_file" value="phiX.fasta" ftype="fasta" /> <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" /> <param name="rod_bind_type_selector" value="dbsnp" /> <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" /> <param name="standard_covs" value="True" /> <param name="covariates" value="ReadGroupCovariate,HomopolymerCovariate,MinimumNQSCovariate,PositionCovariate" /> <param name="gatk_param_type_selector" value="basic" /> <param name="analysis_param_type_selector" value="basic" /> <output name="output_recal" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" /> <output name="output_log" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.log.contains" compare="contains" /> </test> </tests> <help> .. class:: warningmark "This calculation is critically dependent on being able to skip over known variant sites. Please provide a dbSNP ROD or a VCF file containing known sites of genetic variation." However, if you do not provide this file, the '--run_without_dbsnp_potentially_ruining_quality' flag will be automatically used, and the command will be allowed to run. **What it does** This walker is designed to work as the first pass in a two-pass processing step. It does a by-locus traversal operating only at sites that are not in dbSNP. We assume that all reference mismatches we see are therefore errors and indicative of poor base quality. This walker generates tables based on various user-specified covariates (such as read group, reported quality score, cycle, and dinucleotide) Since there is a large amount of data one can then calculate an empirical probability of error given the particular covariates seen at this site, where p(error) = num mismatches / num observations The output file is a CSV list of (the several covariate values, num observations, num mismatches, empirical quality score) The first non-comment line of the output file gives the name of the covariates that were used for this calculation. Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will be added for the user regardless of whether or not they were specified Note: This walker is designed to be used in conjunction with TableRecalibrationWalker. For more information on base quality score recalibration using the GATK, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_bqsr_BaseRecalibrator.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: BaseRecalibrator accepts an aligned BAM input file. **Outputs** The output is in CSV format. Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. ------- **Settings**:: default_read_group If a read has no read group then default to the provided String. default_platform If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid. force_read_group If provided, the read group ID of EVERY read will be forced to be the provided String. This is useful to collapse all data into a single read group. force_platform If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid. window_size_nqs The window size used by MinimumNQSCovariate for its calculation homopolymer_nback The number of previous bases to look at in HomopolymerCovariate exception_if_no_tile If provided, TileCovariate will throw an exception when no tile can be found. The default behavior is to use tile = -1 solid_recal_mode How should we recalibrate solid bases in whichthe reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS (DO_NOTHING|SET_Q_ZERO|SET_Q_ZERO_BASE_N|REMOVE_REF_BIAS) solid_nocall_strategy Defines the behavior of the recalibrator when it encounters no calls in the color space. Options = THROW_EXCEPTION, LEAVE_READ_UNRECALIBRATED, or PURGE_READ (THROW_EXCEPTION|LEAVE_READ_UNRECALIBRATED|PURGE_READ) recal_file Filename for the input covariates table recalibration .csv file out The output CSV file standard_covs Use the standard set of covariates in addition to the ones listed using the -cov argument run_without_dbsnp_potentially_ruining_quality If specified, allows the recalibrator to be used without a dbsnp rod. Very unsafe and for expert users only. ------ **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>