Mercurial > repos > david-hoover > garbage1
changeset 27:6ccafd2695b2 draft
Uploaded
| author | david-hoover |
|---|---|
| date | Thu, 20 Sep 2012 09:57:21 -0400 |
| parents | e6e2bb189314 |
| children | d18608117254 |
| files | base_recalibrator.xml count_covariates.xml print_reads.xml table_recalibration.xml |
| diffstat | 4 files changed, 740 insertions(+), 1165 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/base_recalibrator.xml Thu Sep 20 09:57:21 2012 -0400 @@ -0,0 +1,576 @@ +<tool id="gatk2_base_recalibrator" name="Generates recalibration table" version="0.0.1"> + <description>on BAM files</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 "BaseRecalibrator" + --num_threads 4 ##hard coded, for now + -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 + --out "${output_recal}" + ${standard_covs} + #if str( $covariates ) != "None": + #for $cov in str( $covariates ).split( ',' ): + -cov "${cov}" + #end for + #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}"' + #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 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="standard_covs" type="boolean" truevalue="--standard_covs" falsevalue="" label="Use the standard set of covariates in addition to the ones selected" help="-standard,--standard_covs" /> + <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="DinucCovariate" /> + <!-- 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> + + <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"> + <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="csv" name="output_recal" label="${tool.name} on ${on_string} (Covariate File)" /> + <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> + </outputs> + <tests> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" value="phiX.fasta" ftype="fasta" /> + <param name="input_bam" value="gatk/gatk_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 + recal_file Filename for the outputted covariates table recalibration 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>`_ + +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>
--- a/count_covariates.xml Tue Sep 18 13:01:27 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,576 +0,0 @@ -<tool id="gatk2_count_covariates" name="Count Covariates" version="0.0.1"> - <description>on BAM files</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 "CountCovariates" - --num_threads 4 ##hard coded, for now - -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 - --recal_file "${output_recal}" - ${standard_covs} - #if str( $covariates ) != "None": - #for $cov in str( $covariates ).split( ',' ): - -cov "${cov}" - #end for - #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}"' - #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 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="standard_covs" type="boolean" truevalue="--standard_covs" falsevalue="" label="Use the standard set of covariates in addition to the ones selected" help="-standard,--standard_covs" /> - <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="DinucCovariate" /> - <!-- 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> - - <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"> - <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="csv" name="output_recal" label="${tool.name} on ${on_string} (Covariate File)" /> - <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> - </outputs> - <tests> - <test> - <param name="reference_source_selector" value="history" /> - <param name="ref_file" value="phiX.fasta" ftype="fasta" /> - <param name="input_bam" value="gatk/gatk_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/gsa/wiki/index.php/Base_quality_score_recalibration>`_. - -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: CountCovariates accepts an aligned BAM input file. - - -**Outputs** - -The output is in CSV format. - - -Go `here <http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK>`_ 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 - recal_file Filename for the outputted covariates table recalibration 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>`_ - -If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.* - - </help> -</tool>
--- a/print_reads.xml Tue Sep 18 13:01:27 2012 -0400 +++ b/print_reads.xml Thu Sep 20 09:57:21 2012 -0400 @@ -1,5 +1,5 @@ <tool id="gatk2_print_reads" name="Print Reads" version="0.0.1"> - <description>from BAM files</description> + <description>on BAM files</description> <requirements> <requirement type="package" version="2.1">gatk</requirement> <requirement type="package">samtools</requirement> @@ -7,36 +7,23 @@ <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_${i}" ##hardcode galaxy ext type as bam_index - #end if - #end for + -d "-I" "${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 "PrintReads" - ##--num_threads 4 ##hard coded, for now - --out "${output_bam}" + -o "${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 - --number "${number}" - #if $platform: - --platform "${platform}" - #end if - #if $read_group: - --readGroup "${read_group}" - #end if - #for $sample_file in $sample_file_repeat: - --sample_file "${sample_file.input_sample_file}" - #end for - #for $sample_name in $sample_name_repeat: - --sample_name "${sample_name.sample_name}" - #end for + --recal_file "${input_recal}" + --disable_bam_indexing ' - ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": #for $pedigree in $gatk_param_type.pedigree: @@ -93,51 +80,74 @@ #end for #end if - #if $reference_source.reference_source_selector == "history": + #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 + ${analysis_param_type.simplify_bam} + --preserve_qscores_less_than "${analysis_param_type.preserve_qscores_less_than}" + --smoothing "${analysis_param_type.smoothing}" + --max_quality_score "${analysis_param_type.max_quality_score}" + --window_size_nqs "${analysis_param_type.window_size_nqs}" + --homopolymer_nback "${analysis_param_type.homopolymer_nback}" + ${analysis_param_type.do_not_write_original_quals} + ' + #end if </command> <inputs> + <param name="input_recal" type="data" format="csv" label="Covariates table recalibration file" help="-recalFile,--recal_file &lt;recal_file&gt;" /> <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;"> + <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"/> does not yet work in a repeat...--> + <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"> <!-- 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 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="number" type="integer" value="-1" label="Print the first n reads from the file, discarding the rest" help="-n,--number &lt;number&gt;" /> - <param name="platform" type="text" value="" label="Exclude all reads with this platform from the output" help="-platform,--platform &lt;platform&gt;" /> - <param name="read_group" type="text" value="" label="Exclude all reads with this read group from the output" help="-readGroup,--readGroup &lt;readGroup&gt;" /> - <repeat name="sample_file_repeat" title="File containing a list of samples to include" help="-sf,--sample_file &lt;sample_file&gt;"> - <param name="input_sample_file" type="data" format="text" label="Sample file" /> - </repeat> - <repeat name="sample_name_repeat" title="Sample name to be included in the analysis" help="-sn,--sample_name &lt;sample_name&gt;"> - <param name="sample_name" type="text" label="Sample name" /> - </repeat> - <conditional name="gatk_param_type"> <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options"> <option value="basic" selected="True">Basic</option> @@ -349,41 +359,109 @@ </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="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/> + <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;" /> + <param name="preserve_qscores_less_than" type="integer" value="5" label="Bases with quality scores less than this threshold won't be recalibrated" help="-pQ,--preserve_qscores_less_than &lt;preserve_qscores_less_than&gt;"/> + <param name="smoothing" type="integer" value="1" label="smoothing" help="-sm,--smoothing &lt;smoothing&gt;"/> + <param name="max_quality_score" type="integer" value="50" label="Max quality score" help="-maxQ,--max_quality_score &lt;max_quality_score&gt;"/> + <param name="do_not_write_original_quals" type="boolean" checked="False" truevalue="--doNotWriteOriginalQuals" falsevalue="" label="Do Not Write Original Quality tag" help="-noOQs,--doNotWriteOriginalQuals"/> + </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> - <param name="number" type="integer" value="-1" label="Print the first n reads from the file, discarding the rest" /> - <param name="platform" type="text" value="" label="Exclude all reads with this platform from the output" /> - <param name="read_group" type="text" value="" label="Exclude all reads with this read group from the output" /> - <repeat name="sample_file_repeat" title="File containing a list of samples to include"> - <param name="input_sample_file" type="data" format="text" label="Sample file" /> - </repeat> - <repeat name="sample_name_repeat" title="Sample name to be included in the analysis"> - <param name="sample_name" type="text" label="Sample name" /> - </repeat> <tests> <test> + <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" /> <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="number" value="-1" /> - <param name="platform" value="" /> - <param name="read_group" value="" /> - <param name="sample_file_repeat" value="0" /> - <param name="sample_name_repeat" value="0" /> + <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" /> <param name="gatk_param_type_selector" value="basic" /> - <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" compare="contains"/> - <output name="output_log" file="gatk/gatk_print_reads/gatk_print_reads_out_1.log.contains" compare="contains" /> + <param name="analysis_param_type_selector" value="basic" /> + <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" /> + <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" /> </test> </tests> <help> **What it does** -PrintReads can dynamically merge the contents of multiple input BAM files, resulting in merged output sorted in coordinate order. +This walker is designed to work as the second pass in a two-pass processing step, doing a by-read traversal. For each base in each read this walker calculates various user-specified covariates (such as read group, reported quality score, cycle, and dinuc) Using these values as a key in a large hashmap the walker calculates an empirical base quality score and overwrites the quality score currently in the read. This walker then outputs a new bam file with these updated (recalibrated) reads. Note: This walker expects as input the recalibration table file generated previously by CovariateCounterWalker. Note: This walker is designed to be used in conjunction with CovariateCounterWalker. -For more information on the GATK Print Reads Walker, see this `tool specific page <http://www.broadinstitute.org/gsa/gatkdocs/release/org_broadinstitute_sting_gatk_walkers_PrintReadsWalker.html>`_. +For more information on base quality score recalibration using the GATK, see this `tool specific page <http://www.broadinstitute.org/gsa/wiki/index.php/Base_quality_score_recalibration>`_. 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>`_. @@ -393,7 +471,7 @@ **Inputs** -GenomeAnalysisTK: PrintReads accepts one or more BAM or SAM input files. +GenomeAnalysisTK: TableRecalibration accepts an aligned BAM and a recalibration CSV input files. **Outputs** @@ -407,11 +485,24 @@ **Settings**:: - number int -1 Print the first n reads from the file, discarding the rest - platform String NA Exclude all reads with this platform from the output - readGroup String NA Exclude all reads with this read group from the output - sample_file Set[File] [] File containing a list of samples (one per line). Can be specified multiple times - sample_name Set[String] [] Sample name to be included in the analysis. Can be specified multiple times. + 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 BAM file + 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 + preserve_qscores_less_than Bases with quality scores less than this threshold won't be recalibrated, default=5. In general it's unsafe to change qualities scores below < 5, since base callers use these values to indicate random or bad bases + smoothing Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1 + max_quality_score The integer value at which to cap the quality scores, default=50 + doNotWriteOriginalQuals If true, we will not write the original quality (OQ) tag for each read ------
--- a/table_recalibration.xml Tue Sep 18 13:01:27 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,516 +0,0 @@ -<tool id="gatk2_table_recalibration" name="Table Recalibration" version="0.0.1"> - <description>on BAM files</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 "TableRecalibration" - -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 - --recal_file "${input_recal}" - --disable_bam_indexing - ' - ##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 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 - ${analysis_param_type.simplify_bam} - --preserve_qscores_less_than "${analysis_param_type.preserve_qscores_less_than}" - --smoothing "${analysis_param_type.smoothing}" - --max_quality_score "${analysis_param_type.max_quality_score}" - --window_size_nqs "${analysis_param_type.window_size_nqs}" - --homopolymer_nback "${analysis_param_type.homopolymer_nback}" - ${analysis_param_type.do_not_write_original_quals} - ' - #end if - </command> - <inputs> - <param name="input_recal" type="data" format="csv" label="Covariates table recalibration file" help="-recalFile,--recal_file &lt;recal_file&gt;" /> - <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> - - <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"> - <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="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/> - <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;" /> - <param name="preserve_qscores_less_than" type="integer" value="5" label="Bases with quality scores less than this threshold won't be recalibrated" help="-pQ,--preserve_qscores_less_than &lt;preserve_qscores_less_than&gt;"/> - <param name="smoothing" type="integer" value="1" label="smoothing" help="-sm,--smoothing &lt;smoothing&gt;"/> - <param name="max_quality_score" type="integer" value="50" label="Max quality score" help="-maxQ,--max_quality_score &lt;max_quality_score&gt;"/> - <param name="do_not_write_original_quals" type="boolean" checked="False" truevalue="--doNotWriteOriginalQuals" falsevalue="" label="Do Not Write Original Quality tag" help="-noOQs,--doNotWriteOriginalQuals"/> - </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="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" /> - <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="gatk_param_type_selector" value="basic" /> - <param name="analysis_param_type_selector" value="basic" /> - <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" /> - <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" /> - </test> - </tests> - <help> -**What it does** - -This walker is designed to work as the second pass in a two-pass processing step, doing a by-read traversal. For each base in each read this walker calculates various user-specified covariates (such as read group, reported quality score, cycle, and dinuc) Using these values as a key in a large hashmap the walker calculates an empirical base quality score and overwrites the quality score currently in the read. This walker then outputs a new bam file with these updated (recalibrated) reads. Note: This walker expects as input the recalibration table file generated previously by CovariateCounterWalker. Note: This walker is designed to be used in conjunction with CovariateCounterWalker. - -For more information on base quality score recalibration using the GATK, see this `tool specific page <http://www.broadinstitute.org/gsa/wiki/index.php/Base_quality_score_recalibration>`_. - -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: TableRecalibration accepts an aligned BAM and a recalibration CSV input files. - - -**Outputs** - -The output is in BAM format. - - -Go `here <http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK>`_ 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 BAM file - 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 - preserve_qscores_less_than Bases with quality scores less than this threshold won't be recalibrated, default=5. In general it's unsafe to change qualities scores below < 5, since base callers use these values to indicate random or bad bases - smoothing Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1 - max_quality_score The integer value at which to cap the quality scores, default=50 - doNotWriteOriginalQuals If true, we will not write the original quality (OQ) tag for each read - ------- - -**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>