forked from nf-core/sarek
-
Notifications
You must be signed in to change notification settings - Fork 2
/
nextflow.config
478 lines (439 loc) · 21.9 KB
/
nextflow.config
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
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
nf-core/sarek Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Default config options for all compute environments
----------------------------------------------------------------------------------------
*/
params {
// Workflow flags:
// Mandatory arguments
// Input options
input = null // No default input
input_restart = null // No default automatic input
step = 'mapping' // Starts with mapping
// References
genome = 'GATK.GRCh38'
igenomes_base = 's3://ngi-igenomes/igenomes/'
snpeff_cache = 's3://annotation-cache/snpeff_cache/'
vep_cache = 's3://annotation-cache/vep_cache/'
igenomes_ignore = false
save_reference = false // Built references not saved
build_only_index = false // Only build the reference indexes
download_cache = false // Do not download annotation cache
// Main options
no_intervals = false // Intervals will be built from the fasta file
nucleotides_per_second = 200000 // Default interval size
tools = null // No default Variant_Calling or Annotation tools
skip_tools = null // All tools (markduplicates + baserecalibrator + QC) are used by default
split_fastq = 50000000 // FASTQ files will not be split by default by FASTP
// Modify fastqs (trim/split) with FASTP
trim_fastq = false // No trimming
clip_r1 = 0
clip_r2 = 0
three_prime_clip_r1 = 0
three_prime_clip_r2 = 0
trim_nextseq = 0
length_required = 15 // Default in FastP
save_trimmed = false
save_split_fastqs = false
// UMI tagged reads
umi_read_structure = null // no UMI
group_by_umi_strategy = 'Adjacency' // default strategy when running with UMI for GROUPREADSBYUMI
// Preprocessing
aligner = 'bwa-mem' // Default is bwa-mem, bwa-mem2 and dragmap can be used too
use_gatk_spark = null // GATK Spark implementation of their tools in local mode not used by default
save_mapped = false // Mapped BAMs not saved
save_output_as_bam = false // Output files from preprocessing are saved as bam and not as cram files
seq_center = null // No sequencing center to be written in read group CN field by aligner
seq_platform = 'ILLUMINA' // Default platform written in read group PL field by aligner
// Variant Calling
ascat_ploidy = null // default value for ASCAT
ascat_min_base_qual = 20 // default value for ASCAT
ascat_min_counts = 10 // default value for ASCAT
ascat_min_map_qual = 35 // default value for ASCAT
ascat_purity = null // default value for ASCAT
cf_ploidy = "2" // default value for Control-FREEC
cf_coeff = 0.05 // default value for Control-FREEC
cf_contamination = 0 // default value for Control-FREEC
cf_contamination_adjustment = false // by default we are not using this in Control-FREEC
cf_mincov = 0 // ControlFreec default values
cf_minqual = 0 // ControlFreec default values
cf_window = null // by default we are not using this in Control-FREEC
cnvkit_reference = null // by default the reference is build from the fasta file
concatenate_vcfs = false // by default we don't concatenate the germline-vcf-files
ignore_soft_clipped_bases = false // no --dont-use-soft-clipped-bases for GATK Mutect2
joint_germline = false // g.vcf & joint germline calling are not run by default if HaplotypeCaller is selected
joint_mutect2 = false // if true, enables patient-wise multi-sample somatic variant calling
only_paired_variant_calling = false // if true, skips germline variant calling for normal-paired sample
sentieon_dnascope_emit_mode = 'variant' // default value for Sentieon dnascope
sentieon_dnascope_pcr_indel_model = 'CONSERVATIVE'
sentieon_haplotyper_emit_mode = 'variant' // default value for Sentieon haplotyper
wes = false // Set to true, if data is exome/targeted sequencing data. Used to use correct models in various variant callers
// Annotation
bcftools_annotations = null // No extra annotation file
bcftools_annotations_tbi = null // No extra annotation file index
bcftools_header_lines = null // No header lines to be added to the VCF file
dbnsfp = null // No dbnsfp processed file
dbnsfp_consequence = null // No default consequence for dbnsfp plugin
dbnsfp_fields = "rs_dbSNP,HGVSc_VEP,HGVSp_VEP,1000Gp3_EAS_AF,1000Gp3_AMR_AF,LRT_score,GERP++_RS,gnomAD_exomes_AF" // Default fields for dbnsfp plugin
dbnsfp_tbi = null // No dbnsfp processed file index
outdir_cache = null // No default outdir cache
spliceai_indel = null // No spliceai_indel file
spliceai_indel_tbi = null // No spliceai_indel file index
spliceai_snv = null // No spliceai_snv file
spliceai_snv_tbi = null // No spliceai_snv file index
vep_custom_args = "--everything --filter_common --per_gene --total_length --offline --format vcf" // Default arguments for VEP
vep_dbnsfp = null // dbnsfp plugin disabled within VEP
vep_include_fasta = false // Don't use fasta file for annotation with VEP
vep_loftee = null // loftee plugin disabled within VEP
vep_out_format = "vcf"
vep_spliceai = null // spliceai plugin disabled within VEP
vep_spliceregion = null // spliceregion plugin disabled within VEP
vep_version = "111.0-0" // Should be updated when we update VEP, needs this to get full path to some plugins
// MultiQC options
multiqc_config = null
multiqc_title = null
multiqc_logo = null
max_multiqc_email_size = '25.MB'
multiqc_methods_description = null
// Boilerplate options
outdir = null
publish_dir_mode = 'copy'
email = null
email_on_fail = null
plaintext_email = false
monochrome_logs = false
hook_url = null
help = false
help_full = false
show_hidden = false
version = false
pipelines_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/'
// Config options
config_profile_name = null
config_profile_description = null
custom_config_version = 'master'
custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
config_profile_contact = null
config_profile_url = null
test_data_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek3'
modules_testdata_base_path = null
// Schema validation default options
validate_params = true
}
// Load base.config by default for all pipelines
includeConfig 'conf/base.config'
profiles {
debug {
dumpHashes = true
process.beforeScript = 'echo $HOSTNAME'
cleanup = false
nextflow.enable.configProcessNamesValidation = true
}
conda {
conda.enabled = true
docker.enabled = false
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
conda.channels = ['conda-forge', 'bioconda']
apptainer.enabled = false
}
mamba {
conda.enabled = true
conda.useMamba = true
docker.enabled = false
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
apptainer.enabled = false
}
docker {
docker.enabled = true
conda.enabled = false
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
apptainer.enabled = false
docker.runOptions = '-u $(id -u):$(id -g)'
}
arm {
docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64'
}
singularity {
singularity.enabled = true
singularity.autoMounts = true
conda.enabled = false
docker.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
apptainer.enabled = false
}
podman {
podman.enabled = true
conda.enabled = false
docker.enabled = false
singularity.enabled = false
shifter.enabled = false
charliecloud.enabled = false
apptainer.enabled = false
}
shifter {
shifter.enabled = true
conda.enabled = false
docker.enabled = false
singularity.enabled = false
podman.enabled = false
charliecloud.enabled = false
apptainer.enabled = false
}
charliecloud {
charliecloud.enabled = true
conda.enabled = false
docker.enabled = false
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
apptainer.enabled = false
}
apptainer {
apptainer.enabled = true
apptainer.autoMounts = true
conda.enabled = false
docker.enabled = false
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
wave {
apptainer.ociAutoPull = true
singularity.ociAutoPull = true
wave.enabled = true
wave.freeze = true
wave.strategy = 'conda,container'
}
gitpod {
executor.name = 'local'
executor.cpus = 4
executor.memory = 8.GB
}
// Basic test profile for CI
test { includeConfig 'conf/test.config' }
test_aws {
includeConfig 'conf/test.config'
params.sentieon_dnascope_model = "s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Annotation/Sentieon/SentieonDNAscopeModel1.1.model"
}
test_azure {
includeConfig 'conf/test.config'
params.sentieon_dnascope_model = "az://igenomes/Homo_sapiens/GATK/GRCh38/Annotation/Sentieon/SentieonDNAscopeModel1.1.model"
}
// Extra test profiles for full tests on AWS
test_full { includeConfig 'conf/test_full.config' }
test_full_aws {
includeConfig 'conf/test_full.config'
}
test_full_azure {
includeConfig 'conf/test_full.config'
params.input = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/csv/HCC1395_WXS_somatic_full_test_azure.csv'
params.intervals = 'az://test-data/sarek/S07604624_Padded_Agilent_SureSelectXT_allexons_V6_UTR.bed'
params.igenomes_base = "az://igenomes"
}
test_full_germline { includeConfig 'conf/test_full_germline.config' }
test_full_germline_aws {
includeConfig 'conf/test_full_germline.config'
}
test_full_germline_azure {
includeConfig 'conf/test_full_germline.config'
params.input = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/csv/NA12878_WGS_30x_full_test_azure.csv'
params.igenomes_base = "az://igenomes"
}
test_full_germline_ncbench_agilent {
includeConfig 'conf/test_full_germline_ncbench_agilent.config'
}
spark {
docker.runOptions = ''
}
// Extra test profiles for more complete CI
alignment_from_everything { includeConfig 'conf/test/alignment_from_everything.config' }
alignment_to_fastq { includeConfig 'conf/test/alignment_to_fastq.config' }
annotation { includeConfig 'conf/test/annotation.config' }
markduplicates_bam { includeConfig 'conf/test/markduplicates_bam.config' }
markduplicates_cram { includeConfig 'conf/test/markduplicates_cram.config' }
no_intervals { includeConfig 'conf/test/no_intervals.config' }
pair { includeConfig 'conf/test/pair.config' }
prepare_recalibration_bam { includeConfig 'conf/test/prepare_recalibration_bam.config' }
prepare_recalibration_cram { includeConfig 'conf/test/prepare_recalibration_cram.config' }
recalibrate_bam { includeConfig 'conf/test/recalibrate_bam.config' }
recalibrate_cram { includeConfig 'conf/test/recalibrate_cram.config' }
save_bam_mapped { includeConfig 'conf/test/save_bam_mapped.config' }
sentieon_dedup_bam { includeConfig 'conf/test/sentieon_dedup_bam.config' }
sentieon_dedup_cram { includeConfig 'conf/test/sentieon_dedup_cram.config' }
skip_bqsr { includeConfig 'conf/test/skip_bqsr.config' }
skip_markduplicates { includeConfig 'conf/test/skip_markduplicates.config' }
split_fastq { includeConfig 'conf/test/split_fastq.config' }
targeted { includeConfig 'conf/test/targeted.config' }
tools { includeConfig 'conf/test/tools.config' }
tools_germline { includeConfig 'conf/test/tools_germline.config' }
tools_germline_deepvariant { includeConfig 'conf/test/tools_germline_deepvariant.config' }
tools_somatic { includeConfig 'conf/test/tools_somatic.config' }
tools_somatic_ascat { includeConfig 'conf/test/tools_somatic_ascat.config' }
tools_tumoronly { includeConfig 'conf/test/tools_tumoronly.config' }
trimming { includeConfig 'conf/test/trimming.config' }
umi { includeConfig 'conf/test/umi.config' }
use_gatk_spark { includeConfig 'conf/test/use_gatk_spark.config' }
variantcalling_channels { includeConfig 'conf/test/variantcalling_channels.config' }
}
// Load nf-core custom profiles from different Institutions
includeConfig !System.getenv('NXF_OFFLINE') && params.custom_config_base ? "${params.custom_config_base}/nfcore_custom.config" : "/dev/null"
// Load nf-core/sarek custom profiles from different institutions.
includeConfig !System.getenv('NXF_OFFLINE') && params.custom_config_base ? "${params.custom_config_base}/pipeline/sarek.config" : "/dev/null"
// Set default registry for Apptainer, Docker, Podman, Charliecloud and Singularity independent of -profile
// Will not be used unless Apptainer / Docker / Podman / Charliecloud / Singularity are enabled
// Set to your registry if you have a mirror of containers
apptainer.registry = 'quay.io'
docker.registry = 'quay.io'
podman.registry = 'quay.io'
singularity.registry = 'quay.io'
charliecloud.registry = 'quay.io'
// Load igenomes.config if required
includeConfig !params.igenomes_ignore ? 'conf/igenomes.config' : 'conf/igenomes_ignored.config'
// Export these variables to prevent local Python/R libraries from conflicting with those in the container
// The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container.
// See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable.
env {
PYTHONNOUSERSITE = 1
R_PROFILE_USER = "/.Rprofile"
R_ENVIRON_USER = "/.Renviron"
JULIA_DEPOT_PATH = "/usr/local/share/julia"
}
// Set bash options
process.shell = """\
bash
set -e # Exit if a tool returns a non-zero status/exit code
set -u # Treat unset variables and parameters as an error
set -o pipefail # Returns the status of the last command to exit with a non-zero status or zero if all successfully execute
set -C # No clobber - prevent output redirection from overwriting files.
"""
// Disable process selector warnings by default. Use debug profile to enable warnings.
nextflow.enable.configProcessNamesValidation = false
def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss')
timeline {
enabled = true
file = "${params.outdir}/pipeline_info/execution_timeline_${trace_timestamp}.html"
}
report {
enabled = true
file = "${params.outdir}/pipeline_info/execution_report_${trace_timestamp}.html"
}
trace {
enabled = true
file = "${params.outdir}/pipeline_info/execution_trace_${trace_timestamp}.txt"
}
dag {
enabled = true
file = "${params.outdir}/pipeline_info/pipeline_dag_${trace_timestamp}.html"
}
prov {
enabled = true
formats {
bco {
file = "${params.outdir}/pipeline_info/manifest_${trace_timestamp}.bco.json"
}
}
}
manifest {
name = 'nf-core/sarek'
author = """Maxime Garcia, Szilveszter Juhos, Friederike Hanssen"""
homePage = 'https://github.com/nf-core/sarek'
description = """An open-source analysis pipeline to detect germline or somatic variants from whole genome or targeted sequencing"""
mainScript = 'main.nf'
nextflowVersion = '!>=24.04.2'
version = '3.5.0dev'
doi = '10.12688/f1000research.16665.2, 10.1093/nargab/lqae031, 10.5281/zenodo.3476425'
}
// Nextflow plugins
plugins {
id '[email protected]' // Validation of pipeline parameters and creation of an input channel from a sample sheet
id '[email protected]' // Provenance reports for pipeline runs
}
validation {
defaultIgnoreParams = ["genomes"]
help {
enabled = true
command = "nextflow run $manifest.name -profile <docker/singularity/.../institute> --input samplesheet.csv --outdir <OUTDIR>"
fullParameter = "help_full"
showHiddenParameter = "show_hidden"
beforeText = """
-\033[2m----------------------------------------------------\033[0m-
\033[0;32m,--.\033[0;30m/\033[0;32m,-.\033[0m
\033[0;34m ___ __ __ __ ___ \033[0;32m/,-._.--~\'\033[0m
\033[0;34m |\\ | |__ __ / ` / \\ |__) |__ \033[0;33m} {\033[0m
\033[0;34m | \\| | \\__, \\__/ | \\ |___ \033[0;32m\\`-._,-`-,\033[0m
\033[0;32m`._,._,\'\033[0m
\033[0;37m ____\033[0m
\033[0;37m .´ _ `.\033[0m
\033[0;37m / \033[0;32m|\\\033[0m`-_ \\\033[0m \033[0;34m __ __ ___ \033[0m
\033[0;37m | \033[0;32m| \\\033[0m `-|\033[0m \033[0;34m|__` /\\ |__) |__ |__/\033[0m
\033[0;37m \\ \033[0;32m| \\\033[0m /\033[0m \033[0;34m.__| /¯¯\\ | \\ |___ | \\\033[0m
\033[0;37m `\033[0;32m|\033[0m____\033[0;32m\\\033[0m´\033[0m
\033[0;35m ${manifest.name} ${manifest.version}\033[0m
-\033[2m----------------------------------------------------\033[0m-
"""
afterText = """${manifest.doi ? "* The pipeline\n" : ""}${manifest.doi.tokenize(",").collect { " https://doi.org/${it.trim().replace('https://doi.org/','')}"}.join("\n")}${manifest.doi ? "\n" : ""}
* The nf-core framework
https://doi.org/10.1038/s41587-020-0439-x
* Software dependencies
https://github.com/${manifest.name}/blob/master/CITATIONS.md
"""
}
summary {
beforeText = validation.help.beforeText
afterText = validation.help.afterText
}
}
// Load modules.config for DSL2 module specific options
includeConfig 'conf/modules/modules.config'
// Load more modules specific config for DSL2 module specific options
// prepare reference
includeConfig 'conf/modules/download_cache.config'
includeConfig 'conf/modules/prepare_genome.config'
includeConfig 'conf/modules/prepare_intervals.config'
// preprocessing
includeConfig 'conf/modules/aligner.config'
includeConfig 'conf/modules/alignment_to_fastq.config'
includeConfig 'conf/modules/markduplicates.config'
includeConfig 'conf/modules/sentieon_dedup.config'
includeConfig 'conf/modules/prepare_recalibration.config'
includeConfig 'conf/modules/recalibrate.config'
includeConfig 'conf/modules/trimming.config'
includeConfig 'conf/modules/umi.config'
//ngscheckmate
includeConfig 'conf/modules/ngscheckmate.config'
// variant calling
includeConfig 'conf/modules/ascat.config'
includeConfig 'conf/modules/cnvkit.config'
includeConfig 'conf/modules/controlfreec.config'
includeConfig 'conf/modules/deepvariant.config'
includeConfig 'conf/modules/freebayes.config'
includeConfig 'conf/modules/haplotypecaller.config'
includeConfig 'conf/modules/joint_germline.config'
includeConfig 'conf/modules/manta.config'
includeConfig 'conf/modules/mpileup.config'
includeConfig 'conf/modules/msisensorpro.config'
includeConfig 'conf/modules/mutect2.config'
includeConfig 'conf/modules/sentieon_dnascope.config'
includeConfig 'conf/modules/sentieon_dnascope_joint_germline.config'
includeConfig 'conf/modules/sentieon_haplotyper.config'
includeConfig 'conf/modules/sentieon_haplotyper_joint_germline.config'
includeConfig 'conf/modules/strelka.config'
includeConfig 'conf/modules/tiddit.config'
includeConfig 'conf/modules/post_variant_calling.config'
includeConfig 'conf/modules/lofreq.config'
//annotate
includeConfig 'conf/modules/annotate.config'