Mercurial > repos > xuebing > sharplabtool
diff tools/gatk/unified_genotyper.xml @ 0:9071e359b9a3
Uploaded
| author | xuebing |
|---|---|
| date | Fri, 09 Mar 2012 19:37:19 -0500 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/gatk/unified_genotyper.xml Fri Mar 09 19:37:19 2012 -0500 @@ -0,0 +1,414 @@ +<tool id="gatk_unified_genotyper" name="Unified Genotyper" version="0.0.1"> + <description>SNP and indel caller</description> + <command interpreter="python">gatk_wrapper.py + --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}" + -d "" "${input_bam.input_bam.metadata.bam_index}" "bam_index" "gatk_input_${i}" ##hardcode galaxy ext type as bam_index + #end for + -p 'java + -jar "${GALAXY_DATA_INDEX_DIR}/shared/jars/gatk/GenomeAnalysisTK.jar" + -T "UnifiedGenotyper" + -o "${output_vcf}" + -et "NO_ET" ##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 + --standard_min_confidence_threshold_for_calling "${standard_min_confidence_threshold_for_calling}" + --standard_min_confidence_threshold_for_emitting "${standard_min_confidence_threshold_for_emitting}" + ' + #set $rod_binding_names = dict() + #if str( $input_dbsnp_rod ) != "None": + -d "-D" "${input_dbsnp_rod}" "${input_dbsnp_rod.ext}" "dbsnp_rod" + #end if + #for $rod_binding in $rod_bind: + #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom': + #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name + #else + #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector + #end if + #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1 + -d "-B:${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]}" + #if str( $rod_binding.rod_bind_type.rodToIntervalTrackName ): + -p '--rodToIntervalTrackName "${rod_bind_name}"' + #end if + #end for + + ##start standard gatk options + #if $gatk_param_type.gatk_param_type_selector == "advanced": + #for $sample_metadata in $gatk_param_type.sample_metadata: + -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #end for + #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 $name not in [ "__current_case__", "read_filter_type_selector" ]: + --${name} "${param}" + #end if + #end for + ' + #end for + #if str( $gatk_param_type.input_intervals ) != "None": + -d "-L" "${gatk_param_type.input_intervals}" "${gatk_param_type.input_intervals.ext}" "input_intervals" + #end if + #if str( $gatk_param_type.input_exclude_intervals ) != "None": + -d "-XL" "${gatk_param_type.input_exclude_intervals}" "${gatk_param_type.input_exclude_intervals.ext}" "input_intervals" + #end if + + -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_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}" + ' + #if str( $gatk_param_type.read_group_black_list ) != "None": + -d "-read_group_black_list" "${gatk_param_type.read_group_black_list}" "txt" "input_read_group_black_list" + #end if + #end if + #if $reference_source.reference_source_selector == "history": + -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input" + #end if + ##end standard gatk options + ##start analysis specific options + #if $analysis_param_type.analysis_param_type_selector == "advanced": + -p ' + --genotype_likelihoods_model "${analysis_param_type.genotype_likelihoods_model}" + --p_nonref_model "${analysis_param_type.p_nonref_model}" + --heterozygosity "${analysis_param_type.heterozygosity}" + --pcr_error_rate "${analysis_param_type.pcr_error_rate}" + --genotyping_mode "${analysis_param_type.genotyping_mode}" + --output_mode "${analysis_param_type.output_mode}" + ${analysis_param_type.noSLOD} + --min_base_quality_score "${analysis_param_type.min_base_quality_score}" + --min_mapping_quality_score "${analysis_param_type.min_mapping_quality_score}" + --max_deletion_fraction "${analysis_param_type.max_deletion_fraction}" + --min_indel_count_for_genotyping "${analysis_param_type.min_indel_count_for_genotyping}" + --indel_heterozygosity "${analysis_param_type.indel_heterozygosity}" + --indelGapContinuationPenalty "${analysis_param_type.indelGapContinuationPenalty}" + --indelGapOpenPenalty "${analysis_param_type.indelGapOpenPenalty}" + --indelHaplotypeSize "${analysis_param_type.indelHaplotypeSize}" + ${analysis_param_type.doContextDependentGapPenalties} + #if $analysis_param_type.annotation.value: + #for $annotation in $analysis_param_type.annotation.value: + --annotation "${annotation}" + #end for + #end if + #if $analysis_param_type.group.value: + #for $group in $analysis_param_type.group.value: + --group "${group}" + #end for + #end if + ' + #end if + </command> + <inputs> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> + <option value="cached">Locally cached</option> + <option value="history">History</option> + </param> + <when value="cached"> + <repeat name="input_bams" title="Sample BAM file" min="1"> + <param name="input_bam" type="data" format="bam" label="BAM file"> + <validator type="unspecified_build" /> + <validator type="dataset_metadata_in_file" filename="picard_index.loc" metadata_name="dbkey" metadata_column="1" 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"> + <options from_data_table="picard_indexes"> + <!-- <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> does not yet work in a repeat...--> + </options> + </param> + </when> + <when value="history"> <!-- FIX ME!!!! --> + <repeat name="input_bams" title="Sample BAM file" min="1"> + <param name="input_bam" type="data" format="bam" label="BAM file" /> + </repeat> + <param name="ref_file" type="data" format="fasta" label="Using reference file" /> + </when> + </conditional> + + <param name="input_dbsnp_rod" type="data" format="gatk_dbsnp" optional="True" label="dbSNP reference ordered data (ROD)" /> + <repeat name="rod_bind" title="Binding for reference-ordered data"> + <conditional name="rod_bind_type"> + <param name="rod_bind_type_selector" type="select" label="Binding Type"> + <option value="snps" selected="True">SNPs</option> + <option value="indels">INDELs</option> + <option value="custom">Custom</option> + </param> + <when value="snps"> + <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /> + </when> + <when value="indels"> + <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /> + </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" /> + <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /> + </when> + </conditional> + </repeat> + + <param name="standard_min_confidence_threshold_for_calling" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called" /> + <param name="standard_min_confidence_threshold_for_emitting" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)" /> + + + <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="sample_metadata" title="Sample Metadata"> + <param name="sample_metadata_file" type="data" format="txt" label="Sample file(s) in JSON format" /> + </repeat> + <repeat name="read_filter" title="Read Filter"> + <conditional name="read_filter_type"> + <param name="read_filter_type_selector" type="select" label="Read Filter Type"> + <option value="MaxReadLength" selected="True">MaxReadLength</option> + <option value="ZeroMappingQualityRead">ZeroMappingQualityRead</option> + </param> + <when value="ZeroMappingQualityRead"> + <!-- no extra options --> + </when> + <when value="MaxReadLength"> + <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/> + </when> + </conditional> + </repeat> + <param name="input_intervals" type="data" format="picard_interval_list" optional="True" label="A list of genomic intervals over which to operate" /> + <param name="input_exclude_intervals" type="data" format="picard_interval_list" optional="True" label="A list of genomic intervals to exclude from processing" /> + + <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <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="Downsampling Type"> + <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="Type of reads downsampling to employ at a given locus" help="Downsampling Type"> + <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="0.1"/> + </when> + <when value="downsample_to_coverage"> + <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0"/> + </when> + </conditional> + </when> + <when value="BY_SAMPLE"> + <conditional name="downsample_to_type"> + <param name="downsample_to_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="Downsampling Type"> + <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="0.1"/> + </when> + <when value="downsample_to_coverage"> + <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0"/> + </when> + </conditional> + </when> + </conditional> + <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine"> + <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="integer" label="BAQ gap open penalty (Phred Scaled)" value="40" help="Default value is 40. 30 is perhaps better for whole genome call sets."/> + <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" /> + <param name="default_base_qualities" type="integer" label="Value to be used for all base quality scores, when some are missing" value="-1"/> + <param name="validation_strictness" type="select" label="How strict should we be with validation"> + <option value="STRICT" selected="True">STRICT</option> + <option value="LENIENT">LENIENT</option> + <option value="SILENT">SILENT</option> + </param> + <param name="interval_merging" type="select" label="Interval merging rule"> + <option value="ALL" selected="True">ALL</option> + <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option> + </param> + <param name="read_group_black_list" type="data" format="txt" optional="True" label="Read group black list" /> + </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="genotype_likelihoods_model" type="select" label="Genotype likelihoods calculation model to employ"> + <option value="BOTH" selected="True">BOTH</option> + <option value="SNP">SNP</option> + <option value="INDEL">INDEL</option> + </param> + <param name="p_nonref_model" type="select" label="Non-reference probability calculation model to employ"> + <option value="EXACT" selected="True">EXACT</option> + <option value="GRID_SEARCH">GRID_SEARCH</option> + </param> + <param name="heterozygosity" type="float" value="1e-3" label="Heterozygosity value used to compute prior likelihoods for any locus" /> + <param name="pcr_error_rate" type="float" value="1e-4" label="The PCR error rate to be used for computing fragment-based likelihoods" /> + <param name="genotyping_mode" type="select" label="How to determine the alternate allele to use for genotyping"> + <option value="DISCOVERY" selected="True">DISCOVERY</option> + <option value="GENOTYPE_GIVEN_ALLELES">GENOTYPE_GIVEN_ALLELES</option> + </param> + <param name="output_mode" type="select" label="Should we output confident genotypes (i.e. including ref calls) or just the variants?"> + <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="noSLOD" type="boolean" truevalue="--noSLOD" falsevalue="" label="Do not calculate the SLOD" /> + <param name="min_base_quality_score" type="integer" value="17" label="Minimum base quality required to consider a base for calling" /> + <param name="min_mapping_quality_score" type="integer" value="20" label="Minimum read mapping quality required to consider a read for calling" /> + <param name="max_deletion_fraction" type="float" value="0.05" label="Maximum fraction of reads with deletions spanning this locus for it to be callable" help="to disable, set to < 0 or > 1" /> + <param name="min_indel_count_for_genotyping" type="integer" value="5" label="Minimum number of consensus indels required to trigger genotyping run" /> + <param name="indel_heterozygosity" type="float" value="0.000125" label="Heterozygosity for indel calling" help="1.0/8000==0.000125"/> + <param name="indelGapContinuationPenalty" type="float" value="10.0" label="Indel gap continuation penalty" /> + <param name="indelGapOpenPenalty" type="float" value="45.0" label="Indel gap open penalty" /> + <param name="indelHaplotypeSize" type="integer" value="80" label="Indel haplotype size" /> + <param name="doContextDependentGapPenalties" type="boolean" truevalue="--doContextDependentGapPenalties" falsevalue="" label="Vary gap penalties by context" /> + <param name="annotation" type="select" multiple="True" display="checkboxes" label="Annotation Types"> + <option value="AlleleBalance">AlleleBalance</option> + <option value="BaseQualityRankSumTest">BaseQualityRankSumTest</option> + <option value="DepthOfCoverage">DepthOfCoverage</option> + <option value="HomopolymerRun">HomopolymerRun</option> + <option value="MappingQualityRankSumTest">MappingQualityRankSumTest</option> + <option value="MappingQualityZero">MappingQualityZero</option> + <option value="QualByDepth">QualByDepth</option> + <option value="RMSMappingQuality">RMSMappingQuality</option> + <option value="SpanningDeletions">SpanningDeletions</option> + <option value="HaplotypeScore">HaplotypeScore</option> + </param> + <param name="group" type="select" multiple="True" display="checkboxes" label="Annotation Interfaces/Groups"> + <option value="Standard">Standard</option> + <option value="Experimental">Experimental</option> + <option value="WorkInProgress">WorkInProgress</option> + <!-- <option value="none">none</option> --> + </param> + </when> + </conditional> + </inputs> + <outputs> + <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (VCF)" /> + <data format="txt" name="output_log" label="${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_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" /> + <param name="input_dbsnp_rod" /> + <param name="rod_bind_type_selector" value="snps" /> + <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" /> + <param name="rodToIntervalTrackName" /> + <param name="standard_min_confidence_threshold_for_calling" value="4" /> + <param name="standard_min_confidence_threshold_for_emitting" value="4" /> + <param name="gatk_param_type_selector" value="basic" /> + <param name="analysis_param_type_selector" value="advanced" /> + <param name="genotype_likelihoods_model" value="BOTH" /> + <param name="p_nonref_model" value="EXACT" /> + <param name="heterozygosity" value="0.001" /> + <param name="pcr_error_rate" value="0.0001" /> + <param name="genotyping_mode" value="DISCOVERY" /> + <param name="output_mode" value="EMIT_ALL_CONFIDENT_SITES" /> + <param name="noSLOD" /> + <param name="min_base_quality_score" value="17" /> + <param name="min_mapping_quality_score" value="20" /> + <param name="max_deletion_fraction" value="-1" /> + <param name="min_indel_count_for_genotyping" value="2" /> + <param name="indel_heterozygosity" value="0.000125" /> + <param name="indelGapContinuationPenalty" value="10" /> + <param name="indelGapOpenPenalty" value="3" /> + <param name="indelHaplotypeSize" value="80" /> + <param name="doContextDependentGapPenalties" /> + <!-- <param name="annotation" value="" /> + <param name="group" value="" /> --> + <output name="output_interval" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.vcf" lines_diff="2"/> + <output name="output_log" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.log.contains" compare="contains"/> + </test> + </tests> + <help> +**What it does** + + A variant caller which unifies the approaches of several disparate callers. Works for single-sample and + multi-sample data. The user can choose from several different incorporated calculation models. + +------ + +Please cite the website "http://addlink.here" as well as: + +Add citation here 2011. + +------ + +**Input formats** + +GenomeAnalysisTK: UnifiedGenotyper accepts an aligned BAM input file. + +------ + +**Outputs** + +The output is in VCF format, see http://addlink.here for more details. + +------- + +**Settings**:: + + genotype_likelihoods_model Genotype likelihoods calculation model to employ -- BOTH is the default option, while INDEL is also available for calling indels and SNP is available for calling SNPs only (SNP|INDEL|BOTH) + p_nonref_model Non-reference probability calculation model to employ -- EXACT is the default option, while GRID_SEARCH is also available. (EXACT|GRID_SEARCH) + heterozygosity Heterozygosity value used to compute prior likelihoods for any locus + pcr_error_rate The PCR error rate to be used for computing fragment-based likelihoods + genotyping_mode Should we output confident genotypes (i.e. including ref calls) or just the variants? (DISCOVERY|GENOTYPE_GIVEN_ALLELES) + output_mode Should we output confident genotypes (i.e. including ref calls) or just the variants? (EMIT_VARIANTS_ONLY|EMIT_ALL_CONFIDENT_SITES|EMIT_ALL_SITES) + standard_min_confidence_threshold_for_calling The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called + standard_min_confidence_threshold_for_emitting The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold) + noSLOD If provided, we will not calculate the SLOD + min_base_quality_score Minimum base quality required to consider a base for calling + min_mapping_quality_score Minimum read mapping quality required to consider a read for calling + max_deletion_fraction Maximum fraction of reads with deletions spanning this locus for it to be callable [to disable, set to < 0 or > 1; default:0.05] + min_indel_count_for_genotyping Minimum number of consensus indels required to trigger genotyping run + indel_heterozygosity Heterozygosity for indel calling + indelGapContinuationPenalty Indel gap continuation penalty + indelGapOpenPenalty Indel gap open penalty + indelHaplotypeSize Indel haplotype size + doContextDependentGapPenalties Vary gap penalties by context + indel_recal_file Filename for the input covariates table recalibration .csv file - EXPERIMENTAL, DO NO USE + indelDebug Output indel debug info + out File to which variants should be written + annotation One or more specific annotations to apply to variant calls + group One or more classes/groups of annotations to apply to variant calls + + </help> +</tool>