-
Notifications
You must be signed in to change notification settings - Fork 0
/
nextflow.config
323 lines (295 loc) · 13.1 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
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
nf-core/hybrider Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Default config options for all compute environments
----------------------------------------------------------------------------------------
*/
// Global default params, used in configs
params {
// TODO nf-core: Specify your pipeline's command line flags
// Input and filtering options
vcfs = "/data/home/lucas.freitas/nextflow_modules/nf-core-hybrider/test/samples.csv"
// reads = "/data/home/lucas.freitas/nextflow_modules/nf-core-hybrider/test/raw_files.csv"
meta = "/data/home/lucas.freitas/nextflow_modules/nf-core-hybrider/test/Metadata_SecondAssembly_f.txt"
locmiss = 0.70 // Threshold for filtering out loci based on missingness (1==nomissing)
indmiss = 0.30 // Threshold for filtering out individuals based on missingness (1==nomissing)
maf = 0.05 // Threshold for filtering out loci based on Minor allele frequency
popinfo = false // Whether or not use POP column from meta, this is used for various plotting and conversion functions
outdir = "results"
// reference = []
// datatype = "pairddrad"
// assembly_method = "denovo"
// overhang = "CATGC,AATT"
// downstream = false
// upstream = true
// Skips
skip_filtering = false
skip_str = false
skip_admix = false
skip_plot = false
skip_ml = false
skip_vep = false
// Structure parameters
noadmix = false //wish to run with no admixture model?
freqscorr = true // is the allele frequency correlated in your model?
inferalpha = true // Do you wish to infer alpha value?
alpha = 0.199 // Initial value of alpha if you wish to infer it from data.
inferlambda = false // Do you wish to infer lambda from data?
lambda = 1 // Generic value for lambda
ploidy = 2 // Ploidy of the data
burnin = 2000 // Burnin of MCMC algorithm chain
mcmc = 20000 // Total length of MCMC algorithm chain
rep_per_k = 2 // Number of repetitions for each K value (usually 10)
k_value = 1 // Number of Ks to test the data (usually 10)
// Plot cluster parameters
plot_admix = true
plot_str = true
writecsv = true
// Prepare data to ML parameters
inferbypop = false
whichpop = "any"
inferbyclust = true // Do you wish to infer species by Q values?
smaller = true // Do you wish to use smaller group to get allele frequency from
method = "mean" // Either mean, str or admix to get ancestry coefficients from
upper = 0.9 // Upper limit of Q value to define a putative species
lower = 0.1 // Lower limit of Q value to define a putative species
rminvariable = true // Do you wish to remove invariable genotypes from the final matrix?
dropna = true // Do you wish to drop all columns that contains any NA value?
// Run ML snp selection
kfold = 5 //N folds to perform cross-validation
pvalue = 0.05 //P-value threshold for initial dimensionality reduction with chi2 test
corr = 0.8 //Value of r² threshold to filter variables highly correlated with each other, this will filter everything greater than threshold.
nsnps = 30 //Number of SNPs to select.
// Run VEP on filtered VCF
gff = "/storages/caico/home/lucas.freitas/Mestrado_Files/GSC_monkey_1.0/GCF_009761245.1_GSC_monkey_1.0/GCF_009761245.1_GSC_monkey_1.0_genomic.gff"
reference = "/storages/caico/home/lucas.freitas/Mestrado_Files/GSC_monkey_1.0/GCF_009761245.1_GSC_monkey_1.0/GCF_009761245.1_GSC_monkey_1.0_genomic.fna"
// 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
version = false
// Config options
config_profile_name = null
config_profile_description = null
custom_config_version = 'master'
custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
config_profile_contact = null
config_profile_url = null
// Max resource options
// Defaults only, expecting to be overwritten
max_memory = '128.GB'
max_cpus = 16
max_time = '240.h'
// Schema validation default options
validationFailUnrecognisedParams = false
validationLenientMode = false
validationSchemaIgnoreParams = 'genomes,igenomes_base'
validationShowHiddenParams = false
validate_params = true
}
// Load base.config by default for all pipelines
includeConfig 'conf/base.config'
// Load nf-core custom profiles from different Institutions
try {
includeConfig "${params.custom_config_base}/nfcore_custom.config"
} catch (Exception e) {
System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config")
}
// Load nf-core/hybrider custom profiles from different institutions.
// Warning: Uncomment only if a pipeline-specific instititutional config already exists on nf-core/configs!
// try {
// includeConfig "${params.custom_config_base}/pipeline/hybrider.config"
// } catch (Exception e) {
// System.err.println("WARNING: Could not load nf-core/config/hybrider profiles: ${params.custom_config_base}/pipeline/hybrider.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
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
}
test { includeConfig 'conf/test.config' }
test_full { includeConfig 'conf/test_full.config' }
}
// 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 = 'quay.io'
podman.registry = 'quay.io'
singularity.registry = 'quay.io'
// Nextflow plugins
plugins {
id '[email protected]' // 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']
// 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"
}
manifest {
name = 'lfreitasl/hybrider'
author = """Lucas de Freitas Lacerda"""
homePage = 'https://github.com/lfreitasl/hybrider'
description = """This a pipeline to analyse ddRADseq data based on VCF files generated from assembly steps"""
mainScript = 'main.nf'
nextflowVersion = '!>=23.04.0'
version = '1.0dev'
doi = ''
}
// Load modules.config for DSL2 module specific options
includeConfig 'conf/modules.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
}
}
}