Mercurial > repos > devteam > unified_genotyper

comparison unified_genotyper.xml @ 0:66dd4d4c1743 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author devteam
date Tue, 01 Apr 2014 10:49:12 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:66dd4d4c1743
1 <tool id="gatk_unified_genotyper" name="Unified Genotyper" version="0.0.6">
2 <description>SNP and indel caller</description>
3 <requirements>
4 <requirement type="package" version="1.4">gatk</requirement>
5 <requirement type="package" version="0.1.18">samtools</requirement>
6 </requirements>
7 <macros>
8 <import>gatk_macros.xml</import>
9 </macros>
10 <command interpreter="python">gatk_wrapper.py
11 --max_jvm_heap_fraction "1"
12 --stdout "${output_log}"
13 #for $i, $input_bam in enumerate( $reference_source.input_bams ):
14 -d "-I" "${input_bam.input_bam}" "${input_bam.input_bam.ext}" "gatk_input_${i}"
15 #if str( $input_bam.input_bam.metadata.bam_index ) != "None":
16 -d "" "${input_bam.input_bam.metadata.bam_index}" "bam_index" "gatk_input_${i}" ##hardcode galaxy ext type as bam_index
17 #end if
18 #end for
19 -p 'java
20 -jar "\$JAVA_JAR_PATH/GenomeAnalysisTK.jar"
21 -T "UnifiedGenotyper"
22 --num_threads \${GALAXY_SLOTS:-4}
23 --out "${output_vcf}"
24 --metrics_file "${output_metrics}"
25 -et "NO_ET" ##ET no phone home
26 ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
27 #if $reference_source.reference_source_selector != "history":
28 -R "${reference_source.ref_file.fields.path}"
29 #end if
30 --genotype_likelihoods_model "${genotype_likelihoods_model}"
31 --standard_min_confidence_threshold_for_calling "${standard_min_confidence_threshold_for_calling}"
32 --standard_min_confidence_threshold_for_emitting "${standard_min_confidence_threshold_for_emitting}"
33 '
34 #set $rod_binding_names = dict()
35 #for $rod_binding in $rod_bind:
36 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
37 #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
38 #else
39 #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
40 #end if
41 #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
42 -d "--dbsnp:${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[$rod_bind_name]}"
43 #end for
44
45 #include source=$standard_gatk_options#
46 ##start analysis specific options
47 #if $analysis_param_type.analysis_param_type_selector == "advanced":
48 -p '
49 --p_nonref_model "${analysis_param_type.p_nonref_model}"
50 --heterozygosity "${analysis_param_type.heterozygosity}"
51 --pcr_error_rate "${analysis_param_type.pcr_error_rate}"
52 --genotyping_mode "${analysis_param_type.genotyping_mode_type.genotyping_mode}"
53 #if str( $analysis_param_type.genotyping_mode_type.genotyping_mode ) == 'GENOTYPE_GIVEN_ALLELES':
54 --alleles "${analysis_param_type.genotyping_mode_type.input_alleles_rod}"
55 #end if
56 --output_mode "${analysis_param_type.output_mode}"
57 ${analysis_param_type.compute_SLOD}
58 --min_base_quality_score "${analysis_param_type.min_base_quality_score}"
59 --max_deletion_fraction "${analysis_param_type.max_deletion_fraction}"
60 --max_alternate_alleles "${analysis_param_type.max_alternate_alleles}"
61 --min_indel_count_for_genotyping "${analysis_param_type.min_indel_count_for_genotyping}"
62 --indel_heterozygosity "${analysis_param_type.indel_heterozygosity}"
63 --indelGapContinuationPenalty "${analysis_param_type.indelGapContinuationPenalty}"
64 --indelGapOpenPenalty "${analysis_param_type.indelGapOpenPenalty}"
65 --indelHaplotypeSize "${analysis_param_type.indelHaplotypeSize}"
66 ${analysis_param_type.doContextDependentGapPenalties}
67 #if str( $analysis_param_type.annotation ) != "None":
68 #for $annotation in str( $analysis_param_type.annotation.fields.gatk_value ).split( ','):
69 --annotation "${annotation}"
70 #end for
71 #end if
72 #for $additional_annotation in $analysis_param_type.additional_annotations:
73 --annotation "${additional_annotation.additional_annotation_name}"
74 #end for
75 #if str( $analysis_param_type.group ) != "None":
76 #for $group in str( $analysis_param_type.group ).split( ','):
77 --group "${group}"
78 #end for
79 #end if
80 #if str( $analysis_param_type.exclude_annotations ) != "None":
81 #for $annotation in str( $analysis_param_type.exclude_annotations.fields.gatk_value ).split( ','):
82 --excludeAnnotation "${annotation}"
83 #end for
84 #end if
85 ${analysis_param_type.multiallelic}
86 '
87 ## #if str( $analysis_param_type.snpEff_rod_bind_type.snpEff_rod_bind_type_selector ) == 'set_snpEff':
88 ## -p '--annotation "SnpEff"'
89 ## -d "--snpEffFile:${analysis_param_type.snpEff_rod_bind_type.snpEff_rod_name},%(file_type)s" "${analysis_param_type.snpEff_rod_bind_type.snpEff_input_rod}" "${analysis_param_type.snpEff_rod_bind_type.snpEff_input_rod.ext}" "input_snpEff_${analysis_param_type.snpEff_rod_bind_type.snpEff_rod_name}"
90 ## #else:
91 ## -p '--excludeAnnotation "SnpEff"'
92 ## #end if
93 #end if
94 </command>
95 <inputs>
96 <conditional name="reference_source">
97 <expand macro="reference_source_selector_param" />
98 <when value="cached">
99 <repeat name="input_bams" title="BAM file" min="1" help="-I,--input_file &amp;lt;input_file&amp;gt;">
100 <param name="input_bam" type="data" format="bam" label="BAM file">
101 <validator type="unspecified_build" />
102 <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 -->
103 </param>
104 </repeat>
105 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
106 <options from_data_table="gatk_picard_indexes">
107 <!-- <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> does not yet work in a repeat...-->
108 </options>
109 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
110 </param>
111 </when>
112 <when value="history"> <!-- FIX ME!!!! -->
113 <repeat name="input_bams" title="BAM file" min="1" help="-I,--input_file &amp;lt;input_file&amp;gt;">
114 <param name="input_bam" type="data" format="bam" label="BAM file" >
115 </param>
116 </repeat>
117 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
118 </when>
119 </conditional>
120
121 <repeat name="rod_bind" title="Binding for reference-ordered data" help="-D,--dbsnp &amp;lt;dbsnp&amp;gt;">
122 <conditional name="rod_bind_type">
123 <param name="rod_bind_type_selector" type="select" label="Binding Type">
124 <option value="dbsnp" selected="True">dbSNP</option>
125 <option value="snps">SNPs</option>
126 <option value="indels">INDELs</option>
127 <option value="custom">Custom</option>
128 </param>
129 <when value="dbsnp">
130 <param name="input_rod" type="data" format="vcf" label="ROD file" />
131 </when>
132 <when value="snps">
133 <param name="input_rod" type="data" format="vcf" label="ROD file" />
134 </when>
135 <when value="indels">
136 <param name="input_rod" type="data" format="vcf" label="ROD file" />
137 </when>
138 <when value="custom">
139 <param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/>
140 <param name="input_rod" type="data" format="vcf" label="ROD file" />
141 </when>
142 </conditional>
143 </repeat>
144
145 <param name="genotype_likelihoods_model" type="select" label="Genotype likelihoods calculation model to employ" help="-glm,--genotype_likelihoods_model &amp;lt;genotype_likelihoods_model&amp;gt;">
146 <option value="BOTH" selected="True">BOTH</option>
147 <option value="SNP">SNP</option>
148 <option value="INDEL">INDEL</option>
149 </param>
150
151 <param name="standard_min_confidence_threshold_for_calling" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called" help="-stand_call_conf,--standard_min_confidence_threshold_for_calling &amp;lt;standard_min_confidence_threshold_for_calling&amp;gt;" />
152 <param name="standard_min_confidence_threshold_for_emitting" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)" help="-stand_emit_conf,--standard_min_confidence_threshold_for_emitting &amp;lt;standard_min_confidence_threshold_for_emitting&amp;gt;" />
153
154
155 <expand macro="gatk_param_type_conditional" />
156
157 <expand macro="analysis_type_conditional">
158 <param name="p_nonref_model" type="select" label="Non-reference probability calculation model to employ" help="-pnrm,--p_nonref_model &amp;lt;p_nonref_model&amp;gt;">
159 <option value="EXACT" selected="True">EXACT</option>
160 <option value="GRID_SEARCH">GRID_SEARCH</option>
161 </param>
162 <param name="heterozygosity" type="float" value="1e-3" label="Heterozygosity value used to compute prior likelihoods for any locus" help="-hets,--heterozygosity &amp;lt;heterozygosity&amp;gt;" />
163 <param name="pcr_error_rate" type="float" value="1e-4" label="The PCR error rate to be used for computing fragment-based likelihoods" help="-pcr_error,--pcr_error_rate &amp;lt;pcr_error_rate&amp;gt;" />
164 <conditional name="genotyping_mode_type">
165 <param name="genotyping_mode" type="select" label="How to determine the alternate allele to use for genotyping" help="-gt_mode,--genotyping_mode &amp;lt;genotyping_mode&amp;gt;">
166 <option value="DISCOVERY" selected="True">DISCOVERY</option>
167 <option value="GENOTYPE_GIVEN_ALLELES">GENOTYPE_GIVEN_ALLELES</option>
168 </param>
169 <when value="DISCOVERY">
170 <!-- Do nothing here -->
171 </when>
172 <when value="GENOTYPE_GIVEN_ALLELES">
173 <param name="input_alleles_rod" type="data" format="vcf" label="Alleles ROD file" help="-alleles,--alleles &amp;lt;alleles&amp;gt;" />
174 </when>
175 </conditional>
176 <param name="output_mode" type="select" label="Should we output confident genotypes (i.e. including ref calls) or just the variants?" help="-out_mode,--output_mode &amp;lt;output_mode&amp;gt;">
177 <option value="EMIT_VARIANTS_ONLY" selected="True">EMIT_VARIANTS_ONLY</option>
178 <option value="EMIT_ALL_CONFIDENT_SITES">EMIT_ALL_CONFIDENT_SITES</option>
179 <option value="EMIT_ALL_SITES">EMIT_ALL_SITES</option>
180 </param>
181 <param name="compute_SLOD" type="boolean" truevalue="--computeSLOD" falsevalue="" label="Compute the SLOD" help="--computeSLOD" />
182 <param name="min_base_quality_score" type="integer" value="17" label="Minimum base quality required to consider a base for calling" help="-mbq,--min_base_quality_score &amp;lt;min_base_quality_score&amp;gt;" />
183 <param name="max_deletion_fraction" type="float" value="0.05" label="Maximum fraction of reads with deletions spanning this locus for it to be callable" help="to disable, set to &lt; 0 or &gt; 1 (-deletions,--max_deletion_fraction &amp;lt;max_deletion_fraction&amp;gt;)" />
184 <param name="max_alternate_alleles" type="integer" value="5" label="Maximum number of alternate alleles to genotype" help="-maxAlleles,--max_alternate_alleles &amp;lt;max_alternate_alleles&amp;gt;" />
185 <param name="min_indel_count_for_genotyping" type="integer" value="5" label="Minimum number of consensus indels required to trigger genotyping run" help="-minIndelCnt,--min_indel_count_for_genotyping &amp;lt;min_indel_count_for_genotyping&amp;gt;" />
186 <param name="indel_heterozygosity" type="float" value="0.000125" label="Heterozygosity for indel calling" help="1.0/8000==0.000125 (-indelHeterozygosity,--indel_heterozygosity &amp;lt;indel_heterozygosity&amp;gt;)"/>
187 <param name="indelGapContinuationPenalty" type="float" value="10.0" label="Indel gap continuation penalty" help="--indelGapContinuationPenalty" />
188 <param name="indelGapOpenPenalty" type="float" value="45.0" label="Indel gap open penalty" help="--indelGapOpenPenalty" />
189 <param name="indelHaplotypeSize" type="integer" value="80" label="Indel haplotype size" help="--indelHaplotypeSize" />
190 <param name="doContextDependentGapPenalties" type="boolean" truevalue="--doContextDependentGapPenalties" falsevalue="" label="Vary gap penalties by context" help="--doContextDependentGapPenalties" />
191 <param name="annotation" type="select" multiple="True" display="checkboxes" label="Annotation Types" help="-A,--annotation &amp;lt;annotation&amp;gt;">
192 <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs -->
193 <options from_data_table="gatk_annotations">
194 <filter type="multiple_splitter" column="tools_valid_for" separator=","/>
195 <filter type="static_value" value="UnifiedGenotyper" column="tools_valid_for"/>
196 </options>
197 </param>
198 <repeat name="additional_annotations" title="Additional annotation" help="-A,--annotation &amp;lt;annotation&amp;gt;">
199 <param name="additional_annotation_name" type="text" value="" label="Annotation name" />
200 </repeat>
201 <!--
202 <conditional name="snpEff_rod_bind_type">
203 <param name="snpEff_rod_bind_type_selector" type="select" label="Provide a snpEff reference-ordered data file">
204 <option value="set_snpEff">Set snpEff</option>
205 <option value="exclude_snpEff" selected="True">Don't set snpEff</option>
206 </param>
207 <when value="exclude_snpEff">
208 </when>
209 <when value="set_snpEff">
210 <param name="snpEff_input_rod" type="data" format="vcf" label="ROD file" />
211 <param name="snpEff_rod_name" type="hidden" value="snpEff" label="ROD Name"/>
212 </when>
213 </conditional>
214 -->
215 <param name="group" type="select" multiple="True" display="checkboxes" label="Annotation Interfaces/Groups" help="-G,--group &amp;lt;group&amp;gt;">
216 <option value="RodRequiringAnnotation">RodRequiringAnnotation</option>
217 <option value="Standard">Standard</option>
218 <option value="Experimental">Experimental</option>
219 <option value="WorkInProgress">WorkInProgress</option>
220 <option value="RankSumTest">RankSumTest</option>
221 <!-- <option value="none">none</option> -->
222 </param>
223 <!-- <param name="family_string" type="text" value="" label="Family String"/> -->
224 <param name="exclude_annotations" type="select" multiple="True" display="checkboxes" label="Annotations to exclude" help="-XA,--excludeAnnotation &amp;lt;excludeAnnotation&amp;gt;" >
225 <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs -->
226 <options from_data_table="gatk_annotations">
227 <filter type="multiple_splitter" column="tools_valid_for" separator=","/>
228 <filter type="static_value" value="UnifiedGenotyper" column="tools_valid_for"/>
229 </options>
230 </param>
231 <param name="multiallelic" type="boolean" truevalue="--multiallelic" falsevalue="" label="Allow the discovery of multiple alleles (SNPs only)" help="--multiallelic" />
232 </expand>
233 </inputs>
234 <outputs>
235 <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (VCF)" />
236 <data format="txt" name="output_metrics" label="${tool.name} on ${on_string} (metrics)" />
237 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
238 </outputs>
239 <trackster_conf/>
240 <tests>
241 <test>
242 <param name="reference_source_selector" value="history" />
243 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
244 <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" />
245 <param name="rod_bind_type_selector" value="dbsnp" />
246 <param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" />
247 <param name="standard_min_confidence_threshold_for_calling" value="0" />
248 <param name="standard_min_confidence_threshold_for_emitting" value="4" />
249 <param name="gatk_param_type_selector" value="basic" />
250 <param name="analysis_param_type_selector" value="advanced" />
251 <param name="genotype_likelihoods_model" value="BOTH" />
252 <param name="p_nonref_model" value="EXACT" />
253 <param name="heterozygosity" value="0.001" />
254 <param name="pcr_error_rate" value="0.0001" />
255 <param name="genotyping_mode" value="DISCOVERY" />
256 <param name="output_mode" value="EMIT_ALL_CONFIDENT_SITES" />
257 <param name="compute_SLOD" />
258 <param name="min_base_quality_score" value="17" />
259 <param name="max_deletion_fraction" value="-1" />
260 <param name="min_indel_count_for_genotyping" value="2" />
261 <param name="indel_heterozygosity" value="0.000125" />
262 <param name="indelGapContinuationPenalty" value="10" />
263 <param name="indelGapOpenPenalty" value="3" />
264 <param name="indelHaplotypeSize" value="80" />
265 <param name="doContextDependentGapPenalties" />
266 <!-- <param name="annotation" value="" />
267 <param name="group" value="" /> -->
268 <output name="output_vcf" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.vcf" lines_diff="4" />
269 <output name="output_metrics" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.metrics" />
270 <output name="output_log" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.log.contains" compare="contains" />
271 </test>
272 </tests>
273 <help>
274 **What it does**
275
276 A variant caller which unifies the approaches of several disparate callers. Works for single-sample and multi-sample data. The user can choose from several different incorporated calculation models.
277
278 For more information on the GATK Unified Genotyper, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Unified_genotyper&gt;`_.
279
280 To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
281
282 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
283
284 ------
285
286 **Inputs**
287
288 GenomeAnalysisTK: UnifiedGenotyper accepts an aligned BAM input file.
289
290
291 **Outputs**
292
293 The output is in VCF format.
294
295
296 Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
297
298 -------
299
300 **Settings**::
301
302 genotype_likelihoods_model Genotype likelihoods calculation model to employ -- BOTH is the default option, while INDEL is also available for calling indels and SNP is available for calling SNPs only (SNP|INDEL|BOTH)
303 p_nonref_model Non-reference probability calculation model to employ -- EXACT is the default option, while GRID_SEARCH is also available. (EXACT|GRID_SEARCH)
304 heterozygosity Heterozygosity value used to compute prior likelihoods for any locus
305 pcr_error_rate The PCR error rate to be used for computing fragment-based likelihoods
306 genotyping_mode Should we output confident genotypes (i.e. including ref calls) or just the variants? (DISCOVERY|GENOTYPE_GIVEN_ALLELES)
307 output_mode Should we output confident genotypes (i.e. including ref calls) or just the variants? (EMIT_VARIANTS_ONLY|EMIT_ALL_CONFIDENT_SITES|EMIT_ALL_SITES)
308 standard_min_confidence_threshold_for_calling The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called
309 standard_min_confidence_threshold_for_emitting The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)
310 noSLOD If provided, we will not calculate the SLOD
311 min_base_quality_score Minimum base quality required to consider a base for calling
312 max_deletion_fraction Maximum fraction of reads with deletions spanning this locus for it to be callable [to disable, set to &lt; 0 or &gt; 1; default:0.05]
313 min_indel_count_for_genotyping Minimum number of consensus indels required to trigger genotyping run
314 indel_heterozygosity Heterozygosity for indel calling
315 indelGapContinuationPenalty Indel gap continuation penalty
316 indelGapOpenPenalty Indel gap open penalty
317 indelHaplotypeSize Indel haplotype size
318 doContextDependentGapPenalties Vary gap penalties by context
319 indel_recal_file Filename for the input covariates table recalibration .csv file - EXPERIMENTAL, DO NO USE
320 indelDebug Output indel debug info
321 out File to which variants should be written
322 annotation One or more specific annotations to apply to variant calls
323 group One or more classes/groups of annotations to apply to variant calls
324
325 @CITATION_SECTION@
326 </help>
327 </tool>