# HG changeset patch # User david-hoover # Date 1347487919 14400 # Node ID 5aded99bf002ca473022df9b4ade4133295154bf # Parent d5e8dbe8072ea94654c84253bb00bb8664cd0aa5 Uploaded diff -r d5e8dbe8072e -r 5aded99bf002 count_covariates.xml --- a/count_covariates.xml Wed Sep 12 18:10:34 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,576 +0,0 @@ - - on BAM files - - gatk - samtools - - gatk2_wrapper.py - --max_jvm_heap_fraction "1" - --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 'java - -jar "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/GenomeAnalysisTK.jar" - -T "CountCovariates" - --num_threads 4 ##hard coded, for now - -et "NO_ET" -K "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/gatk2_key_file" ##ET no phone home - ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout - #if $reference_source.reference_source_selector != "history": - -R "${reference_source.ref_file.fields.path}" - #end if - --recal_file "${output_recal}" - ${standard_covs} - #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 - - ##start standard gatk options - #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $pedigree in $gatk_param_type.pedigree: - -p '--pedigree "${pedigree.pedigree_file}"' - #end for - #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: - -p '--pedigreeString "${pedigree_string.pedigree_string}"' - #end for - -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' - #for $read_filter in $gatk_param_type.read_filter: - -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" - ###raise Exception( str( dir( $read_filter ) ) ) - #for $name, $param in $read_filter.read_filter_type.iteritems(): - #if $name not in [ "__current_case__", "read_filter_type_selector" ]: - #if hasattr( $param.input, 'truevalue' ): - ${param} - #else: - --${name} "${param}" - #end if - #end if - #end for - ' - #end for - #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ): - -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}" - #end for - - #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ): - -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" - #end for - - -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' - - -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' - #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": - -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"' - #end if - -p ' - --baq "${gatk_param_type.baq}" - --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}" - ${gatk_param_type.use_original_qualities} - --defaultBaseQualities "${gatk_param_type.default_base_qualities}" - --validation_strictness "${gatk_param_type.validation_strictness}" - --interval_merging "${gatk_param_type.interval_merging}" - ${gatk_param_type.disable_experimental_low_memory_sharding} - ${gatk_param_type.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 - - ##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/gsa/wiki/index.php/Base_quality_score_recalibration>`_. - -To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3>`_. - -If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions>`_. - ------- - -**Inputs** - -GenomeAnalysisTK: CountCovariates accepts an aligned BAM input file. - - -**Outputs** - -The output is in CSV format. - - -Go `here <http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK>`_ 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 - recal_file Filename for the outputted covariates table recalibration 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** - -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.* - - - diff -r d5e8dbe8072e -r 5aded99bf002 indel_realigner.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/indel_realigner.xml Wed Sep 12 18:11:59 2012 -0400 @@ -0,0 +1,492 @@ + + - perform local realignment + + gatk + samtools + + gatk2_wrapper.py + --max_jvm_heap_fraction "1" + --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 'java + -jar "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/GenomeAnalysisTK.jar" + -T "IndelRealigner" + -o "${output_bam}" + -et "NO_ET" -K "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/gatk2_key_file" ##ET no phone home + ##--num_threads 4 ##hard coded, for now + ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout + #if $reference_source.reference_source_selector != "history": + -R "${reference_source.ref_file.fields.path}" + #end if + -LOD "${lod_threshold}" + ${knowns_only} + ' + + #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 + #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1 + -d "-known:${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 + + ##start standard gatk options + #if $gatk_param_type.gatk_param_type_selector == "advanced": + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' + #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' + #for $read_filter in $gatk_param_type.read_filter: + -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" + ###raise Exception( str( dir( $read_filter ) ) ) + #for $name, $param in $read_filter.read_filter_type.iteritems(): + #if $name not in [ "__current_case__", "read_filter_type_selector" ]: + #if hasattr( $param.input, 'truevalue' ): + ${param} + #else: + --${name} "${param}" + #end if + #end if + #end for + ' + #end for + #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ): + -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}" + #end for + + #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ): + -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" + #end for + + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' + + -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' + #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": + -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"' + #end if + -p ' + --baq "${gatk_param_type.baq}" + --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}" + ${gatk_param_type.use_original_qualities} + --defaultBaseQualities "${gatk_param_type.default_base_qualities}" + --validation_strictness "${gatk_param_type.validation_strictness}" + --interval_merging "${gatk_param_type.interval_merging}" + ${gatk_param_type.disable_experimental_low_memory_sharding} + ${gatk_param_type.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 $reference_source.reference_source_selector == "history": + -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input" + #end if + ##end standard gatk options + ##start analysis specific options + -d "-targetIntervals" "${target_intervals}" "${target_intervals.ext}" "gatk_target_intervals" + -p ' + --disable_bam_indexing + ' + #if $analysis_param_type.analysis_param_type_selector == "advanced": + -p ' + --entropyThreshold "${analysis_param_type.entropy_threshold}" + ${analysis_param_type.simplify_bam} + --consensusDeterminationModel "${analysis_param_type.consensus_determination_model}" + --maxIsizeForMovement "${analysis_param_type.max_insert_size_for_movement}" + --maxPositionalMoveAllowed "${analysis_param_type.max_positional_move_allowed}" + --maxConsensuses "${analysis_param_type.max_consensuses}" + --maxReadsForConsensuses "${analysis_param_type.max_reads_for_consensuses}" + --maxReadsForRealignment "${analysis_param_type.max_reads_for_realignment}" + ${analysis_param_type.no_original_alignment_tags} + ' + #end if + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +**What it does** + +Performs local realignment of reads based on misalignments due to the presence of indels. Unlike most mappers, this walker uses the full alignment context to determine whether an appropriate alternate reference (i.e. indel) exists and updates SAMRecords accordingly. + +For more information on local realignment around indels using the GATK, see this `tool specific page <http://www.broadinstitute.org/gsa/wiki/index.php/Local_realignment_around_indels>`_. + +To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3>`_. + +If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions>`_. + +------ + +**Inputs** + +GenomeAnalysisTK: IndelRealigner accepts an aligned BAM and a list of intervals to realign as input files. + + +**Outputs** + +The output is in the BAM format. + + +Go `here <http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK>`_ for details on GATK file formats. + +------- + +**Settings**:: + + targetIntervals intervals file output from RealignerTargetCreator + LODThresholdForCleaning LOD threshold above which the cleaner will clean + entropyThreshold percentage of mismatches at a locus to be considered having high entropy + out Output bam + bam_compression Compression level to use for writing BAM files + disable_bam_indexing Turn off on-the-fly creation of indices for output BAM files. + simplifyBAM If provided, output BAM files will be simplified to include just key reads for downstream variation discovery analyses (removing duplicates, PF-, non-primary reads), as well stripping all extended tags from the kept reads except the read group identifier + useOnlyKnownIndels Don't run 'Smith-Waterman' to generate alternate consenses; use only known indels provided as RODs for constructing the alternate references. + maxReadsInMemory max reads allowed to be kept in memory at a time by the SAMFileWriter. Keep it low to minimize memory consumption (but the tool may skip realignment on regions with too much coverage. If it is too low, it may generate errors during realignment); keep it high to maximize realignment (but make sure to give Java enough memory). + maxIsizeForMovement maximum insert size of read pairs that we attempt to realign + maxPositionalMoveAllowed maximum positional move in basepairs that a read can be adjusted during realignment + maxConsensuses max alternate consensuses to try (necessary to improve performance in deep coverage) + maxReadsForConsensuses max reads used for finding the alternate consensuses (necessary to improve performance in deep coverage) + maxReadsForRealignment max reads allowed at an interval for realignment; if this value is exceeded, realignment is not attempted and the reads are passed to the output file(s) as-is + noOriginalAlignmentTags Don't output the original cigar or alignment start tags for each realigned read in the output bam. + +------ + +**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.* + + +