view tools/gatk/count_covariates.xml @ 1:cdcb0ce84a1b

Uploaded
author xuebing
date Fri, 09 Mar 2012 19:45:15 -0500
parents 9071e359b9a3
children
line wrap: on
line source

<tool id="gatk_count_covariates" name="Count Covariates" version="0.0.1">
  <description>on BAM files</description>
  <command interpreter="python">gatk_wrapper.py
   --stdout "${output_log}"
   -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
   -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
   -p 'java 
    -jar "${GALAXY_DATA_INDEX_DIR}/shared/jars/gatk/GenomeAnalysisTK.jar"
    -T "CountCovariates"
    --num_threads 4 ##hard coded, for now
    -et "NO_ET" ##ET no phone home
    ##-log "${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 $covariates.value:
        #for $cov in $covariates.value:
            -cov "${cov}"
        #end for
    #end if
   '
    
    #set $snp_dataset_provided = False
    #if str( $input_dbsnp_rod ) != "None":
        -d "-D" "${input_dbsnp_rod}" "${input_dbsnp_rod.ext}" "dbsnp_rod"
        #set $snp_dataset_provided = True
    #end if
    #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 ) == 'snps':
            #set $snp_dataset_provided = True
        #end if
        #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
        -d "-B:${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]}"
        #if str( $rod_binding.rod_bind_type.rodToIntervalTrackName ):
            -p '--rodToIntervalTrackName "${rod_bind_name}"'
        #end if
    #end for
    
    ##start standard gatk options
    #if $gatk_param_type.gatk_param_type_selector == "advanced":
        #for $sample_metadata in $gatk_param_type.sample_metadata:
            -p '--sample_metadata "${sample_metadata.sample_metadata_file}"'
        #end for
        #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 $name not in [ "__current_case__", "read_filter_type_selector" ]:
                    --${name} "${param}"
                #end if
            #end for
            '
        #end for
        #if str( $gatk_param_type.input_intervals ) != "None":
            -d "-L" "${gatk_param_type.input_intervals}" "${gatk_param_type.input_intervals.ext}" "input_intervals"
        #end if
        #if str( $gatk_param_type.input_exclude_intervals ) != "None":
            -d "-XL" "${gatk_param_type.input_exclude_intervals}" "${gatk_param_type.input_exclude_intervals.ext}" "input_intervals"
        #end if
        
        -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"'
        -p '--downsampling_type "${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}"
        '
        #if str( $gatk_param_type.read_group_black_list ) != "None":
            -d "-read_group_black_list" "${gatk_param_type.read_group_black_list}" "txt" "input_read_group_black_list"
        #end if
    #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
  </command>
  <inputs>
    <conditional name="reference_source">
      <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
        <option value="cached">Locally cached</option>
        <option value="history">History</option>
      </param>
      <when value="cached">
        <param name="input_bam" type="data" format="bam" label="BAM file">
          <validator type="unspecified_build" />
          <validator type="dataset_metadata_in_file" filename="picard_index.loc" metadata_name="dbkey" metadata_column="1" 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">
          <options from_data_table="picard_indexes">
            <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
          </options>
        </param>
      </when>
      <when value="history"> <!-- FIX ME!!!! -->
        <param name="input_bam" type="data" format="bam" label="BAM file" />
        <param name="ref_file" type="data" format="fasta" label="Using reference file" />
      </when>
    </conditional>
    <param name="standard_covs" type="boolean" truevalue="--standard_covs" falsevalue="" label="Use the standard set of covariates in addition to the ones selected" />
    <param name="covariates" type="select" multiple="True" display="checkboxes" label="Covariates to be used in the recalibration" >
      <!-- might we want to load the available covariates from an external configuration file, since additional ones can be added to local installs? -->
      <option value="ReadGroupCovariate" />
      <option value="QualityScoreCovariate" />
      <option value="CycleCovariate" />
      <option value="DinucCovariate" />
      <!-- covariates below were pull from source code, since the list option doesn't seem to work (when tried) -->
      <option value="HomopolymerCovariate" />
      <option value="MappingQualityCovariate" />
      <option value="MinimumNQSCovariate" />
      <option value="PositionCovariate" />
      <option value="PrimerRoundCovariate" />
      <option value="TileCovariate" />
    </param>
    <param name="input_dbsnp_rod" type="data" format="gatk_dbsnp" optional="True" label="dbSNP reference ordered data (ROD)" />
    <repeat name="rod_bind" title="Binding for reference-ordered data">
        <conditional name="rod_bind_type">
	      <param name="rod_bind_type_selector" type="select" label="Binding Type">
	        <option value="snps" selected="True">SNPs</option>
	        <option value="indels">INDELs</option>
	        <option value="mask">Mask</option>
	        <option value="custom">Custom</option>
	      </param>
          <when value="snps">
              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
          </when>
          <when value="indels">
              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
          </when>
          <when value="custom">
              <param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/>
              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
          </when>
        </conditional>
    </repeat>
    
    <conditional name="gatk_param_type">
      <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options">
        <option value="basic" selected="True">Basic</option>
        <option value="advanced">Advanced</option>
      </param>
      <when value="basic">
        <!-- Do nothing here -->
      </when>
      <when value="advanced">
        <repeat name="sample_metadata" title="Sample Metadata">
            <param name="sample_metadata_file" type="data" format="txt" label="Sample file(s) in JSON format" />
        </repeat>
        <repeat name="read_filter" title="Read Filter">
            <conditional name="read_filter_type">
		      <param name="read_filter_type_selector" type="select" label="Read Filter Type">
		        <option value="MaxReadLength" selected="True">MaxReadLength</option>
		        <option value="ZeroMappingQualityRead">ZeroMappingQualityRead</option>
		      </param>
	          <when value="ZeroMappingQualityRead">
	              <!-- no extra options -->
	          </when>
	          <when value="MaxReadLength">
	              <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/>
	          </when>
            </conditional>
        </repeat>
        <param name="input_intervals" type="data" format="picard_interval_list" optional="True" label="A list of genomic intervals over which to operate" />
        <param name="input_exclude_intervals" type="data" format="picard_interval_list" optional="True" label="A list of genomic intervals to exclude from processing" />
        <param name="BTI_merge_rule" type="select" label="BTI merge rule">
          <option value="UNION" selected="True">UNION</option>
          <option value="INTERSECTION">INTERSECTION</option>
        </param>
        <conditional name="downsampling_type">
          <param name="downsampling_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="Downsampling Type">
            <option value="NONE" selected="True">NONE</option>
            <option value="ALL_READS">ALL_READS</option>
            <option value="BY_SAMPLE">BY_SAMPLE</option>
          </param>
          <when value="NONE">
	          <!-- no more options here -->
	      </when>
          <when value="ALL_READS">
	          <conditional name="downsample_to_type">
	              <param name="downsample_to_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="Downsampling Type">
	                  <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
	                  <option value="downsample_to_coverage">Downsample by Coverage</option>
	              </param>
	              <when value="downsample_to_fraction">
	                  <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="0.1"/>
	              </when>
	              <when value="downsample_to_coverage">
	                  <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0"/>
	              </when>
	          </conditional>
	      </when>
          <when value="BY_SAMPLE">
	          <conditional name="downsample_to_type">
	              <param name="downsample_to_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="Downsampling Type">
	                  <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
	                  <option value="downsample_to_coverage">Downsample by Coverage</option>
	              </param>
	              <when value="downsample_to_fraction">
	                  <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="0.1"/>
	              </when>
	              <when value="downsample_to_coverage">
	                  <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0"/>
	              </when>
	          </conditional>
	      </when>
        </conditional>
        <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine">
          <option value="OFF" selected="True">OFF</option>
          <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option>
          <option value="RECALCULATE">RECALCULATE</option>
        </param>
        <param name="baq_gap_open_penalty" type="integer" label="BAQ gap open penalty (Phred Scaled)" value="40" help="Default value is 40. 30 is perhaps better for whole genome call sets."/>
        <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" />
        <param name="default_base_qualities" type="integer" label="Value to be used for all base quality scores, when some are missing" value="-1"/>
        <param name="validation_strictness" type="select" label="How strict should we be with validation">
          <option value="STRICT" selected="True">STRICT</option>
          <option value="LENIENT">LENIENT</option>
          <option value="SILENT">SILENT</option>
        </param>
        <param name="interval_merging" type="select" label="Interval merging rule">
          <option value="ALL" selected="True">ALL</option>
          <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option>
        </param>
        <param name="read_group_black_list" type="data" format="txt" optional="True" label="Read group black list" />
      </when>
    </conditional>
    
    <conditional name="analysis_param_type">
      <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
        <option value="basic" selected="True">Basic</option>
        <option value="advanced">Advanced</option>
      </param>
      <when value="basic">
        <!-- Do nothing here -->
      </when>
      <when value="advanced">
        <conditional name="default_read_group_type">
          <param name="default_read_group_type_selector" type="select" label="Set 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">
          <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">
            <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">
          <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"/>
        <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">
              <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">
              <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="window_size_nqs" type="integer" value="5" label="Window size used by MinimumNQSCovariate"/>
        <param name="homopolymer_nback" type="integer" value="7" label="number of previous bases to look at in HomopolymerCovariate" />
      </when>
    </conditional>
  </inputs>
  <outputs>
    <data format="csv" name="output_recal" label="${tool.name} on ${on_string} (Covariate File)" />
    <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
  </outputs>
  <tests>
      <test>
          <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="input_dbsnp_rod"  />
          <param name="rod_bind_type_selector" value="snps" />
          <param name="rodToIntervalTrackName" />
          <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
          <param name="standard_covs" value="True" />
          <param name="covariates" value="ReadGroupCovariate,HomopolymerCovariate,MinimumNQSCovariate,PositionCovariate" />
          <param name="gatk_param_type_selector" value="basic" />
          <param name="analysis_param_type_selector" value="basic" />
          <output name="output_recal" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" /> 
          <output name="output_log" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.log.contains" compare="contains" />
      </test>
  </tests>
  <help>
.. 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.


------

Please cite the website "http://addlink.here" as well as:

Add citation here 2011.

------

**Input formats**

GenomeAnalysisTK: CountCovariates accepts an aligned BAM input file.

------

**Outputs**

The output is in CSV format, see http://addlink.here for more details.

-------

**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.

  </help>
</tool>