# HG changeset patch # User lz_hust # Date 1559387307 14400 # Node ID 3a8ef2ad04143350293323c6ac7c6b7ad89269bd # Parent 5312036ae97e7d4b1648acb56ffd6131f9d0ef06 Uploaded diff -r 5312036ae97e -r 3a8ef2ad0414 base_recalibrator.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/base_recalibrator.xml Sat Jun 01 07:08:27 2019 -0400 @@ -0,0 +1,307 @@ + + 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@ + + +