1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
|
<tool id="makeflow_gatk" name="Makeflow-GATK" version="1.0.0">
<description> A Distributed version of GATK using Makeflow</description>
<requirements>
<requirement type="package" version="1.4">gatk</requirement>
<requirement type="package">samtools</requirement>
<requirement type="package">picard</requirement>
</requirements>
<command interpreter="python">
makeflow_gatk_wrapper.py
-T $algo
--input_file=$INPUT
--reference_sequence=$REFERENCE
--user_id=$__user_id__
--pwfile=${GALAXY_DATA_INDEX_DIR}/mypwfile
--num-seq-part=$numreads
--out=$VCF_File
#if $Makeflow_Log:
--mf_log=$Makeflow_Log
#end if
#if $Work_Queue_Log:
--wq_log=$Work_Queue_Log
#end if
#if $Debug_Log:
--output_dblog=$Debug_Log
#end if
#if $checkparams.useparam=="full":
#if $BQSR:
--BQSR=$BQSR
#end if
#if $EXCLUDE_INTERVALS:
--excludeIntervals=$EXCLUDE_INTERVALS
#end if
#if $INTERVALS:
--intervals=$$INTERVALS
#end if
#if $RG_BLACK_LIST:
--read_group_black_list=$RG_BLACK_LIST
#end if
#if $BAQ:
--baq=$BAQ
#end if
#if $BAQ_GOP:
--baqGapOpenPenalty=$BAQ_GOP
#end if
#if $DEF_BASE_QUALITY:
--defaultBaseQualities=$DEF_BASE_QUALITY
#end if
#if $DOWNSAMPLE_COVERAGE:
--downsample_to_coverage=$DOWNSAMPLE_COVERAGE
#end if
#if $DOWNSAMPLE_FRACTION:
--downsample_to_fraction=$DOWNSAMPLE_FRACTION
#end if
#if $DOWNSAMPLE_TYPE:
--downsampling_type=$DOWNSAMPLE_TYPE
#end if
#if $GATK_KEY:
--gatk_key=$GATK_KEY
#end if
#if $QSCORE_PRIOR:
--globalQScorePrior=$QSCORE_PRIOR
#end if
#if $INTERVAL_MERGING:
--interval_merging=$INTERVAL_MERGING
#end if
#if $INTERVAL_PADDING:
--interval_padding=$INTERVAL_PADDING
#end if
#if $INTERVAL_RULE:
--interval_set_rule=$INTERVAL_RULE
#end if
#if $LOG_LEVEL:
--logging_level=$LOG_LEVEL
#end if
#if $MAX_RUN:
--maxRuntime=$MAX_RUN
#end if
#if $MAX_RUN_UNIT:
--maxRuntimeUnits=$MAX_RUN_UNIT
#end if
#if $CTHREADS_PER_DTHREADS:
--num_cpu_threads_per_data_thread=$CTHREADS_PER_DTHREADS
#end if
#if $NUM_THREADS:
--num_threads=$NUM_THREADS
#end if
#if $PEDIGREE:
--pedigree=$PEDIGREE
#end if
#if $PEDI_STR:
--pedigreeString=$PEDI_STR
#end if
#if $PEDI_VALID:
--pedigreeValidationType=$PEDI_VALID
#end if
#if $ET:
--phone_home=$ET
#end if
#if $PRES_LOW_QSCORE:
--preserve_qscores_less_than=$PRES_LOW_QSCORE
#end if
#if $BUFF_SIZE:
--read_buffer_size=$BUFF_SIZE
#end if
#if $BUFF_FILT:
--read_filter=$BUFF_FILT
#end if
#if $TAG:
--tag=$TAG
#end if
#if $UNSAFE:
--unsafe=$UNSAFE
#end if
#if $VALID_STRICT
--validation_strictness=$VALID_STRICT
#end if
#if $HETER
--heterozygosity=$HETER
#end if
#if $INDEL_HETER
--indel_heterozygosity=$INDEL_HETER
#end if
#if $ALLOW_MISENCOD:
--allow_potentially_misencoded_quality_scores
#end if
#if $DISABLE_INDEL_Q:
--disable_indel_quals
#end if
#if $EMIT_ORIG:
--emit_original_quals
#end if
#if $FIX_MISENCOD:
--fix_misencoded_quality_scores
#end if
#if $KEEP_RECORDS:
--keep_program_records
#end if
#if $MON_THREADS:
--monitorThreadEfficiency
#end if
#if $RAND_SEED:
--nonDeterministicRandomSeed
#end if
#if $REMOVE_RECORDS:
--remove_program_records
#end if
#if $ORIG_QUALS:
--useOriginalQualities
#end if
#if $VERSION:
--version
#end if
#if $MAPPING:
--sample_rename_mapping_file=$MAPPING
#end if
#if $ALLOW_BQSR:
--allow_bqsr_on_reduced_bams_despite_repeated_warnings
#end if
#end if
</command>
<inputs>
<param format="bam" name="INPUT" type="data" label="Input BAM file" />
<param format="fasta" name="REFERENCE" type="data" metadata_name="dbkey" label="Input Reference" />
<param name="algo" type="select" label="GATK Algorithm">
<option value="HaplotypeCaller">HaplotypeCaller</option>
</param>
<param name="numreads" type="integer" value="10000" label="Number of Sequences per Partition" />
<conditional name="checkparams">
<param name="useparam" type="select" label="Other options" help="Select other flags and their values">
<option value="pre_set">Default settings</option>
<option value="full">View list</option>
</param>
<when value="pre_set" />
<when value="full">
<param name="BQSR" type="data" label="BQSR" help="The input covariates table file which enables on-the-fly base quality score recalibration (intended for use with BaseRecalibrator and PrintReads)" />
<param name="EXCLUDE_INTERVALS" type="data" label="excludeIntervals" help="One or more genomic intervals to exclude from processing. Can be explicitly specified on the command line or in a file (including a rod file)" />
<param name="INTERVALS" type="data" label="intervals" help="One or more genomic intervals over which to operate. Can be explicitly specified on the command line or in a file (including a rod file)" />
<param name="RG_BLACK_LIST" type="data" label="read_group_black_list" help="Filters out read groups matching : or a .txt file containing the filter strings one per line." />
<param name="BAQ" type="text" label="baq" help="Type of BAQ calculation to apply in the engine" />
<param name="BAQ_GOP" type="text" label="baqGapOpenPenalty" help="BAQ gap open penalty (Phred Scaled). Default value is 40. 30 is perhaps better for whole genome call sets" />
<param name="DEF_BASE_QUALITY" type="text" label="defaultBaseQualities" help="If reads are missing some or all base quality scores, this value will be used for all base quality scores" />
<param name="DOWNSAMPLE_COVERAGE" type="text" label="downsample_to_coverage" help="Coverage [integer] to downsample to. For locus-based traversals (eg., LocusWalkers and ActiveRegionWalkers),this controls the maximum depth of coverage at each locus. For non-locus-based traversals (eg., ReadWalkers), this controls the maximum number of reads sharing the same alignment start position. Note that this downsampling option does NOT produce an unbiased random sampling from all available reads at each locus: instead, the primary goal of the to-coverage downsampler is to maintain an even representation of reads from all alignment start positions when removing excess coverage. For a true across-the-board unbiased random sampling of reads, use -dfrac instead. Also note that the coverage target is an approximate goal that is not guaranteed to be met exactly: the downsampling algorithm will under some circumstances retain slightly more coverage than requested." />
<param name="DOWNSAMPLE_FRACTION" type="text" label="downsample_to_fraction" help="Fraction [0.0-1.0] of reads to downsample to" />
<param name="DOWNSAMPLE_TYPE" type="text" label="downsampling_type" help="Type of reads downsampling to employ at a given locus. Reads will be selected randomly to be removed from the pile based on the method described here" />
<param name="GATK_KEY" type="data" label="gatk_key" help="GATK Key file. Required if running with -et NO_ET." />
<param name="QSCORE_PRIOR" type="text" label="globalQScorePrior" help="The global Qscore Bayesian prior to use in the BQSR. If specified, this value will be used as the prior for all mismatch quality scores instead of the actual reported quality score" />
<param name="INTERVAL_MERGING" type="text" label="interval_merging" help="Indicates the interval merging rule we should use for abutting intervals" />
<param name="INTERVAL_PADDING" type="text" label="interval_padding" help="Indicates how many basepairs of padding to include around each of the intervals specified with the -L/--intervals argument" />
<param name="INTERVAL_RULE" type="text" label="interval_set_rule" help="Indicates the set merging approach the interval parser should use to combine the various -L or -XL inputs" />
<param name="LOG_LEVEL" type="text" label="logging_level" help="Set the minimum level of logging, i.e. setting INFO get's you INFO up to FATAL, setting ERROR gets you ERROR and FATAL level logging." />
<param name="MAX_RUN" type="text" label="maxRuntime" help="If provided, that GATK will stop execution cleanly as soon after maxRuntime has been exceeded, truncating the run but not exiting with a failure. By default the value is interpreted in minutes, but this can be changed by maxRuntimeUnits" />
<param name="MAX_RUN_UNIT" type="text" label="maxRuntimeUnits" help="The TimeUnit for maxRuntime [MINUTES]" />
<param name="CTHREADS_PER_DTHREADS" type="text" label="num_cpu_threads_per_data_thread" help="How many CPU threads should be allocated per data thread to running this analysis?" />
<param name="NUM_THREADS" type="text" label="num_threads" help="How many data threads should be allocated to running this analysis." />
<param name="PEDIGREE" type="data" label="pedigree" help="Pedigree files for samples" />
<param name="PEDI_STR" type="text" label="pedigreeString" help="Pedigree string for samples" />
<param name="PEDI_VALID" type="text" label="pedigreeValidationType" help="How strict should we be in validating the pedigree information?" />
<param name="ET" type="text" label="phone_home" help="What kind of GATK run report should we generate? AWS is the default, can be NO_ET so nothing is posted to the run repository. " />
<param name="PRES_LOW_QSCORE" type="text" label="preserve_qscores_less_than" help="Bases with quality scores less than this threshold won't be recalibrated (with -BQSR)" />
<param name="BUFF_SIZE" type="text" label="read_buffer_size" help="Number of reads per SAM file to buffer in memory" />
<param name="BUFF_FILT" type="text" label="read_filter" help="Specify filtration criteria to apply to each read individually" />
<param name="TAG" type="text" label="tag" help="Arbitrary tag string to identify this GATK run as part of a group of runs, for later analysis" />
<param name="VALID_STRICT" type="text" label="validation_strictness" help="How strict should we be with validation" />
<param name="HETER" type="text" label="heterozygosity" help="Heterozygosity value used to compute prior likelihoods for any locus. See the GATKDocs for full details on the meaning of this population genetics concept" />
<param name="INDEL_HETER" type="text" label="indel_heterozygosity" help="Heterozygosity for indel calling. See the GATKDocs for heterozygosity for full details on the meaning of this population genetics concept" />
<param name="UNSAFE" type="boolean" checked="true" label="unsafe" help="If set, enables unsafe operations: nothing will be checked at runtime. For expert users only who know what they are doing. We do not support usage of this argument." />
<param name="ALLOW_MISENCOD" type="boolean" checked="true" label="allow_potentially_misencoded_quality_scores" help="Do not fail when encountering base qualities that are too high and that seemingly indicate a problem with the base quality encoding of the BAM file" />
<param name="DISABLE_INDEL_Q" type="boolean" checked="true" label="disable_indel_quals" help="If true, disables printing of base insertion and base deletion tags (with -BQSR)" />
<param name="EMIT_ORIG" type="boolean" checked="true" label="emit_original_quals" help="If true, enables printing of the OQ tag with the original base qualities (with -BQSR)" />
<param name="FIX_MISENCOD" type="boolean" checked="true" label="fix_misencoded_quality_scores" help="Fix mis-encoded base quality scores" />
<param name="KEEP_RECORDS" type="boolean" checked="true" label="keep_program_records" help="Should we override the Walker's default and keep program records from the SAM header" />
<param name="MON_THREADS" type="boolean" checked="true" label="monitorThreadEfficiency" help="Enable GATK threading efficiency monitoring" />
<param name="RAND_SEED" type="boolean" checked="true" label="nonDeterministicRandomSeed" help="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" />
<param name="REMOVE_RECORDS" type="boolean" checked="true" label="remove_program_records" help="Should we override the Walker's default and remove program records from the SAM header" />
<param name="ORIG_QUALS" type="boolean" checked="true" label="useOriginalQualities" help="If set, use the original base quality scores from the OQ tag when present instead of the standard scores" />
<param name="VERSION" type="boolean" checked="true" label="version" help="Version Information" />
<param name="MAPPING" type="data" label="sample_rename_mapping_file" help="Rename sample IDs on-the-fly at runtime using the provided mapping file. This option requires that each BAM file listed in the mapping file have only a single sample specified in its header (though there may be multiple read groups for that sample). Each line of the mapping file must contain the absolute path to a BAM file, followed by whitespace, followed by the new sample name for that BAM file." />
<param name="ALLOW_BQSR" type="boolean" checked="true" label="allow_bqsr_on_reduced_bams_despite_repeated_warnings" help="Do not fail when running base quality score recalibration on a reduced BAM file even though we highly recommend against it" />
</when>
</conditional>
<param name="log_outputs" type="select" label="Select Optional Outputs" display="checkboxes" multiple="true">
<option value="OUTPUT_MFLOG">Makeflow Log</option>
<option value="OUTPUT_WQLOG">Work Queue Log</option>
<option value="OUTPUT_DBLOG">Debug Log</option>
</param>
</inputs>
<outputs>
<data format="vcf" name="VCF_File" label="Haplotype-MF VCF File">
<actions>
<action type="metadata" name="dbkey">
<option type="from_param" name="REFERENCE" param_attribute="dbkey" />
</action>
</actions>
</data>
<data format="mklog" name="Makeflow_Log" label="Haplotype-MF Makeflow Log">
<filter>"OUTPUT_MFLOG" in log_outputs</filter>
</data>
<data format="text" name="Work_Queue_Log" label="Haplotype-MF Work Queue Log">
<filter>"OUTPUT_WQLOG" in log_outputs</filter>
</data>
<data format="text" name="Debug_Log" label="Haplotype-MF Debug Log">
<filter>"OUTPUT_DBLOG" in log_outputs</filter>
</data>
</outputs>
<help>
Required Parameters:
-T TYPE, --analysis_type=TYPE
Type of analysis to run
Optional Inputs:
--BQSR=BQSR The input covariates table file which enables on-the-
fly base quality score recalibration (intended for use
with BaseRecalibrator and PrintReads)
--excludeIntervals=EXCLUDEINTERVALS
One or more genomic intervals to exclude from
processing. Can be explicitly specified on the command
line or in a file (including a rod file)
--input_file=INPUT SAM or BAM file(s)
--intervals=INTERVALS
One or more genomic intervals over which to operate.
Can be explicitly specified on the command line or in
a file (including a rod file)
--read_group_black_list=READ_GROUP_BLACK_LIST
Filters out read groups matching : or a .txt file
containing the filter strings one per line.
--reference_sequence=REF
Reference sequence file
--reference_index=REF_INDEX
Reference sequence file
--reference_dict=REF_DICT
Reference sequence file
Optional Outputs:
--log_to_file=LOG Set the logging location
--out=OUTPUT Output name
Optional Parameters:
--baq=BAQ Type of BAQ calculation to apply in the engine
--baqGapOpenPenalty=BAQGAPOPENPENALTY
BAQ gap open penalty (Phred Scaled). Default value is
40. 30 is perhaps better for whole genome call sets
--defaultBaseQualities=DEFAULTBASEQUALITIES
If reads are missing some or all base quality scores,
this value will be used for all base quality scores
--downsample_to_coverage=DOWNSAMPLE_TO_COVERAGE
Coverage [integer] to downsample to. For locus-based
traversals (eg., LocusWalkers and
ActiveRegionWalkers),this controls the maximum depth
of coverage at each locus. For non-locus-based
traversals (eg., ReadWalkers), this controls the
maximum number of reads sharing the same alignment
start position. Note that this downsampling option
does NOT produce an unbiased random sampling from all
available reads at each locus: instead, the primary
goal of the to-coverage downsampler is to maintain an
even representation of reads from all alignment start
positions when removing excess coverage. For a true
across-the-board unbiased random sampling of reads,
use -dfrac instead. Also note that the coverage target
is an approximate goal that is not guaranteed to be
met exactly: the downsampling algorithm will under
some circumstances retain slightly more coverage than
requested.
--downsample_to_fraction=DOWNSAMPLE_TO_FRACTION
Fraction [0.0-1.0] of reads to downsample to
--downsampling_type=DOWNSAMPLING_TYPE
Type of reads downsampling to employ at a given locus.
Reads will be selected randomly to be removed from the
pile based on the method described here
--gatk_key=GATK_KEY
GATK Key file. Required if running with -et NO_ET.
Please see
http://gatkforums.broadinstitute.org/discussion/1250
/what-is-phone-home-and-how-does-it-affect-me#latest
for details.
--globalQScorePrior=GLOBALQSCOREPRIOR
The global Qscore Bayesian prior to use in the BQSR.
If specified, this value will be used as the prior for
all mismatch quality scores instead of the actual
reported quality score
--interval_merging=INTERVAL_MERGING
Indicates the interval merging rule we should use for
abutting intervals
--interval_padding=INTERVAL_PADDING
Indicates how many basepairs of padding to include
around each of the intervals specified with the
-L/--intervals argument
--interval_set_rule=INTERVAL_SET_RULE
Indicates the set merging approach the interval parser
should use to combine the various -L or -XL inputs
--logging_level=LOGGING_LEVEL
Set the minimum level of logging, i.e. setting INFO
get's you INFO up to FATAL, setting ERROR gets you
ERROR and FATAL level logging.
--maxRuntime=MAXRUNTIME
If provided, that GATK will stop execution cleanly as
soon after maxRuntime has been exceeded, truncating
the run but not exiting with a failure. By default the
value is interpreted in minutes, but this can be
changed by maxRuntimeUnits
--maxRuntimeUnits=MAXRUNTIMEUNITS
The TimeUnit for maxRuntime [MINUTES]
--num_cpu_threads_per_data_thread=NUM_CPU_THREADS_PER_DATA_THREAD
How many CPU threads should be allocated per data
thread to running this analysis?
--num_bam_file_handles=NUM_BAM_FILE_HANDLES
The total number of BAM file handles to keep open
simultaneously
--num_threads=NUM_THREADS
How many data threads should be allocated to running
this analysis.
--pedigree=PEDIGREE
Pedigree files for samples
--pedigreeString=PEDIGREESTRING
Pedigree string for samples
--pedigreeValidationType=PEDIGREEVALIDATIONTYPE
How strict should we be in validating the pedigree
information?
--performanceLog=PLOG
If provided, a GATK runtime performance log will be
written to this file
--phone_home=PHONE_HOME
What kind of GATK run report should we generate? AWS
is the default, can be NO_ET so nothing is posted to
the run repository. Please see
http://gatkforums.broadinstitute.org/discussion/1250
/what-is-phone-home-and-how-does-it-affect-me#latest
for details.
--preserve_qscores_less_than=PRESERVE_QSCORES_LESS_THAN
Bases with quality scores less than this threshold
won't be recalibrated (with -BQSR)
--read_buffer_size=READ_BUFFER_SIZE
Number of reads per SAM file to buffer in memory
--read_filter=READ_FILTER
Specify filtration criteria to apply to each read
individually
--tag=TAG Arbitrary tag string to identify this GATK run as part
of a group of runs, for later analysis
--unsafe=UNSAFE If set, enables unsafe operations: nothing will be
checked at runtime. For expert users only who know
what they are doing. We do not support usage of this
argument.
--validation_strictness=VALIDATION_STRICTNESS
How strict should we be with validation
--heterozygosity=HETEROZYGOSITY
Heterozygosity value used to compute prior likelihoods
for any locus. See the GATKDocs for full details on
the meaning of this population genetics concept
--indel_heterozygosity=INDEL_HETEROZYGOSITY
Heterozygosity for indel calling. See the GATKDocs for
heterozygosity for full details on the meaning of this
population genetics concept
Optional Flags:
--allow_potentially_misencoded_quality_scores
Do not fail when encountering base qualities that are
too high and that seemingly indicate a problem with
the base quality encoding of the BAM file
--disable_indel_quals
If true, disables printing of base insertion and base
deletion tags (with -BQSR)
--emit_original_quals
If true, enables printing of the OQ tag with the
original base qualities (with -BQSR)
--fix_misencoded_quality_scores
Fix mis-encoded base quality scores
--keep_program_records
Should we override the Walker's default and keep
program records from the SAM header
--monitorThreadEfficiency
Enable GATK threading efficiency monitoring
--nonDeterministicRandomSeed
Makes the GATK behave non deterministically, that is,
the random numbers generated will be different in
every run
--remove_program_records
Should we override the Walker's default and remove
program records from the SAM header
--useOriginalQualities
If set, use the original base quality scores from the
OQ tag when present instead of the standard scores
--version Output version information
Advanced Parameters:
--sample_rename_mapping_file=SAMPLE_RENAME_MAPPING_FILE
Rename sample IDs on-the-fly at runtime using the
provided mapping file. This option requires that each
BAM file listed in the mapping file have only a single
sample specified in its header (though there may be
multiple read groups for that sample). Each line of
the mapping file must contain the absolute path to a
BAM file, followed by whitespace, followed by the new
sample name for that BAM file.
Advanced Flags:
--allow_bqsr_on_reduced_bams_despite_repeated_warnings
Do not fail when running base quality score
recalibration on a reduced BAM file even though we
highly recommend against it
</help>
</tool>
|
