Mercurial > repos > iuc > gatk2
annotate haplotype_caller.xml @ 6:35c00763cb5c draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
author | iuc |
---|---|
date | Mon, 04 Jun 2018 05:38:15 -0400 |
parents | f244b8209eb8 |
children |
rev | line source |
---|---|
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
1 <tool id="gatk2_haplotype_caller" name="Haplotype Caller" version="@VERSION@.2"> |
0 | 2 <description>Call SNPs and indels simultaneously via local de-novo assembly of haplotypes in an active region</description> |
3 <macros> | |
4 <import>gatk2_macros.xml</import> | |
5 </macros> | |
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
6 <expand macro="requirements" /> |
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
7 <expand macro="version_command" /> |
0 | 8 <command interpreter="python"> |
9 gatk2_wrapper.py | |
10 --stdout "${output_log}" | |
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
11 @BAM_INPUTS@ |
0 | 12 -p ' |
13 @JAR_PATH@ | |
14 -T "HaplotypeCaller" | |
15 -o "${output_vcf}" | |
16 | |
17 \$GATK2_SITE_OPTIONS | |
18 | |
2 | 19 --num_cpu_threads_per_data_thread \${GALAXY_SLOTS:-4} |
0 | 20 |
21 #if $reference_source.reference_source_selector != "history": | |
22 -R "${reference_source.ref_file.fields.path}" | |
23 #end if | |
24 #if str($input_recal) != 'None': | |
25 --BQSR "${input_recal}" | |
26 #end if | |
27 ' | |
2 | 28 @DBSNP_OPTIONS@ |
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
29 $allow_n_cigar_reads |
0 | 30 #include source=$standard_gatk_options# |
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
31 |
0 | 32 ##start analysis specific options |
33 #if $analysis_param_type.analysis_param_type_selector == "advanced": | |
34 -p ' | |
35 #if $analysis_param_type.heterozygosity.__str__.strip() != '': | |
36 --heterozygosity $analysis_param_type.heterozygosity | |
37 #end if | |
38 --genotyping_mode "${analysis_param_type.genotyping_mode_type.genotyping_mode}" | |
39 #if str( $analysis_param_type.genotyping_mode_type.genotyping_mode ) == 'GENOTYPE_GIVEN_ALLELES': | |
40 --alleles "${analysis_param_type.genotyping_mode_type.input_alleles_rod}" | |
41 #end if | |
2 | 42 #if not $analysis_param_type.emitRefConfidence is None: |
43 --emitRefConfidence $analysis_param_type.emitRefConfidence | |
0 | 44 #end if |
45 | |
46 ## files | |
47 #if str($analysis_param_type.activeRegionIn) != 'None': | |
48 --activeRegionIn "$analysis_param_type.activeRegionIn" | |
49 #end if | |
50 #if str($analysis_param_type.comp) != 'None': | |
51 --comp "$analysis_param_type.comp" | |
52 #end if | |
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
53 ## |
0 | 54 #if str( $analysis_param_type.annotation ) != "None": |
55 #for $annotation in str( $analysis_param_type.annotation.fields.gatk_value ).split( ','): | |
56 --annotation "${annotation}" | |
57 #end for | |
58 #end if | |
59 #for $additional_annotation in $analysis_param_type.additional_annotations: | |
60 --annotation "${additional_annotation.additional_annotation_name}" | |
61 #end for | |
62 #if str( $analysis_param_type.group ) != "None": | |
63 #for $group in str( $analysis_param_type.group ).split( ','): | |
64 --group "${group}" | |
65 #end for | |
66 #end if | |
67 #if str( $analysis_param_type.exclude_annotations ) != "None": | |
68 #for $annotation in str( $analysis_param_type.exclude_annotations.fields.gatk_value ).split( ','): | |
69 --excludeAnnotation "${annotation}" | |
70 #end for | |
71 #end if | |
72 | |
73 ## value setings | |
74 #if $analysis_param_type.contamination_fraction_to_filter.__str__.strip() != '': | |
75 --contamination_fraction_to_filter $analysis_param_type.contamination_fraction_to_filter | |
76 #end if | |
77 #if $analysis_param_type.minPruning.__str__.strip() != '': | |
78 --minPruning $analysis_param_type.minPruning | |
79 #end if | |
80 #if $analysis_param_type.standard_min_confidence_threshold_for_calling.__str__.strip() != '': | |
81 --standard_min_confidence_threshold_for_calling $analysis_param_type.standard_min_confidence_threshold_for_calling | |
82 #end if | |
83 #if $analysis_param_type.standard_min_confidence_threshold_for_emitting.__str__.strip() != '': | |
84 --standard_min_confidence_threshold_for_emitting $analysis_param_type.standard_min_confidence_threshold_for_emitting | |
85 #end if | |
86 #if $analysis_param_type.gcpHMM.__str__.strip() != '': | |
87 --gcpHMM $analysis_param_type.gcpHMM | |
88 #end if | |
89 #if $analysis_param_type.max_alternate_alleles.__str__.strip() != '': | |
90 --max_alternate_alleles $analysis_param_type.max_alternate_alleles | |
91 #end if | |
92 ## mode selections | |
2 | 93 |
0 | 94 #if $analysis_param_type.pair_hmm_implementation.__str__ != "None" and len($analysis_param_type.pair_hmm_implementation.__str__) > 0: |
95 --pair_hmm_implementation $analysis_param_type.pair_hmm_implementation | |
96 #end if | |
97 ## optional outputs | |
98 #if $analysis_param_type.activeRegionOut: | |
99 --activeRegionOut $active_region_out | |
100 #end if | |
101 #if $analysis_param_type.graphOutput: | |
102 --graphOutput $graph_out | |
103 #end if | |
104 ## flags | |
105 $analysis_param_type.useAllelesTrigger | |
106 $analysis_param_type.fullHaplotype | |
107 $analysis_param_type.genotypeFullActiveRegion | |
108 $analysis_param_type.debug | |
109 ' | |
110 #end if | |
111 </command> | |
112 <inputs> | |
2 | 113 <param name="input_recal" type="data" format="gatk_report" optional="true" label="Covariates table recalibration file" help="The input covariates table file which enables on-the-fly base quality score recalibration. Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool. Please be aware that one should only run recalibration with the covariates file created on the same input bam(s) (-BQSR,--BQSR &lt;recal_file&gt;)" /> |
0 | 114 <conditional name="reference_source"> |
115 <expand macro="reference_source_selector_param" /> | |
116 <when value="cached"> | |
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
117 <expand macro="input_bams_cached" /> |
0 | 118 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &lt;reference_sequence&gt;" > |
119 <options from_data_table="gatk2_picard_indexes"> | |
2 | 120 <!-- <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/> does not yet work in a repeat...--> |
0 | 121 </options> |
122 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> | |
123 </param> | |
124 </when> | |
125 <when value="history"> | |
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
126 <expand macro="input_bams_history" /> |
2 | 127 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;" /> |
0 | 128 </when> |
129 </conditional> | |
2 | 130 <expand macro="dbsnp_param" /> |
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
131 |
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
132 <expand macro="allow_n_cigar_reads" /> |
0 | 133 <expand macro="gatk_param_type_conditional" /> |
134 | |
135 <conditional name="analysis_param_type"> | |
136 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options"> | |
137 <option value="basic" selected="True">Basic</option> | |
138 <option value="advanced">Advanced</option> | |
139 </param> | |
140 <when value="basic"> | |
141 <!-- Do nothing here --> | |
142 </when> | |
143 <when value="advanced"> | |
144 | |
145 <param name="activeRegionIn" type="data" format="bed,gatk_interval,picard_interval_list,vcf" optional="true" label="activeRegionIn" help="--activeRegionIn / -AR Use this interval list file as the active regions to process"/> | |
146 <param name="activeRegionOut" type="boolean" checked="False" truevalue="" falsevalue="" label="activeRegionOut" help="--activeRegionOut / -ARO Output the active region to an interval list file"/> | |
147 | |
148 <param name="annotation" type="select" multiple="True" display="checkboxes" label="Annotation Types" help="-A,--annotation &lt;annotation&gt;"> | |
149 <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs --> | |
150 <options from_data_table="gatk2_annotations"> | |
151 <filter type="multiple_splitter" column="tools_valid_for" separator=","/> | |
4 | 152 <filter type="static_value" value="HaplotypeCaller" column="tools_valid_for"/> |
0 | 153 </options> |
154 </param> | |
155 <repeat name="additional_annotations" title="Additional annotation" help="-A,--annotation &lt;annotation&gt;"> | |
156 <param name="additional_annotation_name" type="text" value="" label="Annotation name" /> | |
157 </repeat> | |
158 <!-- | |
159 <conditional name="snpEff_rod_bind_type"> | |
160 <param name="snpEff_rod_bind_type_selector" type="select" label="Provide a snpEff reference-ordered data file"> | |
161 <option value="set_snpEff">Set snpEff</option> | |
162 <option value="exclude_snpEff" selected="True">Don't set snpEff</option> | |
163 </param> | |
164 <when value="exclude_snpEff"> | |
165 </when> | |
166 <when value="set_snpEff"> | |
167 <param name="snpEff_input_rod" type="data" format="vcf" label="ROD file" /> | |
168 <param name="snpEff_rod_name" type="hidden" value="snpEff" label="ROD Name"/> | |
169 </when> | |
170 </conditional> | |
171 --> | |
172 <param name="group" type="select" multiple="True" display="checkboxes" label="Annotation Interfaces/Groups" help="-G,--group &lt;group&gt;"> | |
173 <option value="RodRequiringAnnotation">RodRequiringAnnotation</option> | |
174 <option value="Standard">Standard</option> | |
175 <option value="Experimental">Experimental</option> | |
176 <option value="WorkInProgress">WorkInProgress</option> | |
177 <option value="RankSumTest">RankSumTest</option> | |
178 <!-- <option value="none">none</option> --> | |
179 </param> | |
180 <!-- <param name="family_string" type="text" value="" label="Family String"/> --> | |
181 <param name="exclude_annotations" type="select" multiple="True" display="checkboxes" label="Annotations to exclude" help="-XA,--excludeAnnotation &lt;excludeAnnotation&gt;" > | |
182 <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs --> | |
183 <options from_data_table="gatk2_annotations"> | |
184 <filter type="multiple_splitter" column="tools_valid_for" separator=","/> | |
4 | 185 <filter type="static_value" value="HaplotypeCaller" column="tools_valid_for"/> |
0 | 186 </options> |
187 </param> | |
188 | |
189 <param name="comp" type="data" format="vcf" optional="true" label="comp" help="--comp / -comp comparison VCF file"/> | |
190 <param name="contamination_fraction_to_filter" type="float" value="0.05" optional="true" label="contamination_fraction_to_filter" help="--contamination_fraction_to_filter / -contamination Fraction of contamination in sequencing data (for all samples) to aggressively remove"> | |
191 <validator type="in_range" message="value between 0.00 and 1.00" min="0" max="1"/> | |
192 </param> | |
193 <param name="debug" type="boolean" checked="False" truevalue="-debug" falsevalue="" label="debug" help="--debug / -debug If specified, print out very verbose debug information about each triggering active region"/> | |
194 | |
195 <conditional name="genotyping_mode_type"> | |
196 <param name="genotyping_mode" type="select" label="How to determine the alternate allele to use for genotyping" help="-gt_mode,--genotyping_mode &lt;genotyping_mode&gt;"> | |
197 <option value="DISCOVERY" selected="True">DISCOVERY</option> | |
198 <option value="GENOTYPE_GIVEN_ALLELES">GENOTYPE_GIVEN_ALLELES</option> | |
199 </param> | |
200 <when value="DISCOVERY"> | |
201 <!-- Do nothing here --> | |
202 </when> | |
203 <when value="GENOTYPE_GIVEN_ALLELES"> | |
204 <param name="input_alleles_rod" type="data" format="vcf" label="Alleles ROD file" help="-alleles,--alleles &lt;alleles&gt;" /> | |
205 </when> | |
206 </conditional> | |
207 <param name="graphOutput" type="boolean" checked="False" truevalue="" falsevalue="" label="graphOutput" help="--graphOutput / -graph File to which debug assembly graph information should be written"/> | |
208 <param name="heterozygosity" type="float" value="0.0010" optional="true" label="heterozygosity" help="--heterozygosity / -hets Heterozygosity value used to compute prior likelihoods for any locus"/> | |
209 <param name="minPruning" type="integer" value="1" optional="true" label="minPruning" help="--minPruning / -minPruning The minimum allowed pruning factor in assembly graph. Paths with >= X supporting kmers are pruned from the graph"> | |
210 <validator type="in_range" message="value between 0 and 127" min="0" max="127"/> | |
211 </param> | |
2 | 212 <!-- http://www.broadinstitute.org/gatk/guide/article?id=2940 --> |
213 <param name="emitRefConfidence" type="select" optional="true" label="Output confidence estimates" help="Emitting a per-bp or summarized confidence estimate for a site being strictly homozygous-reference (--emitRefConfidence)"> | |
214 <option value="NONE" selected="True">don't emit anything</option> | |
215 <option value="BP_RESOLUTION">BP_RESOLUTION (emit detailed information for each BP)</option> | |
216 <option value="GVCF">GVCF (emit a block summarized version of the BP_RESOLUTION data)</option> | |
0 | 217 </param> |
218 <param name="pair_hmm_implementation" type="select" optional="true" label="pair_hmm_implementation" help="--pair_hmm_implementation / -pairHMM The PairHMM implementation to use for genotype likelihood calculations"> | |
219 <option value="EXACT">EXACT</option> | |
220 <option value="ORIGINAL">ORIGINAL</option> | |
221 <option value="CACHING">CACHING</option> | |
222 <option value="LOGLESS_CACHING" selected="True">LOGLESS_CACHING</option> | |
223 </param> | |
224 <param name="standard_min_confidence_threshold_for_calling" type="float" value="30.0" optional="true" label="standard_min_confidence_threshold_for_calling" help="--standard_min_confidence_threshold_for_calling / -stand_call_conf The minimum phred-scaled confidence threshold at which variants should be called"/> | |
225 <param name="standard_min_confidence_threshold_for_emitting" type="float" value="30.0" optional="true" label="standard_min_confidence_threshold_for_emitting" help="--standard_min_confidence_threshold_for_emitting / -stand_emit_conf The minimum phred-scaled confidence threshold at which variants should be emitted (and filtered with LowQual if less than the calling threshold)"/> | |
226 <param name="useAllelesTrigger" type="boolean" checked="False" truevalue="-allelesTrigger" falsevalue="" label="useAllelesTrigger" help="--useAllelesTrigger / -allelesTrigger If specified, use additional trigger on variants found in an external alleles file"/> | |
227 <param name="fullHaplotype" type="boolean" checked="False" truevalue="-fullHaplotype" falsevalue="" label="fullHaplotype" help="--fullHaplotype / -fullHaplotype If specified, output the full haplotype sequence instead of converting to individual variants w.r.t. the reference"/> | |
228 <param name="gcpHMM" type="integer" value="10" optional="true" label="gcpHMM" help="--gcpHMM / -gcpHMM Flat gap continuation penalty for use in the Pair HMM"/> | |
229 <param name="genotypeFullActiveRegion" type="boolean" checked="False" truevalue="-genotypeFullActiveRegion" falsevalue="" label="genotypeFullActiveRegion" help="--genotypeFullActiveRegion / -genotypeFullActiveRegion If specified, alternate alleles are considered to be the full active region for the purposes of genotyping"/> | |
230 <param name="max_alternate_alleles" type="integer" value="6" optional="true" label="max_alternate_alleles" help="--max_alternate_alleles / -maxAltAlleles Maximum number of alternate alleles to genotype"/> | |
231 </when> | |
232 </conditional> | |
233 </inputs> | |
234 <outputs> | |
235 <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (VCF)" /> | |
236 <data format="vcf" name="graph_out" label="${tool.name} on ${on_string} graph" > | |
237 <filter>analysis_param_type['analysis_param_type_selector'] == "advanced" and analysis_param_type['graphOutput'] == True</filter> | |
238 </data> | |
239 <data format="vcf" name="active_region_out" label="${tool.name} on ${on_string} activeRegion" > | |
240 <filter>analysis_param_type['analysis_param_type_selector'] == "advanced" and analysis_param_type['activeRegionOut'] == True</filter> | |
241 </data> | |
242 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> | |
243 </outputs> | |
244 <tests> | |
245 <test> | |
6
35c00763cb5c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33
iuc
parents:
4
diff
changeset
|
246 <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" /> |
0 | 247 <param name="reference_source_selector" value="history" /> |
248 <param name="ref_file" value="phiX.fasta" ftype="fasta" /> | |
249 <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" /> | |
250 <param name="gatk_param_type_selector" value="basic" /> | |
251 <param name="analysis_param_type_selector" value="basic" /> | |
252 <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" /> | |
253 <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" /> | |
254 </test> | |
255 </tests> | |
256 <help> | |
257 **What it does** | |
258 | |
259 **HaplotypeCaller** | |
260 calls SNPs and indels simultaneously via local de-novo assembly of haplotypes in an active region. | |
261 Haplotypes are evaluated using an affine gap penalty Pair HMM. | |
262 | |
263 For more information on using read based compression in the GATK, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_haplotypecaller_HaplotypeCaller.html>`_. | |
264 | |
265 To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gatk/guide/topic?name=best-practices>`_. | |
266 | |
267 If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gatk/guide/topic?name=faqs>`_. | |
268 | |
269 ------ | |
270 | |
271 **Inputs** | |
272 | |
273 GenomeAnalysisTK: PrintReads accepts aligned BAM files. | |
274 | |
275 | |
276 **Outputs** | |
277 | |
278 The output is a VCF file with raw, unrecalibrated SNP and indel calls. | |
279 | |
280 | |
281 Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. | |
282 | |
283 ------- | |
284 | |
285 **Settings**:: | |
286 | |
287 activeRegionIn Use this interval list file as the active regions to process | |
288 activeRegionOut Output the active region to this interval list file | |
289 alleles The set of alleles at which to genotype when --genotyping_mode is GENOTYPE_GIVEN_ALLELES | |
290 annotation One or more specific annotations to apply to variant calls | |
291 comp comparison VCF file | |
292 contamination Fraction of contamination in sequencing data (for all samples) to aggressively remove | |
293 dbsnp dbSNP file | |
294 debug If specified, print out very verbose debug information about each triggering active region | |
295 excludeAnnotation One or more specific annotations to exclude | |
296 genotyping_mode Specifies how to determine the alternate alleles to use for genotyping | |
297 graphOutput File to which debug assembly graph information should be written | |
298 group One or more classes/groups of annotations to apply to variant calls | |
299 heterozygosity Heterozygosity value used to compute prior likelihoods for any locus | |
300 minPruning The minimum allowed pruning factor in assembly graph. Paths with less than or equal supporting kmers are pruned from the graph | |
301 pair_hmm_implementation The PairHMM implementation to use for genotype likelihood calculations | |
302 stand_call_conf The minimum phred-scaled confidence threshold at which variants should be called | |
303 stand_emit_conf The minimum phred-scaled confidence threshold at which variants should be emitted (and filtered with LowQual if less than the calling threshold) | |
304 useAllelesTrigger If specified, use additional trigger on variants found in an external alleles file | |
305 fullHaplotype If specified, output the full haplotype sequence instead of converting to individual variants w.r.t. the reference | |
306 gcpHMM Flat gap continuation penalty for use in the Pair HMM | |
307 genotypeFullActiveRegion If specified, alternate alleles are considered to be the full active region for the purposes of genotyping | |
308 max_alternate_alleles Maximum number of alternate alleles to genotype | |
309 | |
310 @CITATION_SECTION@ | |
311 </help> | |
4 | 312 <expand macro="citations" /> |
0 | 313 </tool> |