Mercurial > repos > jjohnson > gatk2

comparison realigner_target_creator.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_realigner_target_creator" name="Realigner Target Creator" version="0.0.4">
2 <description>for use in local realignment</description>
3 <requirements>
4 <requirement type="package" version="2.2">gatk</requirement>
5 <requirement type="package" version="0.1.18">samtools</requirement>
6 </requirements>
7 <command interpreter="python">gatk2_wrapper.py
8 --max_jvm_heap_fraction "1"
9 --stdout "${output_log}"
10 -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
11 #if str( $reference_source.input_bam.metadata.bam_index ) != "None":
12 -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
13 #end if
14 -p 'java
15 -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
16 -T "RealignerTargetCreator"
17 -o "${output_interval}"
18 \$GATK2_SITE_OPTIONS
19 ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home
20 ##--num_threads 4 ##hard coded, for now
21 ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
22 #if $reference_source.reference_source_selector != "history":
23 -R "${reference_source.ref_file.fields.path}"
24 #end if
25 '
26 #set $rod_binding_names = dict()
27 #for $rod_binding in $rod_bind:
28 #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
29 #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
30 #else
31 #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
32 #end if
33 #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
34 -d "-known:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}"
35 #end for
36
37 ##start standard gatk options
38 #if $gatk_param_type.gatk_param_type_selector == "advanced":
39 #for $pedigree in $gatk_param_type.pedigree:
40 -p '--pedigree "${pedigree.pedigree_file}"'
41 #end for
42 #for $pedigree_string in $gatk_param_type.pedigree_string_repeat:
43 -p '--pedigreeString "${pedigree_string.pedigree_string}"'
44 #end for
45 -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"'
46 #for $read_filter in $gatk_param_type.read_filter:
47 -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}"
48 ###raise Exception( str( dir( $read_filter ) ) )
49 #for $name, $param in $read_filter.read_filter_type.iteritems():
50 #if $name not in [ "__current_case__", "read_filter_type_selector" ]:
51 #if hasattr( $param.input, 'truevalue' ):
52 ${param}
53 #else:
54 --${name} "${param}"
55 #end if
56 #end if
57 #end for
58 '
59 #end for
60 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ):
61 -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}"
62 #end for
63
64 #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ):
65 -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}"
66 #end for
67
68 -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"'
69
70 -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"'
71 #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE":
72 -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"'
73 #end if
74 -p '
75 --baq "${gatk_param_type.baq}"
76 --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}"
77 ${gatk_param_type.use_original_qualities}
78 --defaultBaseQualities "${gatk_param_type.default_base_qualities}"
79 --validation_strictness "${gatk_param_type.validation_strictness}"
80 --interval_merging "${gatk_param_type.interval_merging}"
81 ${gatk_param_type.disable_experimental_low_memory_sharding}
82 ${gatk_param_type.non_deterministic_random_seed}
83 '
84 #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ):
85 #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file":
86 -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}"
87 #else
88 -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"'
89 #end if
90 #end for
91 #end if
92
93 #if $reference_source.reference_source_selector == "history":
94 -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
95 #end if
96 ##end standard gatk options
97 ##start analysis specific options
98 #if $analysis_param_type.analysis_param_type_selector == "advanced":
99 -p '
100 --minReadsAtLocus "${analysis_param_type.minReadsAtLocus}"
101 --windowSize "${analysis_param_type.windowSize}"
102 --mismatchFraction "${analysis_param_type.mismatchFraction}"
103 --maxIntervalSize "${analysis_param_type.maxIntervalSize}"
104 '
105 #end if
106 </command>
107 <inputs>
108 <conditional name="reference_source">
109 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
110 <option value="cached">Locally cached</option>
111 <option value="history">History</option>
112 </param>
113 <when value="cached">
114 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;">
115 <validator type="unspecified_build" />
116 <validator type="dataset_metadata_in_data_table" table_name="gatk2_picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select -->
117 </param>
118 <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" >
119 <options from_data_table="gatk2_picard_indexes">
120 <filter type="data_meta" key="dbkey" ref="input_bam" column="dbkey"/>
121 </options>
122 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
123 </param>
124 </when>
125 <when value="history">
126 <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;" />
127 <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
128 <options>
129 <filter type="data_meta" key="dbkey" ref="input_bam" />
130 </options>
131 </param>
132 </when>
133 </conditional>
134
135 <repeat name="rod_bind" title="Binding for reference-ordered data" help="-known,--known &amp;lt;known&amp;gt;">
136 <conditional name="rod_bind_type">
137 <param name="rod_bind_type_selector" type="select" label="Binding Type">
138 <option value="dbsnp" selected="True">dbSNP</option>
139 <option value="snps">SNPs</option>
140 <option value="indels">INDELs</option>
141 <option value="custom">Custom</option>
142 </param>
143 <when value="dbsnp">
144 <param name="input_rod" type="data" format="vcf" label="ROD file" />
145 </when>
146 <when value="snps">
147 <param name="input_rod" type="data" format="vcf" label="ROD file" />
148 </when>
149 <when value="indels">
150 <param name="input_rod" type="data" format="vcf" label="ROD file" />
151 </when>
152 <when value="custom">
153 <param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/>
154 <param name="input_rod" type="data" format="vcf" label="ROD file" />
155 </when>
156 </conditional>
157 </repeat>
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="analysis_param_type">
371 <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
372 <option value="basic" selected="True">Basic</option>
373 <option value="advanced">Advanced</option>
374 </param>
375 <when value="basic">
376 <!-- Do nothing here -->
377 </when>
378 <when value="advanced">
379 <param name="windowSize" type="integer" value="10" label="Window size for calculating entropy or SNP clusters (windowSize)" help="-window,--windowSize &amp;lt;windowSize&amp;gt;" />
380 <param name="mismatchFraction" type="float" value="0.15" label="Fraction of base qualities needing to mismatch for a position to have high entropy (mismatchFraction)" help="to disable set to &lt;= 0 or &gt; 1 (-mismatch,--mismatchFraction &amp;lt;mismatchFraction&amp;gt;)"/>
381 <param name="minReadsAtLocus" type="integer" value="4" label="Minimum reads at a locus to enable using the entropy calculation (minReadsAtLocus)" help="-minReads,--minReadsAtLocus &amp;lt;minReadsAtLocus&amp;gt;" />
382 <param name="maxIntervalSize" type="integer" value="500" label="Maximum interval size" help="-maxInterval,--maxIntervalSize &amp;lt;maxIntervalSize&amp;gt;" />
383 </when>
384 </conditional>
385 </inputs>
386 <outputs>
387 <data format="gatk_interval" name="output_interval" label="${tool.name} on ${on_string} (GATK intervals)" />
388 <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
389 </outputs>
390 <tests>
391 <test>
392 <param name="reference_source_selector" value="history" />
393 <param name="ref_file" value="phiX.fasta" ftype="fasta" />
394 <param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" />
395 <param name="rod_bind_type_selector" value="dbsnp" />
396 <param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" />
397 <param name="gatk_param_type_selector" value="basic" />
398 <param name="analysis_param_type_selector" value="advanced" />
399 <param name="windowSize" value="10" />
400 <param name="mismatchFraction" value="0.15" />
401 <param name="minReadsAtLocus" value="4" />
402 <param name="maxIntervalSize" value="500" />
403 <output name="output_interval" file="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.gatk_interval" />
404 <output name="output_log" file="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.log.contains" compare="contains"/>
405 </test>
406 </tests>
407 <help>
408 **What it does**
409
410 Emits intervals for the Local Indel Realigner to target for cleaning. Ignores 454 reads, MQ0 reads, and reads with consecutive indel operators in the CIGAR string.
411
412 For more information on local realignment around indels using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_indels_RealignerTargetCreator.html&gt;`_.
413
414 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;`_.
415
416 If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.
417
418 ------
419
420 **Inputs**
421
422 GenomeAnalysisTK: RealignerTargetCreator accepts an aligned BAM input file.
423
424
425 **Outputs**
426
427 The output is in GATK Interval format.
428
429
430 Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.
431
432 -------
433
434 **Settings**::
435
436 windowSize window size for calculating entropy or SNP clusters
437 mismatchFraction fraction of base qualities needing to mismatch for a position to have high entropy; to disable set to &lt;= 0 or &gt; 1
438 minReadsAtLocus minimum reads at a locus to enable using the entropy calculation
439 maxIntervalSize maximum interval size
440
441 ------
442
443 **Citation**
444
445 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;`_
446
447 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;`_
448
449 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;`_
450
451 </help>
452 </tool>