annotate variant_combine.xml @ 15:01ff8dd37d4d draft default tip

Uploaded
author lz_hust
date Sat, 01 Jun 2019 07:20:41 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
15
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
1 <tool id="gatk2_variant_combine" name="Combine Variants" version="@VERSION@.0">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
2 <description></description>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
3 <macros>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
4 <import>gatk2_macros.xml</import>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
5 </macros>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
6 <expand macro="requirements" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
7 <expand macro="version_command" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
8 <command interpreter="python">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
9 gatk2_wrapper.py
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
10 --stdout "${output_log}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
11
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
12 #set $priority_order = []
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
13 #for $input_variant in $reference_source.input_variants:
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
14 -d "--variant:${input_variant.input_variant_name},%(file_type)s" "${input_variant.input_variant}" "${input_variant.input_variant.ext}" "input_variant_${input_variant.input_variant_name}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
15 #set $input_variant_name = str( $input_variant.input_variant_name )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
16 #assert $input_variant_name not in $priority_order, "Variant Names must be unique" ##this should be handled by a validator
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
17 #silent $priority_order.append( $input_variant_name )
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
18 #end for
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
19 -p '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
20 @JAR_PATH@
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
21 -T "CombineVariants"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
22 --out "${output_variants}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
23 \$GATK2_SITE_OPTIONS
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
24
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
25 @THREADS@
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
26
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
27 #if $reference_source.reference_source_selector != "history":
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
28 -R "${reference_source.ref_file.fields.path}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
29 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
30 --genotypemergeoption "${genotype_merge_option}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
31 --rod_priority_list "${ ','.join( $priority_order ) }"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
32 '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
33
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
34 #include source=$standard_gatk_options#
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
35
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
36 ##start analysis specific options
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
37 #if $analysis_param_type.analysis_param_type_selector == "advanced":
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
38 -p '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
39 --filteredrecordsmergetype "${analysis_param_type.filtered_records_merge_type}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
40 ${analysis_param_type.print_complex_merges}
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
41 ${analysis_param_type.filtered_are_uncalled}
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
42 ${analysis_param_type.minimal_vcf}
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
43 ${analysis_param_type.assume_identical_samples}
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
44
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
45 #if str( $analysis_param_type.set_key ):
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
46 --setKey "${analysis_param_type.set_key}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
47 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
48
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
49 --minimumN "${analysis_param_type.minimum_n}"
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
50 '
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
51 #end if
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
52 </command>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
53 <inputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
54
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
55 <conditional name="reference_source">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
56 <expand macro="reference_source_selector_param" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
57 <when value="cached">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
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 &amp;lt;variant&amp;gt;)">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
59 <param name="input_variant" type="data" format="vcf" label="Input variant file" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
60 <param name="input_variant_name" type="text" value="" label="Variant name" help="Names must be unique">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
61 <validator type="length" min="1" message="You must provide a unique name for this set of variants" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
62 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
63 </repeat>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
64 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
65 <options from_data_table="gatk2_picard_indexes">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
66 <!-- <filter type="data_meta" key="dbkey" ref="input_variants.input_variant" column="dbkey"/> -->
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
67 </options>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
68 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
69 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
70 </when>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
71 <when value="history"> <!-- FIX ME!!!! -->
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
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 &amp;lt;variant&amp;gt;)">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
73 <param name="input_variant" type="data" format="vcf" label="Input variant file" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
74 <param name="input_variant_name" type="text" value="" label="Variant name" help="Names must be unique">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
75 <validator type="length" min="1" message="You must provide a unique name for this set of variants" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
76 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
77 </repeat>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
78 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
79 </when>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
80 </conditional>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
81
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
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 &amp;lt;genotypemergeoption&amp;gt;" >
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
83 <option value="UNIQUIFY" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
84 <option value="PRIORITIZE" selected="true"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
85 <option value="UNSORTED" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
86 <option value="REQUIRE_UNIQUE" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
87 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
88
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
89 <expand macro="gatk_param_type_conditional" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
90
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
91 <expand macro="analysis_type_conditional">
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
92 <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 &amp;lt;filteredrecordsmergetype&amp;gt;" >
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
93 <option value="KEEP_IF_ANY_UNFILTERED" selected="true"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
94 <option value="KEEP_IF_ALL_UNFILTERED" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
95 </param>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
96
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
97 <param name="print_complex_merges" checked="false" type="boolean" truevalue="--printComplexMerges" falsevalue="" label="Print out interesting sites requiring complex compatibility merging" help="-printComplexMerges,--printComplexMerges" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
98 <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" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
99 <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" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
100
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
101 <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 &amp;lt;setKey&amp;gt;"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
102 <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" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
103 <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 &amp;lt;minimumN&amp;gt;"/>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
104 </expand>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
105
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
106 </inputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
107 <outputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
108 <data format="vcf" name="output_variants" label="${tool.name} on ${on_string} (variants)" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
109 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
110 </outputs>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
111 <tests>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
112 <test>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
113 <param name="reference_source_selector" value="history" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
114 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
115 <param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
116 <param name="input_variant_name" value="from_variant_annotator" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
117 <param name="genotype_merge_option" value="PRIORITIZE" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
118 <param name="gatk_param_type_selector" value="basic" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
119 <param name="analysis_param_type_selector" value="basic" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
120 <output name="output_variants" file="gatk/gatk_variant_combine/gatk_variant_combine_out_1.vcf" lines_diff="4" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
121 <output name="output_log" file="gatk/gatk_variant_combine/gatk_variant_combine_out_1.log.contains" compare="contains" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
122 </test>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
123 </tests>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
124 <help>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
125 **What it does**
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
126
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
127 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.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
128
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
129 For more information on using the CombineVariants module, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_variantutils_CombineVariants.html&gt;`_.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
130
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
131 To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gatk/guide/topic?name=best-practices&gt;`_.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
132
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
133 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
134
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
135 ------
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
136
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
137 **Inputs**
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
138
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
139 GenomeAnalysisTK: CombineVariants accepts variant files as input.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
140
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
141 ------
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
142
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
143 **Outputs**
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
144
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
145 The output is a combined vcf file.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
146
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
147
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
148 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
149
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
150 -------
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
151
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
152 **Settings**::
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
153
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
154 out File to which variants should be written
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
155 genotypemergeoption How should we merge genotype records for samples shared across the ROD files? (UNIQUIFY|PRIORITIZE|UNSORTED|REQUIRE_UNIQUE)
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
156 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)
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
157 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
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
158 printComplexMerges Print out interesting sites requiring complex compatibility merging
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
159 filteredAreUncalled If true, then filtered VCFs are treated as uncalled, so that filtered set annotation don't appear in the combined VCF
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
160 minimalVCF If true, then the output VCF will contain no INFO or genotype INFO field
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
161 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.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
162 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.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
163 minimumN Combine variants and output site only if variant is present in at least N input files.
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
164
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
165 @CITATION_SECTION@
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
166 </help>
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
167 <expand macro="citations" />
01ff8dd37d4d Uploaded
lz_hust
parents:
diff changeset
168 </tool>