# HG changeset patch # User lz_hust # Date 1559387367 14400 # Node ID dcf1482b628c45301b554758495285950ab33393 # Parent 3a8ef2ad04143350293323c6ac7c6b7ad89269bd Uploaded diff -r 3a8ef2ad0414 -r dcf1482b628c depth_of_coverage.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/depth_of_coverage.xml Sat Jun 01 07:09:27 2019 -0400 @@ -0,0 +1,731 @@ + + on BAM files + + gatk2_macros.xml + + + + 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 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'sample' in partition_type or not partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'sample' in partition_type or not partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'sample' in partition_type or not partition_type + gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] ) + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'sample' in partition_type or not partition_type + gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] ) + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + input_calculate_coverage_over_genes is not None and 'sample' in partition_type or not partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + input_calculate_coverage_over_genes is not None and 'sample' in partition_type or not partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'sample' in partition_type or not partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'sample' in partition_type or not partition_type + + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'readgroup' in partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'readgroup' in partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'readgroup' in partition_type + gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] ) + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'readgroup' in partition_type + gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] ) + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + input_calculate_coverage_over_genes is not None and 'readgroup' in partition_type or not partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + input_calculate_coverage_over_genes is not None and 'readgroup' in partition_type or not partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False + 'readgroup' in partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False + 'readgroup' in partition_type + + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'library' in partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_per_sample_stats'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'library' in partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'library' in partition_type + gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] ) + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'library' in partition_type + gatk_param_type['gatk_param_type_selector'] == "advanced" and len( gatk_param_type['input_interval_repeat'] ) + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_interval_statistics'] == False + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + input_calculate_coverage_over_genes is not None and 'library' in partition_type or not partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + input_calculate_coverage_over_genes is not None and 'library' in partition_type or not partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'library' in partition_type + + + + + + + + + + + + + + + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['omit_depth_output_at_each_base'] == False + analysis_param_type['analysis_param_type_selector'] == "basic" or analysis_param_type['print_bin_endpoints_and_exit'] == False + 'library' in partition_type + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +**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@ + + +