-
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathnextflow.config
384 lines (342 loc) · 15.1 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
/*
========================================================================================
socialgene/sgnf Nextflow config file
========================================================================================
Default config options for all compute environments
----------------------------------------------------------------------------------------
*/
manifest {
name = 'socialgene/sgnf'
author = """Chase M. Clark"""
homePage = 'https://github.com/socialgene/sgnf'
description = """Scalable genome mining with SocialGene knowledge graphs"""
mainScript = 'main.nf'
defaultBranch = 'main'
nextflowVersion = '!>=24.0.0'
version = '1.2.2' // x-release-please-version
doi = ''
}
// Global default params, used in configs
params {
input = null
// Boilerplate options
email = null
email_on_fail = null
plaintext_email = false
monochrome_logs = false
hook_url = null
help = false
version = false
validate_params = true
publish_dir_mode = 'copy'
// Config options
config_profile_name = null
config_profile_description = null
custom_config_version = 'master'
custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
config_profile_contact = null
config_profile_url = null
// Tuning resource options
// Defaults only, expecting to be overwritten
// https://nf-co.re/docs/usage/configuration#max-resources
max_memory = '24.GB'
max_cpus = 8
max_time = '24.h'
slurm_queue_size = 15
// ADDITIONAL CONFIGS
mibig = null
local_genbank = null
local_faa = null
local_fna = null
fasta_csv = null
genbank_csv = null
fna_csv = null
ncbi_datasets_command = null
ncbi_genome_download_command = null
ncbi_datasets_file = null
hmm_splits = 1
fasta_splits = 1
genbank_input_buffer = 50 // Decides how many parallel processes will be used for genbank parsing; number of spawned parse processes = (# of input genomes) / (genbank_input_buffer)
build_database = true
sort_fasta = false // used for tests to ensure nr-fasta are the same regardless of execution order
defline_magic = false // set to true if input fasta files contain uniprot deflines (sp| or tr|) (e.g. from uniprot fasta downloads) named defline_magic because may expand to other defline formats in the future
include_sequences = true // set to true if you want to include protein AA sequences in the database
antismash_fulljson = true
// Results Directories
outdir = "socialgene_results"
outdir_download_cache = "${params.outdir}/socialgene_long_cache"
outdir_per_run = "${params.outdir}/socialgene_per_run"
outdir_neo4j = "${params.outdir}/socialgene_neo4j"
outdir_genomes = "${params.outdir_per_run}"
outdir_blast_cache = "${params.outdir_per_run}/blastp_cache"
tracedir = "${params.outdir_per_run}/pipeline_info"
paired_omics_json_path = null
// sg_modules
blastp = false
mmseqs_steps = null // e.g. '90,70,50' for 90% 70% 50%
antismash = false
chembl = false
paired_omics = false
ncbi_taxonomy = false
hmmlist = null // antismash,amrfinder,bigslice,classiphage,pfam,prism,resfams,tigrfam,virus_orthologous_groups
custom_hmm_file = null
goterms = false
// HMM database versions (databases without download versioning are unlisted)
amrfinder_version = '2024-05-02.2'
antismash_hmms_git_sha = '8fd065a63e99ee628b536cc19fa66d5942b784ea'
bigslice_version = 'v1.0.0/bigslice-models.2020-04-27'
prism_hmms_git_sha = '4bf8bbdf2da3b4f1c764de2301be7b02e74af157'
pfam_version = '37.0'
tigrfam_version = '15.0'
vog_version = 'vog211'
chembl_version = '31'
// These effect which HMMS hits are significant and reported
HMMSEARCH_Z = 100000000
HMMSEARCH_IEVALUE = 0.1
HMMSEARCH_E = 100.0
HMMSEARCH_DOME = 10.0
HMMSEARCH_INCE = 0.001
HMMSEARCH_INCDOME = 0.001
hmmsearch_model_threshold = "--cut_ga"
// You can probably ignore these parameters
HMMSEARCH_F1 = 0.02
HMMSEARCH_F2 = 0.001
HMMSEARCH_F3 = 1e-05
HMMSEARCH_SEED = 42
// Unless you're using the multi-step high throuput computing pipeline, you don't need to worry about these
htcondor_request_cpus = 1
htcondor_request_memory = '1GB'
htcondor_request_disk = '5GB'
htcondor_max_idle = 100
htcondor_squid_username = 'cmclark8'
htcondor_WantGlideIn = true
htcondor_WantFlocking = true
htcondor_prep_directory = "${params.outdir}/htcondor_cache"
htcondor = null
domtblout_path = null
domtblout_with_ga = null
domtblout_without_ga = ''
// MultiQC options
multiqc_config = null
multiqc_title = null
multiqc_logo = null
max_multiqc_email_size = '25.MB'
multiqc_methods_description = null
// Docker image versions (versions are synchronized with Nextflow pipeline version)
sgnf_antismash_dockerimage = null
sgnf_hmmer_plus_dockerimage = null
sgnf_hmmer_dockerimage = null
sgnf_minimal_dockerimage = null
sgnf_sgpy_dockerimage = null
// Schema validation default options
validationFailUnrecognisedParams = false
validationLenientMode = false
validationSchemaIgnoreParams = 'genomes,igenomes_base'
validationShowHiddenParams = false
validate_params = true
}
// Load base.config by default for all pipelines
includeConfig 'conf/base.config'
// Load nf-core custom profiles from different Institutions
try {
includeConfig "${params.custom_config_base}/nfcore_custom.config"
} catch (Exception e) {
System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config")
}
includeConfig 'conf/modules.config'
profiles {
debug {
dumpHashes = true
process.beforeScript = 'echo $HOSTNAME'
cleanup = false
}
conda {
conda.enabled = true
docker.enabled = false
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
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
}
gitpod {
executor.name = 'local'
executor.cpus = 4
executor.memory = 8.GB
}
local {
executor.cpus = params.max_cpus
executor.memory = params.max_memory
}
// Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile
// Will not be used unless Apptainer / Docker / Podman / Singularity are enabled
// Set to your registry if you have a mirror of containers
apptainer.registry = 'quay.io'
//docker.registry = 'registry.hub.docker.com'
podman.registry = 'quay.io'
singularity.registry = 'quay.io'
// compute_platform
htcondor { includeConfig 'conf/examples/compute_platform/htcondor.config' }
// input_examples
input_examples { includeConfig 'conf/examples/input_examples/input_examples.config' }
refseq { includeConfig 'conf/examples/input_examples/bgc_genome_databases/refseq.config' }
// input_examples/by_taxa
actinomycetota { includeConfig 'conf/examples/input_examples/by_taxa/actinomycetota.config' }
micromonospora { includeConfig 'conf/examples/input_examples/by_taxa/micromonospora.config' }
ncbi_datasets { includeConfig 'conf/examples/input_examples/by_taxa/ncbi_datasets.config' }
streptomyces_coelicolor { includeConfig 'conf/examples/input_examples/by_taxa/streptomyces_coelicolor.config' }
streptomyces { includeConfig 'conf/examples/input_examples/by_taxa/streptomyces.config' }
// input_examples/protein_databases
cog { includeConfig 'conf/examples/input_examples/protein_databases/cog.config' }
swissprot { includeConfig 'conf/examples/input_examples/protein_databases/swissprot.config' }
uniref100 { includeConfig 'conf/examples/input_examples/protein_databases/uniref100.config' }
// other
jgi_streptomyces_pangenome { includeConfig 'conf/examples/other/jgi_streptomyces_pangenome.config' }
mandelalides { includeConfig 'conf/examples/other/mandelalides.config' }
mibig_genomes { includeConfig 'conf/examples/other/mibig_genomes.config' }
mibig { includeConfig 'conf/examples/other/mibig.config' }
orthologs { includeConfig 'conf/examples/other/orthologs.config' }
ultraquickstart { includeConfig 'conf/examples/ultraquickstart.config' }
test { includeConfig 'conf/tests/test.config' }
slurm {
process.executor = "slurm"
process.queue = "queue"
executor {
queueSize = params.slurm_queue_size
}
}
}
plugins {
id 'nf-validation' // Validation of pipeline parameters and creation of an input channel from a sample sheet
}
// 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"
}
// Capture exit codes from upstream processes when piping
process.shell = ['/bin/bash', '-euo', 'pipefail']
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"
}
includeConfig 'conf/modules2.config'
// Function to ensure that resource requirements don't go beyond
// a maximum limit
def check_max(obj, type) {
if (type == 'memory') {
try {
if (obj.compareTo(params.max_memory as nextflow.util.MemoryUnit) == 1)
return params.max_memory as nextflow.util.MemoryUnit
else
return obj
} catch (all) {
println " ### ERROR ### Max memory '${params.max_memory}' is not valid! Using default value: $obj"
return obj
}
} else if (type == 'time') {
try {
if (obj.compareTo(params.max_time as nextflow.util.Duration) == 1)
return params.max_time as nextflow.util.Duration
else
return obj
} catch (all) {
println " ### ERROR ### Max time '${params.max_time}' is not valid! Using default value: $obj"
return obj
}
} else if (type == 'cpus') {
try {
return Math.min( obj, params.max_cpus as int )
} catch (all) {
println " ### ERROR ### Max cpus '${params.max_cpus}' is not valid! Using default value: $obj"
return obj
}
}
}