Mercurial > repos > iuc > gatk2

comparison variant_select.xml @ 0:340633249b3d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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_select" name="Select Variants" version="0.0.7">
2 <description>from VCF files</description>
3 <expand macro="requirements" />
4 <macros>
5 <import>gatk2_macros.xml</import>
6 </macros>
7 <command interpreter="python">
8 #from binascii import hexlify
9
10 gatk2_wrapper.py
11 --stdout "${output_log}"
12 -d "--variant:variant,%(file_type)s" "${reference_source.input_variant}" "${reference_source.input_variant.ext}" "input_variant"
13 -p '
14 @JAR_PATH@
15 -T "SelectVariants"
16 \$GATK2_SITE_OPTIONS
17
18 @THREADS@
19 -o "${output_vcf}"
20
21 #if $reference_source.reference_source_selector != "history":
22 -R "${reference_source.ref_file.fields.path}"
23 #end if
24 '
25 -p '
26 #if $input_concordance:
27 --concordance "${input_concordance}"
28 #end if
29 #if $input_discordance:
30 --discordance "${input_discordance}"
31 #end if
32
33 #for $exclude_sample_name in $exclude_sample_name_repeat:
34 --exclude_sample_name "${exclude_sample_name.exclude_sample_name}"
35 #end for
36
37 ${exclude_filtered}
38
39 #for $sample_name in $sample_name_repeat:
40 --sample_name "${sample_name.sample_name}"
41 #end for
42 '
43
44 #for $select_expressions in $select_expressions_repeat:
45 #set $select_expression = "--select_expressions '%s'" % ( str( $select_expressions.select_expressions ) )
46 -o '${ hexlify( $select_expression ) }'
47 #end for
48
49 ##start tool specific options
50 #if str( $analysis_param_type.analysis_param_type_selector ) == 'advanced':
51 -p '
52 #for $exclude_sample_file in $analysis_param_type.exclude_sample_file_repeat:
53 --exclude_sample_file "${exclude_sample_file.exclude_sample_file}"
54 #end for
55
56 #for $sample_file in $analysis_param_type.sample_file_repeat:
57 --sample_file "${ample_file.sample_file}"
58 #end for
59
60 #if $analysis_param_type.input_keep_ids:
61 --keepIDs "${analysis_param_type.input_keep_ids}"
62 #end if
63
64 ${analysis_param_type.keep_original_AC}
65
66 ${analysis_param_type.mendelian_violation}
67
68 --mendelianViolationQualThreshold "${analysis_param_type.mendelian_violation_qual_threshold}"
69
70 --remove_fraction_genotypes "${analysis_param_type.remove_fraction_genotypes}"
71
72 --restrictAllelesTo "${analysis_param_type.restrict_alleles_to}"
73
74 #if str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_fraction':
75 --select_random_fraction "${analysis_param_type.select_random_type.select_random_fraction}"
76 #elif str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_number':
77 --select_random_number "${analysis_param_type.select_random_type.select_random_number}"
78 #end if
79
80 #if $analysis_param_type.select_type_to_include:
81 #for $type_to_include in str( $analysis_param_type.select_type_to_include ).split( ',' ):
82 --selectTypeToInclude "${type_to_include}"
83 #end for
84 #end if
85
86 ${analysis_param_type.exclude_non_variants}
87 '
88
89 #for $sample_expressions in $analysis_param_type.sample_expressions_repeat:
90 #set $sample_expression = "--sample_expressions '%s'" % ( str( $sample_expressions.sample_expressions ) )
91 -o '${ hexlify( $sample_expression ) }'
92 #end for
93
94 #end if
95 ##end tool specific options
96
97 #include source=$standard_gatk_options#
98
99
100 </command>
101 <inputs>
102 <conditional name="reference_source">
103 <expand macro="reference_source_selector_param" />
104 <when value="cached">
105 <param name="input_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &amp;lt;variant&amp;gt;" />
106 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
107 <options from_data_table="gatk2_picard_indexes">
108 <filter type="data_meta" key="dbkey" ref="input_variant" column="dbkey"/>
109 </options>
110 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
111 </param>
112 </when>
113 <when value="history"> <!-- FIX ME!!!! -->
114 <param name="input_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &amp;lt;variant&amp;gt;" />
115 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
116 </when>
117 </conditional>
118
119 <repeat name="select_expressions_repeat" title="Criteria to use when selecting the data" help="-select,--select_expressions &amp;lt;select_expressions&amp;gt;">
120 <param name="select_expressions" type="text" label="JEXL expression">
121 <sanitizer>
122 <valid initial="string.printable">
123 <remove value="&apos;"/>
124 </valid>
125 <mapping initial="none"/>
126 </sanitizer>
127 </param>
128 </repeat>
129
130 <param name="input_concordance" type="data" format="vcf" label="Output variants that were also called in this comparison track" optional="True" help="-conc,--concordance &amp;lt;concordance&amp;gt;"/>
131 <param name="input_discordance" type="data" format="vcf" label="Output variants that were not called in this comparison track" optional="True" help="-disc,--discordance &amp;lt;discordance&amp;gt;"/>
132
133 <repeat name="sample_name_repeat" title="Include Samples by name" help="-sn,--sample_name &amp;lt;sample_name&amp;gt;">
134 <param name="sample_name" type="text" label="Include genotypes from this sample"/>
135 </repeat>
136
137 <repeat name="exclude_sample_name_repeat" title="Exclude Samples by name" help="-xl_sn,--exclude_sample_name &amp;lt;exclude_sample_name&amp;gt;">
138 <param name="exclude_sample_name" type="text" label="Exclude genotypes from this sample"/>
139 </repeat>
140
141 <param name="exclude_filtered" type="boolean" truevalue="--excludeFiltered" falsevalue="" label="Don't include filtered loci in the analysis" help="-ef,--excludeFiltered" />
142
143 <expand macro="gatk_param_type_conditional" />
144
145
146 <expand macro="analysis_type_conditional">
147
148 <repeat name="exclude_sample_file_repeat" title="Exclude Samples by file" help="-xl_sf,--exclude_sample_file &amp;lt;exclude_sample_file&amp;gt;">
149 <param name="exclude_sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to exclude"/>
150 </repeat>
151
152 <repeat name="sample_file_repeat" title="Samples by file" help="-sf,--sample_file &amp;lt;sample_file&amp;gt;">
153 <param name="sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to include" />
154 </repeat>
155
156 <param name="input_keep_ids" type="data" format="text" label="Only emit sites whose ID is found in this file" optional="True" help="-IDs,--keepIDs &amp;lt;keepIDs&amp;gt;"/>
157
158 <param name="keep_original_AC" type="boolean" truevalue="--keepOriginalAC" falsevalue="" label="Don't update the AC, AF, or AN values in the INFO field after selecting" help="-keepOriginalAC,--keepOriginalAC" />
159
160 <param name="mendelian_violation" type="boolean" truevalue="--mendelianViolation" falsevalue="" label="output mendelian violation sites only" help="-mv,--mendelianViolation" />
161
162 <param name="mendelian_violation_qual_threshold" type="float" label="Minimum genotype QUAL score for each trio member required to accept a site as a mendelian violation" value="0" help="-mvq,--mendelianViolationQualThreshold &amp;lt;mendelianViolationQualThreshold&amp;gt;" />
163
164 <param name="remove_fraction_genotypes" type="float" label="Selects a fraction (a number between 0 and 1) of the total genotypes at random from the variant track and sets them to nocall" value="0" min="0" max="1" help="-fractionGenotypes,--remove_fraction_genotypes &amp;lt;remove_fraction_genotypes&amp;gt;" />
165
166 <param name="restrict_alleles_to" type="select" label="Select only variants of a particular allelicity" help="-restrictAllelesTo,--restrictAllelesTo &amp;lt;restrictAllelesTo&amp;gt;">
167 <option value="ALL" selected="True">ALL</option>
168 <option value="MULTIALLELIC">MULTIALLELIC</option>
169 <option value="BIALLELIC">BIALLELIC</option>
170 </param>
171
172 <repeat name="sample_expressions_repeat" title="Regular expression to select many samples from the ROD tracks provided" help="-se,--sample_expressions &amp;lt;sample_expressions&amp;gt;">
173 <param name="sample_expressions" type="text" label="Regular expression">
174 <sanitizer>
175 <valid initial="string.printable">
176 <remove value="&apos;"/>
177 </valid>
178 <mapping initial="none"/>
179 </sanitizer>
180 </param>
181 </repeat>
182
183 <conditional name="select_random_type">
184 <param name="select_random_type_selector" type="select" label="Select a random subset of variants">
185 <option value="select_all" selected="True">Use all variants</option>
186 <option value="select_random_fraction">Select random fraction</option>
187 <option value="select_random_number">Select random number</option>
188 </param>
189 <when value="select_all">
190 <!-- Do nothing here -->
191 </when>
192 <when value="select_random_fraction">
193 <param name="select_random_fraction" type="float" value="0" label="Fraction" min="0" max="1" help="-fraction,--select_random_fraction &amp;lt;select_random_fraction&amp;gt;"/>
194 </when>
195 <when value="select_random_number">
196 <param name="select_random_number" type="integer" value="0" label="Count" help="-number,--select_random_number &amp;lt;select_random_number&amp;gt;" />
197 </when>
198 </conditional>
199
200 <param name="exclude_non_variants" type="boolean" truevalue="--excludeNonVariants" falsevalue="" label="Don't include loci found to be non-variant after the subsetting procedure" help="-env,--excludeNonVariants" />
201
202 <param name="select_type_to_include" type="select" label="Select only a certain type of variants from the input file" multiple="True" display="checkboxes" help="-selectType,--selectTypeToInclude &amp;lt;selectTypeToInclude&amp;gt;">
203 <option value="INDEL">INDEL</option>
204 <option value="SNP">SNP</option>
205 <option value="MIXED">MIXED</option>
206 <option value="MNP">MNP</option>
207 <option value="SYMBOLIC">SYMBOLIC</option>
208 <option value="NO_VARIATION">NO_VARIATION</option>
209 </param>
210 </expand>
211
212 </inputs>
213 <outputs>
214 <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (Variant File)" />
215 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
216 </outputs>
217 <tests>
218 <test>
219 <param name="reference_source_selector" value="history" />
220 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
221 <param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" />
222 <param name="select_expressions_repeat" value="0" />
223 <param name="input_concordance" />
224 <param name="input_discordance" />
225 <param name="exclude_sample_name_repeat" value="0" />
226 <param name="exclude_filtered" />
227 <param name="sample_name_repeat" value="0" />
228 <param name="gatk_param_type_selector" value="basic" />
229 <param name="analysis_param_type_selector" value="basic" />
230 <output name="output_vcf" file="gatk/gatk_variant_select/gatk_variant_select_out_1.vcf" lines_diff="4" />
231 <output name="output_log" file="gatk/gatk_variant_select/gatk_variant_select_out_1.log.contains" compare="contains" />
232 </test>
233 </tests>
234 <help>
235 **What it does**
236
237 Often, a VCF containing many samples and/or variants will need to be subset in order to facilitate certain analyses (e.g. comparing and contrasting cases vs. controls; extracting variant or non-variant loci that meet certain requirements, displaying just a few samples in a browser like IGV, etc.). SelectVariants can be used for this purpose. Given a single VCF file, one or more samples can be extracted from the file (based on a complete sample name or a pattern match). Variants can be further selected by specifying criteria for inclusion, i.e. "DP &gt; 1000" (depth of coverage greater than 1000x), "AF &lt; 0.25" (sites with allele frequency less than 0.25). These JEXL expressions are documented in the `Using JEXL expressions section &lt;http://gatkforums.broadinstitute.org/discussion/1255/what-are-jexl-expressions-and-how-can-i-use-them-with-the-gatk&gt;`_. One can optionally include concordance or discordance tracks for use in selecting overlapping variants.
238
239 For more information on using the SelectVariants module, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_variantutils_SelectVariants.html&gt;`_.
240
241 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;`_.
242
243 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
244
245 ------
246
247 **Inputs**
248
249 GenomeAnalysisTK: SelectVariants accepts a VCF input file.
250
251
252 **Outputs**
253
254 The output is in VCF format.
255
256
257 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
258
259 -------
260
261 **Settings**::
262
263
264 out VCFWriter stdout File to which variants should be written
265 variant RodBinding[VariantContext] NA Input VCF file
266 concordance RodBinding[VariantContext] none Output variants that were also called in this comparison track
267 discordance RodBinding[VariantContext] none Output variants that were not called in this comparison track
268 exclude_sample_file Set[File] [] File containing a list of samples (one per line) to exclude. Can be specified multiple times
269 exclude_sample_name Set[String] [] Exclude genotypes from this sample. Can be specified multiple times
270 excludeFiltered boolean false Don't include filtered loci in the analysis
271 excludeNonVariants boolean false Don't include loci found to be non-variant after the subsetting procedure
272 keepIDs File NA Only emit sites whose ID is found in this file (one ID per line)
273 keepOriginalAC boolean false Don't update the AC, AF, or AN values in the INFO field after selecting
274 mendelianViolation Boolean false output mendelian violation sites only
275 mvq double 0.0 Minimum genotype QUAL score for each trio member required to accept a site as a violation
276 remove_fraction_genotypes double 0.0 Selects a fraction (a number between 0 and 1) of the total genotypes at random from the variant track and sets them to nocall
277 restrictAllelesTo NumberAlleleRestriction ALL Select only variants of a particular allelicity. Valid options are ALL (default), MULTIALLELIC or BIALLELIC
278 sample_expressions Set[String] NA Regular expression to select many samples from the ROD tracks provided. Can be specified multiple times
279 sample_file Set[File] NA File containing a list of samples (one per line) to include. Can be specified multiple times
280 sample_name Set[String] [] Include genotypes from this sample. Can be specified multiple times
281 select_expressions ArrayList[String] [] One or more criteria to use when selecting the data
282 select_random_fraction double 0.0 Selects a fraction (a number between 0 and 1) of the total variants at random from the variant track
283 select_random_number int 0 Selects a number of variants at random from the variant track
284 selectTypeToInclude List[Type] [] Select only a certain type of variants from the input file. Valid types are INDEL, SNP, MIXED, MNP, SYMBOLIC, NO_VARIATION. Can be specified multiple times
285
286 @CITATION_SECTION@
287 </help>
288 </tool>