Mercurial > repos > completegenomics > cg_cgatools_linux

comparison cgatools/tools/cgatools_1.5/calldiff.xml @ 0:182426b32995 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author completegenomics
date Mon, 18 Jun 2012 20:15:00 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:182426b32995
1 <tool id="cg_calldiff" name="calldiff(beta) 1.5" version="1.0.0">
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 -->
6
7 <description>compares two Complete Genomics variant files.</description> <!--adds description in toolbar-->
8
9 <requirements>
10 <requirement type="binary">cgatools</requirement>
11 </requirements>
12
13 <command> <!--run executable-->
14 cgatools | head -1;
15 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 $somatic.calibration
29 #end if
30 </command>
31
32 <outputs>
33 <data format="tabular" name="output1" from_work_dir="cg_SuperlocusOutput.tsv" label="${tool.name} on ${on_string}: SuperlocusOutput">
34 <filter>(report1 == 'SuperlocusOutput')</filter>
35 </data>
36 <data format="tabular" name="output2" from_work_dir="cg_SuperlocusStats.tsv" label="${tool.name} on ${on_string}: SuperlocusStats">
37 <filter>(report2 == 'SuperlocusStats')</filter>
38 </data>
39 <data format="tabular" name="output3" from_work_dir="cg_LocusOutput.tsv" label="${tool.name} on ${on_string}: LocusOutput">
40 <filter>(report3 == 'LocusOutput')</filter>
41 </data>
42 <data format="tabular" name="output4" from_work_dir="cg_LocusStats.tsv" label="${tool.name} on ${on_string}: LocusStats">
43 <filter>(report4 == 'LocusStats')</filter>
44 </data>
45 <data format="tabular" name="output5a" from_work_dir="cg_VariantsA.tsv" label="${tool.name} on ${on_string}: VariantsA">
46 <filter>(report5 == 'VariantOutput')</filter>
47 </data>
48 <data format="tabular" name="output5b" from_work_dir="cg_VariantsB.tsv" label="${tool.name} on ${on_string}: VariantsB">
49 <filter>(report5 == 'VariantOutput')</filter>
50 </data>
51 <data format="tabular" name="output6" from_work_dir="cg_SomaticOutput.tsv" label="${tool.name} on ${on_string}: SomaticOutput">
52 <filter>(somatic['report6'] == 'SomaticOutput')</filter>
53 </data>
54 </outputs>
55
56 <inputs>
57 <!--form field to select crr file-->
58 <param name="crr" type="select" label="Reference genome (.crr file)">
59 <options from_data_table="cg_crr_files" />
60 </param>
61
62 <!--conditional to select variant file input-->
63 <conditional name="data_sources">
64 <param name="data_source" type="select" label="Where are the input varfiles?">
65 <option value="in" selected="true">imported into Galaxy</option>
66 <option value="out">located outside Galaxy (available only for local Galaxy instances)</option>
67 </param>
68 <when value="in">
69 <!--form field to select variant files-->
70 <param name="inputA" type="data" format="cg_var" label="Var file A">
71 <validator type="unspecified_build" />
72 <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
73 metadata_name="dbkey" metadata_column="1"
74 message="cgatools is not currently available for this build."/>
75 </param>
76 <param name="inputB" type="data" format="cg_var" label="Var file B">
77 <validator type="unspecified_build" />
78 <validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
79 metadata_name="dbkey" metadata_column="1"
80 message="cgatools is not currently available for this build."/>
81 </param>
82 </when>
83 <when value="out">
84 <!--form field to select crr file-->
85 <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"/>
86 <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."/>
87 </when>
88 </conditional>
89
90 <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.">
91 <option value="">no</option>
92 <option value="--diploid">yes</option>
93 </param>
94
95 <param name="column" type="integer" label="Number of columns for locus compare classification in the locus stats file (default 15)" value="15"/>
96
97 <param name="hypothesis" type="integer" label="Maximum number of possible phasings to consider for a superlocus (default 32)" value="32"/>
98
99 <param name="validation" type="select" label="Reference cover validation" help="Turns on/off validation that all bases of a chromosome are covered by calls of the variant file.">
100 <option value="">on</option>
101 <option value="--no-reference-cover-validation">off</option>
102 </param>
103
104 <param name="report1" type="select" label="Create report SuperlocusOutput">
105 <option value="">no</option>
106 <option value="SuperlocusOutput">yes</option>
107 </param>
108 <param name="report2" type="select" label="Create report SuperlocusStats">
109 <option value="">no</option>
110 <option value="SuperlocusStats">yes</option>
111 </param>
112 <param name="report3" type="select" label="Create report LocusOutput">
113 <option value="">no</option>
114 <option value="LocusOutput">yes</option>
115 </param>
116 <param name="report4" type="select" label="Create report LocusStats">
117 <option value="">no</option>
118 <option value="LocusStats">yes</option>
119 </param>
120 <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.">
121 <option value="">no</option>
122 <option value="VariantOutput">yes</option>
123 </param>
124
125 <conditional name="somatic">
126 <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.">
127 <option value="">no</option>
128 <option value="SomaticOutput">yes</option>
129 </param>
130 <when value="SomaticOutput">
131 <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."/>
132 <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."/>
133 <param name="calibration" type="text" size="300" label="Directory 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"/>
134 </when>
135 </conditional>
136
137 </inputs>
138
139 <help>
140
141 **What it does**
142
143 This tool compares two Complete Genomics variant files.
144
145 **cgatools 1.5.0 Documentation**
146
147 Userguide: http://cgatools.sourceforge.net/docs/1.5.0/cgatools-user-guide.pdf
148
149 Release notes: http://cgatools.sourceforge.net/docs/1.5.0/cgatools-release-notes.pdf
150
151 **Command line reference**::
152
153 COMMAND NAME
154 calldiff - Compares two Complete Genomics variant files.
155
156 DESCRIPTION
157 Compares two Complete Genomics variant files. Divides the genome up into
158 superloci of nearby variants, then compares the superloci. Also refines the
159 comparison to determine per-call or per-locus comparison results.
160
161 Comparison results are usually described by a semi-colon separated string,
162 one per allele. Each allele's comparison result is one of the following
163 classifications:
164
165 ref-identical The alleles of the two variant files are identical, and
166 they are consistent with the reference.
167 alt-identical The alleles of the two variant files are identical, and
168 they are inconsistent with the reference.
169 ref-consistent The alleles of the two variant files are consistent,
170 and they are consistent with the reference.
171 alt-consistent The alleles of the two variant files are consistent,
172 and they are inconsistent with the reference.
173 onlyA The alleles of the two variant files are inconsistent,
174 and only file A is inconsistent with the reference.
175 onlyB The alleles of the two variant files are inconsistent,
176 and only file B is inconsistent with the reference.
177 mismatch The alleles of the two variant files are inconsistent,
178 and they are both inconsistent with the reference.
179 phase-mismatch The two variant files would be consistent if the
180 hapLink field had been empty, but they are
181 inconsistent.
182 ploidy-mismatch The superlocus did not have uniform ploidy.
183
184 In some contexts, this classification is rolled up into a simplified
185 classification, which is one of "identical", "consistent", "onlyA",
186 "onlyB", or "mismatch".
187
188 A good place to start looking at the results is the superlocus-output file.
189 It has columns defined as follows:
190
191 SuperlocusId An identifier given to the superlocus.
192 Chromosome The name of the chromosome.
193 Begin The 0-based offset of the start of the superlocus.
194 End The 0-based offset of the base one past the end of the
195 superlocus.
196 Classification The match classification of the superlocus.
197 Reference The reference sequence.
198 AllelesA A semicolon-separated list of the alleles (one per
199 haplotype) for variant file A, for the phasing with the
200 best comparison result.
201 AllelesB A semicolon-separated list of the alleles (one per
202 haplotype) for variant file B, for the phasing with the
203 best comparison result.
204
205 The locus-output file contains, for each locus in file A and file B that is
206 not consistent with the reference, an annotated set of calls for the locus.
207 The calls are annotated with the following columns:
208
209 SuperlocusId The id of the superlocus containing the locus.
210 File The variant file (A or B).
211 LocusClassification The locus classification is determined by the
212 varType column of the call that is inconsistent
213 with the reference, concatenated with a
214 modifier that describes whether the locus is
215 heterozygous, homozygous, or contains no-calls.
216 If there is no one variant in the locus (i.e.,
217 it is heterozygous alt-alt), the locus
218 classification begins with "other".
219 LocusDiffClassification The match classification for the locus. This is
220 defined to be the best of the comparison of the
221 locus to the same region in the other file, or
222 the comparison of the superlocus.
223
224 The somatic output file contains a list of putative somatic variations of
225 genome A. The output includes only those loci that can be classified as
226 snp, del, ins or sub in file A, and are called reference in the file B.
227 Every locus is annotated with the following columns:
228
229 VarCvgA The totalReadCount from file A for this locus
230 (computed on the fly if file A is not a
231 masterVar file).
232 VarScoreA The varScoreVAF from file A, or varScoreEAF if
233 the "--diploid" option is used.
234 RefCvgB The maximum of the uniqueSequenceCoverage
235 values for the locus in genome B.
236 RefScoreB Minimum of the reference scores of the locus in
237 genome B.
238 SomaticCategory The category used for determining the
239 calibrated scores and the SomaticRank.
240 VarScoreACalib The calibrated variant score of file A, under
241 the model selected by using or not using the
242 "--diploid" option, and corrected for the count
243 of heterozygous variants observed in this
244 genome. See user guide for more information.
245 VarScoreBCalib The calibrated reference score of file B, under
246 the model selected by using or not using the
247 "--diploid" option, and corrected for the count
248 of heterozygous variants observed in this
249 genome. See user guide for more information.
250 SomaticRank The estimated rank of this somatic mutation,
251 amongst all true somatic mutations within this
252 SomaticCategory. The value is a number between
253 0 and 1; a value of 0.012 means, for example,
254 that an estimated 1.2% of the true somatic
255 mutations in this somaticCategory have a
256 somaticScore less than the somaticScore for
257 this mutation. See user guide for more
258 information.
259 SomaticScore An integer that provides a total order on
260 quality for all somatic mutations. It is equal
261 to -10*log10( P(false)/P(true) ), under the
262 assumption that this genome has a rate of
263 somatic mutation equal to 1/Mb for
264 SomaticCategory snp, 1/10Mb for SomaticCategory
265 ins, 1/10Mb for SomaticCategory del, and 1/20Mb
266 for SomaticCategory sub. The computation is
267 based on the assumptions described in the user
268 guide, and is affected by choice of variant
269 model selected by using or not using the
270 "--diploid" option.
271 SomaticQuality Equal to VQHIGH for all somatic mutations where
272 SomaticScore &gt;= -10. Otherwise, this column is
273 empty.
274
275 OPTIONS
276 -h [ --help ]
277 Print this help message.
278
279 --reference arg
280 The input crr file.
281
282 --variantsA arg
283 The "A" input variant file.
284
285 --variantsB arg
286 The "B" input variant file.
287
288 --output-prefix arg
289 The path prefix for all output reports.
290
291 --reports arg (=SuperlocusOutput,SuperlocusStats,LocusOutput,LocusStats)
292 Comma-separated list of reports to generate. (Beware any reports whose
293 name begins with "Debug".) A report is one of:
294 SuperlocusOutput Report for superlocus classification.
295 SuperlocusStats Report for superlocus classification stats.
296 LocusOutput Report for locus classification.
297 LocusStats Report for locus stats.
298 VariantOutput Both variant files annotated by comparison
299 results.If the somatic output report is
300 requested, file A is also annotated with the
301 same score ranks as produced in that report.
302 SomaticOutput Report for the list of simple variations that
303 are present only in file "A", annotated with
304 the score that indicates the probability of
305 the variation being truly somatic. Requires
306 beta, genome-rootA, and genome-rootB options
307 to be provided as well. Note: generating this
308 report slows calldiff by 10x-20x.
309 DebugCallOutput Report for call classification.
310 DebugSuperlocusOutput Report for debug superlocus information.
311 DebugSomaticOutput Report for distribution estimates used for
312 somatic rescoring. Only produced if
313 SomaticOutput is also turned on.
314
315 --diploid
316 Uses varScoreEAF instead of varScoreVAF in somatic score computations.
317 Also, uses diploid variant model instead of variable allele mixture
318 model.
319
320 --locus-stats-column-count arg (=15)
321 The number of columns for locus compare classification in the locus
322 stats file.
323
324 --max-hypothesis-count arg (=32)
325 The maximum number of possible phasings to consider for a superlocus.
326
327 --no-reference-cover-validation
328 Turns off validation that all bases of a chromosome are covered by
329 calls of the variant file.
330
331 --genome-rootA arg
332 The "A" genome directory, for example /data/GS00118-DNA_A01; this
333 directory is expected to contain ASM/REF and ASM/EVIDENCE
334 subdirectories.
335
336 --genome-rootB arg
337 The "B" genome directory.
338
339 --calibration-root arg
340 The directory containing calibration data. For example, there should
341 exist a file calibration-root/0.0.0/metrics.tsv.
342
343 --beta
344 This flag enables the SomaticOutput report, which is beta
345 functionality.
346
347 SUPPORTED FORMAT_VERSION
348 0.3 or later
349 </help>
350 </tool>