Mercurial > repos > jjohnson > gatk2
view variant_select.xml @ 29:c511aa6f93da draft
Temporarily use my own copy of samtools until cross dependency support is in release
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Tue, 19 Feb 2013 20:59:51 -0600 |
| parents | 6ef8eb568700 |
| children | 76f8ca47b810 |
line wrap: on
line source
<tool id="gatk2_variant_select" name="Select Variants" version="0.0.5"> <description>from VCF files</description> <requirements> <requirement type="package" version="2.3">gatk</requirement> </requirements> <command interpreter="python">gatk2_wrapper.py #from binascii import hexlify --max_jvm_heap_fraction "1" --stdout "${output_log}" -d "--variant:variant,%(file_type)s" "${reference_source.input_variant}" "${reference_source.input_variant.ext}" "input_variant" -p 'java -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" -T "SelectVariants" \$GATK2_SITE_OPTIONS \$GATK2_NUM_THREADS ##--num_threads 4 ##hard coded, for now ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home -o "${output_vcf}" #if $reference_source.reference_source_selector != "history": -R "${reference_source.ref_file.fields.path}" #end if ' -p ' #if $input_concordance: --concordance "${input_concordance}" #end if #if $input_discordance: --discordance "${input_discordance}" #end if #for $exclude_sample_name in $exclude_sample_name_repeat: --exclude_sample_name "${exclude_sample_name.exclude_sample_name}" #end for ${exclude_filtered} #for $sample_name in $sample_name_repeat: --sample_name "${sample_name.sample_name}" #end for ' #for $select_expressions in $select_expressions_repeat: #set $select_expression = "--select_expressions '%s'" % ( str( $select_expressions.select_expressions ) ) -o '${ hexlify( $select_expression ) }' #end for ##start tool specific options #if str( $analysis_param_type.analysis_param_type_selector ) == 'advanced': -p ' #for $exclude_sample_file in $analysis_param_type.exclude_sample_file_repeat: --exclude_sample_file "${exclude_sample_file.exclude_sample_file}" #end for #for $sample_file in $analysis_param_type.sample_file_repeat: --sample_file "${ample_file.sample_file}" #end for #if $analysis_param_type.input_keep_ids: --keepIDs "${analysis_param_type.input_keep_ids}" #end if ${analysis_param_type.keep_original_AC} ${analysis_param_type.mendelian_violation} --mendelianViolationQualThreshold "${analysis_param_type.mendelian_violation_qual_threshold}" --remove_fraction_genotypes "${analysis_param_type.remove_fraction_genotypes}" --restrictAllelesTo "${analysis_param_type.restrict_alleles_to}" #if str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_fraction': --select_random_fraction "${analysis_param_type.select_random_type.select_random_fraction}" #elif str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_number': --select_random_number "${analysis_param_type.select_random_type.select_random_number}" #end if #if $analysis_param_type.select_type_to_include: #for $type_to_include in str( $analysis_param_type.select_type_to_include ).split( ',' ): --selectTypeToInclude "${type_to_include}" #end for #end if ${analysis_param_type.exclude_non_variants} ' #for $sample_expressions in $analysis_param_type.sample_expressions_repeat: #set $sample_expression = "--sample_expressions '%s'" % ( str( $sample_expressions.sample_expressions ) ) -o '${ hexlify( $sample_expression ) }' #end for #end if ##end tool specific options ##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.fix_misencoded_quality_scores} ${gatk_param_type.non_deterministic_random_seed} ' #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ): #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file": -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}" #else -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"' #end if #end for #end if #if str( $reference_source.reference_source_selector ) == "history": -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input" #end if ##end standard gatk options </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_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &lt;variant&gt;" /> <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_variant" 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!!!! --> <param name="input_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &lt;variant&gt;" /> <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;" /> </when> </conditional> <repeat name="select_expressions_repeat" title="Criteria to use when selecting the data" help="-select,--select_expressions &lt;select_expressions&gt;"> <param name="select_expressions" type="text" label="JEXL expression"> <sanitizer> <valid initial="string.printable"> <remove value="'"/> </valid> <mapping initial="none"/> </sanitizer> </param> </repeat> <param name="input_concordance" type="data" format="vcf" label="Output variants that were also called in this comparison track" optional="True" help="-conc,--concordance &lt;concordance&gt;"/> <param name="input_discordance" type="data" format="vcf" label="Output variants that were not called in this comparison track" optional="True" help="-disc,--discordance &lt;discordance&gt;"/> <repeat name="sample_name_repeat" title="Include Samples by name" help="-sn,--sample_name &lt;sample_name&gt;"> <param name="sample_name" type="text" label="Include genotypes from this sample"/> </repeat> <repeat name="exclude_sample_name_repeat" title="Exclude Samples by name" help="-xl_sn,--exclude_sample_name &lt;exclude_sample_name&gt;"> <param name="exclude_sample_name" type="text" label="Exclude genotypes from this sample"/> </repeat> <param name="exclude_filtered" type="boolean" truevalue="--excludeFiltered" falsevalue="" label="Don't include filtered loci in the analysis" help="-ef,--excludeFiltered" /> <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"/> <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False" help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/> </when> </conditional> <conditional name="analysis_param_type"> <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> <option value="basic" selected="True">Basic</option> <option value="advanced">Advanced</option> </param> <when value="basic"> <!-- Do nothing here --> </when> <when value="advanced"> <repeat name="exclude_sample_file_repeat" title="Exclude Samples by file" help="-xl_sf,--exclude_sample_file &lt;exclude_sample_file&gt;"> <param name="exclude_sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to exclude"/> </repeat> <repeat name="sample_file_repeat" title="Samples by file" help="-sf,--sample_file &lt;sample_file&gt;"> <param name="sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to include" /> </repeat> <param name="input_keep_ids" type="data" format="text" label="Only emit sites whose ID is found in this file" optional="True" help="-IDs,--keepIDs &lt;keepIDs&gt;"/> <param name="keep_original_AC" type="boolean" truevalue="--keepOriginalAC" falsevalue="" label="Don't update the AC, AF, or AN values in the INFO field after selecting" help="-keepOriginalAC,--keepOriginalAC" /> <param name="mendelian_violation" type="boolean" truevalue="--mendelianViolation" falsevalue="" label="output mendelian violation sites only" help="-mv,--mendelianViolation" /> <param name="mendelian_violation_qual_threshold" type="float" label="Minimum genotype QUAL score for each trio member required to accept a site as a mendelian violation" value="0" help="-mvq,--mendelianViolationQualThreshold &lt;mendelianViolationQualThreshold&gt;" /> <param name="remove_fraction_genotypes" type="float" label="Selects a fraction (a number between 0 and 1) of the total genotypes at random from the variant track and sets them to nocall" value="0" min="0" max="1" help="-fractionGenotypes,--remove_fraction_genotypes &lt;remove_fraction_genotypes&gt;" /> <param name="restrict_alleles_to" type="select" label="Select only variants of a particular allelicity" help="-restrictAllelesTo,--restrictAllelesTo &lt;restrictAllelesTo&gt;"> <option value="ALL" selected="True">ALL</option> <option value="MULTIALLELIC">MULTIALLELIC</option> <option value="BIALLELIC">BIALLELIC</option> </param> <repeat name="sample_expressions_repeat" title="Regular expression to select many samples from the ROD tracks provided" help="-se,--sample_expressions &lt;sample_expressions&gt;"> <param name="sample_expressions" type="text" label="Regular expression"> <sanitizer> <valid initial="string.printable"> <remove value="'"/> </valid> <mapping initial="none"/> </sanitizer> </param> </repeat> <conditional name="select_random_type"> <param name="select_random_type_selector" type="select" label="Select a random subset of variants"> <option value="select_all" selected="True">Use all variants</option> <option value="select_random_fraction">Select random fraction</option> <option value="select_random_number">Select random number</option> </param> <when value="select_all"> <!-- Do nothing here --> </when> <when value="select_random_fraction"> <param name="select_random_fraction" type="float" value="0" label="Fraction" min="0" max="1" help="-fraction,--select_random_fraction &lt;select_random_fraction&gt;"/> </when> <when value="select_random_number"> <param name="select_random_number" type="integer" value="0" label="Count" help="-number,--select_random_number &lt;select_random_number&gt;" /> </when> </conditional> <param name="exclude_non_variants" type="boolean" truevalue="--excludeNonVariants" falsevalue="" label="Don't include loci found to be non-variant after the subsetting procedure" help="-env,--excludeNonVariants" /> <param name="select_type_to_include" type="select" label="Select only a certain type of variants from the input file" multiple="True" display="checkboxes" help="-selectType,--selectTypeToInclude &lt;selectTypeToInclude&gt;"> <option value="INDEL">INDEL</option> <option value="SNP">SNP</option> <option value="MIXED">MIXED</option> <option value="MNP">MNP</option> <option value="SYMBOLIC">SYMBOLIC</option> <option value="NO_VARIATION">NO_VARIATION</option> </param> </when> </conditional> </inputs> <outputs> <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (Variant File)" /> <data format="txt" name="output_log" label="${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_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" /> <param name="select_expressions_repeat" value="0" /> <param name="input_concordance" /> <param name="input_discordance" /> <param name="exclude_sample_name_repeat" value="0" /> <param name="exclude_filtered" /> <param name="sample_name_repeat" value="0" /> <param name="gatk_param_type_selector" value="basic" /> <param name="analysis_param_type_selector" value="basic" /> <output name="output_vcf" file="gatk/gatk_variant_select/gatk_variant_select_out_1.vcf" lines_diff="4" /> <output name="output_log" file="gatk/gatk_variant_select/gatk_variant_select_out_1.log.contains" compare="contains" /> </test> </tests> <help> **What it does** Often, a VCF containing many samples and/or variants will need to be subset in order to facilitate certain analyses (e.g. comparing and contrasting cases vs. controls; extracting variant or non-variant loci that meet certain requirements, displaying just a few samples in a browser like IGV, etc.). SelectVariants can be used for this purpose. Given a single VCF file, one or more samples can be extracted from the file (based on a complete sample name or a pattern match). Variants can be further selected by specifying criteria for inclusion, i.e. "DP > 1000" (depth of coverage greater than 1000x), "AF < 0.25" (sites with allele frequency less than 0.25). These JEXL expressions are documented in the `Using JEXL expressions section <http://gatkforums.broadinstitute.org/discussion/1255/what-are-jexl-expressions-and-how-can-i-use-them-with-the-gatk>`_. One can optionally include concordance or discordance tracks for use in selecting overlapping variants. For more information on using the SelectVariants module, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_variantutils_SelectVariants.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: SelectVariants accepts a VCF input file. **Outputs** The output is in VCF format. Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. ------- **Settings**:: out VCFWriter stdout File to which variants should be written variant RodBinding[VariantContext] NA Input VCF file concordance RodBinding[VariantContext] none Output variants that were also called in this comparison track discordance RodBinding[VariantContext] none Output variants that were not called in this comparison track exclude_sample_file Set[File] [] File containing a list of samples (one per line) to exclude. Can be specified multiple times exclude_sample_name Set[String] [] Exclude genotypes from this sample. Can be specified multiple times excludeFiltered boolean false Don't include filtered loci in the analysis excludeNonVariants boolean false Don't include loci found to be non-variant after the subsetting procedure keepIDs File NA Only emit sites whose ID is found in this file (one ID per line) keepOriginalAC boolean false Don't update the AC, AF, or AN values in the INFO field after selecting mendelianViolation Boolean false output mendelian violation sites only mvq double 0.0 Minimum genotype QUAL score for each trio member required to accept a site as a violation remove_fraction_genotypes double 0.0 Selects a fraction (a number between 0 and 1) of the total genotypes at random from the variant track and sets them to nocall restrictAllelesTo NumberAlleleRestriction ALL Select only variants of a particular allelicity. Valid options are ALL (default), MULTIALLELIC or BIALLELIC sample_expressions Set[String] NA Regular expression to select many samples from the ROD tracks provided. Can be specified multiple times sample_file Set[File] NA File containing a list of samples (one per line) to include. Can be specified multiple times sample_name Set[String] [] Include genotypes from this sample. Can be specified multiple times select_expressions ArrayList[String] [] One or more criteria to use when selecting the data select_random_fraction double 0.0 Selects a fraction (a number between 0 and 1) of the total variants at random from the variant track select_random_number int 0 Selects a number of variants at random from the variant track selectTypeToInclude List[Type] [] Select only a certain type of variants from the input file. Valid types are INDEL, SNP, MIXED, MNP, SYMBOLIC, NO_VARIATION. Can be specified multiple times ------ **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>