Merge branch 'master' into vsc-ugent-fix

.github/workflows/main.yml

@@ -77,6 +77,7 @@ jobs:
           - "phoenix"
           - "prince"
           - "rosalind"
+          - "sage"
           - "sahmri"
           - "sanger"
           - "seg_globe"

README.md

@@ -10,7 +10,6 @@ A repository for hosting Nextflow configuration files containing custom paramete
   - [Configuration and parameters](#configuration-and-parameters)
   - [Offline usage](#offline-usage)
 - [Adding a new config](#adding-a-new-config)
-  - [Checking user hostnames](#checking-user-hostnames)
   - [Testing](#testing)
   - [Documentation](#documentation)
   - [Uploading to `nf-core/configs`](#uploading-to-nf-coreconfigs)
@@ -131,6 +130,7 @@ Currently documentation is available for the following systems:
 - [PHOENIX](docs/phoenix.md)
 - [PRINCE](docs/prince.md)
 - [ROSALIND](docs/rosalind.md)
+- [SAGE BIONETWORKS](docs/sage.md)
 - [SANGER](docs/sanger.md)
 - [SEG_GLOBE](docs/seg_globe.md)
 - [UCT_HPC](docs/uct_hpc.md)

conf/sage.config

@@ -0,0 +1,100 @@
+params {
+  config_profile_description = 'The Sage Bionetworks profile'
+  config_profile_contact = 'Bruno Grande (@BrunoGrandePhD)'
+  config_profile_url = 'https://github.com/Sage-Bionetworks-Workflows'
+}
+
+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'   ) }
+
+  errorStrategy = { task.exitStatus in [143,137,104,134,139,247] ? 'retry' : 'finish' }
+  maxRetries    = 5
+  maxErrors     = '-1'
+
+  // 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' ) }
+  }
+
+  // Preventing Sarek labels from using the actual maximums
+  withLabel:memory_max {
+    memory = { check_max( 128.GB * task.attempt,   'memory' ) }
+  }
+  withLabel:cpus_max {
+    cpus   = { check_max( 24    * slow(task.attempt), 'cpus'   ) }
+  }
+
+}
+
+aws {
+  region = "us-east-1"
+}
+
+params {
+  igenomes_base = 's3://sage-igenomes/igenomes'
+  max_memory    = 500.GB
+  max_cpus      = 64
+  max_time      = 168.h  // One week
+}
+
+// Function to slow the increase of the resource multipler
+// as attempts are made. The rationale is that some CPUs
+// don't need to be increased as fast 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
+        }
+    }
+}

conf/vsc_ugent.config

@@ -20,6 +20,10 @@ singularity {
     cacheDir = "$scratch_dir/singularity"
 }
 
+env {
+    SINGULARITY_CACHEDIR="$scratch_dir/.singularity"
+}
+
 // Define profiles for each cluster
 profiles {
     skitty {
@@ -36,7 +40,6 @@ profiles {
             executor = 'slurm'
             queue = 'skitty'
             maxRetries = 2
-            beforeScript = "export SINGULARITY_CACHEDIR=$scratch_dir/.singularity"
             scratch = "$scratch_dir"
         }
     }
@@ -55,7 +58,6 @@ profiles {
             executor = 'slurm'
             queue = 'swalot'
             maxRetries = 2
-            beforeScript = "export SINGULARITY_CACHEDIR=$scratch_dir/.singularity"
             scratch = "$scratch_dir"
         }
     }
@@ -74,7 +76,6 @@ profiles {
             executor = 'slurm'
             queue = 'victini'
             maxRetries = 2
-            beforeScript = "export SINGULARITY_CACHEDIR=$scratch_dir/.singularity"
             scratch = "$scratch_dir"
         }
     }
@@ -93,7 +94,6 @@ profiles {
             executor = 'slurm'
             queue = 'kirlia'
             maxRetries = 2
-            beforeScript = "export SINGULARITY_CACHEDIR=$scratch_dir/.singularity"
             scratch = "$scratch_dir"
         }
     }
@@ -112,7 +112,6 @@ profiles {
             executor = 'slurm'
             queue = 'doduo'
             maxRetries = 2
-            beforeScript = "export SINGULARITY_CACHEDIR=$scratch_dir/.singularity"
             scratch = "$scratch_dir"
         }
     }

docs/sage.md

@@ -0,0 +1,27 @@
+# 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`
+- Increase the default time limits because we run pipelines on AWS
+- Enable retries by default when exit codes relate to insufficient memory
+- Allow pending jobs to finish if the number of retries are exhausted
+- Slow the increase in the number of allocated CPU cores on retries
+- Define the `check_max()` function, which is missing in Sarek v2
+
+## 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`

nfcore_custom.config

@@ -59,6 +59,7 @@ profiles {
   phoenix      { includeConfig "${params.custom_config_base}/conf/phoenix.config" }
   prince       { includeConfig "${params.custom_config_base}/conf/prince.config" }
   rosalind     { includeConfig "${params.custom_config_base}/conf/rosalind.config" }
+  sage         { includeConfig "${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"}
   seg_globe    { includeConfig "${params.custom_config_base}/conf/seg_globe.config"}