/tools/gatk/table_recalibration.xml
https://bitbucket.org/cistrome/cistrome-harvard/ · XML · 232 lines · 209 code · 20 blank · 3 comment · 0 complexity · f80798fcdf7fd711945ce167933e9285 MD5 · raw file
- <tool id="gatk_table_recalibration" name="Table Recalibration" version="0.0.5">
- <description>on BAM files</description>
- <requirements>
- <requirement type="package" version="1.4">gatk</requirement>
- <requirement type="package">samtools</requirement>
- </requirements>
- <macros>
- <import>gatk_macros.xml</import>
- </macros>
- <command interpreter="python">gatk_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 "${GALAXY_DATA_INDEX_DIR}/shared/jars/gatk/GenomeAnalysisTK.jar"
- -T "TableRecalibration"
- -o "${output_bam}"
- -et "NO_ET" ##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
- --recal_file "${input_recal}"
- --disable_bam_indexing
- '
- #include source=$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
- ${analysis_param_type.simplify_bam}
- --preserve_qscores_less_than "${analysis_param_type.preserve_qscores_less_than}"
- --smoothing "${analysis_param_type.smoothing}"
- --max_quality_score "${analysis_param_type.max_quality_score}"
- --window_size_nqs "${analysis_param_type.window_size_nqs}"
- --homopolymer_nback "${analysis_param_type.homopolymer_nback}"
- ${analysis_param_type.do_not_write_original_quals}
- '
- #end if
- </command>
- <inputs>
- <param name="input_recal" type="data" format="csv" label="Covariates table recalibration file" help="-recalFile,--recal_file &lt;recal_file&gt;" />
- <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="gatk_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="gatk_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>
-
- <expand macro="gatk_param_type_conditional" />
-
-
- <expand macro="analysis_type_conditional">
- <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="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM" help="-simplifyBAM,--simplifyBAM"/>
- <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;" />
- <param name="preserve_qscores_less_than" type="integer" value="5" label="Bases with quality scores less than this threshold won't be recalibrated" help="-pQ,--preserve_qscores_less_than &lt;preserve_qscores_less_than&gt;"/>
- <param name="smoothing" type="integer" value="1" label="smoothing" help="-sm,--smoothing &lt;smoothing&gt;"/>
- <param name="max_quality_score" type="integer" value="50" label="Max quality score" help="-maxQ,--max_quality_score &lt;max_quality_score&gt;"/>
- <param name="do_not_write_original_quals" type="boolean" checked="False" truevalue="--doNotWriteOriginalQuals" falsevalue="" label="Do Not Write Original Quality tag" help="-noOQs,--doNotWriteOriginalQuals"/>
- </expand>
- </inputs>
- <outputs>
- <data format="bam" name="output_bam" label="${tool.name} on ${on_string} (BAM)" />
- <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
- </outputs>
- <tests>
- <test>
- <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" />
- <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="gatk_param_type_selector" value="basic" />
- <param name="analysis_param_type_selector" value="basic" />
- <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" />
- <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" />
- </test>
- </tests>
- <help>
- **What it does**
- This walker is designed to work as the second pass in a two-pass processing step, doing a by-read traversal. For each base in each read this walker calculates various user-specified covariates (such as read group, reported quality score, cycle, and dinuc) Using these values as a key in a large hashmap the walker calculates an empirical base quality score and overwrites the quality score currently in the read. This walker then outputs a new bam file with these updated (recalibrated) reads. Note: This walker expects as input the recalibration table file generated previously by CovariateCounterWalker. Note: This walker is designed to be used in conjunction with CovariateCounterWalker.
- 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: TableRecalibration accepts an aligned BAM and a recalibration CSV input files.
- **Outputs**
- The output is in BAM 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 BAM file
- 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
- preserve_qscores_less_than Bases with quality scores less than this threshold won't be recalibrated, default=5. In general it's unsafe to change qualities scores below < 5, since base callers use these values to indicate random or bad bases
- smoothing Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1
- max_quality_score The integer value at which to cap the quality scores, default=50
- doNotWriteOriginalQuals If true, we will not write the original quality (OQ) tag for each read
- @CITATION_SECTION@
- </help>
- </tool>