Mercurial > repos > lz_hust > gatktools
changeset 14:68426930d59c draft
Deleted selected files
| author | lz_hust |
|---|---|
| date | Sat, 01 Jun 2019 07:17:20 -0400 |
| parents | e4b6c7a08f06 |
| children | 01ff8dd37d4d |
| files | base_recalibrator.xml depth_of_coverage.xml gatk2_annotations.txt.sample gatk2_macros.xml gatk2_picard_index.loc.sample tool_data_table_conf.xml.sample |
| diffstat | 6 files changed, 0 insertions(+), 1481 deletions(-) [+] |
line wrap: on
line diff
--- a/base_recalibrator.xml Sat Jun 01 07:12:31 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,307 +0,0 @@ -<tool id="gatk2_base_recalibrator" name="Base Recalibrator" version="@VERSION@.0"> - <description>calculates covariates used to recalibrate base quality scores of reads</description> - <macros> - <import>gatk2_macros.xml</import> - </macros> - <expand macro="requirements" /> - <expand macro="version_command" /> - <command interpreter="python"> - gatk2_wrapper.py - --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 ' - @JAR_PATH@ - -T "BaseRecalibrator" - \$GATK2_SITE_OPTIONS - - ## according to http://www.broadinstitute.org/gatk/guide/article?id=1975 - --num_cpu_threads_per_data_thread \${GALAXY_SLOTS:-8} - - ## we set non standards at every run and the user can choose which ones are preferred - ## in our select box both standard options (ContextCovariate, CycleCovariate) are selected by default - --no_standard_covs - - #if $reference_source.reference_source_selector != "history": - -R "${reference_source.ref_file.fields.path}" - #end if - #if str($input_recal) != 'None': - --BQSR "${input_recal}" - #end if - --out "${output_recal}" - #if str( $covariates ) != "None": - #for $cov in str( $covariates ).split( ',' ): - -cov "${cov}" - #end for - #end if - ' - - #set $snp_dataset_provided = False - #set $rod_binding_names = dict() - #for $rod_binding in $rod_bind: - #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom': - #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name - #else - #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector - #end if - #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'dbsnp': - #set $snp_dataset_provided = True - #end if - #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1 - -d "--knownSites:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}" - #end for - - #include source=$standard_gatk_options# - - ##start analysis specific options - #if $analysis_param_type.analysis_param_type_selector == "advanced": - -p ' - #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set": - --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}" - #end if - #if str( $analysis_param_type.default_platform ) != "default": - --default_platform "${analysis_param_type.default_platform}" - #end if - #if str( $analysis_param_type.force_read_group_type.force_read_group_type_selector ) == "set": - --force_read_group "${analysis_param_type.force_read_group_type.force_read_group}" - #end if - #if str( $analysis_param_type.force_platform ) != "default": - --force_platform "${analysis_param_type.force_platform}" - #end if - ${analysis_param_type.exception_if_no_tile} - #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set": - #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default": - --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}" - #end if - #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default": - --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}" - #end if - #end if - --window_size_nqs "${analysis_param_type.window_size_nqs}" - --homopolymer_nback "${analysis_param_type.homopolymer_nback}" - ' - #end if - #if not $snp_dataset_provided: - -p '--run_without_dbsnp_potentially_ruining_quality' - #end if - </command> - <inputs> - <conditional name="reference_source"> - <expand macro="reference_source_selector_param" /> - <when value="cached"> - <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &lt;input_file&gt;"> - <validator type="unspecified_build" /> - <validator type="dataset_metadata_in_data_table" table_name="gatk2_picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select --> - </param> - <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &lt;reference_sequence&gt;" > - <options from_data_table="gatk2_picard_indexes"> - <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> - </options> - <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> - </param> - </when> - <when value="history"> - <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &lt;input_file&gt;" /> - <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;"> - <options> - <filter type="data_meta" key="dbkey" ref="input_bam" /> - </options> - </param> - </when> - </conditional> - <param name="input_recal" type="data" format="gatk_report" optional="true" label="Covariates table recalibration file" help="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) (-BQSR,--BQSR &lt;recal_file&gt;)" /> - - <param name="covariates" type="select" multiple="True" display="checkboxes" label="Covariates to be used in the recalibration" help="-cov,--covariate &lt;covariate&gt;" > - <!-- might we want to load the available covariates from an external configuration file, since additional ones can be added to local installs? --> - <option value="ContextCovariate" selected="true"/> - <option value="CycleCovariate" selected="true"/> - <option value="RepeatLengthCovariate" /> - <option value="RepeatUnitCovariate" /> - <option value="RepeatUnitAndLengthCovariate" /> - <!-- - Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will - be added for the user regardless of whether or not they were specified. - <option value="QualityScoreCovariate" /> - <option value="ReadGroupCovariate" /> - --> - </param> - - <repeat name="rod_bind" title="Known Variants" help="Using data sets of known variants (-knownSites,--knownSites &lt;knownSites&gt;)"> - <conditional name="rod_bind_type"> - <param name="rod_bind_type_selector" type="select" label="Variant Type"> - <option value="dbsnp" selected="True">dbSNP</option> - <option value="snps">SNPs</option> - <option value="indels">INDELs</option> - <option value="mask">Mask</option> - <option value="custom">Custom</option> - </param> - <when value="dbsnp"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" /> - </when> - <when value="snps"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" /> - </when> - <when value="indels"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" /> - </when> - <when value="mask"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" /> - </when> - <when value="custom"> - <param name="custom_rod_name" type="text" value="Unknown" label="Customer's variant file"/> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file" /> - </when> - </conditional> - </repeat> - - <expand macro="gatk_param_type_conditional" /> - - <conditional name="analysis_param_type"> - <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> - <option value="basic" selected="True">Basic</option> - <option value="advanced">Advanced</option> - </param> - <when value="basic"> - <!-- Do nothing here --> - </when> - <when value="advanced"> - <conditional name="default_read_group_type"> - <param name="default_read_group_type_selector" type="select" label="Set default Read Group" help="--default_read_group"> - <option value="default" selected="True">Don't Set</option> - <option value="set">Set</option> - </param> - <when value="default"> - <!-- do nothing here --> - </when> - <when value="set"> - <param name="default_read_group" type="text" value="Unknown" label="If a read has no read group then default to the provided String"/> - </when> - </conditional> - <param name="default_platform" type="select" label="Set default Platform" help="--default_platform"> - <option value="default" selected="True">Don't Set</option> - <option value="illumina">illumina</option> - <option value="454">454</option> - <option value="solid">solid</option> - </param> - <conditional name="force_read_group_type"> - <param name="force_read_group_type_selector" type="select" label="Force Read Group" help="--force_read_group"> - <option value="default" selected="True">Don't Force</option> - <option value="set">Force</option> - </param> - <when value="default"> - <!-- do nothing here --> - </when> - <when value="set"> - <param name="force_read_group" type="text" value="Unknown" label="If provided, the read group ID of EVERY read will be forced to be the provided String."/> - </when> - </conditional> - <param name="force_platform" type="select" label="Force Platform" help="--force_platform"> - <option value="default" selected="True">Don't Force</option> - <option value="illumina">illumina</option> - <option value="454">454</option> - <option value="solid">solid</option> - </param> - <param name="exception_if_no_tile" type="boolean" checked="False" truevalue="--exception_if_no_tile" falsevalue="" label="Throw an exception when no tile can be found" help="--exception_if_no_tile"/> - <conditional name="solid_options_type"> - <param name="solid_options_type_selector" type="select" label="Set SOLiD specific options"> - <option value="default" selected="True">Don't Set</option> - <option value="set">Set</option> - </param> - <when value="default"> - <!-- do nothing here --> - </when> - <when value="set"> - <param name="solid_recal_mode" type="select" label="How should we recalibrate solid bases in which the reference was inserted" help="-sMode,--solid_recal_mode &lt;solid_recal_mode&gt;"> - <option value="default" selected="True">Don't set</option> - <option value="DO_NOTHING">DO_NOTHING</option> - <option value="SET_Q_ZERO">SET_Q_ZERO</option> - <option value="SET_Q_ZERO_BASE_N">SET_Q_ZERO_BASE_N</option> - <option value="REMOVE_REF_BIAS">REMOVE_REF_BIAS</option> - </param> - <param name="solid_nocall_strategy" type="select" label="Behavior of the recalibrator when it encounters no calls" help="-solid_nocall_strategy,--solid_nocall_strategy &lt;solid_nocall_strategy&gt;"> - <option value="default" selected="True">Don't set</option> - <option value="THROW_EXCEPTION">THROW_EXCEPTION</option> - <option value="LEAVE_READ_UNRECALIBRATED">LEAVE_READ_UNRECALIBRATED</option> - <option value="PURGE_READ">PURGE_READ</option> - </param> - </when> - </conditional> - <param name="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate" help="window_size_nqs"/> - <param name="homopolymer_nback" type="integer" value="7" label="number of previous bases to look at in HomopolymerCovariate" help="-nback,--homopolymer_nback &lt;homopolymer_nback&gt;" /> - </when> - </conditional> - </inputs> - <outputs> - <data format="gatk_report" name="output_recal" label="${tool.name} on ${on_string} (Covariate File)" /> - <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> - </outputs> - <tests> - <test> - <param name="reference_source_selector" value="history" /> - <param name="ref_file" value="phiX.fasta" ftype="fasta" /> - <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" /> - <param name="rod_bind_type_selector" value="dbsnp" /> - <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" /> - <param name="standard_covs" value="True" /> - <param name="covariates" value="ReadGroupCovariate,HomopolymerCovariate,MinimumNQSCovariate,PositionCovariate" /> - <param name="gatk_param_type_selector" value="basic" /> - <param name="analysis_param_type_selector" value="basic" /> - <output name="output_recal" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" /> - <output name="output_log" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.log.contains" compare="contains" /> - </test> - </tests> - <help> -.. class:: warningmark - -"This calculation is critically dependent on being able to skip over known variant sites. Please provide a dbSNP ROD or a VCF file containing known sites of genetic variation." -However, if you do not provide this file, the '--run_without_dbsnp_potentially_ruining_quality' flag will be automatically used, and the command will be allowed to run. - -**What it does** - -This walker is designed to work as the first pass in a two-pass processing step. It does a by-locus traversal operating only at sites that are not in dbSNP. We assume that all reference mismatches we see are therefore errors and indicative of poor base quality. This walker generates tables based on various user-specified covariates (such as read group, reported quality score, cycle, and dinucleotide) Since there is a large amount of data one can then calculate an empirical probability of error given the particular covariates seen at this site, where p(error) = num mismatches / num observations The output file is a CSV list of (the several covariate values, num observations, num mismatches, empirical quality score) The first non-comment line of the output file gives the name of the covariates that were used for this calculation. Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will be added for the user regardless of whether or not they were specified Note: This walker is designed to be used in conjunction with TableRecalibrationWalker. - -For more information on base quality score recalibration using the GATK, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_bqsr_BaseRecalibrator.html>`_. - -To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gatk/guide/topic?name=best-practices>`_. - -If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gatk/guide/topic?name=faqs>`_. - ------- - -**Inputs** - -GenomeAnalysisTK: BaseRecalibrator accepts an aligned BAM input file. - - -**Outputs** - -The output is in CSV format. - - -Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. - -------- - -**Settings**:: - - - default_read_group If a read has no read group then default to the provided String. - default_platform If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid. - force_read_group If provided, the read group ID of EVERY read will be forced to be the provided String. This is useful to collapse all data into a single read group. - force_platform If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid. - window_size_nqs The window size used by MinimumNQSCovariate for its calculation - homopolymer_nback The number of previous bases to look at in HomopolymerCovariate - exception_if_no_tile If provided, TileCovariate will throw an exception when no tile can be found. The default behavior is to use tile = -1 - solid_recal_mode How should we recalibrate solid bases in whichthe reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS (DO_NOTHING|SET_Q_ZERO|SET_Q_ZERO_BASE_N|REMOVE_REF_BIAS) - solid_nocall_strategy Defines the behavior of the recalibrator when it encounters no calls in the color space. Options = THROW_EXCEPTION, LEAVE_READ_UNRECALIBRATED, or PURGE_READ (THROW_EXCEPTION|LEAVE_READ_UNRECALIBRATED|PURGE_READ) - recal_file Filename for the input covariates table recalibration .csv file - out The output CSV file - standard_covs Use the standard set of covariates in addition to the ones listed using the -cov argument - run_without_dbsnp_potentially_ruining_quality If specified, allows the recalibrator to be used without a dbsnp rod. Very unsafe and for expert users only. - -@CITATION_SECTION@ - </help> - <expand macro="citations" /> -</tool>
--- a/depth_of_coverage.xml Sat Jun 01 07:12:31 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,731 +0,0 @@ -<tool id="gatk2_depth_of_coverage" name="Depth of Coverage" version="@VERSION@.1"> - <description>on BAM files</description> - <macros> - <import>gatk2_macros.xml</import> - </macros> - <expand macro="requirements" /> - <expand macro="version_command" /> - <command interpreter="python">gatk2_wrapper.py - ##--max_jvm_heap_fraction "1" - --stdout "${output_log}" - @BAM_INPUTS@ - -p ' - @JAR_PATH@ - -T "DepthOfCoverage" - \$GATK2_SITE_OPTIONS - - @THREADS@ - - #if $reference_source.reference_source_selector != "history": - -R "${reference_source.ref_file.fields.path}" - #end if - #if str( $input_calculate_coverage_over_genes ) != "None": - --calculateCoverageOverGenes "${input_calculate_coverage_over_genes}" - #end if - #if str( $partition_type ) != "None": - #for $pt in str( $partition_type ).split( ',' ): - --partitionType "${pt}" - #end for - #end if - --out "${output_per_locus_coverage}" - - #for $ct_group in $summary_coverage_threshold_group: - --summaryCoverageThreshold "${ct_group.summary_coverage_threshold}" - #end for - --outputFormat "${output_format}" - ' - - #include source=$standard_gatk_options# - ##start analysis specific options - #if $analysis_param_type.analysis_param_type_selector == "advanced": - -p ' - ${analysis_param_type.ignore_deletion_sites} - ${analysis_param_type.include_deletions} - --maxBaseQuality "${analysis_param_type.max_base_quality}" - --maxMappingQuality "${analysis_param_type.max_mapping_quality}" - --minBaseQuality "${analysis_param_type.min_base_quality}" - --minMappingQuality "${analysis_param_type.min_mapping_quality}" - --nBins "${analysis_param_type.n_bins}" - ${analysis_param_type.omit_depth_output_at_each_base} - ${analysis_param_type.omit_interval_statistics} - ${analysis_param_type.omit_locus_table} - ${analysis_param_type.omit_per_sample_stats} - ${analysis_param_type.print_base_counts} - ${analysis_param_type.print_bin_endpoints_and_exit} - --start "${analysis_param_type.start}" - --stop "${analysis_param_type.stop}" - ' - #end if - ##Move additional files to final location - #if str( $partition_type ) != "None": - #set $partition_types = str( $partition_type ).split( ',' ) - #else: - #set $partition_types = [ 'sample' ] - #end if - #if 'sample' in $partition_types and ( str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.print_bin_endpoints_and_exit ) == "" ): - #if str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.omit_per_sample_stats ) == "": - && mv ${output_per_locus_coverage}.sample_summary ${output_summary_sample} - && mv ${output_per_locus_coverage}.sample_statistics ${output_statistics_sample} - #end if - #if $gatk_param_type.gatk_param_type_selector == "advanced" and len( $gatk_param_type.input_interval_repeat ) and ( str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.omit_interval_statistics ) == "" ): - && mv ${output_per_locus_coverage}.sample_interval_summary ${output_interval_summary_sample} - && mv ${output_per_locus_coverage}.sample_interval_statistics ${output_interval_statistics_sample} - #end if - #if str( $input_calculate_coverage_over_genes ) != "None": - && mv ${output_per_locus_coverage}.sample_gene_summary ${output_gene_summary_sample} - && mv ${output_per_locus_coverage}.sample_gene_statistics ${output_gene_statistics_sample} - #end if - #if str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.omit_depth_output_at_each_base ) == "": - && mv ${output_per_locus_coverage}.sample_cumulative_coverage_counts ${output_cumulative_coverage_counts_sample} - && mv ${output_per_locus_coverage}.sample_cumulative_coverage_proportions ${output_cumulative_coverage_proportions_sample} - #end if - #end if - - #if 'readgroup' in $partition_types and ( str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.print_bin_endpoints_and_exit ) == "" ): - #if str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.omit_per_sample_stats ) == "": - && mv ${output_per_locus_coverage}.read_group_summary ${output_summary_readgroup} - && mv ${output_per_locus_coverage}.read_group_statistics ${output_statistics_readgroup} - #end if - #if $gatk_param_type.gatk_param_type_selector == "advanced" and len( $gatk_param_type.input_interval_repeat ) and ( str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.omit_interval_statistics ) == "" ): - && mv ${output_per_locus_coverage}.read_group_interval_summary ${output_interval_summary_readgroup} - && mv ${output_per_locus_coverage}.read_group_interval_statistics ${output_interval_statistics_readgroup} - #end if - #if str( $input_calculate_coverage_over_genes ) != "None": - && mv ${output_per_locus_coverage}.read_group_gene_summary ${output_gene_summary_readgroup} - && mv ${output_per_locus_coverage}.read_group_gene_statistics ${output_gene_statistics_readgroup} - #end if - #if str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.omit_depth_output_at_each_base ) == "": - && mv ${output_per_locus_coverage}.read_group_cumulative_coverage_counts ${output_cumulative_coverage_counts_readgroup} - && mv ${output_per_locus_coverage}.read_group_cumulative_coverage_proportions ${output_cumulative_coverage_proportions_readgroup} - #end if - #end if - - #if 'library' in $partition_types and ( str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.print_bin_endpoints_and_exit ) == "" ): - #if str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.omit_per_sample_stats ) == "": - && mv ${output_per_locus_coverage}.library_summary ${output_summary_library} - && mv ${output_per_locus_coverage}.library_statistics ${output_statistics_library} - #end if - #if $gatk_param_type.gatk_param_type_selector == "advanced" and len( $gatk_param_type.input_interval_repeat ) and ( str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.omit_interval_statistics ) == "" ): - && mv ${output_per_locus_coverage}.library_interval_summary ${output_interval_summary_library} - && mv ${output_per_locus_coverage}.library_interval_statistics ${output_interval_statistics_library} - #end if - #if str( $input_calculate_coverage_over_genes ) != "None": - && mv ${output_per_locus_coverage}.library_gene_summary ${output_gene_summary_library} - && mv ${output_per_locus_coverage}.library_gene_statistics ${output_gene_statistics_library} - #end if - #if str( $analysis_param_type.analysis_param_type_selector ) == "basic" or str( $analysis_param_type.omit_depth_output_at_each_base ) == "": - && mv ${output_per_locus_coverage}.library_cumulative_coverage_counts ${output_cumulative_coverage_counts_library} - && mv ${output_per_locus_coverage}.library_cumulative_coverage_proportions ${output_cumulative_coverage_proportions_library} - #end if - #end if - - </command> - <inputs> - <conditional name="reference_source"> - <expand macro="reference_source_selector_param" /> - <when value="cached"> - <expand macro="input_bams_cached" /> - <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &lt;reference_sequence&gt;"> - <options from_data_table="gatk2_picard_indexes"> - <!-- <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> does not yet work in a repeat...--> - </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!!!! --> - - <expand macro="input_bams_history" /> - <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;" /> - </when> - </conditional> - - <param name="input_calculate_coverage_over_genes" type="data" format="data" label="RefSeq Rod" optional="True" help="-geneList,--calculateCoverageOverGenes &lt;calculateCoverageOverGenes&gt;" /> - - <param name="partition_type" type="select" label="Partition type for depth of coverage" multiple="True" display="checkboxes" help="-pt,--partitionType &lt;partitionType&gt;"> - <option value="sample" selected="True">sample</option> - <option value="readgroup">readgroup</option> - <option value="library">library</option> - </param> - - <repeat name="summary_coverage_threshold_group" title="Summary coverage threshold" help="-ct,--summaryCoverageThreshold &lt;summaryCoverageThreshold&gt;"> - <param name="summary_coverage_threshold" type="integer" value="15" label="for summary file outputs, report the % of bases covered to >= this number" /> - </repeat> - - <param name="output_format" type="select" label="Output format" help="--outputFormat &lt;outputFormat&gt;" > - <option value="csv">csv</option> - <option value="table">table</option> - <option value="rtable" selected="True">rtable</option> - </param> - - <expand macro="gatk_param_type_conditional" /> - - <expand macro="analysis_type_conditional"> - <param name="ignore_deletion_sites" type="boolean" truevalue="--ignoreDeletionSites" falsevalue="" checked="False" label="Ignore sites consisting only of deletions" help="--ignoreDeletionSites" /> - <param name="include_deletions" type="boolean" truevalue="--includeDeletions" falsevalue="" checked="False" label="Include information on deletions" help="-dels,--includeDeletions" /> - <param name="max_base_quality" type="integer" value="127" label="Maximum quality of bases to count towards depth" help="--maxBaseQuality &lt;maxBaseQuality&gt;" /> - <param name="min_base_quality" type="integer" value="-1" label="Minimum quality of bases to count towards depth" help="-mbq,--minBaseQuality &lt;minBaseQuality&gt;" /> - <param name="max_mapping_quality" type="integer" value="2147483647" label="Maximum mapping quality of reads to count towards depth." help="--maxMappingQuality &lt;maxMappingQuality&gt;" /> - <param name="min_mapping_quality" type="integer" value="127" label="Minimum mapping quality of reads to count towards depth" help="-mmq,--minMappingQuality &lt;minMappingQuality&gt;" /> - <param name="n_bins" type="integer" value="499" label="Number of bins to use for granular binning" help="--nBins &lt;nBins&gt;" /> - <param name="omit_depth_output_at_each_base" type="boolean" truevalue="--omitDepthOutputAtEachBase" falsevalue="" checked="False" label="Omit the output of the depth of coverage at each base" help="-omitBaseOutput,--omitDepthOutputAtEachBase" /> - <param name="omit_interval_statistics" type="boolean" truevalue="--omitIntervalStatistics" falsevalue="" checked="False" label="Omit the per-interval statistics section" help="-omitIntervals,--omitIntervalStatistics" /> - <param name="omit_locus_table" type="boolean" truevalue="--omitLocusTable" falsevalue="" checked="False" label="Do not calculate the per-sample per-depth counts of loci" help="-omitLocusTable,--omitLocusTable" /> - <param name="omit_per_sample_stats" type="boolean" truevalue="--omitPerSampleStats" falsevalue="" checked="False" label="Omit the summary files per-sample." help="-omitSampleSummary,--omitPerSampleStats" /> - <param name="print_base_counts" type="boolean" truevalue="--printBaseCounts" falsevalue="" checked="False" label="Add base counts to per-locus output" help="-baseCounts,--printBaseCounts" /> - <param name="print_bin_endpoints_and_exit" type="boolean" truevalue="--printBinEndpointsAndExit" falsevalue="" checked="False" label="Print the bin values and exits immediately" help="--printBinEndpointsAndExit" /> - <param name="start" type="integer" value="1" label="Starting (left endpoint) for granular binning" help="--start &lt;start&gt;" /> - <param name="stop" type="integer" value="500" label="Ending (right endpoint) for granular binning" help="--stop &lt;stop&gt;" /> - </expand> - </inputs> - <outputs> - <data format="tabular" name="output_per_locus_coverage" label="${tool.name} on ${on_string} (per locus coverage)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_summary_sample" label="${tool.name} on ${on_string} (output summary sample)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'sample' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_statistics_sample" label="${tool.name} on ${on_string} (output statistics sample)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'sample' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_interval_summary_sample" label="${tool.name} on ${on_string} (output interval summary sample)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'sample' in partition_type or not partition_type</filter> - <filter>gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] )</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_interval_statistics_sample" label="${tool.name} on ${on_string} (output interval statistics sample)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'sample' in partition_type or not partition_type</filter> - <filter>gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] )</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_gene_summary_sample" label="${tool.name} on ${on_string} (output gene summary sample)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>input_calculate_coverage_over_genes is not None and 'sample' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_gene_statistics_sample" label="${tool.name} on ${on_string} (output gene statistics sample)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>input_calculate_coverage_over_genes is not None and 'sample' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_cumulative_coverage_counts_sample" label="${tool.name} on ${on_string} (output cumulative coverage counts sample)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'sample' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_cumulative_coverage_proportions_sample" label="${tool.name} on ${on_string} (output cumulative coverage proportions sample)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'sample' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - - <data format="tabular" name="output_summary_readgroup" label="${tool.name} on ${on_string} (output summary readgroup)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'readgroup' in partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_statistics_readgroup" label="${tool.name} on ${on_string} (output statistics readgroup)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'readgroup' in partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_interval_summary_readgroup" label="${tool.name} on ${on_string} (output interval summary readgroup)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'readgroup' in partition_type</filter> - <filter>gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] )</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_interval_statistics_readgroup" label="${tool.name} on ${on_string} (output interval statistics readgroup)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'readgroup' in partition_type</filter> - <filter>gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] )</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_gene_summary_readgroup" label="${tool.name} on ${on_string} (output gene summary readgroup)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>input_calculate_coverage_over_genes is not None and 'readgroup' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_gene_statistics_readgroup" label="${tool.name} on ${on_string} (output gene statistics readgroup)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>input_calculate_coverage_over_genes is not None and 'readgroup' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_cumulative_coverage_counts_readgroup" label="${tool.name} on ${on_string} (output cumulative coverage counts readgroup)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False</filter> - <filter>'readgroup' in partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_cumulative_coverage_proportions_readgroup" label="${tool.name} on ${on_string} (output cumulative coverage proportions readgroup)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False</filter> - <filter>'readgroup' in partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - - <data format="tabular" name="output_summary_library" label="${tool.name} on ${on_string} (output summary library)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'library' in partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_statistics_library" label="${tool.name} on ${on_string} (output statistics library)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'library' in partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_interval_summary_library" label="${tool.name} on ${on_string} (output interval summary library)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'library' in partition_type</filter> - <filter>gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] )</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_interval_statistics_library" label="${tool.name} on ${on_string} (output interval statistics library)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'library' in partition_type</filter> - <filter>gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] )</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_gene_summary_library" label="${tool.name} on ${on_string} (output gene summary library)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>input_calculate_coverage_over_genes is not None and 'library' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_gene_statistics_library" label="${tool.name} on ${on_string} (output gene statistics library)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>input_calculate_coverage_over_genes is not None and 'library' in partition_type or not partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_cumulative_coverage_counts_library" label="${tool.name} on ${on_string} (output cumulative coverage counts library)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'library' in partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="tabular" name="output_cumulative_coverage_proportions_library" label="${tool.name} on ${on_string} (output cumulative coverage proportions library)" > - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False</filter> - <filter>analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False</filter> - <filter>'library' in partition_type</filter> - <actions> - <conditional name="output_format"> - <when value="rtable"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - <when value="csv"> - <action type="format"> - <option type="from_param" name="output_format" /> - </action> - </when> - </conditional> - </actions> - </data> - - <data format="tabular" name="output_log" label="${tool.name} on ${on_string} (log)" /> - </outputs> - <trackster_conf/> - <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_calculate_coverage_over_genes" /> - <param name="partition_type" value="sample" /> - <param name="summary_coverage_threshold_group" value="0" /> - <param name="output_format" value="rtable" /> - <param name="gatk_param_type_selector" value="basic" /> - <param name="analysis_param_type_selector" value="basic" /> - <output name="output_per_locus_coverage" file="gatk/gatk_depth_of_coverage/gatk_depth_of_coverage_out_1_output_per_locus_coverage.tabular" /> - <output name="output_summary_sample" file="gatk/gatk_depth_of_coverage/gatk_depth_of_coverage_out_1_output_summary_sample.tabular" /> - <output name="output_statistics_sample" file="gatk/gatk_depth_of_coverage/gatk_depth_of_coverage_out_1_output_statistics_sample.tabular" /> - <output name="output_cumulative_coverage_counts_sample" file="gatk/gatk_depth_of_coverage/gatk_depth_of_coverage_out_1_output_cumulative_coverage_counts_sample.tabular" /> - <output name="output_cumulative_coverage_proportions_sample" file="gatk/gatk_depth_of_coverage/gatk_depth_of_coverage_out_1_output_output_cumulative_coverage_proportions_sample.tabular" /> - <output name="output_log" file="gatk/gatk_depth_of_coverage/gatk_depth_of_coverage_out_1.log.contains" compare="contains" /> - </test> - </tests> - <help> -**What it does** - -DepthOfCoverage processes a set of bam files to determine coverage at different levels of partitioning and aggregation. Coverage can be analyzed per locus, per interval, per gene, or in total; can be partitioned by sample, by read group, by technology, by center, or by library; and can be summarized by mean, median, quartiles, and/or percentage of bases covered to or beyond a threshold. Additionally, reads and bases can be filtered by mapping or base quality score. - -For more information on the GATK Depth of Coverage, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_coverage_DepthOfCoverage.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: DepthOfCoverage accepts aligned BAM input files. - - -**Outputs** - -The output is in various table formats. - - -Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. - -------- - -**Settings**:: - - calculateCoverageOverGenes File NA Calculate the coverage statistics over this list of genes. Currently accepts RefSeq. - ignoreDeletionSites boolean false Ignore sites consisting only of deletions - includeDeletions boolean false Include information on deletions - maxBaseQuality byte 127 Maximum quality of bases to count towards depth. Defaults to 127 (Byte.MAX_VALUE). - maxMappingQuality int 2147483647 Maximum mapping quality of reads to count towards depth. Defaults to 2^31-1 (Integer.MAX_VALUE). - minBaseQuality byte -1 Minimum quality of bases to count towards depth. Defaults to -1. - minMappingQuality int -1 Minimum mapping quality of reads to count towards depth. Defaults to -1. - nBins int 499 Number of bins to use for granular binning - omitDepthOutputAtEachBase boolean false Will omit the output of the depth of coverage at each base, which should result in speedup - omitIntervalStatistics boolean false Will omit the per-interval statistics section, which should result in speedup - omitLocusTable boolean false Will not calculate the per-sample per-depth counts of loci, which should result in speedup - omitPerSampleStats boolean false Omits the summary files per-sample. These statistics are still calculated, so this argument will not improve runtime. - outputFormat String rtable the format of the output file (e.g. csv, table, rtable); defaults to r-readable table - partitionType Set[Partition] [sample] Partition type for depth of coverage. Defaults to sample. Can be any combination of sample, readgroup, library. - printBaseCounts boolean false Will add base counts to per-locus output. - printBinEndpointsAndExit boolean false Prints the bin values and exits immediately. Use to calibrate what bins you want before running on data. - start int 1 Starting (left endpoint) for granular binning - stop int 500 Ending (right endpoint) for granular binning - summaryCoverageThreshold int[] [15] for summary file outputs, report the % of bases coverd to >= this number. Defaults to 15; can take multiple arguments. - -@CITATION_SECTION@ - </help> - <expand macro="citations" /> -</tool>
--- a/gatk2_annotations.txt.sample Sat Jun 01 07:12:31 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,26 +0,0 @@ -#unique_id name gatk_value tools_valid_for -AlleleBalance AlleleBalance AlleleBalance UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -AlleleBalanceBySample AlleleBalanceBySample AlleleBalanceBySample UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -BaseCounts BaseCounts BaseCounts UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -BaseQualityRankSumTest BaseQualityRankSumTest BaseQualityRankSumTest UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -ChromosomeCounts ChromosomeCounts ChromosomeCounts UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -Coverage Coverage Coverage UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -DepthPerAlleleBySample DepthPerAlleleBySample DepthPerAlleleBySample UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -FisherStrand FisherStrand FisherStrand UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -GCContent GCContent GCContent UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -HaplotypeScore HaplotypeScore HaplotypeScore UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -HardyWeinberg HardyWeinberg HardyWeinberg UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -HomopolymerRun HomopolymerRun HomopolymerRun UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -InbreedingCoeff InbreedingCoeff InbreedingCoeff UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -LowMQ LowMQ LowMQ UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -MVLikelihoodRatio MVLikelihoodRatio MVLikelihoodRatio VariantAnnotator,VariantRecalibrator,HaplotypeCaller -MappingQualityRankSumTest MappingQualityRankSumTest MappingQualityRankSumTest UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -MappingQualityZero MappingQualityZero MappingQualityZero UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -MappingQualityZeroBySample MappingQualityZeroBySample MappingQualityZeroBySample UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -NBaseCount NBaseCount NBaseCount UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -QualByDepth QualByDepth QualByDepth UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -RMSMappingQuality RMSMappingQuality RMSMappingQuality UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -ReadPosRankSumTest ReadPosRankSumTest ReadPosRankSumTest UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -SampleList SampleList SampleList UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller -SnpEff SnpEff SnpEff VariantAnnotator,VariantRecalibrator,HaplotypeCaller -SpanningDeletions SpanningDeletions SpanningDeletions UnifiedGenotyper,VariantAnnotator,VariantRecalibrator,HaplotypeCaller
--- a/gatk2_macros.xml Sat Jun 01 07:12:31 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,379 +0,0 @@ -<macros> - <xml name="requirements"> - <requirements> - <requirement type="package">gatk2</requirement> - <requirement type="package" version="0.1.19">samtools</requirement> - <requirement type="package" version="1.56.0">picard</requirement> - <requirement type="set_environment">GATK2_PATH</requirement> - <requirement type="set_environment">GATK2_SITE_OPTIONS</requirement> - <yield /> - </requirements> - </xml> - <xml name="version_command"> - <version_command>java -jar "$GATK2_PATH/GenomeAnalysisTK.jar" --help|grep '^The Genome'</version_command> - </xml> - <token name="@THREADS@"> - --num_threads \${GALAXY_SLOTS:-4} - </token> - <token name="@VERSION@">2.8</token> - <token name="@JAR_PATH@"> - java -jar "\$GATK2_PATH/GenomeAnalysisTK.jar" - </token> - <token name="@DBSNP_OPTIONS@"> - #if $dbsnp_rod_bind_type.dbsnp_rod_bind_type_selector == 'set_dbsnp' - -d "--dbsnp:${dbsnp_rod_bind_type.dbsnp_rod_name},%(file_type)s" "${dbsnp_rod_bind_type.dbsnp_input_rod}" "${dbsnp_rod_bind_type.dbsnp_input_rod.ext}" "input_dbsnp_${dbsnp_rod_bind_type.dbsnp_rod_name}" - #end if - </token> - <token name="@BAM_INPUTS@"> - #for $i, $input_bam in enumerate( $reference_source.input_bams ): - -d "-I" "${input_bam}" "${input_bam.ext}" "gatk_input_${i}" - #if str( $input_bam.metadata.bam_index ) != "None": - -d "" "${input_bam.metadata.bam_index}" "bam_index" "gatk_input_${i}" ##hardcode galaxy ext type as bam_index - #end if - #end for - </token> - <xml name="input_variants" token_help="-input,--input &lt;input&gt;"> - <param name="input_variants" type="data" format="vcf" label="Variant file to annotate" multiple="True" min="1" help="@HELP@"/> - </xml> - <xml name="input_bams_history"> - <param name="input_bams" type="data" format="bam" label="BAM file" multiple="True" min="1" help="-I,--input_file &lt;input_file&gt;"/> - </xml> - <xml name="input_bams_cached"> - <param name="input_bams" type="data" format="bam" label="BAM file" multiple="True" min="1" 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> - </xml> - <template name="standard_gatk_options"> - ##start standard gatk options - #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $pedigree in $gatk_param_type.pedigree_files: - -p '--pedigree "${pedigree}"' - #end for - #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: - -p '--pedigreeString "${pedigree_string.pedigree_string}"' - #end for - -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' - #set default_read_filters = ['MalformedRead'] - #for $read_filter in $gatk_param_type.read_filter: - -p ' - #if $read_filter.read_filter_type.read_filter_type_selector not in $default_read_filters: - --read_filter "${read_filter.read_filter_type.read_filter_type_selector}" - #end if - #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_interval in enumerate( $gatk_param_type.input_intervals ): - -d "--intervals" "${input_interval}" "${input_interval.ext}" "input_intervals_${interval_count}" - #end for - - #for $interval_count, $input_interval in enumerate( $gatk_param_type.input_exclude_intervals ): - -d "--excludeIntervals" "${input_interval}" "${input_interval.ext}" "input_exlude_intervals_${interval_count}" - #end for - - -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' - -p '--interval_padding "${gatk_param_type.interval_padding}"' - -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 - </template> - <xml name="gatk_param_type_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"> - <param name="pedigree_files" type="data" format="txt" label="Pedigree files for samples" multiple="True" help="-ped,--pedigree &lt;pedigree&gt;"/> - <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &lt;pedigreeString&gt;"> - <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/> - </repeat> - <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information" help="-pedValidationType,--pedigreeValidationType &lt;pedigreeValidationType&gt;"> - <option value="STRICT" selected="True">STRICT</option> - <option value="SILENT">SILENT</option> - </param> - <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &lt;read_filter&gt;"> - <conditional name="read_filter_type"> - <param name="read_filter_type_selector" type="select" label="Read Filter Type"> - <option value="BadCigar">BadCigar</option> - <option value="BadMate">BadMate</option> - <option value="DuplicateRead">DuplicateRead</option> - <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option> - <option value="MalformedRead">MalformedRead</option> - <option value="MappingQuality">MappingQuality</option> - <option value="MappingQualityUnavailable">MappingQualityUnavailable</option> - <option value="MappingQualityZero">MappingQualityZero</option> - <option value="MateSameStrand">MateSameStrand</option> - <option value="MaxInsertSize">MaxInsertSize</option> - <option value="MaxReadLength" selected="True">MaxReadLength</option> - <option value="MissingReadGroup">MissingReadGroup</option> - <option value="NoOriginalQualityScores">NoOriginalQualityScores</option> - <option value="NotPrimaryAlignment">NotPrimaryAlignment</option> - <option value="Platform454">Platform454</option> - <option value="Platform">Platform</option> - <option value="PlatformUnit">PlatformUnit</option> - <option value="ReadGroupBlackList">ReadGroupBlackList</option> - <option value="ReadName">ReadName</option> - <option value="ReadStrand">ReadStrand</option> - <option value="ReassignMappingQuality">ReassignMappingQuality</option> - <option value="Sample">Sample</option> - <option value="SingleReadGroup">SingleReadGroup</option> - <option value="UnmappedRead">UnmappedRead</option> - </param> - <when value="BadCigar"> - <!-- no extra options --> - </when> - <when value="BadMate"> - <!-- no extra options --> - </when> - <when value="DuplicateRead"> - <!-- no extra options --> - </when> - <when value="FailsVendorQualityCheck"> - <!-- no extra options --> - </when> - <when value="MalformedRead"> - <param name="filter_mismatching_base_and_quals" type="boolean" truevalue="--filter_mismatching_base_and_quals" falsevalue="" checked="false" label="filter out the reads with mismatching number of bases and base qualities" help="filter out the mismatch reads instead of quitting with an error"/> - </when> - <when value="MappingQuality"> - <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/> - </when> - <when value="MappingQualityUnavailable"> - <!-- no extra options --> - </when> - <when value="MappingQualityZero"> - <!-- no extra options --> - </when> - <when value="MateSameStrand"> - <!-- no extra options --> - </when> - <when value="MaxInsertSize"> - <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/> - </when> - <when value="MaxReadLength"> - <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/> - </when> - <when value="MissingReadGroup"> - <!-- no extra options --> - </when> - <when value="NoOriginalQualityScores"> - <!-- no extra options --> - </when> - <when value="NotPrimaryAlignment"> - <!-- no extra options --> - </when> - <when value="Platform454"> - <!-- no extra options --> - </when> - <when value="Platform"> - <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/> - </when> - <when value="PlatformUnit"> - <!-- no extra options --> - </when> - <when value="ReadGroupBlackList"> - <!-- no extra options --> - </when> - <when value="ReadName"> - <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/> - </when> - <when value="ReadStrand"> - <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/> - </when> - <when value="ReassignMappingQuality"> - <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/> - </when> - <when value="Sample"> - <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/> - </when> - <when value="SingleReadGroup"> - <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/> - </when> - <when value="UnmappedRead"> - <!-- no extra options --> - </when> - </conditional> - </repeat> - <param name="input_intervals" multiple="True" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Operate on Genomic intervals" help="-L,--intervals &lt;intervals&gt;" /> - <param name="input_exclude_intervals" multiple="True" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Exclude Genomic intervals" help="-XL,--excludeIntervals &lt;excludeIntervals&gt;" /> - - <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> - <param name="interval_padding" type="integer" value="0" min="0" label="Amount of padding (in bp) to add to each interval" - help="This is typically used to add padding around exons when analyzing exomes. (--interval_padding / -ip)"/> - - <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> - </xml> - <xml name="analysis_type_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"> - <yield /> - </when> - </conditional> - </xml> - <xml name="reference_source_selector_param"> - <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> - </xml> - - <xml name="allow_n_cigar_reads"> - <param name="allow_n_cigar_reads" type="boolean" truevalue="-U ALLOW_N_CIGAR_READS" falsevalue="" - label="Allow N in CIGAR strings" help="This is required for RNA-seq data. (-U ALLOW_N_CIGAR_READS)" /> - </xml> - - <xml name="dbsnp_param"> - <conditional name="dbsnp_rod_bind_type"> - <param name="dbsnp_rod_bind_type_selector" type="select" label="Provide a dbSNP Reference-Ordered Data (ROD) file" help="-D,--dbsnp &lt;dbsnp&gt;"> - <option value="set_dbsnp" selected="True">Set dbSNP</option> - <option value="exclude_dbsnp">Don't set dbSNP</option> - </param> - <when value="exclude_dbsnp" /> - <when value="set_dbsnp"> - <param name="dbsnp_input_rod" type="data" format="vcf" label="dbSNP ROD file" /> - <param name="dbsnp_rod_name" type="text" value="dbsnp" label="dbsnp ROD name"> - <validator type="regex" message="Value must be a not empty string composed by alphanumeric characters and underscores">^\w+$</validator> - </param> - </when> - </conditional> - </xml> - <token name="@CITATION_SECTION@">------ - -**Citation** - -For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. <http://www.ncbi.nlm.nih.gov/pubmed/21478889>`_ - -If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.* - - </token> - <xml name="citations"> - <citations> - <citation type="doi">10.1038/ng.806</citation> - <citation type="doi">10.1101/gr.107524.110</citation> - <citation type="doi">10.1002/0471250953.bi1110s43</citation> - </citations> - </xml> -</macros>
--- a/gatk2_picard_index.loc.sample Sat Jun 01 07:12:31 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,26 +0,0 @@ -#This is a sample file distributed with Galaxy that enables tools -#to use a directory of Picard dict and associated files. You will need -#to create these data files and then create a picard_index.loc file -#similar to this one (store it in this directory) that points to -#the directories in which those files are stored. The picard_index.loc -#file has this format (longer white space is the TAB character): -# -#<unique_build_id> <dbkey> <display_name> <fasta_file_path> -# -#So, for example, if you had hg18 indexed and stored in -#/depot/data2/galaxy/srma/hg18/, -#then the srma_index.loc entry would look like this: -# -#hg18 hg18 hg18 Pretty /depot/data2/galaxy/picard/hg18/hg18.fa -# -#and your /depot/data2/galaxy/srma/hg18/ directory -#would contain the following three files: -#hg18.fa -#hg18.dict -#hg18.fa.fai -# -#The dictionary file for each reference (ex. hg18.dict) must be -#created via Picard (http://picard.sourceforge.net). Note that -#the dict file does not have the .fa extension although the -#path list in the loc file does include it. -#
--- a/tool_data_table_conf.xml.sample Sat Jun 01 07:12:31 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,12 +0,0 @@ -<tables> - <!-- Location of Picard dict files valid for GATK --> - <table name="gatk2_picard_indexes" comment_char="#" allow_duplicate_entries="False"> - <columns>value, dbkey, name, path</columns> - <file path="tool-data/gatk2_picard_index.loc" /> - </table> - <!-- Available of GATK references --> - <table name="gatk2_annotations" comment_char="#" allow_duplicate_entries="False"> - <columns>value, name, gatk_value, tools_valid_for</columns> - <file path="tool-data/gatk2_annotations.txt" /> - </table> -</tables>