Mercurial > repos > devteam > variant_select

comparison variant_select.xml @ 0:135e8721ffc5 draft

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 10:49:48 -0400
parents
children 227aa321a671
comparison
equal deleted inserted replaced
-1:000000000000 0:135e8721ffc5
1 <tool id="gatk_variant_select" name="Select Variants" version="0.0.2">
2 <description>from VCF files</description>
3 <requirements>
4 <requirement type="package" version="1.4">gatk</requirement>
5 </requirements>
6 <macros>
7 <import>gatk_macros.xml</import>
8 </macros>
9 <command interpreter="python">gatk_wrapper.py
10 #from binascii import hexlify
11 --max_jvm_heap_fraction "1"
12 --stdout "${output_log}"
13 -d "--variant:variant,%(file_type)s" "${reference_source.input_variant}" "${reference_source.input_variant.ext}" "input_variant"
14 -p 'java
15 -jar "\$JAVA_JAR_PATH/GenomeAnalysisTK.jar"
16 -T "SelectVariants"
17 --num_threads \${GALAXY_SLOTS:-4}
18 -et "NO_ET" ##ET no phone home
19 -o "${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
45 #for $select_expressions in $select_expressions_repeat:
46 #set $select_expression = "--select_expressions '%s'" % ( str( $select_expressions.select_expressions ) )
47 -o '${ hexlify( $select_expression ) }'
48 #end for
49
50 ##start tool specific options
51 #if str( $analysis_param_type.analysis_param_type_selector ) == 'advanced':
52 -p '
53 #for $exclude_sample_file in $analysis_param_type.exclude_sample_file_repeat:
54 --exclude_sample_file "${exclude_sample_file.exclude_sample_file}"
55 #end for
56
57 #for $sample_file in $analysis_param_type.sample_file_repeat:
58 --sample_file "${ample_file.sample_file}"
59 #end for
60
61 #if $analysis_param_type.input_keep_ids:
62 --keepIDs "${analysis_param_type.input_keep_ids}"
63 #end if
64
65 ${analysis_param_type.keep_original_AC}
66
67 ${analysis_param_type.mendelian_violation}
68
69 --mendelianViolationQualThreshold "${analysis_param_type.mendelian_violation_qual_threshold}"
70
71 --remove_fraction_genotypes "${analysis_param_type.remove_fraction_genotypes}"
72
73 --restrictAllelesTo "${analysis_param_type.restrict_alleles_to}"
74
75 #if str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_fraction':
76 --select_random_fraction "${analysis_param_type.select_random_type.select_random_fraction}"
77 #elif str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_number':
78 --select_random_number "${analysis_param_type.select_random_type.select_random_number}"
79 #end if
80
81 #if $analysis_param_type.select_type_to_include:
82 #for $type_to_include in str( $analysis_param_type.select_type_to_include ).split( ',' ):
83 --selectTypeToInclude "${type_to_include}"
84 #end for
85 #end if
86
87 ${analysis_param_type.exclude_non_variants}
88 '
89
90 #for $sample_expressions in $analysis_param_type.sample_expressions_repeat:
91 #set $sample_expression = "--sample_expressions '%s'" % ( str( $sample_expressions.sample_expressions ) )
92 -o '${ hexlify( $sample_expression ) }'
93 #end for
94
95 #end if
96 ##end tool specific options
97
98 #include source=$standard_gatk_options#
99
100
101 </command>
102 <inputs>
103 <conditional name="reference_source">
104 <expand macro="reference_source_selector_param" />
105 <when value="cached">
106 <param name="input_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &amp;lt;variant&amp;gt;" />
107 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
108 <options from_data_table="gatk_picard_indexes">
109 <filter type="data_meta" key="dbkey" ref="input_variant" column="dbkey"/>
110 </options>
111 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
112 </param>
113 </when>
114 <when value="history"> <!-- FIX ME!!!! -->
115 <param name="input_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &amp;lt;variant&amp;gt;" />
116 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
117 </when>
118 </conditional>
119
120 <repeat name="select_expressions_repeat" title="Criteria to use when selecting the data" help="-select,--select_expressions &amp;lt;select_expressions&amp;gt;">
121 <param name="select_expressions" type="text" label="JEXL expression">
122 <sanitizer>
123 <valid initial="string.printable">
124 <remove value="&apos;"/>
125 </valid>
126 <mapping initial="none"/>
127 </sanitizer>
128 </param>
129 </repeat>
130
131 <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;"/>
132 <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;"/>
133
134 <repeat name="sample_name_repeat" title="Include Samples by name" help="-sn,--sample_name &amp;lt;sample_name&amp;gt;">
135 <param name="sample_name" type="text" label="Include genotypes from this sample"/>
136 </repeat>
137
138 <repeat name="exclude_sample_name_repeat" title="Exclude Samples by name" help="-xl_sn,--exclude_sample_name &amp;lt;exclude_sample_name&amp;gt;">
139 <param name="exclude_sample_name" type="text" label="Exclude genotypes from this sample"/>
140 </repeat>
141
142 <param name="exclude_filtered" type="boolean" truevalue="--excludeFiltered" falsevalue="" label="Don't include filtered loci in the analysis" help="-ef,--excludeFiltered" />
143
144 <expand macro="gatk_param_type_conditional" />
145
146
147 <expand macro="analysis_type_conditional">
148
149 <repeat name="exclude_sample_file_repeat" title="Exclude Samples by file" help="-xl_sf,--exclude_sample_file &amp;lt;exclude_sample_file&amp;gt;">
150 <param name="exclude_sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to exclude"/>
151 </repeat>
152
153 <repeat name="sample_file_repeat" title="Samples by file" help="-sf,--sample_file &amp;lt;sample_file&amp;gt;">
154 <param name="sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to include" />
155 </repeat>
156
157 <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;"/>
158
159 <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" />
160
161 <param name="mendelian_violation" type="boolean" truevalue="--mendelianViolation" falsevalue="" label="output mendelian violation sites only" help="-mv,--mendelianViolation" />
162
163 <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;" />
164
165 <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;" />
166
167 <param name="restrict_alleles_to" type="select" label="Select only variants of a particular allelicity" help="-restrictAllelesTo,--restrictAllelesTo &amp;lt;restrictAllelesTo&amp;gt;">
168 <option value="ALL" selected="True">ALL</option>
169 <option value="MULTIALLELIC">MULTIALLELIC</option>
170 <option value="BIALLELIC">BIALLELIC</option>
171 </param>
172
173 <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;">
174 <param name="sample_expressions" type="text" label="Regular expression">
175 <sanitizer>
176 <valid initial="string.printable">
177 <remove value="&apos;"/>
178 </valid>
179 <mapping initial="none"/>
180 </sanitizer>
181 </param>
182 </repeat>
183
184 <conditional name="select_random_type">
185 <param name="select_random_type_selector" type="select" label="Select a random subset of variants">
186 <option value="select_all" selected="True">Use all variants</option>
187 <option value="select_random_fraction">Select random fraction</option>
188 <option value="select_random_number">Select random number</option>
189 </param>
190 <when value="select_all">
191 <!-- Do nothing here -->
192 </when>
193 <when value="select_random_fraction">
194 <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;"/>
195 </when>
196 <when value="select_random_number">
197 <param name="select_random_number" type="integer" value="0" label="Count" help="-number,--select_random_number &amp;lt;select_random_number&amp;gt;" />
198 </when>
199 </conditional>
200
201 <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" />
202
203 <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;">
204 <option value="INDEL">INDEL</option>
205 <option value="SNP">SNP</option>
206 <option value="MIXED">MIXED</option>
207 <option value="MNP">MNP</option>
208 <option value="SYMBOLIC">SYMBOLIC</option>
209 <option value="NO_VARIATION">NO_VARIATION</option>
210 </param>
211 </expand>
212
213 </inputs>
214 <outputs>
215 <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (Variant File)" />
216 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
217 </outputs>
218 <tests>
219 <test>
220 <param name="reference_source_selector" value="history" />
221 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
222 <param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" />
223 <param name="select_expressions_repeat" value="0" />
224 <param name="input_concordance" />
225 <param name="input_discordance" />
226 <param name="exclude_sample_name_repeat" value="0" />
227 <param name="exclude_filtered" />
228 <param name="sample_name_repeat" value="0" />
229 <param name="gatk_param_type_selector" value="basic" />
230 <param name="analysis_param_type_selector" value="basic" />
231 <output name="output_vcf" file="gatk/gatk_variant_select/gatk_variant_select_out_1.vcf" lines_diff="4" />
232 <output name="output_log" file="gatk/gatk_variant_select/gatk_variant_select_out_1.log.contains" compare="contains" />
233 </test>
234 </tests>
235 <help>
236 **What it does**
237
238 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 (http://www.broadinstitute.org/gsa/wiki/index.php/Using_JEXL_expressions). One can optionally include concordance or discordance tracks for use in selecting overlapping variants.
239
240 For more information on using the SelectVariants module, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/SelectVariants&gt;`_.
241
242 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;`_.
243
244 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
245
246 ------
247
248 **Inputs**
249
250 GenomeAnalysisTK: SelectVariants accepts a VCF input file.
251
252
253 **Outputs**
254
255 The output is in VCF format.
256
257
258 Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
259
260 -------
261
262 **Settings**::
263
264
265 out VCFWriter stdout File to which variants should be written
266 variant RodBinding[VariantContext] NA Input VCF file
267 concordance RodBinding[VariantContext] none Output variants that were also called in this comparison track
268 discordance RodBinding[VariantContext] none Output variants that were not called in this comparison track
269 exclude_sample_file Set[File] [] File containing a list of samples (one per line) to exclude. Can be specified multiple times
270 exclude_sample_name Set[String] [] Exclude genotypes from this sample. Can be specified multiple times
271 excludeFiltered boolean false Don't include filtered loci in the analysis
272 excludeNonVariants boolean false Don't include loci found to be non-variant after the subsetting procedure
273 keepIDs File NA Only emit sites whose ID is found in this file (one ID per line)
274 keepOriginalAC boolean false Don't update the AC, AF, or AN values in the INFO field after selecting
275 mendelianViolation Boolean false output mendelian violation sites only
276 mvq double 0.0 Minimum genotype QUAL score for each trio member required to accept a site as a violation
277 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
278 restrictAllelesTo NumberAlleleRestriction ALL Select only variants of a particular allelicity. Valid options are ALL (default), MULTIALLELIC or BIALLELIC
279 sample_expressions Set[String] NA Regular expression to select many samples from the ROD tracks provided. Can be specified multiple times
280 sample_file Set[File] NA File containing a list of samples (one per line) to include. Can be specified multiple times
281 sample_name Set[String] [] Include genotypes from this sample. Can be specified multiple times
282 select_expressions ArrayList[String] [] One or more criteria to use when selecting the data
283 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
284 select_random_number int 0 Selects a number of variants at random from the variant track
285 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
286
287 @CITATION_SECTION@
288 </help>
289 </tool>