Mercurial > repos > iuc > gatk2
comparison variant_combine.xml @ 0:340633249b3d draft
Uploaded
author | bgruening |
---|---|
date | Mon, 02 Dec 2013 06:18:36 -0500 |
parents | |
children | f244b8209eb8 |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:340633249b3d |
---|---|
1 <tool id="gatk2_variant_combine" name="Combine Variants" version="0.0.7"> | |
2 <description></description> | |
3 <expand macro="requirements" /> | |
4 <macros> | |
5 <import>gatk2_macros.xml</import> | |
6 </macros> | |
7 <command interpreter="python"> | |
8 gatk2_wrapper.py | |
9 --stdout "${output_log}" | |
10 | |
11 #set $priority_order = [] | |
12 #for $input_variant in $reference_source.input_variants: | |
13 -d "--variant:${input_variant.input_variant_name},%(file_type)s" "${input_variant.input_variant}" "${input_variant.input_variant.ext}" "input_variant_${input_variant.input_variant_name}" | |
14 #set $input_variant_name = str( $input_variant.input_variant_name ) | |
15 #assert $input_variant_name not in $priority_order, "Variant Names must be unique" ##this should be handled by a validator | |
16 #silent $priority_order.append( $input_variant_name ) | |
17 #end for | |
18 -p ' | |
19 @JAR_PATH@ | |
20 -T "CombineVariants" | |
21 --out "${output_variants}" | |
22 \$GATK2_SITE_OPTIONS | |
23 | |
24 @THREADS@ | |
25 | |
26 #if $reference_source.reference_source_selector != "history": | |
27 -R "${reference_source.ref_file.fields.path}" | |
28 #end if | |
29 --genotypemergeoption "${genotype_merge_option}" | |
30 --rod_priority_list "${ ','.join( $priority_order ) }" | |
31 ' | |
32 | |
33 #include source=$standard_gatk_options# | |
34 | |
35 | |
36 ##start analysis specific options | |
37 #if $analysis_param_type.analysis_param_type_selector == "advanced": | |
38 -p ' | |
39 --filteredrecordsmergetype "${analysis_param_type.filtered_records_merge_type}" | |
40 ${analysis_param_type.print_complex_merges} | |
41 ${analysis_param_type.filtered_are_uncalled} | |
42 ${analysis_param_type.minimal_vcf} | |
43 ${analysis_param_type.assume_identical_samples} | |
44 | |
45 #if str( $analysis_param_type.set_key ): | |
46 --setKey "${analysis_param_type.set_key}" | |
47 #end if | |
48 | |
49 --minimumN "${analysis_param_type.minimum_n}" | |
50 ' | |
51 #end if | |
52 </command> | |
53 <inputs> | |
54 | |
55 <conditional name="reference_source"> | |
56 <expand macro="reference_source_selector_param" /> | |
57 <when value="cached"> | |
58 <repeat min="1" name="input_variants" title="Variants to Merge" help="Records will be prioritized in the order that you list them here (-V,--variant &lt;variant&gt;)"> | |
59 <param name="input_variant" type="data" format="vcf" label="Input variant file" /> | |
60 <param name="input_variant_name" type="text" value="" label="Variant name" help="Names must be unique"> | |
61 <validator type="length" min="1" message="You must provide a unique name for this set of variants" /> | |
62 </param> | |
63 </repeat> | |
64 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &lt;reference_sequence&gt;"> | |
65 <options from_data_table="gatk2_picard_indexes"> | |
66 <!-- <filter type="data_meta" key="dbkey" ref="input_variants.input_variant" column="dbkey"/> --> | |
67 </options> | |
68 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> | |
69 </param> | |
70 </when> | |
71 <when value="history"> <!-- FIX ME!!!! --> | |
72 <repeat min="1" name="input_variants" title="Variants to Merge" help="Records will be prioritized in the order that you list them here (-V,--variant &lt;variant&gt;)"> | |
73 <param name="input_variant" type="data" format="vcf" label="Input variant file" /> | |
74 <param name="input_variant_name" type="text" value="" label="Variant name" help="Names must be unique"> | |
75 <validator type="length" min="1" message="You must provide a unique name for this set of variants" /> | |
76 </param> | |
77 </repeat> | |
78 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &lt;reference_sequence&gt;" /> | |
79 </when> | |
80 </conditional> | |
81 | |
82 <param name="genotype_merge_option" type="select" label="How should we merge genotype records across records for samples shared across the ROD files" help="-genotypeMergeOptions,--genotypemergeoption &lt;genotypemergeoption&gt;" > | |
83 <option value="UNIQUIFY" /> | |
84 <option value="PRIORITIZE" selected="true"/> | |
85 <option value="UNSORTED" /> | |
86 <option value="REQUIRE_UNIQUE" /> | |
87 </param> | |
88 | |
89 <expand macro="gatk_param_type_conditional" /> | |
90 | |
91 | |
92 <expand macro="analysis_type_conditional"> | |
93 <param name="filtered_records_merge_type" type="select" label="How should we deal with records seen at the same site in the VCF, but with different FILTER fields?" help="-filteredRecordsMergeType,--filteredrecordsmergetype &lt;filteredrecordsmergetype&gt;" > | |
94 <option value="KEEP_IF_ANY_UNFILTERED" selected="true"/> | |
95 <option value="KEEP_IF_ALL_UNFILTERED" /> | |
96 </param> | |
97 | |
98 <param name="print_complex_merges" checked="false" type="boolean" truevalue="--printComplexMerges" falsevalue="" label="Print out interesting sites requiring complex compatibility merging" help="-printComplexMerges,--printComplexMerges" /> | |
99 <param name="filtered_are_uncalled" checked="false" type="boolean" truevalue="--filteredAreUncalled" falsevalue="" label="If true, then filtered VCFs are treated as uncalled, so that filtered set annotation don't appear in the combined VCF" help="-filteredAreUncalled,--filteredAreUncalled" /> | |
100 <param name="minimal_vcf" checked="false" type="boolean" truevalue="--minimalVCF" falsevalue="" label="If true, then the output VCF will contain no INFO or genotype INFO field" help="-minimalVCF,--minimalVCF" /> | |
101 | |
102 <param name="set_key" type="text" value="" label="Key, by default set, in the INFO key=value tag emitted describing which set the combined VCF record came from." help="-setKey,--setKey &lt;setKey&gt;"/> | |
103 <param name="assume_identical_samples" checked="false" type="boolean" truevalue="--assumeIdenticalSamples" falsevalue="" label="If true, assume input VCFs have identical sample sets and disjoint calls so that one can simply perform a merge sort to combine the VCFs into one, drastically reducing the runtime." help="-assumeIdenticalSamples,--assumeIdenticalSamples" /> | |
104 <param name="minimum_n" type="integer" value="1" label="Combine variants and output site only if variant is present in at least N input files." help="-minN,--minimumN &lt;minimumN&gt;"/> | |
105 | |
106 </expand> | |
107 | |
108 | |
109 </inputs> | |
110 <outputs> | |
111 <data format="vcf" name="output_variants" label="${tool.name} on ${on_string} (variants)" /> | |
112 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> | |
113 </outputs> | |
114 <tests> | |
115 <test> | |
116 <param name="reference_source_selector" value="history" /> | |
117 <param name="ref_file" value="phiX.fasta" ftype="fasta" /> | |
118 <param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" /> | |
119 <param name="input_variant_name" value="from_variant_annotator" /> | |
120 <param name="genotype_merge_option" value="PRIORITIZE" /> | |
121 <param name="gatk_param_type_selector" value="basic" /> | |
122 <param name="analysis_param_type_selector" value="basic" /> | |
123 <output name="output_variants" file="gatk/gatk_variant_combine/gatk_variant_combine_out_1.vcf" lines_diff="4" /> | |
124 <output name="output_log" file="gatk/gatk_variant_combine/gatk_variant_combine_out_1.log.contains" compare="contains" /> | |
125 </test> | |
126 </tests> | |
127 <help> | |
128 **What it does** | |
129 | |
130 Combines VCF records from different sources; supports both full merges and set unions. Merge: combines multiple records into a single one; if sample names overlap then they are uniquified. Union: assumes each rod represents the same set of samples (although this is not enforced); using the priority list (if provided), emits a single record instance at every position represented in the rods. | |
131 | |
132 For more information on using the CombineVariants module, see this `tool specific page <http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_variantutils_CombineVariants.html>`_. | |
133 | |
134 To learn about best practices for variant detection using GATK, see this `overview <http://www.broadinstitute.org/gatk/guide/topic?name=best-practices>`_. | |
135 | |
136 If you encounter errors, please view the `GATK FAQ <http://www.broadinstitute.org/gatk/guide/topic?name=faqs>`_. | |
137 | |
138 ------ | |
139 | |
140 **Inputs** | |
141 | |
142 GenomeAnalysisTK: CombineVariants accepts variant files as input. | |
143 | |
144 ------ | |
145 | |
146 **Outputs** | |
147 | |
148 The output is a combined vcf file. | |
149 | |
150 | |
151 Go `here <http://www.broadinstitute.org/gatk/guide/topic?name=intro>`_ for details on GATK file formats. | |
152 | |
153 ------- | |
154 | |
155 **Settings**:: | |
156 | |
157 out File to which variants should be written | |
158 genotypemergeoption How should we merge genotype records for samples shared across the ROD files? (UNIQUIFY|PRIORITIZE|UNSORTED|REQUIRE_UNIQUE) | |
159 filteredrecordsmergetype How should we deal with records seen at the same site in the VCF, but with different FILTER fields? KEEP_IF_ANY_UNFILTERED PASSes the record if any record is unfiltered, KEEP_IF_ALL_UNFILTERED requires all records to be unfiltered (KEEP_IF_ANY_UNFILTERED|KEEP_IF_ALL_UNFILTERED) | |
160 rod_priority_list When taking the union of variants containing genotypes: a comma-separated string describing the priority ordering for the genotypes as far as which record gets emitted; a complete priority list MUST be provided | |
161 printComplexMerges Print out interesting sites requiring complex compatibility merging | |
162 filteredAreUncalled If true, then filtered VCFs are treated as uncalled, so that filtered set annotation don't appear in the combined VCF | |
163 minimalVCF If true, then the output VCF will contain no INFO or genotype INFO field | |
164 setKey Key, by default set, in the INFO key=value tag emitted describing which set the combined VCF record came from. Set to null if you don't want the set field emitted. | |
165 assumeIdenticalSamples If true, assume input VCFs have identical sample sets and disjoint calls so that one can simply perform a merge sort to combine the VCFs into one, drastically reducing the runtime. | |
166 minimumN Combine variants and output site only if variant is present in at least N input files. | |
167 | |
168 @CITATION_SECTION@ | |
169 </help> | |
170 </tool> |