Merge branch 'master' into kevbrick-patch-1
Alexander Peltzer
2 years ago
committed by
GitHub
commit
211a1bcb73
@ -0,0 +1,56 @@
|
||||
cff-version: 1.2.0
|
||||
message: "If you use `nf-core tools` in your work, please cite the `nf-core` publication"
|
||||
authors:
|
||||
- family-names: Ewels
|
||||
given-names: Philip
|
||||
- family-names: Peltzer
|
||||
given-names: Alexander
|
||||
- family-names: Fillinger
|
||||
given-names: Sven
|
||||
- family-names: Patel
|
||||
given-names: Harshil
|
||||
- family-names: Alneberg
|
||||
given-names: Johannes
|
||||
- family-names: Wilm
|
||||
given-names: Andreas
|
||||
- family-names: Ulysse Garcia
|
||||
given-names: Maxime
|
||||
- family-names: Di Tommaso
|
||||
given-names: Paolo
|
||||
- family-names: Nahnsen
|
||||
given-names: Sven
|
||||
title: "The nf-core framework for community-curated bioinformatics pipelines."
|
||||
version: 2.4.1
|
||||
doi: 10.1038/s41587-020-0439-x
|
||||
date-released: 2022-05-16
|
||||
url: https://github.com/nf-core/tools
|
||||
prefered-citation:
|
||||
type: article
|
||||
authors:
|
||||
- family-names: Ewels
|
||||
given-names: Philip
|
||||
- family-names: Peltzer
|
||||
given-names: Alexander
|
||||
- family-names: Fillinger
|
||||
given-names: Sven
|
||||
- family-names: Patel
|
||||
given-names: Harshil
|
||||
- family-names: Alneberg
|
||||
given-names: Johannes
|
||||
- family-names: Wilm
|
||||
given-names: Andreas
|
||||
- family-names: Ulysse Garcia
|
||||
given-names: Maxime
|
||||
- family-names: Di Tommaso
|
||||
given-names: Paolo
|
||||
- family-names: Nahnsen
|
||||
given-names: Sven
|
||||
doi: 10.1038/s41587-020-0439-x
|
||||
journal: nature biotechnology
|
||||
start: 276
|
||||
end: 278
|
||||
title: "The nf-core framework for community-curated bioinformatics pipelines."
|
||||
issue: 3
|
||||
volume: 38
|
||||
year: 2020
|
||||
url: https://dx.doi.org/10.1038/s41587-020-0439-x
|
||||
@ -0,0 +1,40 @@
|
||||
/*
|
||||
* --------------------------------------------------------------
|
||||
* nf-core pipelines config file for AD project using CRA HPC
|
||||
* --------------------------------------------------------------
|
||||
*/
|
||||
|
||||
params {
|
||||
config_profile_name = 'adcra'
|
||||
config_profile_description = 'CRA HPC profile provided by nf-core/configs'
|
||||
config_profile_contact = 'Kalayanee Chairat (@kalayaneech)'
|
||||
config_profile_url = 'https://bioinformatics.kmutt.ac.th/'
|
||||
}
|
||||
|
||||
params {
|
||||
max_cpus = 16
|
||||
max_memory = 128.GB
|
||||
max_time = 120.h
|
||||
}
|
||||
|
||||
// Specify the job scheduler
|
||||
executor {
|
||||
name = 'slurm'
|
||||
queueSize = 20
|
||||
submitRateLimit = '6/1min'
|
||||
}
|
||||
|
||||
singularity {
|
||||
enabled = true
|
||||
autoMounts = true
|
||||
}
|
||||
|
||||
process {
|
||||
scratch = true
|
||||
queue = 'unlimit'
|
||||
queueStatInterval = '10 min'
|
||||
maxRetries = 3
|
||||
errorStrategy = { task.attempt <=3 ? 'retry' : 'finish' }
|
||||
cache = 'lenient'
|
||||
exitStatusReadTimeoutMillis = '2700000'
|
||||
}
|
||||
@ -0,0 +1,54 @@
|
||||
//Profile config names for nf-core/configs
|
||||
params {
|
||||
config_profile_description = 'Cancer Research UK Manchester Institute HPC cluster profile provided by nf-core/configs'
|
||||
config_profile_contact = 'Stephen Kitcatt, Simon Pearce (@skitcattCRUKMI, @sppearce)'
|
||||
config_profile_url = 'http://scicom.picr.man.ac.uk/projects/user-support/wiki'
|
||||
}
|
||||
|
||||
singularity {
|
||||
cacheDir = '/lmod/nextflow_software'
|
||||
enabled = true
|
||||
autoMounts = true
|
||||
}
|
||||
|
||||
process {
|
||||
beforeScript = 'module load apps/singularity/3.8.0'
|
||||
executor = 'pbs'
|
||||
|
||||
errorStrategy = {task.exitStatus in [143,137,104,134,139,140] ? 'retry' : 'finish'}
|
||||
maxErrors = '-1'
|
||||
maxRetries = 3
|
||||
|
||||
withLabel:process_single {
|
||||
cpus = { check_max( 1 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 5.GB * task.attempt, 'memory' ) }
|
||||
}
|
||||
|
||||
withLabel:process_low {
|
||||
cpus = { check_max( 1 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 5.GB * task.attempt, 'memory' ) }
|
||||
}
|
||||
|
||||
withLabel:process_medium {
|
||||
cpus = { check_max( 4 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 20.GB * task.attempt, 'memory' ) }
|
||||
}
|
||||
|
||||
withLabel:process_high {
|
||||
cpus = { check_max( 16 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 80.GB * task.attempt, 'memory' ) }
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
executor {
|
||||
name = 'pbs'
|
||||
queueSize = 1000
|
||||
pollInterval = '10 sec'
|
||||
}
|
||||
|
||||
params {
|
||||
max_memory = 2000.GB
|
||||
max_cpus = 32
|
||||
max_time = 72.h
|
||||
}
|
||||
@ -0,0 +1,104 @@
|
||||
params {
|
||||
config_profile_description = 'HKI clusters profile provided by nf-core/configs.'
|
||||
config_profile_contact = 'James Fellows Yates (@jfy133)'
|
||||
config_profile_url = 'https://leibniz-hki.de'
|
||||
}
|
||||
|
||||
profiles {
|
||||
apate {
|
||||
params {
|
||||
config_profile_description = 'apate HKI cluster profile provided by nf-core/configs'
|
||||
config_profile_contact = 'James Fellows Yates (@jfy133)'
|
||||
config_profile_url = 'https://leibniz-hki.de'
|
||||
max_memory = 128.GB
|
||||
max_cpus = 32
|
||||
max_time = 1440.h
|
||||
}
|
||||
process {
|
||||
executor = 'local'
|
||||
maxRetries = 2
|
||||
}
|
||||
|
||||
executor {
|
||||
queueSize = 8
|
||||
}
|
||||
|
||||
singularity {
|
||||
enabled = true
|
||||
autoMounts = true
|
||||
cacheDir = '/Net/Groups/ccdata/apps/singularity'
|
||||
}
|
||||
|
||||
conda {
|
||||
cacheDir = '/Net/Groups/ccdata/apps/conda_envs'
|
||||
}
|
||||
|
||||
cleanup = true
|
||||
}
|
||||
|
||||
aither {
|
||||
params {
|
||||
config_profile_description = 'aither HKI cluster profile provided by nf-core/configs'
|
||||
config_profile_contact = 'James Fellows Yates (@jfy133)'
|
||||
config_profile_url = 'https://leibniz-hki.de'
|
||||
max_memory = 128.GB
|
||||
max_cpus = 32
|
||||
max_time = 1440.h
|
||||
}
|
||||
process {
|
||||
executor = 'local'
|
||||
maxRetries = 2
|
||||
}
|
||||
|
||||
executor {
|
||||
queueSize = 8
|
||||
}
|
||||
|
||||
singularity {
|
||||
enabled = true
|
||||
autoMounts = true
|
||||
cacheDir = '/Net/Groups/ccdata/apps/singularity'
|
||||
}
|
||||
|
||||
conda {
|
||||
cacheDir = '/Net/Groups/ccdata/apps/conda_envs'
|
||||
}
|
||||
|
||||
cleanup = true
|
||||
}
|
||||
|
||||
arges {
|
||||
params {
|
||||
config_profile_description = 'arges HKI cluster profile provided by nf-core/configs'
|
||||
config_profile_contact = 'James Fellows Yates (@jfy133)'
|
||||
config_profile_url = 'https://leibniz-hki.de'
|
||||
max_memory = 64.GB
|
||||
max_cpus = 12
|
||||
max_time = 1440.h
|
||||
}
|
||||
process {
|
||||
executor = 'local'
|
||||
maxRetries = 2
|
||||
}
|
||||
|
||||
executor {
|
||||
queueSize = 8
|
||||
}
|
||||
|
||||
singularity {
|
||||
enabled = true
|
||||
autoMounts = true
|
||||
cacheDir = '/Net/Groups/ccdata/apps/singularity'
|
||||
}
|
||||
|
||||
conda {
|
||||
cacheDir = '/Net/Groups/ccdata/apps/conda_envs'
|
||||
}
|
||||
|
||||
cleanup = true
|
||||
}
|
||||
|
||||
debug {
|
||||
cleanup = false
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,25 @@
|
||||
params {
|
||||
config_profile_contact = 'Adrija Kalvisa <adrija.kalvisa@sund.ku.dk>'
|
||||
config_profile_description = 'dangpufl01 configuration'
|
||||
config_profile_url = ''
|
||||
|
||||
// General cpus/memory/time requirements
|
||||
max_cpus = 30
|
||||
max_memory = 200.GB
|
||||
max_time = 72.h
|
||||
}
|
||||
|
||||
process {
|
||||
executor = 'slurm'
|
||||
|
||||
}
|
||||
|
||||
executor {
|
||||
queueSize = 5
|
||||
}
|
||||
|
||||
singularity {
|
||||
enabled = true
|
||||
autoMounts = true
|
||||
runOptions = '--bind /projects:/projects'
|
||||
}
|
||||
@ -0,0 +1,21 @@
|
||||
params {
|
||||
config_profile_description = 'University of Hawaii at Manoa'
|
||||
config_profile_url = 'http://www.hawaii.edu/its/ci/'
|
||||
config_profile_contact = 'Cedric Arisdakessian'
|
||||
|
||||
max_memory = 400.GB
|
||||
max_cpus = 96
|
||||
max_time = 72.h
|
||||
}
|
||||
|
||||
process {
|
||||
executor = 'slurm'
|
||||
queue = 'shared,exclusive,kill-shared,kill-exclusive'
|
||||
module = 'tools/Singularity'
|
||||
}
|
||||
|
||||
singularity {
|
||||
enabled = true
|
||||
cacheDir = "$HOME/.singularity_images_cache"
|
||||
autoMounts = true
|
||||
}
|
||||
@ -0,0 +1,46 @@
|
||||
//Profile config names for nf-core/configs
|
||||
params {
|
||||
config_profile_description = 'Cluster profile for medair (local cluster of Clinical Genomics Gothenburg)'
|
||||
config_profile_contact = 'Clinical Genomics, Gothenburg (cgg-rd@gu.se, cgg-it@gu.se)'
|
||||
config_profile_url = 'https://www.scilifelab.se/units/clinical-genomics-goteborg/'
|
||||
}
|
||||
|
||||
//Nextflow parameters
|
||||
singularity {
|
||||
enabled = true
|
||||
cacheDir = "/apps/bio/dependencies/nf-core/singularities"
|
||||
}
|
||||
|
||||
profiles {
|
||||
|
||||
wgs {
|
||||
process {
|
||||
queue = 'wgs.q'
|
||||
executor = 'sge'
|
||||
penv = 'mpi'
|
||||
process.clusterOptions = '-l excl=1'
|
||||
params.max_cpus = 40
|
||||
params.max_time = 48.h
|
||||
params.max_memory = 128.GB
|
||||
}
|
||||
}
|
||||
|
||||
production {
|
||||
process {
|
||||
queue = 'production.q'
|
||||
executor = 'sge'
|
||||
penv = 'mpi'
|
||||
process.clusterOptions = '-l excl=1'
|
||||
params.max_cpus = 40
|
||||
params.max_time = 480.h
|
||||
params.max_memory = 128.GB
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
//Specific parameter for pipelines that can use Sentieon (e.g. nf-core/sarek, nf-core/raredisease)
|
||||
process {
|
||||
withLabel:'sentieon' {
|
||||
container = "/apps/bio/singularities/sentieon-211204-peta.simg"
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,73 @@
|
||||
// Sheffield Bioinformatics Core Configuration Profile - ShARC
|
||||
// Custom Pipeline Resource Config for nf-core/atacseq
|
||||
|
||||
// process-specific resource requirements - reduced specification from those in atacseq/conf/base.config
|
||||
|
||||
process {
|
||||
|
||||
// error and retry handling
|
||||
|
||||
errorStrategy = { task.exitStatus in [143,137,104,134,139,140] ? 'retry' : 'finish' }
|
||||
maxRetries = 2
|
||||
|
||||
|
||||
// process labels
|
||||
|
||||
withLabel:process_low {
|
||||
cpus = { check_max( 2 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 12.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 4.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_medium {
|
||||
cpus = { check_max( 4 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 32.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 6.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_high {
|
||||
cpus = { check_max( 8 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 128.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 8.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_long {
|
||||
time = { check_max( 12.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
// function 'check_max()' to ensure that resource requirements don't go beyond 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: $obj"
|
||||
return obj
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -0,0 +1,73 @@
|
||||
// Sheffield Bioinformatics Core Configuration Profile - ShARC
|
||||
// Custom Pipeline Resource Config for nf-core/chipseq
|
||||
|
||||
// process-specific resource requirements - reduced specification from those in chipseq/conf/base.config
|
||||
|
||||
process {
|
||||
|
||||
// error and retry handling
|
||||
|
||||
errorStrategy = { task.exitStatus in [143,137,104,134,139,140] ? 'retry' : 'finish' }
|
||||
maxRetries = 2
|
||||
|
||||
|
||||
// process labels
|
||||
|
||||
withLabel:process_low {
|
||||
cpus = { check_max( 2 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 12.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 4.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_medium {
|
||||
cpus = { check_max( 4 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 32.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 6.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_high {
|
||||
cpus = { check_max( 8 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 128.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 8.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_long {
|
||||
time = { check_max( 12.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
// function 'check_max()' to ensure that resource requirements don't go beyond maximum limit
|
||||
|
||||
def check_max(obj, type) {
|
||||
if (type == 'memory') {
|
||||
try {
|
||||
if (obj.compareTo(params.max_memory as nextflow.util.MemoryUnit) == 1)
|
||||
return params.max_memory as nextflow.util.MemoryUnit
|
||||
else
|
||||
return obj
|
||||
} catch (all) {
|
||||
println " ### ERROR ### Max memory '${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
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -0,0 +1,29 @@
|
||||
// Profile config names for nf-core/configs
|
||||
|
||||
params {
|
||||
// Specific nf-core/configs params
|
||||
config_profile_contact = 'Edmund Miller(@emiller88)'
|
||||
config_profile_description = 'nf-core/demultiplex AWS Tower profile provided by nf-core/configs'
|
||||
}
|
||||
|
||||
aws {
|
||||
batch {
|
||||
maxParallelTransfers = 24
|
||||
maxTransferAttempts = 3
|
||||
}
|
||||
client {
|
||||
maxConnections = 24
|
||||
uploadMaxThreads = 24
|
||||
maxErrorRetry = 3
|
||||
socketTimeout = 3600000
|
||||
uploadRetrySleep = 1000
|
||||
uploadChunkSize = 32.MB
|
||||
}
|
||||
}
|
||||
|
||||
process {
|
||||
withName: BASES2FASTQ {
|
||||
cpus = 16
|
||||
memory = 48.GB
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,7 @@
|
||||
// rnafusion/hasta specific profile config for Clinical Genomics Stockholm usage
|
||||
|
||||
params {
|
||||
all = true
|
||||
trim = true
|
||||
fusioninspector_filter = true
|
||||
}
|
||||
@ -0,0 +1,77 @@
|
||||
// Sheffield Bioinformatics Core Configuration Profile - ShARC
|
||||
// Custom Pipeline Resource Config for nf-core/rnaseq
|
||||
|
||||
// process-specific resource requirements - reduced specification from those in rnaseq/conf/base.config
|
||||
|
||||
process {
|
||||
|
||||
// error and retry handling
|
||||
|
||||
errorStrategy = { task.exitStatus in [143,137,104,134,139,140] ? 'retry' : 'finish' }
|
||||
maxRetries = 2
|
||||
|
||||
|
||||
// process labels
|
||||
|
||||
withLabel:process_low {
|
||||
cpus = { check_max( 2 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 12.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 4.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_medium {
|
||||
cpus = { check_max( 4 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 32.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 6.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_high {
|
||||
cpus = { check_max( 8 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 128.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 8.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_long {
|
||||
time = { check_max( 12.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_high_memory {
|
||||
memory = { check_max( 160.GB * task.attempt, 'memory' ) }
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
// function 'check_max()' to ensure that resource requirements don't go beyond 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
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -0,0 +1,18 @@
|
||||
// Profile config names for nf-core/configs
|
||||
|
||||
params {
|
||||
// Specific nf-core/configs params
|
||||
config_profile_description = 'Cancer Research UK Manchester Institute HPC cluster profile provided by nf-core/configs'
|
||||
config_profile_contact = 'Stephen Kitcatt, Simon Pearce (@skitcattCRUKMI, @sppearce)'
|
||||
config_profile_url = 'http://scicom.picr.man.ac.uk/projects/user-support/wiki'
|
||||
}
|
||||
|
||||
// Specific nf-core/sarek process configuration
|
||||
process {
|
||||
|
||||
withName: 'SAMTOOLS_MPILEUP' {
|
||||
cpus = 1
|
||||
memory = { 5.GB * task.attempt }
|
||||
}
|
||||
|
||||
}
|
||||
@ -0,0 +1,111 @@
|
||||
// Sheffield Bioinformatics Core Configuration Profile - ShARC
|
||||
// Custom Pipeline Resource Config for nf-core/sarek
|
||||
|
||||
// process-specific resource requirements - reduced specification from those in sarek/conf/base.config
|
||||
|
||||
process {
|
||||
|
||||
// error and retry handling
|
||||
|
||||
errorStrategy = { task.exitStatus in [143,137,104,134,139,140,247] ? 'retry' : 'finish' }
|
||||
maxRetries = 2
|
||||
|
||||
|
||||
// process labels
|
||||
|
||||
withLabel:process_low {
|
||||
cpus = { check_max( 2 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 16.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 4.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_medium {
|
||||
cpus = { check_max( 6 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 72.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 6.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_high {
|
||||
cpus = { check_max( 12 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 192.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 8.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_long {
|
||||
time = { check_max( 12.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withLabel:process_high_memory {
|
||||
memory = { check_max( 240.GB * task.attempt, 'memory' ) }
|
||||
}
|
||||
|
||||
|
||||
// process name
|
||||
|
||||
withName:'BWAMEM1_MEM|BWAMEM2_MEM' {
|
||||
cpus = { check_max( 12 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 192.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 8.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withName:'FASTP' {
|
||||
cpus = { check_max( 12 * task.attempt, 'cpus' ) }
|
||||
}
|
||||
|
||||
withName:'FASTQC|FASTP|MOSDEPTH|SAMTOOLS_CONVERT' {
|
||||
memory = { check_max( 4.GB * task.attempt, 'memory' ) }
|
||||
}
|
||||
|
||||
withName:'GATK4_APPLYBQSR|GATK4_APPLYBQSR_SPARK|GATK4_BASERECALIBRATOR|SAMTOOLS_STATS' {
|
||||
cpus = { check_max( 4 * task.attempt, 'cpus' ) }
|
||||
}
|
||||
|
||||
withName:'GATK4_APPLYBQSR|GATK4_APPLYBQSR_SPARK|GATK4_BASERECALIBRATOR|GATK4_GATHERBQSRREPORTS' {
|
||||
memory = { check_max( 72.GB * task.attempt, 'memory' ) }
|
||||
}
|
||||
|
||||
withName:'GATK4_MARKDUPLICATES' {
|
||||
cpus = { check_max( 12 * task.attempt, 'cpus' ) }
|
||||
memory = { check_max( 240.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 12.h * task.attempt, 'time' ) }
|
||||
}
|
||||
|
||||
withName:'FREEBAYES|SAMTOOLS_STATS|SAMTOOLS_INDEX|UNZIP' {
|
||||
cpus = { check_max( 1 * task.attempt, 'cpus' ) }
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
// function 'check_max()' to ensure that resource requirements don't go beyond 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
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,120 @@
|
||||
// Config profile metadata
|
||||
params {
|
||||
config_profile_description = 'The Sage Bionetworks profile'
|
||||
config_profile_contact = 'Bruno Grande (@BrunoGrandePhD)'
|
||||
config_profile_url = 'https://github.com/Sage-Bionetworks-Workflows'
|
||||
}
|
||||
|
||||
// Leverage us-east-1 mirror of select human and mouse genomes
|
||||
params {
|
||||
igenomes_base = 's3://sage-igenomes/igenomes'
|
||||
max_memory = '128.GB'
|
||||
max_cpus = 16
|
||||
max_time = '240.h'
|
||||
}
|
||||
|
||||
// Enable retries globally for certain exit codes
|
||||
process {
|
||||
errorStrategy = { task.exitStatus in [143,137,104,134,139,247] ? 'retry' : 'finish' }
|
||||
maxRetries = 5
|
||||
maxErrors = '-1'
|
||||
}
|
||||
|
||||
// Increase time limit to allow file transfers to finish
|
||||
// The default is 12 hours, which results in timeouts
|
||||
threadPool.FileTransfer.maxAwait = '24 hour'
|
||||
|
||||
// Configure Nextflow to be more reliable on AWS
|
||||
aws {
|
||||
region = "us-east-1"
|
||||
client {
|
||||
uploadChunkSize = 209715200
|
||||
uploadMaxThreads = 4
|
||||
}
|
||||
batch {
|
||||
maxParallelTransfers = 1
|
||||
maxTransferAttempts = 5
|
||||
delayBetweenAttempts = '120 sec'
|
||||
}
|
||||
}
|
||||
executor {
|
||||
name = 'awsbatch'
|
||||
// Ensure unlimited queue size on AWS Batch
|
||||
queueSize = 500
|
||||
// Slow down the rate at which AWS Batch jobs accumulate in
|
||||
// the queue (an attempt to prevent orphaned EBS volumes)
|
||||
submitRateLimit = '5 / 1 sec'
|
||||
}
|
||||
|
||||
// Adjust default resource allocations (see `../docs/sage.md`)
|
||||
process {
|
||||
|
||||
cpus = { check_max( 1 * slow(task.attempt), 'cpus' ) }
|
||||
memory = { check_max( 6.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 24.h * task.attempt, 'time' ) }
|
||||
|
||||
// Process-specific resource requirements
|
||||
withLabel:process_low {
|
||||
cpus = { check_max( 4 * slow(task.attempt), 'cpus' ) }
|
||||
memory = { check_max( 12.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 24.h * task.attempt, 'time' ) }
|
||||
}
|
||||
withLabel:process_medium {
|
||||
cpus = { check_max( 12 * slow(task.attempt), 'cpus' ) }
|
||||
memory = { check_max( 36.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 48.h * task.attempt, 'time' ) }
|
||||
}
|
||||
withLabel:process_high {
|
||||
cpus = { check_max( 24 * slow(task.attempt), 'cpus' ) }
|
||||
memory = { check_max( 72.GB * task.attempt, 'memory' ) }
|
||||
time = { check_max( 96.h * task.attempt, 'time' ) }
|
||||
}
|
||||
withLabel:process_long {
|
||||
time = { check_max( 192.h * task.attempt, 'time' ) }
|
||||
}
|
||||
withLabel:process_high_memory {
|
||||
memory = { check_max( 128.GB * task.attempt, 'memory' ) }
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// Function to slow the increase of the resource multipler
|
||||
// as attempts are made. The rationale is that the number
|
||||
// of CPU cores isn't a limiting factor as often as memory.
|
||||
def slow(attempt, factor = 2) {
|
||||
return Math.ceil( attempt / factor) as int
|
||||
}
|
||||
|
||||
|
||||
// Function to ensure that resource requirements don't go
|
||||
// beyond a maximum limit (copied here for Sarek v2)
|
||||
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: $obj"
|
||||
return obj
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -1,35 +1,33 @@
|
||||
// Profile details
|
||||
params {
|
||||
config_profile_description = 'The Wellcome Sanger Institute HPC cluster profile'
|
||||
config_profile_contact = 'Anthony Underwood (@aunderwo)'
|
||||
config_profile_url = 'https://www.sanger.ac.uk/group/informatics-support-group/'
|
||||
}
|
||||
|
||||
singularity {
|
||||
enabled = true
|
||||
cacheDir = "${baseDir}/singularity"
|
||||
runOptions = '--bind /lustre --bind /nfs/pathnfs01 --bind /nfs/pathnfs02 --bind /nfs/pathnfs03 --bind /nfs/pathnfs04 --bind /nfs/pathnfs05 --bind /nfs/pathnfs06 --no-home'
|
||||
config_profile_description = 'The Wellcome Sanger Institute HPC cluster (farm5) profile'
|
||||
config_profile_contact = 'Priyanka Surana (@priyanka-surana)'
|
||||
config_profile_url = 'https://www.sanger.ac.uk'
|
||||
}
|
||||
|
||||
// Queue and retry strategy
|
||||
process{
|
||||
executor = 'lsf'
|
||||
queue = 'normal'
|
||||
errorStrategy = { task.attempt <= 5 ? "retry" : "finish" }
|
||||
process.maxRetries = 5
|
||||
withLabel:process_long {
|
||||
queue = 'long'
|
||||
}
|
||||
executor = 'lsf'
|
||||
queue = { task.time < 12.h ? 'normal' : task.time < 48.h ? 'long' : 'basement' }
|
||||
errorStrategy = 'retry'
|
||||
maxRetries = 5
|
||||
}
|
||||
|
||||
// Executor details
|
||||
executor{
|
||||
name = 'lsf'
|
||||
perJobMemLimit = true
|
||||
poolSize = 4
|
||||
submitRateLimit = '5 sec'
|
||||
killBatchSize = 50
|
||||
name = 'lsf'
|
||||
perJobMemLimit = true
|
||||
poolSize = 4
|
||||
submitRateLimit = '5 sec'
|
||||
killBatchSize = 50
|
||||
}
|
||||
|
||||
// Max resources
|
||||
params {
|
||||
max_memory = 128.GB
|
||||
max_cpus = 64
|
||||
max_time = 48.h
|
||||
max_memory = 683.GB
|
||||
max_cpus = 256
|
||||
max_time = 720.h
|
||||
}
|
||||
|
||||
// For singularity
|
||||
singularity.runOptions = '--bind /lustre --bind /nfs'
|
||||
|
||||
@ -0,0 +1,59 @@
|
||||
// Sheffield Bioinformatics Core Configuration Profile - ShARC
|
||||
// Base Institutional Configuration
|
||||
|
||||
|
||||
// nf-core specific parameters displayed in header summary of each run
|
||||
|
||||
params {
|
||||
|
||||
config_profile_description = 'Sheffield Bioinformatics Core - ShARC'
|
||||
config_profile_contact = 'Lewis Quayle (l.quayle@sheffield.ac.uk)'
|
||||
config_profile_url = 'https://docs.hpc.shef.ac.uk/en/latest/sharc/index.html'
|
||||
|
||||
}
|
||||
|
||||
|
||||
// hpc resource limits
|
||||
|
||||
params {
|
||||
|
||||
max_cpus = 16
|
||||
max_memory = 256.GB
|
||||
max_time = 96.h
|
||||
|
||||
}
|
||||
|
||||
|
||||
// hpc configuration specific to ShARC
|
||||
|
||||
process {
|
||||
|
||||
// scheduler
|
||||
|
||||
executor = 'sge'
|
||||
penv = 'smp'
|
||||
queue = { task.time <= 6.h ? 'shortint.q' : 'all.q' }
|
||||
clusterOptions = { "-l rmem=${ (task.memory.toGiga() / task.cpus) }G" }
|
||||
|
||||
}
|
||||
|
||||
|
||||
// optional executor settings
|
||||
|
||||
executor {
|
||||
|
||||
queueSize = 10
|
||||
submitRateLimit = '1 sec'
|
||||
|
||||
}
|
||||
|
||||
|
||||
// container engine
|
||||
|
||||
singularity {
|
||||
|
||||
enabled = true
|
||||
autoMounts = true
|
||||
|
||||
}
|
||||
|
||||
@ -0,0 +1,14 @@
|
||||
params {
|
||||
config_profile_description = 'Telethon Institute of Genetic and Medicine (TIGEM) provided by nf-core/configs.'
|
||||
config_profile_contact = 'Giuseppe Martone (@giusmar)'
|
||||
config_profile_url = 'https://github.com/giusmar'
|
||||
}
|
||||
|
||||
process.executor = 'slurm'
|
||||
google.zone = 'europe-west1'
|
||||
|
||||
singularity {
|
||||
enabled = true
|
||||
autoMounts = true
|
||||
cacheDir = 'work/singularity'
|
||||
}
|
||||
@ -0,0 +1,34 @@
|
||||
params {
|
||||
|
||||
config_profile_description = 'University College London Myriad cluster'
|
||||
config_profile_contact = 'Chris Wyatt (ucbtcdr@ucl.ac.uk)'
|
||||
config_profile_url = 'https://www.rc.ucl.ac.uk/docs/Clusters/Myriad/'
|
||||
|
||||
}
|
||||
|
||||
process {
|
||||
executor='sge'
|
||||
penv = 'smp'
|
||||
}
|
||||
|
||||
params {
|
||||
// Defaults only, expecting to be overwritten
|
||||
max_memory = 128.GB
|
||||
max_cpus = 36
|
||||
max_time = 72.h
|
||||
// igenomes_base = 's3://ngi-igenomes/igenomes/'
|
||||
}
|
||||
|
||||
// optional executor settings
|
||||
|
||||
executor {
|
||||
|
||||
queueSize = 10
|
||||
submitRateLimit = '1 sec'
|
||||
|
||||
}
|
||||
|
||||
singularity {
|
||||
enabled = true
|
||||
autoMounts = true
|
||||
}
|
||||
@ -0,0 +1,39 @@
|
||||
# nf-core/configs: CRA HPC Configuration
|
||||
|
||||
nfcore pipeline sarek and rnaseq have been tested on the CRA HPC.
|
||||
|
||||
## Before running the pipeline
|
||||
|
||||
- You will need an account to use the CRA HPC cluster in order to run the pipeline.
|
||||
- Make sure that Singularity and Nextflow are installed.
|
||||
- Downlode pipeline singularity images to a HPC system using [nf-core tools](https://nf-co.re/tools/#downloading-pipelines-for-offline-use)
|
||||
|
||||
```
|
||||
$ conda install nf-core
|
||||
$ nf-core download
|
||||
```
|
||||
|
||||
- You will need to specify a Singularity cache directory in your ~./bashrc. This will store your container images in this cache directory without repeatedly downloading them every time you run a pipeline. Since space on home directory is limited, using lustre file system is recommended.
|
||||
|
||||
```
|
||||
export NXF_SINGULARITY_CACHEDIR = "/lustre/fs0/storage/yourCRAAccount/cache_dir"
|
||||
```
|
||||
|
||||
- Download iGenome reference to be used as a local copy.
|
||||
|
||||
```
|
||||
$ aws s3 --no-sign-request --region eu-west-1 sync s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/ /lustre/fs0/storage/yourCRAAccount/references/Homo_sapiens/GATK/GRCh38/
|
||||
```
|
||||
|
||||
## Running the pipeline using the adcra config profile
|
||||
|
||||
- Run the pipeline within a [screen](https://linuxize.com/post/how-to-use-linux-screen/) or [tmux](https://linuxize.com/post/getting-started-with-tmux/) session.
|
||||
- Specify the config profile with `-profile adcra`.
|
||||
- Using lustre file systems to store results (`--outdir`) and intermediate files (`-work-dir`) is recommended.
|
||||
|
||||
```
|
||||
nextflow run /path/to/nf-core/<pipeline-name> -profile adcra \
|
||||
--genome GRCh38 \
|
||||
--igenomes_base /path/to/genome_references/ \
|
||||
... # the rest of pipeline flags
|
||||
```
|
||||
@ -0,0 +1,15 @@
|
||||
# nf-core/configs: Cancer Research UK Manchester Institute Configuration
|
||||
|
||||
All nf-core pipelines have been successfully configured for the use on the HPC (phoenix) at Cancer Research UK Manchester Institute.
|
||||
|
||||
To use, run the pipeline with `-profile crukmi`. This will download and launch the [`crukmi.config`](../conf/crukmi.config) which has been pre-configured with a setup suitable for the phoenix HPC. Using this profile, singularity images will be downloaded to run on the cluster.
|
||||
|
||||
Before running the pipeline you will need to load Nextflow using the environment module system, for example via:
|
||||
|
||||
```bash
|
||||
## Load Nextflow and Singularity environment modules
|
||||
module purge
|
||||
module load apps/nextflow/22.04.5
|
||||
```
|
||||
|
||||
The pipeline should always be executed inside a workspace on the `/scratch/` system. All of the intermediate files required to run the pipeline will be stored in the `work/` directory. It is recommended to delete this directory after the pipeline has finished successfully because it can get quite large, and all of the main output files will be saved in the `results/` directory.
|
||||
@ -0,0 +1,45 @@
|
||||
# nf-core/configs: GIS Aquila Configuration
|
||||
|
||||
All nf-core pipelines have been successfully configured for use on the cluster of the GIS (Genome Institute of Singapore (Aquila)).
|
||||
|
||||
To use, run the pipeline with `-profile gis`. This will download and launch the [`gis.config`](../conf/gis.config) which has been pre-configured with a setup suitable for the GIS Aquila cluster. Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline.
|
||||
|
||||
## How to use on GIS core
|
||||
|
||||
Before running the pipeline you will need to load Nextflow using the environment module system on GIS Aquila. You can do this by issuing the commands below:
|
||||
|
||||
```bash
|
||||
# Login to a compute node
|
||||
srun --pty bash
|
||||
|
||||
## Load Nextflow and Singularity environment modules
|
||||
module purge
|
||||
source /mnt/projects/rpd/rc/init.2017-04
|
||||
module load miniconda3
|
||||
|
||||
|
||||
# Run a nextflow pipeline with dependencies bundled in a conda environment
|
||||
set +u
|
||||
source activate nfcore-rnaseq-1.0dev
|
||||
set -u
|
||||
|
||||
# Run a downloaded/git-cloned nextflow workflow from
|
||||
nextflow run \\
|
||||
nf-core/workflow \\
|
||||
-resume \\
|
||||
-profile gis \\
|
||||
--email my-email@example.org \\
|
||||
-c my-specific.config
|
||||
...
|
||||
|
||||
|
||||
# Or use the nf-core client
|
||||
nextflow run nf-core/rnaseq ...
|
||||
|
||||
```
|
||||
|
||||
## Databanks
|
||||
|
||||
A local copy of several genomes are available in `/mnt/projects/rpd/genomes.testing/S3_igenomes/` directory.
|
||||
|
||||
> NB: You will need an account to use the HPC cluster on GIS in order to run the pipeline. If in doubt contact IT or go to [Andreas Wilm](https://github.com/andreas-wilm)
|
||||
@ -0,0 +1,24 @@
|
||||
# nf-core/configs: HKI Configuration
|
||||
|
||||
All nf-core pipelines have been successfully configured for use on clusters at the [Leibniz Institute for Natural Product Research and Infection Biology Hans Knöll Institute](https://www.leibniz-hki.de/en).
|
||||
|
||||
To use, run the pipeline with `-profile hki,<cluster>`. This will download and launch the [`hki.config`](../conf/hki.config) which contains specific profiles for each cluster. The number of parallel jobs that run is currently limited to 8.
|
||||
|
||||
The currently available profiles are:
|
||||
|
||||
- apate (uses singularity, cleanup set to true by default)
|
||||
- arges (uses singularity, cleanup set to true by default)
|
||||
- aither (uses singularity, cleanup set to true by default)
|
||||
- debug (sets cleanup to false for debugging purposes, use e.g. `profile hki,<cluster>,debug`)
|
||||
|
||||
Note that Nextflow is not necessarily installed by default on the HKI HPC cluster(s). You will need to install it into a directory you have write access to.
|
||||
Follow these instructions from the Nextflow documentation.
|
||||
|
||||
- Install Nextflow : [here](https://www.nextflow.io/docs/latest/getstarted.html#)
|
||||
|
||||
All of the intermediate files required to run the pipeline will be stored in the `work/` directory. It is recommended to delete this directory after the pipeline
|
||||
has finished successfully because it can get quite large, and all of the main output files will be saved in the `results/` directory anyway.
|
||||
|
||||
> NB: You will need an account to use the HKI HPC clusters in order to run the pipeline. If in doubt contact the ICT Service Desk.
|
||||
> NB: Nextflow will need to submit the jobs via SLURM to the HKI HPC clusters and as such the commands above will have to be executed on the login
|
||||
> node. If in doubt contact ICT.
|
||||
@ -0,0 +1,35 @@
|
||||
# nf-core/configs: ku_sund_dangpu configuration
|
||||
|
||||
All nf-core pipelines have been successfully configured for use on the DANGPU at the
|
||||
Novo Nordisk Foundation Center for Stem Cell Medicine (reNEW) and the Novo Nordisk Foundation Center for Protein Research (CPR) at the University of Copenhagen.
|
||||
|
||||
To use, run the pipeline with `-profile ku_sund_dangpu`. This will download and launch the [`ku_sund_dangpu.config`](../conf/ku_sund_dangpu.config) which has been pre-configured with a setup suitable for the DANGPU.
|
||||
|
||||
## Modules
|
||||
|
||||
Before running the pipeline you will need to load Nextflow and Singularity using the environment module system on DANGPU. You can do this by issuing the commands below:
|
||||
|
||||
```bash
|
||||
## Load Nextflow and Singularity environment modules
|
||||
module purge
|
||||
module load java/11.0.15 nextflow/22.04.4 singularity/3.8.0
|
||||
# alternative modules for older nextflow version (v.21) that works with java 8:
|
||||
# module load jdk/1.8.0_291 nextflow/21.04.1.5556 singularity/3.8.0
|
||||
export NXF_OPTS='-Xms1g -Xmx4g'
|
||||
export NXF_HOME=/projects/dan1/people/${USER}/cache/nxf-home
|
||||
export NXF_TEMP=/scratch/tmp
|
||||
export NXF_SINGULARITY_CACHEDIR=/projects/dan1/people/${USER}/cache/singularity-images
|
||||
```
|
||||
|
||||
Create the user-specific nextflow directories if they don't exist yet:
|
||||
|
||||
```
|
||||
mkdir $NXF_SINGULARITY_CACHEDIR
|
||||
mkdir $NXF_HOME
|
||||
```
|
||||
|
||||
Finally, download and test the pipeline of choice using the `-profile ku_sund_dangpu`. Note that normally you would run resource-intensive commands with slurm, but in case of nf-core pipelines you do not have to do this: we have pre-configured slurm to be the resource manager within the `ku_sund_dangpu profile`. Just make sure that the pipeline is run within a tmux session.
|
||||
|
||||
```
|
||||
nextflow run nf-core/rnaseq -profile test,ku_sund_dangpu
|
||||
```
|
||||
@ -0,0 +1,45 @@
|
||||
# nf-core/configs Mana (at University of Hawaii at Manoa) Configuration
|
||||
|
||||
To use, run the pipeline with `-profile mana`. It will use the following parameters for Mana (UHM HPCC):
|
||||
|
||||
- Load singularity and use it as default container technology
|
||||
- Setup a container cache directory in your home (~/.singularity_images_cache)
|
||||
- Select appropriate queues (currently: `shared,exclusive,kill-shared,kill-exclusive`)
|
||||
- Set the maximum available resources (available in 09/02/2022):
|
||||
- CPUs: 96
|
||||
- Memory: 400.GB
|
||||
- Time: 72.h
|
||||
|
||||
## Pre-requisites
|
||||
|
||||
In order to run a nf-core pipeline on Mana, you will need to setup nextflow in your environment.
|
||||
At the moment, nextflow is not available as a module (but might be in the future).
|
||||
|
||||
### Install nextflow in a conda environment
|
||||
|
||||
Before we start, we will need to work on an interactive node (currently, mana doesn't let you execute any program in the login node):
|
||||
|
||||
```bash
|
||||
# Request an interactive sandbox node for 30 min
|
||||
srun --pty -t 30 -p sandbox /bin/bash
|
||||
```
|
||||
|
||||
To setup nextflow on your account, follow these steps.
|
||||
|
||||
```bash
|
||||
# Load the latest anaconda3 module
|
||||
module load lang/Anaconda3/2022.05
|
||||
|
||||
# Initialize environment
|
||||
. $(conda info --base)/etc/profile.d/conda.sh
|
||||
|
||||
# Install nextflow (here in base environment, but you can create a new one if you'd like)
|
||||
conda install -c bioconda nextflow
|
||||
```
|
||||
|
||||
If you want these settings to be persistent, you can add the first 2 commands in your .bash_profile file like this:
|
||||
|
||||
```bash
|
||||
echo "module load lang/Anaconda3/2022.05" >> ~/.bash_profile
|
||||
echo "$(conda info --base)/etc/profile.d/conda.sh" >> ~/.bash_profile
|
||||
```
|
||||
@ -0,0 +1,70 @@
|
||||
# nf-core/configs: Medair Configuration
|
||||
|
||||
All nf-core pipelines have been successfully configured for use on the Medair cluster at Clinical Genomics Gothenburg.
|
||||
|
||||
To use, run the pipeline with `-profile medair`. This will download and launch the [`medair.config`](../conf/medair.config) which has been pre-configured with a setup suitable for the Medair cluster.
|
||||
It will enable Nextflow to manage the pipeline jobs via the `SGE` job scheduler.
|
||||
Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline.
|
||||
|
||||
You will need an account to use the Medair cluster in order to download or run pipelines. If in doubt, contact cgg-it.
|
||||
|
||||
## Download nf-core pipelines
|
||||
|
||||
### Set-up: load Nextflow and nf-core tools
|
||||
|
||||
First you need to load relevant softwares: Nextflow and nf-core tools. You can do it as follow:
|
||||
|
||||
```bash
|
||||
## Load Nextflow
|
||||
module load nextflow
|
||||
## Load nf-core tools
|
||||
module load miniconda
|
||||
source activate nf-core
|
||||
```
|
||||
|
||||
### Storage of Singularity images
|
||||
|
||||
When downloading a nf-core pipeline for the first time (or a specific version of a pipeline), you can choose to store the Singularity image for future use. We chose to have a central location for these images on medair: `/apps/bio/dependencies/nf-core/singularities`.
|
||||
|
||||
For Nexflow to know where to store new images, run or add the following to your `.bashrc`:
|
||||
|
||||
```bash
|
||||
export NXF_SINGULARITY_CACHEDIR="/apps/bio/dependencies/nf-core/singularities"
|
||||
```
|
||||
|
||||
> Comment: This was also added to cronuser.
|
||||
|
||||
### Download a pipeline
|
||||
|
||||
We have started to download pipelines in the following location: `/apps/bio/repos/nf-core/`
|
||||
|
||||
Use the `nf-core download --singularity-cache-only` command to start a download. It will open an interactive menu. Choose `singularity` for the software container image, and `none` for the compression type.
|
||||
|
||||
## Run nf-core pipelines
|
||||
|
||||
Nextflow will need to submit the jobs via the job scheduler to the HPC cluster and as such the commands below will have to be executed on one of the login nodes. If in doubt contact cgg-it (cgg-it[at]gu.se).
|
||||
|
||||
### Set-up: load Nextflow and Singularity
|
||||
|
||||
Before running a pipeline you will need to load Nextflow and Singularity using the environment module system on Medair. You can do this by issuing the commands below:
|
||||
|
||||
```bash
|
||||
## Load Nextflow and Singularity environment modules
|
||||
module purge
|
||||
module load nextflow
|
||||
module load singularity
|
||||
```
|
||||
|
||||
### Choose a profile
|
||||
|
||||
Depending on what you are running, you can choose between the `wgs` and `production` profiles. Jobs running with the `wgs` profile run on a queue with higher priority. Jobs running with the `production` profile can last longer (max time: 20 days, versus 2 days for the `wgs` profile).
|
||||
|
||||
For example, the following job would run with the `wgs` profile:
|
||||
|
||||
```bash
|
||||
run nextflow nf-core/raredisease -profile medair,wgs
|
||||
```
|
||||
|
||||
### Sentieon
|
||||
|
||||
In some pipelines (sarek, raredisease) it is possible to use Sentieon for alignment and variant calling. If ones uses the label `sentieon` for running a process, the config file contains the path to the Sentieon singularity image on Medair.
|
||||
@ -0,0 +1,11 @@
|
||||
# nf-core/configs: ATAC-Seq Specific Configuration - Sheffield Bioinformatics Core Facility ShARC
|
||||
|
||||
Specific configuration for [nf-co.re/atacseq](https://nf-co.re/atacseq) pipeline
|
||||
|
||||
## Usage
|
||||
|
||||
To use, run nextflow with the pipeline using `-profile sbc_sharc` (note the single hyphen).
|
||||
|
||||
This will download and launch the atacseq specific [`sbc_sharc.config`](../../../conf/pipeline/atacseq/sbc_sharc.config) which has been pre-configured with a setup suitable for the [University of Sheffield ShARC cluster](https://docs.hpc.shef.ac.uk/en/latest/index.html) and will automatically load the appropriate pipeline-specific configuration file.
|
||||
|
||||
Example: `nextflow run nf-core/atacseq -profile sbc_sharc`
|
||||
@ -0,0 +1,11 @@
|
||||
# nf-core/configs: ChIP-Seq Specific Configuration - Sheffield Bioinformatics Core Facility ShARC
|
||||
|
||||
Specific configuration for [nf-co.re/chipseq](https://nf-co.re/chipseq) pipeline
|
||||
|
||||
## Usage
|
||||
|
||||
To use, run nextflow with the pipeline using `-profile sbc_sharc` (note the single hyphen).
|
||||
|
||||
This will download and launch the chipseq specific [`sbc_sharc.config`](../../../conf/pipeline/chipseq/sbc_sharc.config) which has been pre-configured with a setup suitable for the [University of Sheffield ShARC cluster](https://docs.hpc.shef.ac.uk/en/latest/index.html) and will automatically load the appropriate pipeline-specific configuration file.
|
||||
|
||||
Example: `nextflow run nf-core/chipseq -profile sbc_sharc`
|
||||
@ -0,0 +1,19 @@
|
||||
# nf-core/configs: AWS Tower Demultiplex specific configuration
|
||||
|
||||
Extra specific configuration for demultiplex pipeline
|
||||
|
||||
## Usage
|
||||
|
||||
To use, run the pipeline with `-profile aws_tower`.
|
||||
|
||||
This will download and launch the demultiplex specific [`aws_tower.config`](../../../conf/pipeline/demultiplex/aws_tower.config) which has been pre-configured with a setup suitable for AWS batch through tower.
|
||||
|
||||
Example: `nextflow run nf-core/demultiplex -profile aws_tower`
|
||||
|
||||
## eager specific configurations for eva
|
||||
|
||||
Specific configurations for AWS has been made for demultiplex.
|
||||
|
||||
### General profiles
|
||||
|
||||
- The general AWS Tower profile runs with default nf-core/demultiplex parameters, but with modifications to account file transfer speed and optimized bases2fastq resources.
|
||||
@ -0,0 +1,19 @@
|
||||
# nf-core/configs: HASTA rnafusion specific configuration
|
||||
|
||||
Extra specific configuration for rnafusion pipeline
|
||||
|
||||
## Usage
|
||||
|
||||
To use, run the pipeline with `-profile hasta`.
|
||||
|
||||
This will download and launch the rnafusion specific [`hasta.config`](../../../conf/pipeline/rnafusion/munin.config) which has been pre-configured with a setup suitable for the `HASTA` cluster.
|
||||
|
||||
Example: `nextflow run nf-core/rnafusion -profile hasta`
|
||||
|
||||
## rnafusion specific configurations for HASTA
|
||||
|
||||
Specific configurations for `HASTA` has been made for rnafusion.
|
||||
|
||||
- Always run all the analysis steps (all = true)
|
||||
- Use trimming (trim = true)
|
||||
- Take the fusions identified by at least 2 fusion detection tools to the fusioninspector analysis (fusioninspector_filter = true)
|
||||
@ -0,0 +1,11 @@
|
||||
# nf-core/configs: RNA-Seq Specific Configuration - Sheffield Bioinformatics Core Facility ShARC
|
||||
|
||||
Specific configuration for [nf-co.re/rnaseq](https://nf-co.re/rnaseq) pipeline
|
||||
|
||||
## Usage
|
||||
|
||||
To use, run nextflow with the pipeline using `-profile sbc_sharc` (note the single hyphen).
|
||||
|
||||
This will download and launch the rnaseq specific [`sbc_sharc.config`](../../../conf/pipeline/rnaseq/sbc_sharc.config) which has been pre-configured with a setup suitable for the [University of Sheffield ShARC cluster](https://docs.hpc.shef.ac.uk/en/latest/index.html) and will automatically load the appropriate pipeline-specific configuration file.
|
||||
|
||||
Example: `nextflow run nf-core/rnaseq -profile sbc_sharc`
|
||||
@ -0,0 +1,17 @@
|
||||
# nf-core/configs: CRUK-MI sarek specific configuration
|
||||
|
||||
Extra specific configuration for sarek pipeline
|
||||
|
||||
## Usage
|
||||
|
||||
To use, run the pipeline with `-profile crukmi`.
|
||||
|
||||
This will download and launch the sarek specific [`crukmi.config`](../../../conf/pipeline/sarek/munin.config) which has been pre-configured with a setup suitable for the Cancer Research UK Manchester Institute cluster (phoenix).
|
||||
|
||||
Example: `nextflow run nf-core/sarek -profile crukmi`
|
||||
|
||||
## Sarek specific configurations for CRUK-MI
|
||||
|
||||
Specific configurations for `CRUK-MI` has been made for sarek.
|
||||
|
||||
- Initial requested resources for SAMTOOLS_MPILEUP are only 5GB and 1 core.
|
||||
@ -0,0 +1,11 @@
|
||||
# nf-core/configs: Sarek Specific Configuration - Sheffield Bioinformatics Core Facility ShARC
|
||||
|
||||
Specific configuration for [nf-co.re/sarek](https://nf-co.re/sarek) pipeline
|
||||
|
||||
## Usage
|
||||
|
||||
To use, run nextflow with the pipeline using `-profile sbc_sharc` (note the single hyphen).
|
||||
|
||||
This will download and launch the sarek specific [`sbc_sharc.config`](../../../conf/pipeline/sarek/sbc_sharc.config) which has been pre-configured with a setup suitable for the [University of Sheffield ShARC cluster](https://docs.hpc.shef.ac.uk/en/latest/index.html) and will automatically load the appropriate pipeline-specific configuration file.
|
||||
|
||||
Example: `nextflow run nf-core/sarek -profile sbc_sharc`
|
||||
@ -0,0 +1,31 @@
|
||||
# nf-core/configs: Sage Bionetworks Global Configuration
|
||||
|
||||
To use this custom configuration, run the pipeline with `-profile sage`. This will download and load the [`sage.config`](../conf/sage.config), which contains a number of optimizations relevant to Sage employees running workflows on AWS (_e.g._ using Nextflow Tower). This profile will also load any applicable pipeline-specific configuration.
|
||||
|
||||
This global configuration includes the following tweaks:
|
||||
|
||||
- Update the default value for `igenomes_base` to `s3://sage-igenomes`
|
||||
- Enable retries by default when exit codes relate to insufficient memory
|
||||
- Allow pending jobs to finish if the number of retries are exhausted
|
||||
- Increase the amount of time allowed for file transfers
|
||||
- Improve reliability of file transfers with retries and reduced concurrency
|
||||
- Increase the default chunk size for multipart uploads to S3
|
||||
- Slow down job submission rate to avoid overwhelming any APIs
|
||||
- Define the `check_max()` function, which is missing in Sarek v2
|
||||
- Slow the increase in the number of allocated CPU cores on retries
|
||||
- Increase the default time limits because we run pipelines on AWS
|
||||
|
||||
## Additional information about iGenomes
|
||||
|
||||
The following iGenomes prefixes have been copied from `s3://ngi-igenomes/` (`eu-west-1`) to `s3://sage-igenomes` (`us-east-1`). See [this script](https://github.com/Sage-Bionetworks-Workflows/nextflow-infra/blob/main/bin/mirror-igenomes.sh) for more information. The `sage-igenomes` S3 bucket has been configured to openly available, but files cannot be downloaded out of `us-east-1` to avoid egress charges. You can check the `conf/igenomes.config` file in each nf-core pipeline to figure out the mapping between genome IDs (_i.e._ for `--genome`) and iGenomes prefixes ([example](https://github.com/nf-core/rnaseq/blob/89bf536ce4faa98b4d50a8ec0a0343780bc62e0a/conf/igenomes.config#L14-L26)).
|
||||
|
||||
- **Human Genome Builds**
|
||||
- `Homo_sapiens/Ensembl/GRCh37`
|
||||
- `Homo_sapiens/GATK/GRCh37`
|
||||
- `Homo_sapiens/UCSC/hg19`
|
||||
- `Homo_sapiens/GATK/GRCh38`
|
||||
- `Homo_sapiens/NCBI/GRCh38`
|
||||
- `Homo_sapiens/UCSC/hg38`
|
||||
- **Mouse Genome Builds**
|
||||
- `Mus_musculus/Ensembl/GRCm38`
|
||||
- `Mus_musculus/UCSC/mm10`
|
||||
@ -0,0 +1,40 @@
|
||||
# nf-core/configs: Sheffield Bioinformatics Core Facility ShARC Configuration
|
||||
|
||||
## Using the SBC_ShARC Institutional Configuration Profile
|
||||
|
||||
To use [`sbc_sharc.config`](../conf/sbc_sharc.config), run nextflow with an nf-core pipeline using `-profile sbc_sharc` (note the single hyphen).
|
||||
|
||||
This will download and launch [`sbc_sharc.config`](../conf/sbc_sharc.config) which has been pre-configured with a setup suitable for the ShARC cluster and will automatically load the appropriate pipeline-specific configuration file.
|
||||
|
||||
The following nf-core pipelines have been successfully configured for use on the the [University of Sheffield ShARC cluster](https://docs.hpc.shef.ac.uk/en/latest/index.html):
|
||||
|
||||
- [nf-co.re/atacseq](https://nf-co.re/atacseq)
|
||||
- [nf-co.re/chipseq](https://nf-co.re/chipseq)
|
||||
- [nf-co.re/rnaseq](https://nf-co.re/rnaseq)
|
||||
- [nf-co.re/sarek](https://nf-co.re/sarek)
|
||||
|
||||
When using [`sbc_sharc.config`](../conf/sbc_sharc.config) with the pipelines listed above, the appropriate configuration file from the list below will be loaded automatically:
|
||||
|
||||
- [atacseq sbc_sharc.config](../conf/pipeline/atacseq/sbc_sharc.config)
|
||||
- [chipseq sbc_sharc.config](../conf/pipeline/chipseq/sbc_sharc.config)
|
||||
- [rnaseq sbc_sharc.config](../conf/pipeline/rnaseq/sbc_sharc.config)
|
||||
- [sarek sbc_sharc.config](../conf/pipeline/sarek/sbc_sharc.config)
|
||||
|
||||
The [`sbc_sharc.config`](../conf/sbc_sharc.config) configuration file might work with other nf-core pipelines as it stands but we cannot guarantee they will run without issue. We will be continuing to create, test and optimise configurations for new pipelines in the future.
|
||||
|
||||
## A Note on Singularity Containers
|
||||
|
||||
The [`sbc_sharc.config`](../conf/sbc_sharc.config) configuration file supports running nf-core pipelines with Singularity containers; Singularity images will be downloaded automatically before execution of the pipeline.
|
||||
|
||||
When you run nextflow for the first time, Singularity will create a hidden directory `.singularity` in your `$HOME` directory `/home/$USER` which has very very limited (10GB) space available. It is therefore a good idea to create a directory somewhere else (e.g., `/data/$USER`) with more room and link the locations. To do this, run the following series of commands:
|
||||
|
||||
```shell
|
||||
# change directory to $HOME
|
||||
cd $HOME
|
||||
|
||||
# make the directory that will be linked to
|
||||
mkdir /data/$USER/.singularity
|
||||
|
||||
# link the new directory with the existing one
|
||||
ln -s /data/$USER/.singularity .singularity
|
||||
```
|
||||
@ -0,0 +1,7 @@
|
||||
# nf-core/configs: TIGEM configuration
|
||||
|
||||
To use, run the pipeline with `-profile tigem`. This will download and launch the tigem.config which has been pre-configured with a setup suitable for the TIGEM personal biocluster.
|
||||
|
||||
---
|
||||
|
||||
This configuration profile can be used on TIGEM clusters, with the pre-installed SLURM job scheduling system. An additional parameter is `google.zone` to allow downloading data from GCP for a specific time zone. It should not interfere with any local or other AWS configuration.
|
||||
@ -0,0 +1,51 @@
|
||||
# nf-core/configs: Myriad Configuration
|
||||
|
||||
All nf-core pipelines have been successfully configured for use on UCL's myriad cluster [University College London](https://www.rc.ucl.ac.uk/docs/Clusters/Myriad/).
|
||||
|
||||
To use, run the pipeline with `-profile ucl_myriad`. This will download and launch the [`ucl_myriad.config`](../conf/ucl_myriad.config) which has been pre-configured with a setup suitable for the myriad cluster. Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline.
|
||||
|
||||
## Using Nextflow on Myriad
|
||||
|
||||
Before running the pipeline you will need to install and configure Nextflow and Singularity.
|
||||
|
||||
### Singularity
|
||||
|
||||
This can be done with the following commands:
|
||||
|
||||
```bash
|
||||
## Load Singularity environment modules - these commands can be placed in your ~/.bashrc also
|
||||
module add java/openjdk-11/11.0.1
|
||||
module add singularity-env/1.0.0
|
||||
```
|
||||
|
||||
Then set the correct configuration of the cache directories, where <YOUR_ID> is replaced with you credentials which you can find by entering `whoami` into the terminal once you are logged into myriad. Once you have added your credentials save these lines into your .bashrc file in the base directory (e.g. /home/<YOUR_ID>/.bashrc):
|
||||
|
||||
```bash
|
||||
# Set all the Singularity cache dirs to Scratch
|
||||
export SINGULARITY_CACHEDIR=/home/<YOUR_ID>/Scratch/.singularity/
|
||||
export SINGULARITY_TMPDIR=/home/<YOUR_ID>/Scratch/.singularity/tmp
|
||||
export SINGULARITY_LOCALCACHEDIR=/home/<YOUR_ID>/Scratch/.singularity/localcache
|
||||
export SINGULARITY_PULLFOLDER=/home/<YOUR_ID>/Scratch/.singularity/pull
|
||||
|
||||
# Bind your Scratch directory so it is accessible from inside the container
|
||||
export SINGULARITY_BINDPATH=/scratch/scratch/<YOUR_ID>
|
||||
```
|
||||
|
||||
### Nextflow
|
||||
|
||||
Download the latest release of nextflow. Warning: the self-update line should update to the latest version, but sometimes not, so please check which is the latest release (https://github.com/nextflow-io/nextflow/releases), you can then manually set this by entering (`NXF_VER=XX.XX.X`).
|
||||
|
||||
```bash
|
||||
## Download Nextflow-all
|
||||
curl -s https://get.nextflow.io | bash
|
||||
NXF_VER=22.10.0
|
||||
nextflow -self-update
|
||||
chmod a+x nextflow
|
||||
mv nextflow ~/bin/nextflow
|
||||
```
|
||||
|
||||
Then make sure that your bin PATH is executable, by placing the following line in your .bashrc:
|
||||
|
||||
```bash
|
||||
export PATH=$PATH:/home/<YOUR_ID>/bin
|
||||
```
|
||||
@ -0,0 +1,13 @@
|
||||
/*
|
||||
* -------------------------------------------------
|
||||
* nfcore/atacseq custom profile Nextflow config file
|
||||
* -------------------------------------------------
|
||||
* Config options for custom environments.
|
||||
* Cluster-specific config options should be saved
|
||||
* in the conf/pipeline/atacseq folder and imported
|
||||
* under a profile name here.
|
||||
*/
|
||||
|
||||
profiles {
|
||||
sbc_sharc { includeConfig "${params.custom_config_base}/conf/pipeline/atacseq/sbc_sharc.config" }
|
||||
}
|
||||
@ -0,0 +1,13 @@
|
||||
/*
|
||||
* -------------------------------------------------
|
||||
* nfcore/chipseq custom profile Nextflow config file
|
||||
* -------------------------------------------------
|
||||
* Config options for custom environments.
|
||||
* Cluster-specific config options should be saved
|
||||
* in the conf/pipeline/chipseq folder and imported
|
||||
* under a profile name here.
|
||||
*/
|
||||
|
||||
profiles {
|
||||
sbc_sharc { includeConfig "${params.custom_config_base}/conf/pipeline/chipseq/sbc_sharc.config" }
|
||||
}
|
||||
@ -0,0 +1,13 @@
|
||||
/*
|
||||
* -------------------------------------------------
|
||||
* nfcore/demultiplex custom profile Nextflow config file
|
||||
* -------------------------------------------------
|
||||
* Config options for custom environments.
|
||||
* Cluster-specific config options should be saved
|
||||
* in the conf/pipeline/demultiplex folder and imported
|
||||
* under a profile name here.
|
||||
*/
|
||||
|
||||
profiles {
|
||||
aws_tower { includeConfig "${params.custom_config_base}/conf/pipeline/demultiplex/aws_tower.config" }
|
||||
}
|
||||
Loading…
Reference in New Issue