Mercurial > repos > jjohnson > gatk2

comparison variant_filtration.xml @ 0:74c05070a3f8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jjohnson
date Thu, 01 Nov 2012 13:53:22 -0400
parents
children 7533db8dfb5b
comparison
equal deleted inserted replaced
-1:000000000000 0:74c05070a3f8
1 <tool id="gatk2_variant_filtration" name="Variant Filtration" version="0.0.4">
2 <description>on VCF files</description>
3 <requirements>
4 <requirement type="package" version="2.2">gatk</requirement>
5 </requirements>
6 <command interpreter="python">gatk2_wrapper.py
7 #from binascii import hexlify
8 --max_jvm_heap_fraction "1"
9 --stdout "${output_log}"
10 -d "--variant:variant,%(file_type)s" "${reference_source.input_variant}" "${reference_source.input_variant.ext}" "input_variant"
11 -p 'java
12 -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
13 -T "VariantFiltration"
14 \$GATK2_SITE_OPTIONS
15 ##--num_threads 4 ##hard coded, for now
16 ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
17 -o "${output_vcf}"
18 ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
19 #if $reference_source.reference_source_selector != "history":
20 -R "${reference_source.ref_file.fields.path}"
21 #end if
22 '
23 #for $variant_filter in $variant_filters:
24 #set $variant_filter = "--%sExpression '%s' --%sName '%s'" % ( str( $variant_filter.is_genotype_filter ), str( $variant_filter.filter_expression ), str( $variant_filter.is_genotype_filter ), str( $variant_filter.filter_name ) )
25 -o '${ hexlify( $variant_filter ) }'
26 #end for
27
28 #if str( $mask_rod_bind_type.mask_rod_bind_type_selector ) == 'set_mask':
29 -d "--mask:${mask_rod_bind_type.mask_rod_name},%(file_type)s" "${mask_rod_bind_type.input_mask_rod}" "${mask_rod_bind_type.input_mask_rod.ext}" "input_mask_${mask_rod_bind_type.mask_rod_name}"
30 -p '
31 --maskExtension "${mask_rod_bind_type.mask_extension}"
32 --maskName "${mask_rod_bind_type.mask_rod_name}"
33 '
34 #end if
35
36 ##start standard gatk options
37 #if $gatk_param_type.gatk_param_type_selector == "advanced":
38 #for $pedigree in $gatk_param_type.pedigree:
39 -p '--pedigree "${pedigree.pedigree_file}"'
40 #end for
41 #for $pedigree_string in $gatk_param_type.pedigree_string_repeat:
42 -p '--pedigreeString "${pedigree_string.pedigree_string}"'
43 #end for
44 -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"'
45 #for $read_filter in $gatk_param_type.read_filter:
46 -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}"
47 ###raise Exception( str( dir( $read_filter ) ) )
48 #for $name, $param in $read_filter.read_filter_type.iteritems():
49 #if $name not in [ "__current_case__", "read_filter_type_selector" ]:
50 #if hasattr( $param.input, 'truevalue' ):
51 ${param}
52 #else:
53 --${name} "${param}"
54 #end if
55 #end if
56 #end for
57 '
58 #end for
59 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ):
60 -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}"
61 #end for
62
63 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ):
64 -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}"
65 #end for
66
67 -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"'
68
69 -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"'
70 #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE":
71 -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"'
72 #end if
73 -p '
74 --baq "${gatk_param_type.baq}"
75 --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}"
76 ${gatk_param_type.use_original_qualities}
77 --defaultBaseQualities "${gatk_param_type.default_base_qualities}"
78 --validation_strictness "${gatk_param_type.validation_strictness}"
79 --interval_merging "${gatk_param_type.interval_merging}"
80 ${gatk_param_type.disable_experimental_low_memory_sharding}
81 ${gatk_param_type.non_deterministic_random_seed}
82 '
83 #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ):
84 #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file":
85 -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}"
86 #else
87 -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"'
88 #end if
89 #end for
90 #end if
91
92 #if str( $reference_source.reference_source_selector ) == "history":
93 -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
94 #end if
95 ##end standard gatk options
96
97 ##start analysis specific options
98 #if $cluster_snp_type.cluster_snp_type_selector == "cluster_snp":
99 -p '
100 --clusterSize "${cluster_snp_type.cluster_size}"
101 --clusterWindowSize "${cluster_snp_type.cluster_window_size}"
102 '
103 #end if
104 -p '${missing_values_in_expressions_should_evaluate_as_failing}'
105 </command>
106 <inputs>
107 <conditional name="reference_source">
108 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
109 <option value="cached">Locally cached</option>
110 <option value="history">History</option>
111 </param>
112 <when value="cached">
113 <param name="input_variant" type="data" format="vcf" label="Variant file to annotate" help="-V,--variant &amp;lt;variant&amp;gt;" />
114 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
115 <options from_data_table="gatk2_picard_indexes">
116 <filter type="data_meta" key="dbkey" ref="input_variant" column="dbkey"/>
117 </options>
118 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
119 </param>
120 </when>
121 <when value="history"> <!-- FIX ME!!!! -->
122 <param name="input_variant" type="data" format="vcf" label="Variant file to annotate" help="-V,--variant &amp;lt;variant&amp;gt;" />
123 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
124 </when>
125 </conditional>
126
127
128 <repeat name="variant_filters" title="Variant Filters">
129 <param name="filter_expression" value="AB &lt; 0.2 || MQ0 &gt; 50" type="text" label="Filter expression" help="JEXL formatted expressions (-filter,--filterExpression &amp;lt;filterExpression&amp;gt;)">
130 <sanitizer>
131 <valid initial="string.printable">
132 <remove value="&apos;"/>
133 </valid>
134 <mapping initial="none"/>
135 </sanitizer>
136 </param>
137 <param name="filter_name" value="custom_filter" type="text" label="Filter name" help="-filterName,--filterName &amp;lt;filterName&amp;gt;"/>
138 <param name="is_genotype_filter" type="boolean" truevalue="genotypeFilter" falsevalue="filter" label="Use filter at the individual sample level" help="Use -G_filter,--genotypeFilterExpression &amp;lt;genotypeFilterExpression&amp;gt; and -G_filterName,--genotypeFilterName &amp;lt;genotypeFilterName&amp;gt; for filter type" />
139 </repeat>
140
141
142
143 <conditional name="mask_rod_bind_type">
144 <param name="mask_rod_bind_type_selector" type="select" label="Provide a Mask reference-ordered data file">
145 <option value="set_mask" selected="True">Set maskP</option>
146 <option value="exclude_mask">Don't set mask</option>
147 </param>
148 <when value="exclude_mask">
149 <!-- Do nothing here -->
150 </when>
151 <when value="set_mask">
152 <param name="input_mask_rod" type="data" format="bed,gatk_dbsnp,vcf" label="Mask ROD file" help="--mask &amp;lt;mask&amp;gt;" />
153 <param name="mask_rod_name" type="text" value="Mask" label="Mask Name" help="-maskName,--maskName &amp;lt;maskName&amp;gt;"/>
154 <param name="mask_extension" type="integer" value="0" label="Mask Extension" help="-maskExtend,--maskExtension &amp;lt;maskExtension&amp;gt;"/>
155 </when>
156 </conditional>
157
158
159 <conditional name="gatk_param_type">
160 <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options">
161 <option value="basic" selected="True">Basic</option>
162 <option value="advanced">Advanced</option>
163 </param>
164 <when value="basic">
165 <!-- Do nothing here -->
166 </when>
167 <when value="advanced">
168 <repeat name="pedigree" title="Pedigree file" help="-ped,--pedigree &amp;lt;pedigree&amp;gt;">
169 <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples"/>
170 </repeat>
171 <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &amp;lt;pedigreeString&amp;gt;">
172 <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/>
173 </repeat>
174 <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information" help="-pedValidationType,--pedigreeValidationType &amp;lt;pedigreeValidationType&amp;gt;">
175 <option value="STRICT" selected="True">STRICT</option>
176 <option value="SILENT">SILENT</option>
177 </param>
178 <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &amp;lt;read_filter&amp;gt;">
179 <conditional name="read_filter_type">
180 <param name="read_filter_type_selector" type="select" label="Read Filter Type">
181 <option value="BadCigar">BadCigar</option>
182 <option value="BadMate">BadMate</option>
183 <option value="DuplicateRead">DuplicateRead</option>
184 <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option>
185 <option value="MalformedRead">MalformedRead</option>
186 <option value="MappingQuality">MappingQuality</option>
187 <option value="MappingQualityUnavailable">MappingQualityUnavailable</option>
188 <option value="MappingQualityZero">MappingQualityZero</option>
189 <option value="MateSameStrand">MateSameStrand</option>
190 <option value="MaxInsertSize">MaxInsertSize</option>
191 <option value="MaxReadLength" selected="True">MaxReadLength</option>
192 <option value="MissingReadGroup">MissingReadGroup</option>
193 <option value="NoOriginalQualityScores">NoOriginalQualityScores</option>
194 <option value="NotPrimaryAlignment">NotPrimaryAlignment</option>
195 <option value="Platform454">Platform454</option>
196 <option value="Platform">Platform</option>
197 <option value="PlatformUnit">PlatformUnit</option>
198 <option value="ReadGroupBlackList">ReadGroupBlackList</option>
199 <option value="ReadName">ReadName</option>
200 <option value="ReadStrand">ReadStrand</option>
201 <option value="ReassignMappingQuality">ReassignMappingQuality</option>
202 <option value="Sample">Sample</option>
203 <option value="SingleReadGroup">SingleReadGroup</option>
204 <option value="UnmappedRead">UnmappedRead</option>
205 </param>
206 <when value="BadCigar">
207 <!-- no extra options -->
208 </when>
209 <when value="BadMate">
210 <!-- no extra options -->
211 </when>
212 <when value="DuplicateRead">
213 <!-- no extra options -->
214 </when>
215 <when value="FailsVendorQualityCheck">
216 <!-- no extra options -->
217 </when>
218 <when value="MalformedRead">
219 <!-- no extra options -->
220 </when>
221 <when value="MappingQuality">
222 <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/>
223 </when>
224 <when value="MappingQualityUnavailable">
225 <!-- no extra options -->
226 </when>
227 <when value="MappingQualityZero">
228 <!-- no extra options -->
229 </when>
230 <when value="MateSameStrand">
231 <!-- no extra options -->
232 </when>
233 <when value="MaxInsertSize">
234 <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/>
235 </when>
236 <when value="MaxReadLength">
237 <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/>
238 </when>
239 <when value="MissingReadGroup">
240 <!-- no extra options -->
241 </when>
242 <when value="NoOriginalQualityScores">
243 <!-- no extra options -->
244 </when>
245 <when value="NotPrimaryAlignment">
246 <!-- no extra options -->
247 </when>
248 <when value="Platform454">
249 <!-- no extra options -->
250 </when>
251 <when value="Platform">
252 <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/>
253 </when>
254 <when value="PlatformUnit">
255 <!-- no extra options -->
256 </when>
257 <when value="ReadGroupBlackList">
258 <!-- no extra options -->
259 </when>
260 <when value="ReadName">
261 <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/>
262 </when>
263 <when value="ReadStrand">
264 <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/>
265 </when>
266 <when value="ReassignMappingQuality">
267 <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/>
268 </when>
269 <when value="Sample">
270 <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/>
271 </when>
272 <when value="SingleReadGroup">
273 <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/>
274 </when>
275 <when value="UnmappedRead">
276 <!-- no extra options -->
277 </when>
278 </conditional>
279 </repeat>
280 <repeat name="input_interval_repeat" title="Operate on Genomic intervals" help="-L,--intervals &amp;lt;intervals&amp;gt;">
281 <param name="input_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
282 </repeat>
283 <repeat name="input_exclude_interval_repeat" title="Exclude Genomic intervals" help="-XL,--excludeIntervals &amp;lt;excludeIntervals&amp;gt;">
284 <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
285 </repeat>
286
287 <param name="interval_set_rule" type="select" label="Interval set rule" help="-isr,--interval_set_rule &amp;lt;interval_set_rule&amp;gt;">
288 <option value="UNION" selected="True">UNION</option>
289 <option value="INTERSECTION">INTERSECTION</option>
290 </param>
291
292 <conditional name="downsampling_type">
293 <param name="downsampling_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="-dt,--downsampling_type &amp;lt;downsampling_type&amp;gt;">
294 <option value="NONE" selected="True">NONE</option>
295 <option value="ALL_READS">ALL_READS</option>
296 <option value="BY_SAMPLE">BY_SAMPLE</option>
297 </param>
298 <when value="NONE">
299 <!-- no more options here -->
300 </when>
301 <when value="ALL_READS">
302 <conditional name="downsample_to_type">
303 <param name="downsample_to_type_selector" type="select" label="Downsample method">
304 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
305 <option value="downsample_to_coverage">Downsample by Coverage</option>
306 </param>
307 <when value="downsample_to_fraction">
308 <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &amp;lt;downsample_to_fraction&amp;gt;"/>
309 </when>
310 <when value="downsample_to_coverage">
311 <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &amp;lt;downsample_to_coverage&amp;gt;"/>
312 </when>
313 </conditional>
314 </when>
315 <when value="BY_SAMPLE">
316 <conditional name="downsample_to_type">
317 <param name="downsample_to_type_selector" type="select" label="Downsample method">
318 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
319 <option value="downsample_to_coverage">Downsample by Coverage</option>
320 </param>
321 <when value="downsample_to_fraction">
322 <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &amp;lt;downsample_to_fraction&amp;gt;"/>
323 </when>
324 <when value="downsample_to_coverage">
325 <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &amp;lt;downsample_to_coverage&amp;gt;"/>
326 </when>
327 </conditional>
328 </when>
329 </conditional>
330 <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine" help="-baq,--baq &amp;lt;baq&amp;gt;">
331 <option value="OFF" selected="True">OFF</option>
332 <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option>
333 <option value="RECALCULATE">RECALCULATE</option>
334 </param>
335 <param name="baq_gap_open_penalty" type="float" label="BAQ gap open penalty (Phred Scaled)" value="40" help="Default value is 40. 30 is perhaps better for whole genome call sets. -baqGOP,--baqGapOpenPenalty &amp;lt;baqGapOpenPenalty&amp;gt;" />
336 <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" help="-OQ,--useOriginalQualities" />
337 <param name="default_base_qualities" type="integer" label="Value to be used for all base quality scores, when some are missing" value="-1" help="-DBQ,--defaultBaseQualities &amp;lt;defaultBaseQualities&amp;gt;"/>
338 <param name="validation_strictness" type="select" label="How strict should we be with validation" help="-S,--validation_strictness &amp;lt;validation_strictness&amp;gt;">
339 <option value="STRICT" selected="True">STRICT</option>
340 <option value="LENIENT">LENIENT</option>
341 <option value="SILENT">SILENT</option>
342 <!-- <option value="DEFAULT_STRINGENCY">DEFAULT_STRINGENCY</option> listed in docs, but not valid value...-->
343 </param>
344 <param name="interval_merging" type="select" label="Interval merging rule" help="-im,--interval_merging &amp;lt;interval_merging&amp;gt;">
345 <option value="ALL" selected="True">ALL</option>
346 <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option>
347 </param>
348
349 <repeat name="read_group_black_list_repeat" title="Read group black list" help="-rgbl,--read_group_black_list &amp;lt;read_group_black_list&amp;gt;">
350 <conditional name="read_group_black_list_type">
351 <param name="read_group_black_list_type_selector" type="select" label="Type of reads read group black list">
352 <option value="file" selected="True">Filters in file</option>
353 <option value="text">Specify filters as a string</option>
354 </param>
355 <when value="file">
356 <param name="read_group_black_list" type="data" format="txt" label="Read group black list file" />
357 </when>
358 <when value="text">
359 <param name="read_group_black_list" type="text" value="tag:string" label="Read group black list tag:string" />
360 </when>
361 </conditional>
362 </repeat>
363
364 <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/>
365 <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False" help="-ndrs,--nonDeterministicRandomSeed"/>
366
367 </when>
368 </conditional>
369
370 <conditional name="cluster_snp_type">
371 <param name="cluster_snp_type_selector" type="select" label="Cluster SNPs">
372 <option value="cluster_snp">Cluster SNPs</option>
373 <option value="do_not_cluster_snp" selected="True">Do not cluster SNPs</option>
374 </param>
375 <when value="do_not_cluster_snp">
376 <!-- Do nothing here -->
377 </when>
378 <when value="cluster_snp">
379 <param name="cluster_size" type="integer" value="3" label="The number of SNPs which make up a cluster" help="-cluster,--clusterSize &amp;lt;clusterSize&amp;gt;"/>
380 <param name="cluster_window_size" type="integer" value="0" label="The window size (in bases) in which to evaluate clustered SNPs" help="-window,--clusterWindowSize &amp;lt;clusterWindowSize&amp;gt;"/>
381 </when>
382 </conditional>
383
384 <param name="missing_values_in_expressions_should_evaluate_as_failing" type="boolean" truevalue="--missingValuesInExpressionsShouldEvaluateAsFailing" falsevalue="" label="Should missing values be considered failing the expression" help="--missingValuesInExpressionsShouldEvaluateAsFailing" />
385
386 </inputs>
387 <outputs>
388 <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (Variant File)" />
389 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
390 </outputs>
391 <tests>
392 <test>
393 <param name="reference_source_selector" value="history" />
394 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
395 <param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" />
396 <param name="filter_expression" value="MQ &lt; 37.74 || MQ0 &gt; 50" />
397 <param name="filter_name" value="Galaxy_filter" />
398 <param name="is_genotype_filter" />
399 <param name="mask_rod_bind_type_selector" value="set_mask" />
400 <param name="input_mask_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
401 <param name="mask_rod_name" value="." />
402 <param name="mask_extension" value="0" />
403 <param name="gatk_param_type_selector" value="basic" />
404 <param name="cluster_snp_type_selector" value="do_not_cluster_snp" />
405 <param name="missing_values_in_expressions_should_evaluate_as_failing" />
406 <output name="output_vcf" file="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" lines_diff="4" />
407 <output name="output_log" file="gatk/gatk_variant_filtration/gatk_variant_filtration_out_1.log.contains" compare="contains" />
408 </test>
409 </tests>
410 <help>
411 **What it does**
412
413 Filters variant calls using a number of user-selectable, parameterizable criteria.
414
415 For more information on using the VariantFiltration module, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_filters_VariantFiltration.html&gt;`_.
416
417 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;`_.
418
419 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
420
421 ------
422
423 **Inputs**
424
425 GenomeAnalysisTK: VariantFiltration accepts a VCF input file.
426
427
428 **Outputs**
429
430 The output is in VCF format.
431
432 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
433
434 -------
435
436 **Settings**::
437
438
439 filterExpression One or more expression used with INFO fields to filter (see wiki docs for more info)
440 filterName Names to use for the list of filters (must be a 1-to-1 mapping); this name is put in the FILTER field for variants that get filtered
441 genotypeFilterExpression One or more expression used with FORMAT (sample/genotype-level) fields to filter (see wiki docs for more info)
442 genotypeFilterName Names to use for the list of sample/genotype filters (must be a 1-to-1 mapping); this name is put in the FILTER field for variants that get filtered
443 clusterSize The number of SNPs which make up a cluster (see also --clusterWindowSize); [default:3]
444 clusterWindowSize The window size (in bases) in which to evaluate clustered SNPs (to disable the clustered SNP filter, set this value to less than 1); [default:0]
445 maskName The text to put in the FILTER field if a 'mask' rod is provided and overlaps with a variant call; [default:'Mask']
446 missingValuesInExpressionsShouldEvaluateAsFailing When evaluating the JEXL expressions, should missing values be considered failing the expression (by default they are considered passing)?
447
448 ------
449
450 **Citation**
451
452 For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_
453
454 Please also site `McKenna A, Hanna M, Banks E, Sivachenko A, Cibulskis K, Kernytsky A, Garimella K, Altshuler D, Gabriel S, Daly M, DePristo MA (2010). The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data. Genome Res. 20:1297-303. Epub 2010 Jul 19. &lt;http://www.ncbi.nlm.nih.gov/pubmed/20644199&gt;`_
455
456 If you use this tool in Galaxy, please cite `Blankenberg D, Von Kuster G, Coraor N, Ananda G, Lazarus R, Mangan M, Nekrutenko A, Taylor J. Galaxy: a web-based genome analysis tool for experimentalists. Curr Protoc Mol Biol. 2010 Jan;Chapter 19:Unit 19.10.1-21. &lt;http://www.ncbi.nlm.nih.gov/pubmed/20069535&gt;`_
457
458
459 </help>
460 </tool>