Merge branch 'master' into bgrande/sage-aws

.github/workflows/main.yml

@@ -30,6 +30,7 @@ jobs:
       matrix:
         profile:
           - "abims"
+          - "adcra"
           - "alice"
           - "aws_tower"
           - "awsbatch"
@@ -49,6 +50,7 @@ jobs:
           - "cheaha"
           - "computerome"
           - "crick"
+          - "crukmi"
           - "denbi_qbic"
           - "ebc"
           - "eddie"

README.md

@@ -67,6 +67,8 @@ Before adding your config file to nf-core/configs, we highly recommend writing a
 N.B. In your config file, please also make sure to add an extra `params` section with `params.config_profile_description`, `params.config_profile_contact` and `params.config_profile_url` set to reasonable values.
 Users will get information on who wrote the configuration profile then when executing a nf-core pipeline and can report back if there are things missing for example.
 
+N.B. If you try to specify a shell environment variable within your profile, in some cases you may get an error during testing of something like `Unknown config attribute env.USER_SCRATCH -- check config file: /home/runner/work/configs/configs/nextflow.config` (where the bash environment variable is `$USER_SCRATCH`). This is because the github runner will not have your institutional environment variables set. To fix this you can define this as an internal variable, and set a fallback value for that variable. A good example is in the [VSC_UGENT profile](`https://github.com/nf-core/configs/blob/69468e7ca769643b151a6cfd1ab24185fc341c06/conf/vsc_ugent.config#L2`).
+
 ### Testing
 
 If you want to add a new custom config file to `nf-core/configs` please test that your pipeline of choice runs as expected by using the [`-c`](https://www.nextflow.io/docs/latest/config.html) parameter.
@@ -86,6 +88,7 @@ See [`nf-core/configs/docs`](https://github.com/nf-core/configs/tree/master/docs
 Currently documentation is available for the following systems:
 
 - [ABIMS](docs/abims.md)
+- [ADCRA](docs/adcra.md)
 - [ALICE](docs/alice.md)
 - [AWSBATCH](docs/awsbatch.md)
 - [AWS_TOWER](docs/aws_tower.md)
@@ -103,6 +106,7 @@ Currently documentation is available for the following systems:
 - [CHEAHA](docs/cheaha.md)
 - [Computerome](docs/computerome.md)
 - [CRICK](docs/crick.md)
+- [Cancer Research UK Manchester Institute](docs/crukmi.md)
 - [CZBIOHUB_AWS](docs/czbiohub.md)
 - [DENBI_QBIC](docs/denbi_qbic.md)
 - [EBC](docs/ebc.md)
@@ -203,6 +207,7 @@ Currently documentation is available for the following pipelines within specific
 - rnavar
   - [MUNIN](docs/pipeline/rnavar/munin.md)
 - sarek
+  - [Cancer Research UK Manchester Institute](docs/pipeline/sarek/crukmi.md)
   - [MUNIN](docs/pipeline/sarek/munin.md)
   - [UPPMAX](docs/pipeline/sarek/uppmax.md)
 - taxprofiler

conf/adcra.config

@@ -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'
+}

conf/cheaha.config

@@ -1,3 +1,6 @@
+// Define the Scratch directory
+def scratch_dir = System.getenv("USER_SCRATCH") ?: "/tmp"
+
 params {
     config_profile_name = 'cheaha'
     config_profile_description = 'University of Alabama at Birmingham Cheaha HPC'
@@ -6,14 +9,14 @@ params {
 }
 
 env {
-    TMPDIR="$USER_SCRATCH"
+    TMPDIR="$USER"
-    SINGULARITY_TMPDIR="$USER_SCRATCH"
+    SINGULARITY_TMPDIR="$scratch_dir"
 }
 
 singularity {
     enabled = true
     autoMounts = true
-    runOptions = "--contain --workdir $USER_SCRATCH"
+    runOptions = "--contain --workdir $scratch_dir"
 }
 
 process {

conf/crukmi.config

@@ -0,0 +1,52 @@
+//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'
+}
+
+env {
+    SINGULARITY_CACHEDIR = '/lmod/nextflow_software'
+}
+
+singularity {
+  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_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
+}

conf/pipeline/sarek/crukmi.config

@@ -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 }
+  }
+
+}

docs/adcra.md

@@ -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
+```

docs/crukmi.md

@@ -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.

docs/pipeline/sarek/crukmi.md

@@ -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.

nfcore_custom.config

@@ -11,6 +11,7 @@
 //Please use a new line per include Config section to allow easier linting/parsing. Thank you.
 profiles {
   abims        { includeConfig "${params.custom_config_base}/conf/abims.config" }
+  adcra        { includeConfig "${params.custom_config_base}/conf/adcra.config" }
   alice        { includeConfig "${params.custom_config_base}/conf/alice.config" }
   aws_tower    { includeConfig "${params.custom_config_base}/conf/aws_tower.config" }
   awsbatch     { includeConfig "${params.custom_config_base}/conf/awsbatch.config" }
@@ -30,6 +31,7 @@ profiles {
   cheaha       { includeConfig "${params.custom_config_base}/conf/cheaha.config" }
   computerome  { includeConfig "${params.custom_config_base}/conf/computerome.config" }
   crick        { includeConfig "${params.custom_config_base}/conf/crick.config" }
+  crukmi       { includeConfig "${params.custom_config_base}/conf/crukmi.config" }
   czbiohub_aws { includeConfig "${params.custom_config_base}/conf/czbiohub_aws.config" }
   denbi_qbic   { includeConfig "${params.custom_config_base}/conf/denbi_qbic.config" }
   ebc          { includeConfig "${params.custom_config_base}/conf/ebc.config" }

pipeline/sarek.config

@@ -9,10 +9,11 @@
  */
 
 profiles {
-  munin { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/munin.config" }
-  uppmax { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/uppmax.config" }
-  icr_davros { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/icr_davros.config" }
   cfc { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/cfc.config" }
   cfc_dev { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/cfc.config" }
+  crukmi { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/crukmi.config" }
   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 "${params.custom_config_base}/conf/pipeline/sarek/munin.config" }
+  uppmax { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/uppmax.config" }
 }