Mercurial > repos > devteam > testing_cgatools

comparison testing_cgatools-982e19c29ec0/cgatools/tools/cgatools_1.6/calldiff.xml @ 0:ef23f9cd599b draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Thu, 27 Sep 2012 13:37:59 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:ef23f9cd599b
1 <tool id="cg_calldiff" name="calldiff(beta) 1.6" version="1.0.1">
2 <!--
3 This tool creates a GUI for the calldiff function of cgatools from Complete Genomics, Inc.
4 written 6-18-2012 by bcrain@completegenomics.com
5 updated 8-14-2012 by bcrain@completegenomics.com
6 -->
7
8 <description>compares two Complete Genomics variant files.</description>
9
10 <command>
11 <!-- print version of cgatools to STDOUT-->
12 cgatools | head -1;
13
14 <!-- print command lines to STDOUT-->
15 echo "cgatools calldiff --beta
16 --reference ${crr.fields.path}
17 --variantsA $data_sources.inputA
18 --variantsB $data_sources.inputB
19 $validation
20 $diploid
21 --locus-stats-column-count $column
22 --max-hypothesis-count $hypothesis
23 --output-prefix cg_
24 --reports `echo ${report1} ${report2} ${report3} ${report4} ${report5} ${somatic.report6} | sed 's/ */,/g'`
25 #if $somatic.report6 == "SomaticOutput"
26 --genome-rootA $somatic.genomeA
27 --genome-rootB $somatic.genomeB
28 --calibration-root $somatic.calibration
29 #end if
30 ";
31
32 <!-- execute cgatools-->
33 cgatools calldiff --beta
34 --reference ${crr.fields.path}
35 --variantsA $data_sources.inputA
36 --variantsB $data_sources.inputB
37 $validation
38 $diploid
39 --locus-stats-column-count $column
40 --max-hypothesis-count $hypothesis
41 --output-prefix cg_
42 --reports `echo ${report1} ${report2} ${report3} ${report4} ${report5} ${somatic.report6} | sed 's/ */,/g'`
43 #if $somatic.report6 == "SomaticOutput"
44 --genome-rootA $somatic.genomeA
45 --genome-rootB $somatic.genomeB
46 --calibration-root $somatic.calibration
47 #end if
48 </command>
49
50 <outputs>
51 <data format="tabular" name="output1" from_work_dir="cg_SuperlocusOutput.tsv" label="${tool.name} SuperlocusOutput">
52 <filter>(report1 == 'SuperlocusOutput')</filter>
53 </data>
54 <data format="tabular" name="output2" from_work_dir="cg_SuperlocusStats.tsv" label="${tool.name} SuperlocusStats">
55 <filter>(report2 == 'SuperlocusStats')</filter>
56 </data>
57 <data format="tabular" name="output3" from_work_dir="cg_LocusOutput.tsv" label="${tool.name} LocusOutput">
58 <filter>(report3 == 'LocusOutput')</filter>
59 </data>
60 <data format="tabular" name="output4" from_work_dir="cg_LocusStats.tsv" label="${tool.name} LocusStats">
61 <filter>(report4 == 'LocusStats')</filter>
62 </data>
63 <data format="tabular" name="output5a" from_work_dir="cg_VariantsA.tsv" label="${tool.name} VariantsA">
64 <filter>(report5 == 'VariantOutput')</filter>
65 </data>
66 <data format="tabular" name="output5b" from_work_dir="cg_VariantsB.tsv" label="${tool.name} VariantsB">
67 <filter>(report5 == 'VariantOutput')</filter>
68 </data>
69 <data format="tabular" name="output6" from_work_dir="cg_SomaticOutput.tsv" label="${tool.name} SomaticOutput">
70 <filter>(somatic['report6'] == 'SomaticOutput')</filter>
71 </data>
72 </outputs>
73
74 <inputs>
75 <!--form field to select crr file-->
76 <param name="crr" type="select" label="Reference genome (.crr file)">
77 <options from_data_table="cg_crr_files" />
78 </param>
79
80 <!--conditional to select variant file input-->
81 <conditional name="data_sources">
82 <param name="data_source" type="select" label="Where are the input varfiles?">
83 <option value="in" selected="true">imported into Galaxy</option>
84 <option value="out">located outside Galaxy (data on server or mounted drive)</option>
85 </param>
86
87 <!--form field to select variant files-->
88 <when value="in">
89 <param name="inputA" type="data" format="cg_var" label="Var file A">
90 <validator type="dataset_ok_validator" />
91 <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
92 metadata_name="dbkey" metadata_column="1"
93 message="cgatools is not currently available for this build."/>
94 </param>
95 <param name="inputB" type="data" format="cg_var" label="Var file B">
96 <validator type="dataset_ok_validator" />
97 <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
98 metadata_name="dbkey" metadata_column="1"
99 message="cgatools is not currently available for this build."/>
100 </param>
101 </when>
102
103 <!--form field to enter input files-->
104 <when value="out">
105 <param name="inputA" type="text" label="Variant file A (/path/varfile)" size="300" help="Variant file can be compressed (gz, bz2), e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01_2000/ASM/var-GS00000YYYY-ASM.tsv.bz2">
106 <validator type="empty_field" message="You must supply a var file"/>
107 </param>
108 <param name="inputB" type="text" label="Variant file B (/path/varfile)" size="300" help="Variant file can be compressed (gz, bz2), e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01_2000/ASM/var-GS00000YYYY-ASM.tsv.bz2.">
109 <validator type="empty_field" message="You must supply a var file"/>
110 </param>
111 </when>
112 </conditional>
113
114 <!--other parameters-->
115 <param name="diploid" type="select" label="Use diploid variant model" help="Uses varScoreEAF instead of varScoreVAF in somatic score computations. Also, uses diploid variant model instead of variable allele mixture model.">
116 <option value="">no</option>
117 <option value="--diploid">yes</option>
118 </param>
119
120 <param name="column" type="integer" label="Number of columns for locus compare classification in the locus stats file (default 15)" value="15">
121 <validator type="empty_field" message="You must enter a value, the default is 15" />
122 </param>
123
124 <param name="hypothesis" type="integer" label="Maximum number of possible phasings to consider for a superlocus (default 32)" value="32">
125 <validator type="empty_field" message="You must enter a value, the default is 32" />
126 </param>
127
128 <param name="validation" type="select" label="Reference cover validation (default on)" help="Turns on/off validation that all bases of a chromosome are covered by calls of the variant file.">
129 <option value="">on</option>
130 <option value="--no-reference-cover-validation">off</option>
131 </param>
132
133 <!--form fields to select ooutput reports-->
134 <param name="report1" type="select" label="Create report SuperlocusOutput">
135 <option value="">no</option>
136 <option value="SuperlocusOutput">yes</option>
137 </param>
138 <param name="report2" type="select" label="Create report SuperlocusStats">
139 <option value="">no</option>
140 <option value="SuperlocusStats">yes</option>
141 </param>
142 <param name="report3" type="select" label="Create report LocusOutput">
143 <option value="">no</option>
144 <option value="LocusOutput">yes</option>
145 </param>
146 <param name="report4" type="select" label="Create report LocusStats">
147 <option value="">no</option>
148 <option value="LocusStats">yes</option>
149 </param>
150 <param name="report5" type="select" label="Create report VariantOutput" help="Both variant files annotated by comparison results. If the somatic output report is requested, file A is also annotated with the same score ranks as produced in that report.">
151 <option value="">no</option>
152 <option value="VariantOutput">yes</option>
153 </param>
154
155 <!--conditional to select somatic reports and related inputs-->
156 <conditional name="somatic">
157 <param name="report6" type="select" label="Create report SomaticOutput" help="This report can only be generated on local Galaxy instances. Report for the list of simple variations that are present only in file 'A', annotated with the score that indicates the probability of the variation being truly somatic. Note: generating this report slows calldiff by 10x-20x.">
158 <option value="">no</option>
159 <option value="SomaticOutput">yes</option>
160 </param>
161
162 <when value="SomaticOutput">
163 <param name="genomeA" type="text" size="300" label="Directory for genome A (/path/dir)" help="The 'A' genome directory, e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01_2000; this directory is expected to contain ASM/REF and ASM/EVIDENCE subdirectories.">
164 <validator type="empty_field" message="You must supply the genome root directory for this sample"/>
165 </param>
166 <param name="genomeB" type="text" size="300" label="Directory for genome B (/path/dir)" help="The 'B' genome directory, e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01_2000; this directory is expected to contain ASM/REF and ASM/EVIDENCE subdirectories.">
167 <validator type="empty_field" message="You must supply the genome root directory for this sample"/>
168 </param>
169 <param name="calibration" type="text" size="300" label="Directory containing calibration data (/path/dir)" help="The directory containing calibration data. For example, there should exist a file calibration-root/0.0.0/metrics.tsv. Calibration data can be downloaded from ftp://ftp.completegenomics.com/ScoreCalibrationFiles/var-calibration-v1.tgz">
170 <validator type="empty_field" message="You must supply the directory containing the calibration data"/>
171 </param>
172 </when>
173 </conditional>
174
175 </inputs>
176
177 <help>
178
179 **What it does**
180
181 This tool uses cgatools calldiff to compare two Complete Genomics variant files.
182
183 **cgatools 1.6.0 Documentation**
184
185 Userguide: http://cgatools.sourceforge.net/docs/1.6.0/cgatools-user-guide.pdf
186
187 Release notes: http://cgatools.sourceforge.net/docs/1.6.0/cgatools-release-notes.pdf
188
189 **Command line reference**::
190
191 COMMAND NAME
192 calldiff - Compares two Complete Genomics variant files.
193
194 DESCRIPTION
195 Compares two Complete Genomics variant files. Divides the genome up into
196 superloci of nearby variants, then compares the superloci. Also refines the
197 comparison to determine per-call or per-locus comparison results.
198
199 Comparison results are usually described by a semi-colon separated string,
200 one per allele. Each allele's comparison result is one of the following
201 classifications:
202
203 ref-identical The alleles of the two variant files are identical, and
204 they are consistent with the reference.
205 alt-identical The alleles of the two variant files are identical, and
206 they are inconsistent with the reference.
207 ref-consistent The alleles of the two variant files are consistent,
208 and they are consistent with the reference.
209 alt-consistent The alleles of the two variant files are consistent,
210 and they are inconsistent with the reference.
211 onlyA The alleles of the two variant files are inconsistent,
212 and only file A is inconsistent with the reference.
213 onlyB The alleles of the two variant files are inconsistent,
214 and only file B is inconsistent with the reference.
215 mismatch The alleles of the two variant files are inconsistent,
216 and they are both inconsistent with the reference.
217 phase-mismatch The two variant files would be consistent if the
218 hapLink field had been empty, but they are
219 inconsistent.
220 ploidy-mismatch The superlocus did not have uniform ploidy.
221
222 In some contexts, this classification is rolled up into a simplified
223 classification, which is one of "identical", "consistent", "onlyA",
224 "onlyB", or "mismatch".
225
226 A good place to start looking at the results is the superlocus-output file.
227 It has columns defined as follows:
228
229 SuperlocusId An identifier given to the superlocus.
230 Chromosome The name of the chromosome.
231 Begin The 0-based offset of the start of the superlocus.
232 End The 0-based offset of the base one past the end of the
233 superlocus.
234 Classification The match classification of the superlocus.
235 Reference The reference sequence.
236 AllelesA A semicolon-separated list of the alleles (one per
237 haplotype) for variant file A, for the phasing with the
238 best comparison result.
239 AllelesB A semicolon-separated list of the alleles (one per
240 haplotype) for variant file B, for the phasing with the
241 best comparison result.
242
243 The locus-output file contains, for each locus in file A and file B that is
244 not consistent with the reference, an annotated set of calls for the locus.
245 The calls are annotated with the following columns:
246
247 SuperlocusId The id of the superlocus containing the locus.
248 File The variant file (A or B).
249 LocusClassification The locus classification is determined by the
250 varType column of the call that is inconsistent
251 with the reference, concatenated with a
252 modifier that describes whether the locus is
253 heterozygous, homozygous, or contains no-calls.
254 If there is no one variant in the locus (i.e.,
255 it is heterozygous alt-alt), the locus
256 classification begins with "other".
257 LocusDiffClassification The match classification for the locus. This is
258 defined to be the best of the comparison of the
259 locus to the same region in the other file, or
260 the comparison of the superlocus.
261
262 The somatic output file contains a list of putative somatic variations of
263 genome A. The output includes only those loci that can be classified as
264 snp, del, ins or sub in file A, and are called reference in the file B.
265 Every locus is annotated with the following columns:
266
267 VarCvgA The totalReadCount from file A for this locus
268 (computed on the fly if file A is not a
269 masterVar file).
270 VarScoreA The varScoreVAF from file A, or varScoreEAF if
271 the "--diploid" option is used.
272 RefCvgB The maximum of the uniqueSequenceCoverage
273 values for the locus in genome B.
274 RefScoreB Minimum of the reference scores of the locus in
275 genome B.
276 SomaticCategory The category used for determining the
277 calibrated scores and the SomaticRank.
278 VarScoreACalib The calibrated variant score of file A, under
279 the model selected by using or not using the
280 "--diploid" option, and corrected for the count
281 of heterozygous variants observed in this
282 genome. See user guide for more information.
283 VarScoreBCalib The calibrated reference score of file B, under
284 the model selected by using or not using the
285 "--diploid" option, and corrected for the count
286 of heterozygous variants observed in this
287 genome. See user guide for more information.
288 SomaticRank The estimated rank of this somatic mutation,
289 amongst all true somatic mutations within this
290 SomaticCategory. The value is a number between
291 0 and 1; a value of 0.012 means, for example,
292 that an estimated 1.2% of the true somatic
293 mutations in this somaticCategory have a
294 somaticScore less than the somaticScore for
295 this mutation. See user guide for more
296 information.
297 SomaticScore An integer that provides a total order on
298 quality for all somatic mutations. It is equal
299 to -10*log10( P(false)/P(true) ), under the
300 assumption that this genome has a rate of
301 somatic mutation equal to 1/Mb for
302 SomaticCategory snp, 1/10Mb for SomaticCategory
303 ins, 1/10Mb for SomaticCategory del, and 1/20Mb
304 for SomaticCategory sub. The computation is
305 based on the assumptions described in the user
306 guide, and is affected by choice of variant
307 model selected by using or not using the
308 "--diploid" option.
309 SomaticQuality Equal to VQHIGH for all somatic mutations where
310 SomaticScore &gt;= -10. Otherwise, this column is
311 empty.
312
313 OPTIONS
314 -h [ --help ]
315 Print this help message.
316
317 --reference arg
318 The input crr file.
319
320 --variantsA arg
321 The "A" input variant file.
322
323 --variantsB arg
324 The "B" input variant file.
325
326 --output-prefix arg
327 The path prefix for all output reports.
328
329 --reports arg (=SuperlocusOutput,SuperlocusStats,LocusOutput,LocusStats)
330 Comma-separated list of reports to generate. (Beware any reports whose
331 name begins with "Debug".) A report is one of:
332 SuperlocusOutput Report for superlocus classification.
333 SuperlocusStats Report for superlocus classification stats.
334 LocusOutput Report for locus classification.
335 LocusStats Report for locus stats.
336 VariantOutput Both variant files annotated by comparison
337 results.If the somatic output report is
338 requested, file A is also annotated with the
339 same score ranks as produced in that report.
340 SomaticOutput Report for the list of simple variations that
341 are present only in file "A", annotated with
342 the score that indicates the probability of
343 the variation being truly somatic. Requires
344 beta, genome-rootA, and genome-rootB options
345 to be provided as well. Note: generating this
346 report slows calldiff by 10x-20x.
347 DebugCallOutput Report for call classification.
348 DebugSuperlocusOutput Report for debug superlocus information.
349 DebugSomaticOutput Report for distribution estimates used for
350 somatic rescoring. Only produced if
351 SomaticOutput is also turned on.
352
353 --diploid
354 Uses varScoreEAF instead of varScoreVAF in somatic score computations.
355 Also, uses diploid variant model instead of variable allele mixture
356 model.
357
358 --locus-stats-column-count arg (=15)
359 The number of columns for locus compare classification in the locus
360 stats file.
361
362 --max-hypothesis-count arg (=32)
363 The maximum number of possible phasings to consider for a superlocus.
364
365 --no-reference-cover-validation
366 Turns off validation that all bases of a chromosome are covered by
367 calls of the variant file.
368
369 --genome-rootA arg
370 The "A" genome directory, for example /data/GS00118-DNA_A01; this
371 directory is expected to contain ASM/REF and ASM/EVIDENCE
372 subdirectories.
373
374 --genome-rootB arg
375 The "B" genome directory.
376
377 --calibration-root arg
378 The directory containing calibration data. For example, there should
379 exist a file calibration-root/0.0.0/metrics.tsv.
380
381 --beta
382 This flag enables the SomaticOutput report, which is beta
383 functionality.
384
385 SUPPORTED FORMAT_VERSION
386 0.3 or later
387 </help>
388 </tool>