This repository has been archived by the owner on Jan 25, 2020. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 45
/
Qc.wdl
609 lines (553 loc) · 19.1 KB
/
Qc.wdl
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
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
version 1.0
## Copyright Broad Institute, 2018
##
## This WDL defines tasks used for QC of human whole-genome or exome sequencing data.
##
## Runtime parameters are often optimized for Broad's Google Cloud Platform implementation.
## For program versions, see docker containers.
##
## LICENSING :
## This script is released under the WDL source code license (BSD-3) (see LICENSE in
## https://github.com/broadinstitute/wdl). Note however that the programs it calls may
## be subject to different licenses. Users are responsible for checking that they are
## authorized to run all programs before running this script. Please see the docker
## page at https://hub.docker.com/r/broadinstitute/genomes-in-the-cloud/ for detailed
## licensing information pertaining to the included programs.
# Collect sequencing yield quality metrics
task CollectQualityYieldMetrics {
input {
File input_bam
String metrics_filename
Int preemptible_tries
}
Int disk_size = ceil(size(input_bam, "GiB")) + 20
command {
java -Xms2000m -jar /usr/gitc/picard.jar \
CollectQualityYieldMetrics \
INPUT=~{input_bam} \
OQ=true \
OUTPUT=~{metrics_filename}
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
disks: "local-disk " + disk_size + " HDD"
memory: "3 GiB"
preemptible: preemptible_tries
}
output {
File quality_yield_metrics = "~{metrics_filename}"
}
}
# Collect base quality and insert size metrics
task CollectUnsortedReadgroupBamQualityMetrics {
input {
File input_bam
String output_bam_prefix
Int preemptible_tries
}
Int disk_size = ceil(size(input_bam, "GiB")) + 20
command {
java -Xms5000m -jar /usr/gitc/picard.jar \
CollectMultipleMetrics \
INPUT=~{input_bam} \
OUTPUT=~{output_bam_prefix} \
ASSUME_SORTED=true \
PROGRAM=null \
PROGRAM=CollectBaseDistributionByCycle \
PROGRAM=CollectInsertSizeMetrics \
PROGRAM=MeanQualityByCycle \
PROGRAM=QualityScoreDistribution \
METRIC_ACCUMULATION_LEVEL=null \
METRIC_ACCUMULATION_LEVEL=ALL_READS
touch ~{output_bam_prefix}.insert_size_metrics
touch ~{output_bam_prefix}.insert_size_histogram.pdf
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
memory: "7 GiB"
disks: "local-disk " + disk_size + " HDD"
preemptible: preemptible_tries
}
output {
File base_distribution_by_cycle_pdf = "~{output_bam_prefix}.base_distribution_by_cycle.pdf"
File base_distribution_by_cycle_metrics = "~{output_bam_prefix}.base_distribution_by_cycle_metrics"
File insert_size_histogram_pdf = "~{output_bam_prefix}.insert_size_histogram.pdf"
File insert_size_metrics = "~{output_bam_prefix}.insert_size_metrics"
File quality_by_cycle_pdf = "~{output_bam_prefix}.quality_by_cycle.pdf"
File quality_by_cycle_metrics = "~{output_bam_prefix}.quality_by_cycle_metrics"
File quality_distribution_pdf = "~{output_bam_prefix}.quality_distribution.pdf"
File quality_distribution_metrics = "~{output_bam_prefix}.quality_distribution_metrics"
}
}
# Collect alignment summary and GC bias quality metrics
task CollectReadgroupBamQualityMetrics {
input {
File input_bam
File input_bam_index
String output_bam_prefix
File ref_dict
File ref_fasta
File ref_fasta_index
Boolean collect_gc_bias_metrics = true
Int preemptible_tries
}
Float ref_size = size(ref_fasta, "GiB") + size(ref_fasta_index, "GiB") + size(ref_dict, "GiB")
Int disk_size = ceil(size(input_bam, "GiB") + ref_size) + 20
command {
# These are optionally generated, but need to exist for Cromwell's sake
touch ~{output_bam_prefix}.gc_bias.detail_metrics \
~{output_bam_prefix}.gc_bias.pdf \
~{output_bam_prefix}.gc_bias.summary_metrics
java -Xms5000m -jar /usr/gitc/picard.jar \
CollectMultipleMetrics \
INPUT=~{input_bam} \
REFERENCE_SEQUENCE=~{ref_fasta} \
OUTPUT=~{output_bam_prefix} \
ASSUME_SORTED=true \
PROGRAM=null \
PROGRAM=CollectAlignmentSummaryMetrics \
~{true='PROGRAM="CollectGcBiasMetrics"' false="" collect_gc_bias_metrics} \
METRIC_ACCUMULATION_LEVEL=null \
METRIC_ACCUMULATION_LEVEL=READ_GROUP
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
memory: "7 GiB"
disks: "local-disk " + disk_size + " HDD"
preemptible: preemptible_tries
}
output {
File alignment_summary_metrics = "~{output_bam_prefix}.alignment_summary_metrics"
File gc_bias_detail_metrics = "~{output_bam_prefix}.gc_bias.detail_metrics"
File gc_bias_pdf = "~{output_bam_prefix}.gc_bias.pdf"
File gc_bias_summary_metrics = "~{output_bam_prefix}.gc_bias.summary_metrics"
}
}
# Collect quality metrics from the aggregated bam
task CollectAggregationMetrics {
input {
File input_bam
File input_bam_index
String output_bam_prefix
File ref_dict
File ref_fasta
File ref_fasta_index
Boolean collect_gc_bias_metrics = true
Int preemptible_tries
}
Float ref_size = size(ref_fasta, "GiB") + size(ref_fasta_index, "GiB") + size(ref_dict, "GiB")
Int disk_size = ceil(size(input_bam, "GiB") + ref_size) + 20
command {
# These are optionally generated, but need to exist for Cromwell's sake
touch ~{output_bam_prefix}.gc_bias.detail_metrics \
~{output_bam_prefix}.gc_bias.pdf \
~{output_bam_prefix}.gc_bias.summary_metrics \
~{output_bam_prefix}.insert_size_metrics \
~{output_bam_prefix}.insert_size_histogram.pdf
java -Xms5000m -jar /usr/gitc/picard.jar \
CollectMultipleMetrics \
INPUT=~{input_bam} \
REFERENCE_SEQUENCE=~{ref_fasta} \
OUTPUT=~{output_bam_prefix} \
ASSUME_SORTED=true \
PROGRAM=null \
PROGRAM=CollectAlignmentSummaryMetrics \
PROGRAM=CollectInsertSizeMetrics \
PROGRAM=CollectSequencingArtifactMetrics \
PROGRAM=QualityScoreDistribution \
~{true='PROGRAM="CollectGcBiasMetrics"' false="" collect_gc_bias_metrics} \
METRIC_ACCUMULATION_LEVEL=null \
METRIC_ACCUMULATION_LEVEL=SAMPLE \
METRIC_ACCUMULATION_LEVEL=LIBRARY
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
memory: "7 GiB"
disks: "local-disk " + disk_size + " HDD"
preemptible: preemptible_tries
}
output {
File alignment_summary_metrics = "~{output_bam_prefix}.alignment_summary_metrics"
File bait_bias_detail_metrics = "~{output_bam_prefix}.bait_bias_detail_metrics"
File bait_bias_summary_metrics = "~{output_bam_prefix}.bait_bias_summary_metrics"
File gc_bias_detail_metrics = "~{output_bam_prefix}.gc_bias.detail_metrics"
File gc_bias_pdf = "~{output_bam_prefix}.gc_bias.pdf"
File gc_bias_summary_metrics = "~{output_bam_prefix}.gc_bias.summary_metrics"
File insert_size_histogram_pdf = "~{output_bam_prefix}.insert_size_histogram.pdf"
File insert_size_metrics = "~{output_bam_prefix}.insert_size_metrics"
File pre_adapter_detail_metrics = "~{output_bam_prefix}.pre_adapter_detail_metrics"
File pre_adapter_summary_metrics = "~{output_bam_prefix}.pre_adapter_summary_metrics"
File quality_distribution_pdf = "~{output_bam_prefix}.quality_distribution.pdf"
File quality_distribution_metrics = "~{output_bam_prefix}.quality_distribution_metrics"
File error_summary_metrics = "~{output_bam_prefix}.error_summary_metrics"
}
}
# Check that the fingerprints of separate readgroups all match
task CrossCheckFingerprints {
input {
Array[File] input_bams
Array[File] input_bam_indexes
File? haplotype_database_file
String metrics_filename
Float total_input_size
Int preemptible_tries
Float lod_threshold
String cross_check_by
}
Int disk_size = ceil(total_input_size) + 20
command <<<
java -Dsamjdk.buffer_size=131072 \
-XX:GCTimeLimit=50 -XX:GCHeapFreeLimit=10 -Xms2000m \
-jar /usr/gitc/picard.jar \
CrosscheckFingerprints \
OUTPUT=~{metrics_filename} \
HAPLOTYPE_MAP=~{haplotype_database_file} \
EXPECT_ALL_GROUPS_TO_MATCH=true \
INPUT=~{sep=' INPUT=' input_bams} \
LOD_THRESHOLD=~{lod_threshold} \
CROSSCHECK_BY=~{cross_check_by}
>>>
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
preemptible: preemptible_tries
memory: "2 GiB"
disks: "local-disk " + disk_size + " HDD"
}
output {
File cross_check_fingerprints_metrics = "~{metrics_filename}"
}
}
# Check that the fingerprint of the sample BAM matches the sample array
task CheckFingerprint {
input {
File input_bam
File input_bam_index
String output_basename
File? haplotype_database_file
File? genotypes
File? genotypes_index
String sample
Int preemptible_tries
}
Int disk_size = ceil(size(input_bam, "GiB")) + 20
# Picard has different behavior depending on whether or not the OUTPUT parameter ends with a '.', so we are explicitly
# passing in where we want the two metrics files to go to avoid any potential confusion.
String summary_metrics_location = "~{output_basename}.fingerprinting_summary_metrics"
String detail_metrics_location = "~{output_basename}.fingerprinting_detail_metrics"
command <<<
java -Dsamjdk.buffer_size=131072 \
-XX:GCTimeLimit=50 -XX:GCHeapFreeLimit=10 -Xms2g \
-jar /usr/gitc/picard.jar \
CheckFingerprint \
INPUT=~{input_bam} \
SUMMARY_OUTPUT=~{summary_metrics_location} \
DETAIL_OUTPUT=~{detail_metrics_location} \
GENOTYPES=~{genotypes} \
HAPLOTYPE_MAP=~{haplotype_database_file} \
SAMPLE_ALIAS="~{sample}" \
IGNORE_READ_GROUPS=true
>>>
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
preemptible: preemptible_tries
memory: "3 GiB"
disks: "local-disk " + disk_size + " HDD"
}
output {
File summary_metrics = summary_metrics_location
File detail_metrics = detail_metrics_location
}
}
task CheckPreValidation {
input {
File duplication_metrics
File chimerism_metrics
Float max_duplication_in_reasonable_sample
Float max_chimerism_in_reasonable_sample
Int preemptible_tries
}
command <<<
set -o pipefail
set -e
grep -A 1 PERCENT_DUPLICATION ~{duplication_metrics} > duplication.csv
grep -A 3 PCT_CHIMERAS ~{chimerism_metrics} | grep -v OF_PAIR > chimerism.csv
python <<CODE
import csv
with open('duplication.csv') as dupfile:
reader = csv.DictReader(dupfile, delimiter='\t')
for row in reader:
with open("duplication_value.txt","w") as file:
file.write(row['PERCENT_DUPLICATION'])
file.close()
with open('chimerism.csv') as chimfile:
reader = csv.DictReader(chimfile, delimiter='\t')
for row in reader:
with open("chimerism_value.txt","w") as file:
file.write(row['PCT_CHIMERAS'])
file.close()
CODE
>>>
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
preemptible: preemptible_tries
docker: "us.gcr.io/broad-gotc-prod/python:2.7"
memory: "2 GiB"
}
output {
Float duplication_rate = read_float("duplication_value.txt")
Float chimerism_rate = read_float("chimerism_value.txt")
Boolean is_outlier_data = duplication_rate > max_duplication_in_reasonable_sample || chimerism_rate > max_chimerism_in_reasonable_sample
}
}
task ValidateSamFile {
input {
File input_bam
File? input_bam_index
String report_filename
File ref_dict
File ref_fasta
File ref_fasta_index
Int? max_output
Array[String]? ignore
Boolean? is_outlier_data
Int preemptible_tries
Int memory_multiplier = 1
}
Float ref_size = size(ref_fasta, "GiB") + size(ref_fasta_index, "GiB") + size(ref_dict, "GiB")
Int disk_size = ceil(size(input_bam, "GiB") + ref_size) + 20
Int memory_size = ceil(7 * memory_multiplier)
Int java_memory_size = (memory_size - 1) * 1000
command {
java -Xms~{java_memory_size}m -jar /usr/gitc/picard.jar \
ValidateSamFile \
INPUT=~{input_bam} \
OUTPUT=~{report_filename} \
REFERENCE_SEQUENCE=~{ref_fasta} \
~{"MAX_OUTPUT=" + max_output} \
IGNORE=~{default="null" sep=" IGNORE=" ignore} \
MODE=VERBOSE \
~{default='SKIP_MATE_VALIDATION=false' true='SKIP_MATE_VALIDATION=true' false='SKIP_MATE_VALIDATION=false' is_outlier_data} \
IS_BISULFITE_SEQUENCED=false
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
preemptible: preemptible_tries
memory: "~{memory_size} GiB"
disks: "local-disk " + disk_size + " HDD"
}
output {
File report = "~{report_filename}"
}
}
# Note these tasks will break if the read lengths in the bam are greater than 250.
task CollectWgsMetrics {
input {
File input_bam
File input_bam_index
String metrics_filename
File wgs_coverage_interval_list
File ref_fasta
File ref_fasta_index
Int read_length
Int preemptible_tries
}
Float ref_size = size(ref_fasta, "GiB") + size(ref_fasta_index, "GiB")
Int disk_size = ceil(size(input_bam, "GiB") + ref_size) + 20
command {
java -Xms2000m -jar /usr/gitc/picard.jar \
CollectWgsMetrics \
INPUT=~{input_bam} \
VALIDATION_STRINGENCY=SILENT \
REFERENCE_SEQUENCE=~{ref_fasta} \
INCLUDE_BQ_HISTOGRAM=true \
INTERVALS=~{wgs_coverage_interval_list} \
OUTPUT=~{metrics_filename} \
USE_FAST_ALGORITHM=true \
READ_LENGTH=~{read_length}
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
preemptible: preemptible_tries
memory: "3 GiB"
disks: "local-disk " + disk_size + " HDD"
}
output {
File metrics = "~{metrics_filename}"
}
}
# Collect raw WGS metrics (commonly used QC thresholds)
task CollectRawWgsMetrics {
input {
File input_bam
File input_bam_index
String metrics_filename
File wgs_coverage_interval_list
File ref_fasta
File ref_fasta_index
Int read_length
Int preemptible_tries
Int memory_multiplier = 1
}
Float ref_size = size(ref_fasta, "GiB") + size(ref_fasta_index, "GiB")
Int disk_size = ceil(size(input_bam, "GiB") + ref_size) + 20
Int memory_size = ceil((if (disk_size < 110) then 5 else 7) * memory_multiplier)
String java_memory_size = (memory_size - 1) * 1000
command {
java -Xms~{java_memory_size}m -jar /usr/gitc/picard.jar \
CollectRawWgsMetrics \
INPUT=~{input_bam} \
VALIDATION_STRINGENCY=SILENT \
REFERENCE_SEQUENCE=~{ref_fasta} \
INCLUDE_BQ_HISTOGRAM=true \
INTERVALS=~{wgs_coverage_interval_list} \
OUTPUT=~{metrics_filename} \
USE_FAST_ALGORITHM=true \
READ_LENGTH=~{read_length}
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
preemptible: preemptible_tries
memory: "~{memory_size} GiB"
disks: "local-disk " + disk_size + " HDD"
}
output {
File metrics = "~{metrics_filename}"
}
}
task CollectHsMetrics {
input {
File input_bam
File input_bam_index
File ref_fasta
File ref_fasta_index
String metrics_filename
File target_interval_list
File bait_interval_list
Int preemptible_tries
Int memory_multiplier = 1
}
Float ref_size = size(ref_fasta, "GiB") + size(ref_fasta_index, "GiB")
Int disk_size = ceil(size(input_bam, "GiB") + ref_size) + 20
# Try to fit the input bam into memory, within reason.
Int rounded_bam_size = ceil(size(input_bam, "GiB") + 0.5)
Int rounded_memory_size = ceil((if (rounded_bam_size > 10) then 10 else rounded_bam_size) * memory_multiplier)
Int memory_size = if rounded_memory_size < 7 then 7 else rounded_memory_size
Int java_memory_size = (memory_size - 1) * 1000
# There are probably more metrics we want to generate with this tool
command {
java -Xms~{java_memory_size}m -jar /usr/gitc/picard.jar \
CollectHsMetrics \
INPUT=~{input_bam} \
REFERENCE_SEQUENCE=~{ref_fasta} \
VALIDATION_STRINGENCY=SILENT \
TARGET_INTERVALS=~{target_interval_list} \
BAIT_INTERVALS=~{bait_interval_list} \
METRIC_ACCUMULATION_LEVEL=null \
METRIC_ACCUMULATION_LEVEL=SAMPLE \
METRIC_ACCUMULATION_LEVEL=LIBRARY \
OUTPUT=~{metrics_filename}
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
preemptible: preemptible_tries
memory: "~{memory_size} GiB"
disks: "local-disk " + disk_size + " HDD"
}
output {
File metrics = metrics_filename
}
}
# Generate a checksum per readgroup
task CalculateReadGroupChecksum {
input {
File input_bam
File input_bam_index
String read_group_md5_filename
Int preemptible_tries
}
Int disk_size = ceil(size(input_bam, "GiB")) + 20
command {
java -Xms1000m -jar /usr/gitc/picard.jar \
CalculateReadGroupChecksum \
INPUT=~{input_bam} \
OUTPUT=~{read_group_md5_filename}
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
preemptible: preemptible_tries
memory: "2 GiB"
disks: "local-disk " + disk_size + " HDD"
}
output {
File md5_file = "~{read_group_md5_filename}"
}
}
# Validate a (g)VCF with -gvcf specific validation
task ValidateVCF {
input {
File input_vcf
File input_vcf_index
File ref_fasta
File ref_fasta_index
File ref_dict
File dbsnp_vcf
File dbsnp_vcf_index
File calling_interval_list
Int preemptible_tries
Boolean is_gvcf = true
String gatk_docker = "us.gcr.io/broad-gatk/gatk:4.0.10.1"
}
Float ref_size = size(ref_fasta, "GiB") + size(ref_fasta_index, "GiB") + size(ref_dict, "GiB")
Int disk_size = ceil(size(input_vcf, "GiB") + size(dbsnp_vcf, "GiB") + ref_size) + 20
command {
gatk --java-options -Xms6000m \
ValidateVariants \
-V ~{input_vcf} \
-R ~{ref_fasta} \
-L ~{calling_interval_list} \
~{true="-gvcf" false="" is_gvcf} \
--validation-type-to-exclude ALLELES \
--dbsnp ~{dbsnp_vcf}
}
runtime {
docker: gatk_docker
preemptible: preemptible_tries
memory: "7000 MiB"
disks: "local-disk " + disk_size + " HDD"
}
}
# Collect variant calling metrics from GVCF output
task CollectVariantCallingMetrics {
input {
File input_vcf
File input_vcf_index
String metrics_basename
File dbsnp_vcf
File dbsnp_vcf_index
File ref_dict
File evaluation_interval_list
Boolean is_gvcf = true
Int preemptible_tries
}
Int disk_size = ceil(size(input_vcf, "GiB") + size(dbsnp_vcf, "GiB")) + 20
command {
java -Xms2000m -jar /usr/gitc/picard.jar \
CollectVariantCallingMetrics \
INPUT=~{input_vcf} \
OUTPUT=~{metrics_basename} \
DBSNP=~{dbsnp_vcf} \
SEQUENCE_DICTIONARY=~{ref_dict} \
TARGET_INTERVALS=~{evaluation_interval_list} \
~{true="GVCF_INPUT=true" false="" is_gvcf}
}
runtime {
docker: "us.gcr.io/broad-gotc-prod/genomes-in-the-cloud:2.4.1-1540490856"
preemptible: preemptible_tries
memory: "3 GiB"
disks: "local-disk " + disk_size + " HDD"
}
output {
File summary_metrics = "~{metrics_basename}.variant_calling_summary_metrics"
File detail_metrics = "~{metrics_basename}.variant_calling_detail_metrics"
}
}