Merge pull request #146 from adrlar/master

Adding config for ICR davros cluster

.github/workflows/main.yml

@@ -16,7 +16,7 @@ jobs:
     needs: test_all_profiles
     strategy:
         matrix:
-          profile: ['awsbatch', 'bi','bigpurple', 'binac', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'kraken', 'munin', 'pasteur', 'phoenix', 'prince', 'shh', 'uct_hex', 'uppmax', 'utd_ganymede', 'uzh']
+          profile: ['awsbatch', 'bi','bigpurple', 'binac', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'kraken', 'munin', 'pasteur', 'phoenix', 'prince', 'shh', 'uct_hex', 'uppmax', 'utd_ganymede', 'uzh']
     steps:
       - uses: actions/checkout@v1
       - name: Install Nextflow

conf/icr_davros.config

@@ -0,0 +1,39 @@
+/*
+ * -------------------------------------------------
+ *  Nextflow nf-core config file for ICR davros HPC
+ * -------------------------------------------------
+ * Defines LSF process executor and singularity
+ * settings.
+ * 
+ */
+params {
+  config_profile_description = "Nextflow nf-core profile for ICR davros HPC"
+  config_profile_contact = "Adrian Larkeryd (@adrlar)"
+}
+
+singularity {
+  enabled = true
+  // runOptions = "--bind /mnt:/mnt --bind /data:/data"
+  autoMounts = true
+}
+
+executor {
+  // This is set because of an issue with too many
+  // singularity containers launching at once, they
+  // cause an singularity error with exit code 255.
+  submitRateLimit = "2 sec"
+}
+
+process {
+  executor = "LSF"
+}
+
+params {
+  // LSF cluster set up with memory tied to cores,
+  // it can't be requested. Locked at 12G per core. 
+  cpus = 10
+  max_cpus = 20
+  max_memory = 12.GB
+  max_time = 168.h
+  igenomes_base = "/mnt/scratch/readonly/igenomes"
+}

conf/pipeline/sarek/icr_davros.config

@@ -0,0 +1,13 @@
+/*
+ * -------------------------------------------------
+ *  Nextflow nf-core config file for ICR davros HPC
+ * -------------------------------------------------
+ */
+process {
+  errorStrategy = {task.exitStatus in [104,134,137,139,141,143,255] ? 'retry' : 'finish'}
+  maxRetries = 5
+  withName:MapReads {
+    memory = {check_resource(12.GB)}
+    time = {check_resource(48.h * task.attempt)}
+  }
+}

docs/icr_davros.md

@@ -0,0 +1,22 @@
+# nf-core/configs: Institute of Cancer Research (Davros HPC) Configuration
+
+Deployment and testing of nf-core pipelines at the Davros cluster is on-going.
+
+To run an nf-core pipeline on Davros, run the pipeline with `-profile icr_davros`. This will download and launch the [`icr_davros.config`](../conf/icr_davros.config) which has been pre-configured with a setup suitable for the Davros HPC 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.
+
+Before running the pipeline you will need to load Nextflow using the environment module system. You can do this by issuing the commands below:
+
+```bash
+## Load Nextflow environment modules
+module load Nextflow/19.10.0
+```
+
+Singularity is installed on the compute nodes of Davros, but not the login nodes. There is no module for Singularity.
+
+A subset of the [AWS-iGenomes](https://github.com/ewels/AWS-iGenomes) resource has been made available locally on Davros so you should be able to run the pipeline against any reference available in the `igenomes.config` specific to the nf-core pipeline you want to execute. You can do this by simply using the `--genome <GENOME_ID>` parameter. Some of the more exotic genomes may not have been downloaded onto Davros so have a look in the `igenomes_base` path specified in [`icr_davros.config`](../conf/icr_davros.config), and if your genome of interest isn't present please contact [Scientific Computing](mailto:schelpdesk@icr.ac.uk).
+
+Alternatively, if you are running the pipeline regularly for genomes that arent available in the iGenomes resource, we recommend creating a config file with paths to your reference genome indices (see [`reference genomes documentation`](https://nf-co.re/usage/reference_genomes) for instructions).
+
+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. All of the main output files will be saved in the `results/` directory.
+
+>NB: Nextflow will need to submit the jobs via LSF to the HPC cluster. This can be done from an interactive or normal job. If in doubt contact Scientific Computing.

nfcore_custom.config

@@ -25,6 +25,7 @@ profiles {
                  includeConfig "${params.custom_config_base}/conf/czbiohub_aws.config";
                  includeConfig "${params.custom_config_base}/conf/czbiohub_aws_highpriority.config"}
   ebc          { includeConfig "${params.custom_config_base}/conf/ebc.config" }
+  icr_davros   { includeConfig "${params.custom_config_base}/conf/icr_davros.config" }
   genotoul     { includeConfig "${params.custom_config_base}/conf/genotoul.config" }
   google       { includeConfig "${params.custom_config_base}/conf/google.config" }
   denbi_qbic   { includeConfig "${params.custom_config_base}/conf/denbi_qbic.config" }
@@ -53,6 +54,7 @@ params {
     cbe: ['.cbe.vbc.ac.at'],
     cfc: ['.hpc.uni-tuebingen.de'],
     crick: ['.thecrick.org'],
+    icr_davros: ['.davros.compute.estate'],
     genotoul: ['.genologin1.toulouse.inra.fr', '.genologin2.toulouse.inra.fr'],
     genouest: ['.genouest.org'],
     uppmax: ['.uppmax.uu.se'],

pipeline/sarek.config

@@ -11,4 +11,5 @@
 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" }
 }