comparison variants_validate.xml @ 11:432aafa6830a draft

Uploaded
author david-hoover
date Wed, 12 Sep 2012 17:54:46 -0400
parents
children 1326b011a3b9
comparison
equal deleted inserted replaced
10:b138c5569231 11:432aafa6830a
1 <tool id="gatk2_validate_variants" name="Validate Variants" version="0.0.1">
2 <description></description>
3 <requirements>
4 <requirement type="package" version="2.1">gatk</requirement>
5 </requirements>
6 <command interpreter="python">gatk2_wrapper.py
7 --max_jvm_heap_fraction "1"
8 --stdout "${output_log}"
9 -d "--variant:variant,%(file_type)s" "${reference_source.input_variant}" "${reference_source.input_variant.ext}" "input_variant"
10 -p 'java
11 -jar "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/GenomeAnalysisTK.jar"
12 -T "ValidateVariants"
13
14 -et "NO_ET" -K "/data/galaxy/galaxy3/tool-data/shared/jars/gatk2/gatk2_key_file" ##ET no phone home
15 ##--num_threads 4 ##hard coded, for now
16 ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
17 #if $reference_source.reference_source_selector != "history":
18 -R "${reference_source.ref_file.fields.path}"
19 #end if
20 ${warn_on_errors}
21 ${do_not_validate_filtered_records}
22 '
23
24 #if str( $dbsnp_rod_bind_type.dbsnp_rod_bind_type_selector ) == 'set_dbsnp':
25 -d "--dbsnp:${dbsnp_rod_bind_type.dbsnp_rod_name},%(file_type)s" "${dbsnp_rod_bind_type.dbsnp_input_rod}" "${dbsnp_rod_bind_type.dbsnp_input_rod.ext}" "input_dbsnp_${dbsnp_rod_bind_type.dbsnp_rod_name}"
26 #end if
27
28 ##start standard gatk options
29 #if $gatk_param_type.gatk_param_type_selector == "advanced":
30 #for $pedigree in $gatk_param_type.pedigree:
31 -p '--pedigree "${pedigree.pedigree_file}"'
32 #end for
33 #for $pedigree_string in $gatk_param_type.pedigree_string_repeat:
34 -p '--pedigreeString "${pedigree_string.pedigree_string}"'
35 #end for
36 -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"'
37 #for $read_filter in $gatk_param_type.read_filter:
38 -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}"
39 ###raise Exception( str( dir( $read_filter ) ) )
40 #for $name, $param in $read_filter.read_filter_type.iteritems():
41 #if $name not in [ "__current_case__", "read_filter_type_selector" ]:
42 #if hasattr( $param.input, 'truevalue' ):
43 ${param}
44 #else:
45 --${name} "${param}"
46 #end if
47 #end if
48 #end for
49 '
50 #end for
51 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ):
52 -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}"
53 #end for
54
55 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ):
56 -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}"
57 #end for
58
59 -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"'
60
61 -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"'
62 #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE":
63 -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"'
64 #end if
65 -p '
66 --baq "${gatk_param_type.baq}"
67 --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}"
68 ${gatk_param_type.use_original_qualities}
69 --defaultBaseQualities "${gatk_param_type.default_base_qualities}"
70 --validation_strictness "${gatk_param_type.validation_strictness}"
71 --interval_merging "${gatk_param_type.interval_merging}"
72 ${gatk_param_type.disable_experimental_low_memory_sharding}
73 ${gatk_param_type.non_deterministic_random_seed}
74 '
75 #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ):
76 #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file":
77 -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}"
78 #else
79 -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"'
80 #end if
81 #end for
82 #end if
83
84 #if $reference_source.reference_source_selector == "history":
85 -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
86 #end if
87 ##end standard gatk options
88
89 </command>
90 <inputs>
91
92 <conditional name="reference_source">
93 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
94 <option value="cached">Locally cached</option>
95 <option value="history">History</option>
96 </param>
97 <when value="cached">
98 <param name="input_variant" type="data" format="vcf" label="Input variant file" help="-V,--variant &amp;lt;variant&amp;gt;" />
99 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
100 <options from_data_table="gatk2_picard_indexes">
101 <filter type="data_meta" key="dbkey" ref="input_variant" column="dbkey"/>
102 </options>
103 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
104 </param>
105 </when>
106 <when value="history"> <!-- FIX ME!!!! -->
107 <param name="input_variant" type="data" format="vcf" label="Input variant file" help="-V,--variant &amp;lt;variant&amp;gt;" />
108 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
109 </when>
110 </conditional>
111
112 <conditional name="dbsnp_rod_bind_type">
113 <param name="dbsnp_rod_bind_type_selector" type="select" label="Provide a dbSNP reference-ordered data file" help="-D,--dbsnp &amp;lt;dbsnp&amp;gt;">
114 <option value="set_dbsnp" selected="True">Set dbSNP</option>
115 <option value="exclude_dbsnp">Don't set dbSNP</option>
116 </param>
117 <when value="exclude_dbsnp">
118 <!-- Do nothing here -->
119 </when>
120 <when value="set_dbsnp">
121 <param name="dbsnp_input_rod" type="data" format="vcf" label="ROD file" />
122 <param name="dbsnp_rod_name" type="hidden" value="dbsnp" label="ROD Name"/>
123 </when>
124 </conditional>
125
126 <param name="warn_on_errors" type="boolean" checked="False" truevalue="-warnOnErrors" falsevalue="" label="instead of terminating the run at the first error, print warning messages for each error seen." help="-warnOnErrors,--warnOnErrors"/>
127 <param name="do_not_validate_filtered_records" type="boolean" checked="False" truevalue="-doNotValidateFilteredRecords" falsevalue="" label="do not try to validate records that are FILTERed." help="-doNotValidateFilteredRecords,--doNotValidateFilteredRecords"/>
128
129 <conditional name="gatk_param_type">
130 <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options">
131 <option value="basic" selected="True">Basic</option>
132 <option value="advanced">Advanced</option>
133 </param>
134 <when value="basic">
135 <!-- Do nothing here -->
136 </when>
137 <when value="advanced">
138 <repeat name="pedigree" title="Pedigree file" help="-ped,--pedigree &amp;lt;pedigree&amp;gt;">
139 <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples"/>
140 </repeat>
141 <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &amp;lt;pedigreeString&amp;gt;">
142 <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/>
143 </repeat>
144 <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;">
145 <option value="STRICT" selected="True">STRICT</option>
146 <option value="SILENT">SILENT</option>
147 </param>
148 <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &amp;lt;read_filter&amp;gt;">
149 <conditional name="read_filter_type">
150 <param name="read_filter_type_selector" type="select" label="Read Filter Type">
151 <option value="BadCigar">BadCigar</option>
152 <option value="BadMate">BadMate</option>
153 <option value="DuplicateRead">DuplicateRead</option>
154 <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option>
155 <option value="MalformedRead">MalformedRead</option>
156 <option value="MappingQuality">MappingQuality</option>
157 <option value="MappingQualityUnavailable">MappingQualityUnavailable</option>
158 <option value="MappingQualityZero">MappingQualityZero</option>
159 <option value="MateSameStrand">MateSameStrand</option>
160 <option value="MaxInsertSize">MaxInsertSize</option>
161 <option value="MaxReadLength" selected="True">MaxReadLength</option>
162 <option value="MissingReadGroup">MissingReadGroup</option>
163 <option value="NoOriginalQualityScores">NoOriginalQualityScores</option>
164 <option value="NotPrimaryAlignment">NotPrimaryAlignment</option>
165 <option value="Platform454">Platform454</option>
166 <option value="Platform">Platform</option>
167 <option value="PlatformUnit">PlatformUnit</option>
168 <option value="ReadGroupBlackList">ReadGroupBlackList</option>
169 <option value="ReadName">ReadName</option>
170 <option value="ReadStrand">ReadStrand</option>
171 <option value="ReassignMappingQuality">ReassignMappingQuality</option>
172 <option value="Sample">Sample</option>
173 <option value="SingleReadGroup">SingleReadGroup</option>
174 <option value="UnmappedRead">UnmappedRead</option>
175 </param>
176 <when value="BadCigar">
177 <!-- no extra options -->
178 </when>
179 <when value="BadMate">
180 <!-- no extra options -->
181 </when>
182 <when value="DuplicateRead">
183 <!-- no extra options -->
184 </when>
185 <when value="FailsVendorQualityCheck">
186 <!-- no extra options -->
187 </when>
188 <when value="MalformedRead">
189 <!-- no extra options -->
190 </when>
191 <when value="MappingQuality">
192 <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/>
193 </when>
194 <when value="MappingQualityUnavailable">
195 <!-- no extra options -->
196 </when>
197 <when value="MappingQualityZero">
198 <!-- no extra options -->
199 </when>
200 <when value="MateSameStrand">
201 <!-- no extra options -->
202 </when>
203 <when value="MaxInsertSize">
204 <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/>
205 </when>
206 <when value="MaxReadLength">
207 <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/>
208 </when>
209 <when value="MissingReadGroup">
210 <!-- no extra options -->
211 </when>
212 <when value="NoOriginalQualityScores">
213 <!-- no extra options -->
214 </when>
215 <when value="NotPrimaryAlignment">
216 <!-- no extra options -->
217 </when>
218 <when value="Platform454">
219 <!-- no extra options -->
220 </when>
221 <when value="Platform">
222 <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/>
223 </when>
224 <when value="PlatformUnit">
225 <!-- no extra options -->
226 </when>
227 <when value="ReadGroupBlackList">
228 <!-- no extra options -->
229 </when>
230 <when value="ReadName">
231 <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/>
232 </when>
233 <when value="ReadStrand">
234 <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/>
235 </when>
236 <when value="ReassignMappingQuality">
237 <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/>
238 </when>
239 <when value="Sample">
240 <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/>
241 </when>
242 <when value="SingleReadGroup">
243 <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/>
244 </when>
245 <when value="UnmappedRead">
246 <!-- no extra options -->
247 </when>
248 </conditional>
249 </repeat>
250 <repeat name="input_interval_repeat" title="Operate on Genomic intervals" help="-L,--intervals &amp;lt;intervals&amp;gt;">
251 <param name="input_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
252 </repeat>
253 <repeat name="input_exclude_interval_repeat" title="Exclude Genomic intervals" help="-XL,--excludeIntervals &amp;lt;excludeIntervals&amp;gt;">
254 <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
255 </repeat>
256
257 <param name="interval_set_rule" type="select" label="Interval set rule" help="-isr,--interval_set_rule &amp;lt;interval_set_rule&amp;gt;">
258 <option value="UNION" selected="True">UNION</option>
259 <option value="INTERSECTION">INTERSECTION</option>
260 </param>
261
262 <conditional name="downsampling_type">
263 <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;">
264 <option value="NONE" selected="True">NONE</option>
265 <option value="ALL_READS">ALL_READS</option>
266 <option value="BY_SAMPLE">BY_SAMPLE</option>
267 </param>
268 <when value="NONE">
269 <!-- no more options here -->
270 </when>
271 <when value="ALL_READS">
272 <conditional name="downsample_to_type">
273 <param name="downsample_to_type_selector" type="select" label="Downsample method">
274 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
275 <option value="downsample_to_coverage">Downsample by Coverage</option>
276 </param>
277 <when value="downsample_to_fraction">
278 <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;"/>
279 </when>
280 <when value="downsample_to_coverage">
281 <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;"/>
282 </when>
283 </conditional>
284 </when>
285 <when value="BY_SAMPLE">
286 <conditional name="downsample_to_type">
287 <param name="downsample_to_type_selector" type="select" label="Downsample method">
288 <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
289 <option value="downsample_to_coverage">Downsample by Coverage</option>
290 </param>
291 <when value="downsample_to_fraction">
292 <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;"/>
293 </when>
294 <when value="downsample_to_coverage">
295 <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;"/>
296 </when>
297 </conditional>
298 </when>
299 </conditional>
300 <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine" help="-baq,--baq &amp;lt;baq&amp;gt;">
301 <option value="OFF" selected="True">OFF</option>
302 <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option>
303 <option value="RECALCULATE">RECALCULATE</option>
304 </param>
305 <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;" />
306 <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" help="-OQ,--useOriginalQualities" />
307 <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;"/>
308 <param name="validation_strictness" type="select" label="How strict should we be with validation" help="-S,--validation_strictness &amp;lt;validation_strictness&amp;gt;">
309 <option value="STRICT" selected="True">STRICT</option>
310 <option value="LENIENT">LENIENT</option>
311 <option value="SILENT">SILENT</option>
312 <!-- <option value="DEFAULT_STRINGENCY">DEFAULT_STRINGENCY</option> listed in docs, but not valid value...-->
313 </param>
314 <param name="interval_merging" type="select" label="Interval merging rule" help="-im,--interval_merging &amp;lt;interval_merging&amp;gt;">
315 <option value="ALL" selected="True">ALL</option>
316 <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option>
317 </param>
318
319 <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;">
320 <conditional name="read_group_black_list_type">
321 <param name="read_group_black_list_type_selector" type="select" label="Type of reads read group black list">
322 <option value="file" selected="True">Filters in file</option>
323 <option value="text">Specify filters as a string</option>
324 </param>
325 <when value="file">
326 <param name="read_group_black_list" type="data" format="txt" label="Read group black list file" />
327 </when>
328 <when value="text">
329 <param name="read_group_black_list" type="text" value="tag:string" label="Read group black list tag:string" />
330 </when>
331 </conditional>
332 </repeat>
333
334 <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"/>
335 <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"/>
336
337 </when>
338 </conditional>
339
340 </inputs>
341 <outputs>
342 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
343 </outputs>
344 <tests>
345 <test>
346 <param name="reference_source_selector" value="history" />
347 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
348 <param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" />
349 <param name="dbsnp_rod_bind_type_selector" value="set_dbsnp" />
350 <param name="dbsnp_input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" />
351 <param name="warn_on_errors" value="True"/>
352 <param name="do_not_validate_filtered_records" />
353 <param name="gatk_param_type_selector" value="basic" />
354 <output name="output_log" file="gatk/gatk_validate_variants/gatk_validate_variants_out_1.log.contains" compare="contains" />
355 </test>
356 </tests>
357 <help>
358 **What it does**
359
360 Validates a variants file.
361
362 For more information on using the ValidateVariants module, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/VariantValidator&gt;`_.
363
364 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;`_.
365
366 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
367
368 ------
369
370 **Inputs**
371
372 GenomeAnalysisTK: ValidateVariants accepts variant files as input.
373
374
375 **Outputs**
376
377 The output is a log of variant validation.
378
379
380 Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
381
382 -------
383
384 **Settings**::
385
386 doNotValidateFilteredRecords should we skip validation on filtered records?
387 warnOnErrors should we just emit warnings on errors instead of terminating the run?
388
389 ------
390
391 **Citation**
392
393 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;`_
394
395 If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.*
396
397 </help>
398 </tool>