1
0
Fork 0
mirror of https://github.com/MillironX/nf-configs.git synced 2024-11-21 16:16:04 +00:00

Merge pull request #414 from sheffield-bioinformatics-core/sbc_sharc

Added global institutional and pipeline configs for sbc_sharc
This commit is contained in:
James A. Fellows Yates 2022-09-14 11:46:41 +02:00 committed by GitHub
commit 3fcf708134
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
17 changed files with 520 additions and 0 deletions

View file

@ -83,6 +83,7 @@ jobs:
- "sage"
- "sahmri"
- "sanger"
- "sbc_sharc"
- "seg_globe"
- "uct_hpc"
- "unibe_ibu"

View file

@ -137,6 +137,7 @@ Currently documentation is available for the following systems:
- [ROSALIND](docs/rosalind.md)
- [SAGE BIONETWORKS](docs/sage.md)
- [SANGER](docs/sanger.md)
- [SBC_SHARC](docs/sbc_sharc.md)
- [SEG_GLOBE](docs/seg_globe.md)
- [UCT_HPC](docs/uct_hpc.md)
- [UNIBE_IBU](docs/unibe_ibu.md)
@ -197,6 +198,10 @@ Currently documentation is available for the following pipelines within specific
- ampliseq
- [BINAC](docs/pipeline/ampliseq/binac.md)
- [UPPMAX](docs/pipeline/ampliseq/uppmax.md)
- atacseq
- [SBC_SHARC](docs/pipeline/atacseq/sbc_sharc.md)
- chipseq
- [SBC_SHARC](docs/pipeline/chipseq/sbc_sharc.md)
- eager
- [EVA](docs/pipeline/eager/eva.md)
- mag
@ -204,11 +209,14 @@ Currently documentation is available for the following pipelines within specific
- rnafusion
- [HASTA](docs/pipeline/rnafusion/hasta.md)
- [MUNIN](docs/pipeline/rnafusion/munin.md)
- rnaseq
- [SBC_SHARC](docs/pipeline/rnaseq/sbc_sharc.md)
- rnavar
- [MUNIN](docs/pipeline/rnavar/munin.md)
- sarek
- [Cancer Research UK Manchester Institute](docs/pipeline/sarek/crukmi.md)
- [MUNIN](docs/pipeline/sarek/munin.md)
- [SBC_SHARC](docs/pipeline/sarek/sbc_sharc.md)
- [UPPMAX](docs/pipeline/sarek/uppmax.md)
- taxprofiler
- [EVA](docs/pipeline/taxprofiler/eva.md)

View file

@ -0,0 +1,74 @@
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
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 {
withLabel:process_low {
cpus = { check_max( 2 * task.attempt, 'cpus' ) }
memory = { check_max( 4.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( 8.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( 16.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
}
}
}

View file

@ -0,0 +1,74 @@
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
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 {
withLabel:process_low {
cpus = { check_max( 2 * task.attempt, 'cpus' ) }
memory = { check_max( 4.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( 8.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( 16.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
}
}
}

View file

@ -0,0 +1,79 @@
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
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 {
withLabel:process_low {
cpus = { check_max( 2 * task.attempt, 'cpus' ) }
memory = { check_max( 4.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( 8.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( 16.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( 60.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
}
}
}

View file

@ -0,0 +1,114 @@
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
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 {
// process labels
withLabel:process_low {
cpus = { check_max( 2 * task.attempt, 'cpus' ) }
memory = { check_max( 4.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( 8.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( 16.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( 60.GB * task.attempt, 'memory' ) }
}
// process name
withName:'BWAMEM1_MEM|BWAMEM2_MEM' {
cpus = { check_max( 12 * task.attempt, 'cpus' ) }
memory = { check_max( 16.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( 16.GB * task.attempt, 'memory' ) }
}
withName:'GATK4_MARKDUPLICATES' {
memory = { check_max( 16.GB * task.attempt, 'memory' ) }
}
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
}
}
}

57
conf/sbc_sharc.config Normal file
View file

@ -0,0 +1,57 @@
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Sheffield Bioinformatics Core Configuration Profile - ShARC
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Base Institutional Configuration
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/
params {
// nf-core specific parameters displayed in header summary of each run
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
max_cpus = 16
max_memory = 64.GB
max_time = 96.h
}
// container engine
singularity {
enabled = true
autoMounts = true
}
// 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()}G" }
// error and retry handling
errorStrategy = { task.exitStatus in [143,137,104,134,139,140] ? 'retry' : 'finish' }
maxRetries = 2
}

View file

@ -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`

View file

@ -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`

View file

@ -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`

View file

@ -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`

40
docs/sbc_sharc.md Normal file
View file

@ -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
```

View file

@ -65,6 +65,7 @@ profiles {
sage { includeConfig "${params.custom_config_base}/conf/sage.config" }
sahmri { includeConfig "${params.custom_config_base}/conf/sahmri.config" }
sanger { includeConfig "${params.custom_config_base}/conf/sanger.config"}
sbc_sharc { includeConfig "${params.custom_config_base}/conf/sbc_sharc.config"}
seg_globe { includeConfig "${params.custom_config_base}/conf/seg_globe.config"}
uct_hpc { includeConfig "${params.custom_config_base}/conf/uct_hpc.config" }
unibe_ibu { includeConfig "${params.custom_config_base}/conf/unibe_ibu.config" }

13
pipeline/atacseq.config Normal file
View file

@ -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" }
}

13
pipeline/chipseq.config Normal file
View file

@ -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" }
}

View file

@ -11,5 +11,6 @@
profiles {
eddie { includeConfig "${params.custom_config_base}/conf/pipeline/rnaseq/eddie.config" }
mpcdf { includeConfig "${params.custom_config_base}/conf/pipeline/rnaseq/mpcdf.config" }
sbc_sharc { includeConfig "${params.custom_config_base}/conf/pipeline/rnaseq/sbc_sharc.config" }
utd_sysbio { includeConfig "${params.custom_config_base}/conf/pipeline/rnaseq/utd_sysbio.config" }
}

View file

@ -15,5 +15,6 @@ profiles {
eddie { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/eddie.config" }
icr_davros { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/icr_davros.config" }
munin { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/munin.config" }
sbc_sharc { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/sbc_sharc.config" }
uppmax { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/uppmax.config" }
}