Mercurial > repos > jjohnson > gatk2
changeset 11:5faf7ace8aee draft
Add HaplotypeCaller
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Thu, 08 Nov 2012 10:38:18 -0600 |
| parents | a14e79e7ac75 |
| children | b40671bc73d5 |
| files | haplotype_caller.xml reduce_reads.xml |
| diffstat | 2 files changed, 645 insertions(+), 1 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/haplotype_caller.xml Thu Nov 08 10:38:18 2012 -0600 @@ -0,0 +1,639 @@ +<tool id="gatk2_haplotype_caller" name="Haplotype Caller" version="0.0.4"> + <description>Call SNPs and indels simultaneously via local de-novo assembly of haplotypes in an active region</description> + <requirements> + <requirement type="package" version="2.2">gatk</requirement> + <requirement type="package" version="0.1.18">samtools</requirement> + </requirements> + <command interpreter="python">gatk2_wrapper.py + --max_jvm_heap_fraction "1" + --stdout "${output_log}" + -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input" + #if str( $reference_source.input_bam.metadata.bam_index ) != "None": + -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index + #end if + -p 'java + -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" + -T "HaplotypeCaller" + -o "${output_vcf}" + ## \$GATK2_SITE_OPTIONS + ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home + ##--num_threads 4 ##not supported yet + ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout + #if $reference_source.reference_source_selector != "history": + -R "${reference_source.ref_file.fields.path}" + #end if + #if str($input_recal) != 'None': + --BQSR "${input_recal}" + #end if + --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 $analysis_param_type.analysis_param_type_selector == "advanced": + -p ' + ## files + #if str($analysis_param_type.activeRegionIn) != 'None': + --activeRegionIn "$analysis_param_type.activeRegionIn" + #end if + #if str($analysis_param_type.alleles) != 'None': + --alleles "$analysis_param_type.alleles" + #end if + #if str($analysis_param_type.comp) != 'None': + --comp "$analysis_param_type.comp" + #end if + #if str($analysis_param_type.dbsnp) != 'None': + --dbsnp "$analysis_param_type.dbsnp" + #end if + ## text + #if len($analysis_param_type.annotation.__str__) > 0: + --annotation $analysis_param_type.annotation + #end if + #if len($analysis_param_type.excludeAnnotation.__str__) > 0: + --excludeAnnotation $analysis_param_type.excludeAnnotation + #end if + #if len($analysis_param_type.group.__str__) > 0: + --group $analysis_param_type.group + #end if + ## value setings + #if $analysis_param_type.contamination_fraction_to_filter.__str__.strip() != '': + --contamination_fraction_to_filter $analysis_param_type.contamination_fraction_to_filter + #end if + #if $analysis_param_type.downsampleRegion.__str__.strip() != '': + --downsampleRegion $analysis_param_type.downsampleRegion + #end if + #if $analysis_param_type.heterozygosity.__str__.strip() != '': + --heterozygosity $analysis_param_type.heterozygosity + #end if + #if $analysis_param_type.minPruning.__str__.strip() != '': + --minPruning $analysis_param_type.minPruning + #end if + #if $analysis_param_type.standard_min_confidence_threshold_for_calling.__str__.strip() != '': + --standard_min_confidence_threshold_for_calling $analysis_param_type.standard_min_confidence_threshold_for_calling + #end if + #if $analysis_param_type.standard_min_confidence_threshold_for_emitting.__str__.strip() != '': + --standard_min_confidence_threshold_for_emitting $analysis_param_type.standard_min_confidence_threshold_for_emitting + #end if + #if $analysis_param_type.gcpHMM.__str__.strip() != '': + --gcpHMM $analysis_param_type.gcpHMM + #end if + #if $analysis_param_type.max_alternate_alleles.__str__.strip() != '': + --max_alternate_alleles $analysis_param_type.max_alternate_alleles + #end if + ## mode selections + #if $analysis_param_type.genotyping_mode.__str__ != "None" and len($analysis_param_type.genotyping_mode.__str__) > 0: + --genotyping_mode $analysis_param_type.genotyping_mode + #end if + #if $analysis_param_type.output_mode.__str__ != "None" and len($analysis_param_type.output_mode.__str__) > 0: + --output_mode $analysis_param_type.output_mode + #end if + #if $analysis_param_type.pair_hmm_implementation.__str__ != "None" and len($analysis_param_type.pair_hmm_implementation.__str__) > 0: + --pair_hmm_implementation $analysis_param_type.pair_hmm_implementation + #end if + #if $analysis_param_type.p_nonref_model.__str__ != "None" and len($analysis_param_type.p_nonref_model.__str__) > 0: + --p_nonref_model $analysis_param_type.p_nonref_model + #end if + ## optional outputs + #if $analysis_param_type.activeRegionOut: + --activeRegionOut $active_region_out + #end if + #if $analysis_param_type.graphOutput: + --graphOutput $graph_out + #end if + ## flags + $analysis_param_type.useAllelesTrigger + $analysis_param_type.fullHaplotype + $analysis_param_type.genotypeFullActiveRegion + $analysis_param_type.debug + ' + #end if + </command> + <inputs> + <param name="input_recal" type="data" format="csv" optional="true" label="Covariates table recalibration file" help="-BQSR,--BQSR &lt;recal_file&gt;" > + <help>The input covariates table file which enables on-the-fly base quality score recalibration. + Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool. + Please be aware that one should only run recalibration with the covariates file created on the same input bam(s). + </help> + </param> + <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> + + <conditional name="analysis_param_type"> + <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> + <option value="basic" selected="True">Basic</option> + <option value="advanced">Advanced</option> + </param> + <when value="basic"> + <!-- Do nothing here --> + </when> + <when value="advanced"> + + <param name="activeRegionIn" type="data" format="bed,gatk_interval,picard_interval_list,vcf" optional="true" label="activeRegionIn" help="--activeRegionIn / -AR Use this interval list file as the active regions to process"/> + <param name="activeRegionOut" type="boolean" checked="False" truevalue="" falsevalue="" label="activeRegionOut" help="--activeRegionOut / -ARO Output the active region to an interval list file"/> + <param name="alleles" type="data" format="vcf" optional="true" label="alleles" help="--alleles / -alleles The set of alleles at which to genotype when --genotyping_mode is GENOTYPE_GIVEN_ALLELES"/> + <param name="annotation" type="text" value="" optional="true" label="annotation" help="--annotation / -A One or more specific annotations to apply to variant calls default: ClippingRankSumTest"/> + <param name="comp" type="data" format="vcf" optional="true" label="comp" help="--comp / -comp comparison VCF file"/> + <param name="contamination_fraction_to_filter" type="float" value="0.05" optional="true" label="contamination_fraction_to_filter" help="--contamination_fraction_to_filter / -contamination Fraction of contamination in sequencing data (for all samples) to aggressively remove"> + <validator type="in_range" message="value between 0.00 and 1.00" min="0" max="1"/> + </param> + <param name="dbsnp" type="data" format="vcf" optional="true" label="dbsnp" help="--dbsnp / -D dbSNP file"/> + <param name="debug" type="boolean" checked="False" truevalue="-debug" falsevalue="" label="debug" help="--debug / -debug If specified, print out very verbose debug information about each triggering active region"/> + <param name="downsampleRegion" type="integer" value="1000" optional="true" label="downsampleRegion" help="--downsampleRegion / -dr coverage, per-sample, to downsample each active region to"/> + <param name="excludeAnnotation" type="text" optional="true" label="excludeAnnotation" help="--excludeAnnotation / -XA One or more specific annotations to exclude"/> + <param name="genotyping_mode" type="select" optional="true" label="genotyping_mode" help="--genotyping_mode / -gt_mode Specifies how to determine the alternate alleles to use for genotyping"> + <option value="DISCOVERY" selected="True">DISCOVERY</option> + <option value="GENOTYPE_GIVEN_ALLELES">GENOTYPE_GIVEN_ALLELES</option> + </param> + <param name="graphOutput" type="boolean" checked="False" truevalue="" falsevalue="" label="graphOutput" help="--graphOutput / -graph File to which debug assembly graph information should be written"/> + <param name="group" type="text" optional="true" label="group" help="--group / -G One or more classes/groups of annotations to apply to variant calls"/> + <param name="heterozygosity" type="float" value="0.0010" optional="true" label="heterozygosity" help="--heterozygosity / -hets Heterozygosity value used to compute prior likelihoods for any locus"/> + <param name="minPruning" type="integer" value="1" optional="true" label="minPruning" help="--minPruning / -minPruning The minimum allowed pruning factor in assembly graph. Paths with <= X supporting kmers are pruned from the graph"> + <validator type="in_range" message="value between 0 and 127" min="0" max="127"/> + </param> + <param name="output_mode" type="select" optional="true" label="output_mode" help="--output_mode / -out_mode Specifies which type of calls we should output"> + <option value="EMIT_VARIANTS_ONLY" selected="True">EMIT_VARIANTS_ONLY</option> + <option value="EMIT_ALL_CONFIDENT_SITES">EMIT_ALL_CONFIDENT_SITES</option> + <option value="EMIT_ALL_SITES">EMIT_ALL_SITES</option> + </param> + <param name="pair_hmm_implementation" type="select" optional="true" label="pair_hmm_implementation" help="--pair_hmm_implementation / -pairHMM The PairHMM implementation to use for genotype likelihood calculations"> + <option value="EXACT">EXACT</option> + <option value="ORIGINAL">ORIGINAL</option> + <option value="CACHING">CACHING</option> + <option value="LOGLESS_CACHING" selected="True">LOGLESS_CACHING</option> + </param> + <param name="standard_min_confidence_threshold_for_calling" type="float" value="30.0" optional="true" label="standard_min_confidence_threshold_for_calling" help="--standard_min_confidence_threshold_for_calling / -stand_call_conf The minimum phred-scaled confidence threshold at which variants should be called"/> + <param name="standard_min_confidence_threshold_for_emitting" type="float" value="30.0" optional="true" label="standard_min_confidence_threshold_for_emitting" help="--standard_min_confidence_threshold_for_emitting / -stand_emit_conf The minimum phred-scaled confidence threshold at which variants should be emitted (and filtered with LowQual if less than the calling threshold)"/> + <param name="useAllelesTrigger" type="boolean" checked="False" truevalue="-allelesTrigger" falsevalue="" label="useAllelesTrigger" help="--useAllelesTrigger / -allelesTrigger If specified, use additional trigger on variants found in an external alleles file"/> + <param name="fullHaplotype" type="boolean" checked="False" truevalue="-fullHaplotype" falsevalue="" label="fullHaplotype" help="--fullHaplotype / -fullHaplotype If specified, output the full haplotype sequence instead of converting to individual variants w.r.t. the reference"/> + <param name="gcpHMM" type="integer" value="10" optional="true" label="gcpHMM" help="--gcpHMM / -gcpHMM Flat gap continuation penalty for use in the Pair HMM"/> + <param name="genotypeFullActiveRegion" type="boolean" checked="False" truevalue="-genotypeFullActiveRegion" falsevalue="" label="genotypeFullActiveRegion" help="--genotypeFullActiveRegion / -genotypeFullActiveRegion If specified, alternate alleles are considered to be the full active region for the purposes of genotyping"/> + <param name="max_alternate_alleles" type="integer" value="6" optional="true" label="max_alternate_alleles" help="--max_alternate_alleles / -maxAltAlleles Maximum number of alternate alleles to genotype"/> + <param name="p_nonref_model" type="select" optional="true" label="p_nonref_model" help="--p_nonref_model / -pnrm Non-reference probability calculation model to employ"> + <option value="EXACT_INDEPENDENT" selected="True">EXACT_INDEPENDENT experimental implementation - for testing only</option> + <option value="EXACT_REFERENCE">EXACT_REFERENCE reference implementation of multi-allelic EXACT model. Extremely slow for many alternate alleles</option> + <option value="EXACT_ORIGINAL">EXACT_ORIGINAL original biallelic exact model, for testing only</option> + <option value="EXACT_GENERAL_PLOIDY">implementation that supports any sample ploidy</option> + </param> + + </when> + <plotypes are evaluated using an affine gap penalty Pair HMM./conditional> + </inputs> + <outputs> + <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (VCF)" /> + <data format="vcf" name="graph_out" label="${tool.name} on ${on_string} graph" > + <filter>analysis_param_type['graphOutput'] == True</filter> + </data> + <data format="vcf" name="active_region_out" label="${tool.name} on ${on_string} activeRegion" > + <filter>analysis_param_type['activeRegionOut'] == True</filter> + </data> + <data format="txt" name="output_log" label="${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** + +HaplotypeCaller +Call SNPs and indels simultaneously via local de-novo assembly of haplotypes in an active region. +Haplotypes are evaluated using an affine gap penalty Pair HMM. + +For more information on using read based compression in the GATK, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_haplotypecaller_HaplotypeCaller.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: PrintReads accepts an aligned BAM files. + + +**Outputs** + +The output is a VCF file with raw, unrecalibrated SNP and indel calls. + + +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 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>`_ + +Please also site `McKenna A, Hanna M, Banks E, Sivachenko A, Cibulskis K, Kernytsky A, Garimella K, Altshuler D, Gabriel S, Daly M, DePristo MA (2010). The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data. Genome Res. 20:1297-303. Epub 2010 Jul 19. <http://www.ncbi.nlm.nih.gov/pubmed/20644199>`_ + +If you use this tool in Galaxy, please cite `Blankenberg D, Von Kuster G, Coraor N, Ananda G, Lazarus R, Mangan M, Nekrutenko A, Taylor J. Galaxy: a web-based genome analysis tool for experimentalists. Curr Protoc Mol Biol. 2010 Jan;Chapter 19:Unit 19.10.1-21. <http://www.ncbi.nlm.nih.gov/pubmed/20069535>`_ + + </help> +</tool>
--- a/reduce_reads.xml Tue Nov 06 12:07:36 2012 -0600 +++ b/reduce_reads.xml Thu Nov 08 10:38:18 2012 -0600 @@ -123,7 +123,12 @@ #end if </command> <inputs> - <param name="input_recal" type="data" format="csv" optional="true" label="Covariates table recalibration file" help="-BQSR,--BQSR &lt;recal_file&gt;" /> + <param name="input_recal" type="data" format="csv" optional="true" label="Covariates table recalibration file" help="-BQSR,--BQSR &lt;recal_file&gt;" > + <help>The input covariates table file which enables on-the-fly base quality score recalibration. + Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool. + Please be aware that one should only run recalibration with the covariates file created on the same input bam(s). + </help> + </param> <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>