Merge branch 'nf-core:master' into master

.editorconfig

@@ -8,5 +8,5 @@ trim_trailing_whitespace = true
 indent_size = 4
 indent_style = space
 
-[*.{md,yml,yaml}]
+[*.{md,yml,yaml,cff}]
 indent_size = 2

.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"
@@ -60,12 +62,14 @@ jobs:
           - "google"
           - "hasta"
           - "hebbe"
+          - "hki"
           - "icr_davros"
           - "ifb_core"
           - "imperial"
           - "jax"
           - "lugh"
           - "marvin"
+          - "medair"
           - "mjolnir_globe"
           - "maestro"
           - "mpcdf"
@@ -80,6 +84,7 @@ jobs:
           - "sage"
           - "sahmri"
           - "sanger"
+          - "sbc_sharc"
           - "seg_globe"
           - "uct_hpc"
           - "unibe_ibu"

CITATION.cff

@@ -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

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)
@@ -114,12 +118,14 @@ Currently documentation is available for the following systems:
 - [GOOGLE](docs/google.md)
 - [HASTA](docs/hasta.md)
 - [HEBBE](docs/hebbe.md)
+- [HKI](docs/hki.md)
 - [ICR_DAVROS](docs/icr_davros.md)
 - [IMPERIAL](docs/imperial.md)
 - [JAX](docs/jax.md)
 - [LUGH](docs/lugh.md)
 - [MAESTRO](docs/maestro.md)
 - [MARVIN](docs/marvin.md)
+- [MEDAIR](docs/medair.md)
 - [MJOLNIR_GLOBE](docs/mjolnir_globe.md)
 - [MPCDF](docs/mpcdf.md)
 - [MUNIN](docs/munin.md)
@@ -132,6 +138,7 @@ 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)
@@ -192,16 +199,25 @@ 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
   - [EVA](docs/pipeline/mag/eva.md)
 - 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)

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/cfc.config

@@ -12,7 +12,7 @@ singularity {
 
 process {
   executor = 'slurm'
-  queue = { task.memory > 60.GB || task.cpus > 20 ? 'qbic' : 'compute' }
+  queue = 'qbic'
   scratch = 'true'
 }
 

conf/cfc_dev.config

@@ -11,7 +11,7 @@ singularity {
 
 process {
   executor = 'slurm'
-  queue = { task.memory > 60.GB || task.cpus > 20 ? 'qbic' : 'compute' }
+  queue = 'qbic'
   scratch = 'true'
 }
 

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'
@@ -5,9 +8,15 @@ params {
     config_profile_url = 'https://www.uab.edu/cores/ircp/bds'
 }
 
+env {
+    TMPDIR="$scratch_dir"
+    SINGULARITY_TMPDIR="$scratch_dir"
+}
+
 singularity {
     enabled = true
     autoMounts = true
+    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/google.config

@@ -20,3 +20,5 @@ if (google.lifeSciences.preemptible) {
   process.errorStrategy = { task.exitStatus in [8,10,14] ? 'retry' : 'terminate' }
   process.maxRetries = 5
 }
+
+process.machineType = { task.memory > task.cpus * 6.GB ? ['custom', task.cpus, task.cpus * 6656].join('-') : null }

conf/hasta.config

@@ -25,10 +25,20 @@ process {
 }
 
 profiles {
-    dev_prio {
+    stub_prio {
         params {
            priority = 'development'
            clusterOptions = "--qos=low"
+           max_memory = 6.GB
+           max_cpus   = 1
+           max_time   = 1.h
+        }
+    }
+
+    dev_prio {
+        params {
+            priority = 'development'
+            clusterOptions = "--qos=low"
         }
     }
 

conf/hki.config

@@ -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
+    }
+}

conf/medair.config

@@ -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"
+  }
+}

conf/mpcdf.config

@@ -61,7 +61,7 @@ profiles {
        
         params {
             config_profile_description = 'MPCDF raven profile (unofficially) provided by nf-core/configs.'
-            memory = 2000000.MB
+            max_memory = 2000000.MB
             max_cpus = 72
             max_time = 24.h
         }

conf/pipeline/atacseq/sbc_sharc.config

@@ -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
+    }
+  }
+}

conf/pipeline/chipseq/sbc_sharc.config

@@ -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
+    }
+  }
+}

conf/pipeline/raredisease/hasta.config

@@ -7,7 +7,26 @@ process {
         cpus   = { check_max( 16      * task.attempt, 'cpus' ) }
         memory = { check_max( 80.GB   * task.attempt, 'memory' ) }
     }
-    withName:'QUALIMAP_BAMQC' {
+    withLabel:'sentieon' {
-        ext.args = { "--java-mem-size=${task.memory.giga / 1.15 as long}G" }
+        beforeScript = { "export PATH=\$PATH:\$SENTIEON_INSTALL_DIR/sentieon-genomics-202112.02/bin" }
     }
+    withName: 'BCFTOOLS_VIEW' {
+        if (params.genome == 'GRCh37') {
+            ext.args = '--output-type z --apply-filters PASS --exclude "INFO/clinical_genomics_mipAF > 0.40 | INFO/swegenAF > 0.40 | INFO/clingen_ngiAF > 0.40 | INFO/gnomad_svAF > 0.40 "'
+        } else if (params.genome == 'GRCh38') {
+            ext.args = '--output-type z --apply-filters PASS --exclude "INFO/swegen_FRQ > 0.40"'
+        }
+        publishDir = [
+            enabled: false,
+        ]
+    }
+
+    // Java memory fixes
+    withName:'QUALIMAP_BAMQC' {
+        clusterOptions = { "-A $params.priority ${params.clusterOptions ?: ''} ${task.memory ? "--mem ${task.memory.mega * 1.15 as long}M" : ''}" }
+    }
+    withName:'PICARD_MARKDUPLICATES' {
+        clusterOptions = { "-A $params.priority ${params.clusterOptions ?: ''} ${task.memory ? "--mem ${task.memory.mega * 1.15 as long}M" : ''}" }
+    }
+    
 }

conf/pipeline/rnafusion/hasta.config

@@ -0,0 +1,7 @@
+// rnafusion/hasta specific profile config for Clinical Genomics Stockholm usage
+
+params {
+    all = true
+    trim = true
+    fusioninspector_filter = true
+}

conf/pipeline/rnaseq/sbc_sharc.config

@@ -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
+    }
+  }
+}
+

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 }
+  }
+
+}

conf/pipeline/sarek/sbc_sharc.config

@@ -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
+    }
+  }
+}

conf/pipeline/viralrecon/genomes.config

@@ -8,23 +8,27 @@
 params {
   // Genome reference file paths
   genomes {
+
+    // SARS-CoV-2
     'NC_045512.2' {
       // This version of the reference has been kept here for backwards compatibility.
       // Please use 'MN908947.3' if possible because all primer sets are available / have been pre-prepared relative to that assembly
       fasta            = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz'
       gff              = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.gff.gz'
-      nextclade_dataset           = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-01-18T12_00_00Z.tar.gz'
+      nextclade_dataset           = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-06-14T12_00_00Z.tar.gz'
       nextclade_dataset_name      = 'sars-cov-2'
       nextclade_dataset_reference = 'MN908947'
-      nextclade_dataset_tag       = '2022-01-18T12:00:00Z'
+      nextclade_dataset_tag       = '2022-06-14T12:00:00Z'
     }
+
+    // SARS-CoV-2
     'MN908947.3' {
       fasta            = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.fna.gz'
       gff              = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.gff.gz'
-      nextclade_dataset           = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-01-18T12_00_00Z.tar.gz'
+      nextclade_dataset           = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-06-14T12_00_00Z.tar.gz'
       nextclade_dataset_name      = 'sars-cov-2'
       nextclade_dataset_reference = 'MN908947'
-      nextclade_dataset_tag       = '2022-01-18T12:00:00Z'
+      nextclade_dataset_tag       = '2022-06-14T12:00:00Z'
       primer_sets {
         artic {
           '1' {
@@ -66,5 +70,28 @@ params {
         }
       }
     }
+
+    // Monkeypox
+    'NC_063383.1' {
+      fasta            = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_063383.1/GCF_014621545.1_ASM1462154v1_genomic.220824.fna.gz'
+      gff              = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_063383.1/GCF_014621545.1_ASM1462154v1_genomic.220824.gff.gz'
+      nextclade_dataset           = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_063383.1/nextclade_hMPXV_NC_063383.1_2022-08-19T12_00_00Z.tar.gz'
+      nextclade_dataset_name      = 'hMPXV'
+      nextclade_dataset_reference = 'NC_063383.1'
+      nextclade_dataset_tag       = '2022-08-19T12:00:00Z'
+    }
+
+    // Monkeypox
+    'ON563414.3' {
+      fasta            = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/ON563414.3/GCA_023516015.3_ASM2351601v1_genomic.220824.fna.gz'
+      gff              = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/ON563414.3/GCA_023516015.3_ASM2351601v1_genomic.220824.gff.gz'
+    }
+
+    // Monkeypox
+    'MT903344.1' {
+      fasta            = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MT903344.1/GCA_014621585.1_ASM1462158v1_genomic.220824.fna.gz'
+      gff              = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MT903344.1/GCA_014621585.1_ASM1462158v1_genomic.220824.gff.gz'
+    }
+
   }
 }

conf/sage.config

@@ -1,19 +1,55 @@
+// 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
+  }
+  batch {
+    maxParallelTransfers = 1
+  }
+}
+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'   ) }
 
-  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'   ) }
@@ -37,32 +73,13 @@ process {
     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
+// as attempts are made. The rationale is that the number
-// don't need to be increased as fast as memory.
+// of CPU cores isn't a limiting factor as often as memory.
 def slow(attempt, factor = 2) {
-  return Math.ceil( attempt / factor) as int
+ return Math.ceil( attempt / factor) as int
 }
 
 

conf/sanger.config

@@ -1,35 +1,33 @@
+// Profile details
 params {
-  config_profile_description = 'The Wellcome Sanger Institute HPC cluster profile'
+    config_profile_description = 'The Wellcome Sanger Institute HPC cluster (farm5) profile'
-  config_profile_contact = 'Anthony Underwood (@aunderwo)'
+    config_profile_contact = 'Priyanka Surana (@priyanka-surana)'
-  config_profile_url = 'https://www.sanger.ac.uk/group/informatics-support-group/'
+    config_profile_url = 'https://www.sanger.ac.uk'
-}
-
-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'
 }
 
+// Queue and retry strategy
 process{
-  executor = 'lsf'
+    executor = 'lsf'
-  queue = 'normal'
+    queue = { task.time < 12.h ? 'normal' : task.time < 48.h ? 'long' : 'basement' }
-  errorStrategy = { task.attempt <= 5 ? "retry" : "finish" }
+    errorStrategy = 'retry'
-  process.maxRetries = 5
+    maxRetries = 5
-  withLabel:process_long {
-    queue = 'long'
-  }
 }
 
+// Executor details
 executor{
-  name = 'lsf'
+    name = 'lsf'
-  perJobMemLimit = true
+    perJobMemLimit = true
-  poolSize = 4
+    poolSize = 4
-  submitRateLimit = '5 sec'
+    submitRateLimit = '5 sec'
-  killBatchSize = 50
+    killBatchSize = 50
 }
 
+// Max resources
 params {
-  max_memory = 128.GB
+    max_memory = 683.GB
-  max_cpus = 64
+    max_cpus = 256
-  max_time = 48.h
+    max_time = 720.h
 }
+
+// For singularity
+singularity.runOptions = '--bind /lustre --bind /nfs'

conf/sbc_sharc.config

@@ -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
+
+}

conf/vsc_ugent.config

@@ -9,7 +9,7 @@ workDir = "$scratch_dir/work"
 
 // Reduce the job submit rate to about 5 per second, this way the server won't be bombarded with jobs
 executor {
-    submitRateLimit = '5 sec'
+    submitRateLimit = '3 sec'
 }
 
 // Specify that singularity should be used and where the cache dir will be for the images

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/cheaha.md

@@ -13,6 +13,8 @@ module load Singularity
 module load Nextflow
 ```
 
+Various tasks will be run inside of Singularity containers and all temp files typically written to `/tmp` and `/var/tmp` are instead written to the path pointed to by the `USER_SCRATCH` environment variable. This means that these temp files are stored in a user specific location, making them inaccessible to other users for pipeline reruns. Some of these temp files can be large and cleanup is also the responsibility of the user.
+
 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 HPC cluster on Cheaha in order to run the pipeline. If in doubt contact UAB IT Research Computing.</br></br>

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/hki.md

@@ -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.

docs/medair.md

@@ -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.

docs/pipeline/atacseq/sbc_sharc.md

@@ -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`

docs/pipeline/chipseq/sbc_sharc.md

@@ -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`

docs/pipeline/rnafusion/hasta.md

@@ -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)

docs/pipeline/rnaseq/sbc_sharc.md

@@ -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`

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.

docs/pipeline/sarek/sbc_sharc.md

@@ -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`

docs/sage.md

@@ -5,11 +5,14 @@ To use this custom configuration, run the pipeline with `-profile sage`. This wi
 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
+- Increase the amount of time allowed for file transfers
+- 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
 

docs/sanger.md

@@ -2,8 +2,6 @@
 
 To use, run the pipeline with `-profile sanger`. This will download and launch the [`sanger.config`](../conf/sanger.config) which has been
 pre-configured with a setup suitable for the Wellcome Sanger Institute LSF cluster.
-Using this profile, either a docker image containing all of the required software will be downloaded, and converted to a Singularity image or
-a Singularity image downloaded directly before execution of the pipeline.
 
 ## Running the workflow on the Wellcome Sanger Institute cluster
 
@@ -14,10 +12,12 @@ The latest version of Nextflow is not installed by default on the cluster. You w
 A recommended place to move the `nextflow` executable to is `~/bin` so that it's in the `PATH`.
 
 Nextflow manages each process as a separate job that is submitted to the cluster by using the `bsub` command.
-Since the Nextflow pipeline will submit individual jobs for each process to the cluster and dependencies will be provided bu Singularity images you shoudl make sure that your account has access to the Singularity binary by adding these lines to your `.bashrc` file
+
+If asking Nextflow to use Singularity to run the individual jobs,
+you should make sure that your account has access to the Singularity binary by adding these lines to your `.bashrc` file
 
 ```bash
-[[ -f  /software/pathogen/farm5 ]] && module load ISG/singularity
+[[ -f /software/modules/ISG/singularity ]] && module load ISG/singularity
 ```
 
 Nextflow shouldn't run directly on the submission node but on a compute node.
@@ -26,16 +26,16 @@ To do so make a shell script with a similar structure to the following code and
 ```bash
 #!/bin/bash
 #BSUB -o /path/to/a/log/dir/%J.o
-#BSUB -e /path/to/a/log/dir//%J.e
+#BSUB -e /path/to/a/log/dir/%J.e
 #BSUB -M 8000
-#BSUB -q long
+#BSUB -q oversubscribed
-#BSUB -n 4
+#BSUB -n 2
 
 export HTTP_PROXY='http://wwwcache.sanger.ac.uk:3128'
 export HTTPS_PROXY='http://wwwcache.sanger.ac.uk:3128'
 export NXF_ANSI_LOG=false
 export NXF_OPTS="-Xms8G -Xmx8G -Dnxf.pool.maxThreads=2000"
-export NXF_VER=21.04.0-edge
+export NXF_VER=22.04.0-5697
 
 
 nextflow run \

docs/sbc_sharc.md

@@ -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
+```

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" }
@@ -42,6 +44,7 @@ profiles {
   google       { includeConfig "${params.custom_config_base}/conf/google.config" }
   hasta        { includeConfig "${params.custom_config_base}/conf/hasta.config" }
   hebbe        { includeConfig "${params.custom_config_base}/conf/hebbe.config" }
+  hki          { includeConfig "${params.custom_config_base}/conf/hki.config"}
   icr_davros   { includeConfig "${params.custom_config_base}/conf/icr_davros.config" }
   ifb_core     { includeConfig "${params.custom_config_base}/conf/ifb_core.config" }
   imperial     { includeConfig "${params.custom_config_base}/conf/imperial.config" }
@@ -49,6 +52,7 @@ profiles {
   lugh         { includeConfig "${params.custom_config_base}/conf/lugh.config" }
   maestro      { includeConfig "${params.custom_config_base}/conf/maestro.config" }
   marvin       { includeConfig "${params.custom_config_base}/conf/marvin.config" }
+  medair       { includeConfig "${params.custom_config_base}/conf/medair.config" }
   mjolnir_globe { includeConfig "${params.custom_config_base}/conf/mjolnir_globe.config" }
   mpcdf        { includeConfig "${params.custom_config_base}/conf/mpcdf.config" }
   munin        { includeConfig "${params.custom_config_base}/conf/munin.config" }
@@ -62,6 +66,7 @@ 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" }

pipeline/atacseq.config

@@ -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" }
+}

pipeline/chipseq.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" }
+}

pipeline/rnafusion.config

@@ -9,5 +9,6 @@
  */
 
 profiles {
+  hasta { includeConfig "${params.custom_config_base}/conf/pipeline/rnafusion/hasta.config" }
   munin { includeConfig "${params.custom_config_base}/conf/pipeline/rnafusion/munin.config" }
 }

pipeline/rnaseq.config

@@ -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" }
 }

pipeline/sarek.config

@@ -9,10 +9,12 @@
  */
 
 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 "${params.custom_config_base}/conf/pipeline/sarek/munin.config" }
+  sbc_sharc { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/sbc_sharc.config" }
+  uppmax { includeConfig "${params.custom_config_base}/conf/pipeline/sarek/uppmax.config" }
 }