# HG changeset patch
# User lz_hust
# Date 1559387840 14400
# Node ID 68426930d59c2af6d3399e8c9eb3133ea388af7a
# Parent e4b6c7a08f06b47d4512940f2917a68adb2fe838
Deleted selected files
diff -r e4b6c7a08f06 -r 68426930d59c base_recalibrator.xml
--- 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 @@
-
- calculates covariates used to recalibrate base quality scores of reads
-
- gatk2_macros.xml
-
-
-
-
- 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
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-.. 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@
-
-
-
diff -r e4b6c7a08f06 -r 68426930d59c depth_of_coverage.xml
--- 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 @@
-
- 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@
-
-
-
diff -r e4b6c7a08f06 -r 68426930d59c gatk2_annotations.txt.sample
--- 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
diff -r e4b6c7a08f06 -r 68426930d59c gatk2_macros.xml
--- 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 @@
-
-
-
- gatk2
- samtools
- picard
- GATK2_PATH
- GATK2_SITE_OPTIONS
-
-
-
-
- java -jar "$GATK2_PATH/GenomeAnalysisTK.jar" --help|grep '^The Genome'
-
-
- --num_threads \${GALAXY_SLOTS:-4}
-
- 2.8
-
- java -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
-
-
- #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
-
-
- #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
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- ##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}" "${reference_source.ref_file.ext}" "gatk_input"
- #end if
- ##end standard gatk options
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- ^\w+$
-
-
-
-
- ------
-
-**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.*
-
-
-
-
- 10.1038/ng.806
- 10.1101/gr.107524.110
- 10.1002/0471250953.bi1110s43
-
-
-
diff -r e4b6c7a08f06 -r 68426930d59c gatk2_picard_index.loc.sample
--- 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):
-#
-#
-#
-#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.
-#
diff -r e4b6c7a08f06 -r 68426930d59c tool_data_table_conf.xml.sample
--- 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 @@
-
-
-
- value, dbkey, name, path
-
-
-
-
- value, name, gatk_value, tools_valid_for
-
-
-