diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index f6a2458..0fa938a 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -7,9 +7,7 @@ jobs: runs-on: ubuntu-18.04 steps: - uses: actions/checkout@v1 - - uses: actions/setup-node@v1 - with: - node-version: '10' + - uses: actions/setup-node@v2 - name: Install markdownlint run: | npm install -g markdownlint-cli diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index a3b41fd..c04be6e 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -32,6 +32,7 @@ jobs: - 'ccga_med' - 'cfc' - 'cfc_dev' + - 'cheaha' - 'computerome' - 'crick' - 'denbi_qbic' @@ -47,9 +48,9 @@ jobs: - 'icr_davros' - 'ifb_core' - 'imperial' - - 'imperial_mb' - 'jax' - 'lugh' + - 'marvin' - 'maestro' - 'mpcdf' - 'munin' diff --git a/README.md b/README.md index f2accc6..b6b2d57 100644 --- a/README.md +++ b/README.md @@ -100,6 +100,7 @@ Currently documentation is available for the following systems: * [CCGA_DX](docs/ccga_dx.md) * [CCGA_MED](docs/ccga_med.md) * [CFC](docs/cfc.md) +* [CHEAHA](docs/cheaha.md) * [Computerome](docs/computerome.md) * [CRICK](docs/crick.md) * [CZBIOHUB_AWS](docs/czbiohub.md) @@ -113,9 +114,11 @@ Currently documentation is available for the following systems: * [HASTA](docs/hasta.md) * [HEBBE](docs/hebbe.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) * [MPCDF](docs/mpcdf.md) * [MUNIN](docs/munin.md) * [NU_GENOMICS](docs/nu_genomics.md) diff --git a/conf/cbe.config b/conf/cbe.config index 89da3db..fbc0812 100755 --- a/conf/cbe.config +++ b/conf/cbe.config @@ -7,11 +7,9 @@ params { process { executor = 'slurm' - queue = { task.memory <= 170.GB ? 'c' : 'm' } - module = 'anaconda3/2019.10' - - // --signal option will be handled by nextflow after 21.10.0 release (see https://github.com/nextflow-io/nextflow/issues/2163) - clusterOptions = { '--signal B:USR2 ' << ( (queue == 'c' & task.time <= 1.h) ? '--qos rapid' : ( task.time <= 8.h ? '--qos short': ( task.time <= 48.h ? '--qos medium' : '--qos long' ) ) ) } + queue = { task.memory <= 120.GB ? 'c' : 'm' } + module = ['build-env/.f2021', 'build-env/f2021', 'anaconda3/2021.11'] + clusterOptions = { ( task.queue == 'g' ? '--gres gpu:1 ' : '' ) << ( (task.queue == 'c' & task.time <= 1.h) ? '--qos rapid' : ( task.time <= 8.h ? '--qos short': ( task.time <= 48.h ? '--qos medium' : '--qos long' ) ) ) } } singularity { diff --git a/conf/cheaha.config b/conf/cheaha.config new file mode 100644 index 0000000..323a625 --- /dev/null +++ b/conf/cheaha.config @@ -0,0 +1,24 @@ +params { + config_profile_name = 'cheaha' + config_profile_description = 'University of Alabama at Birmingham Cheaha HPC' + config_profile_contact = 'Lara Ianov (lianov@uab.edu) or Austyn Trull (atrull@uab.edu)' + config_profile_url = 'https://www.uab.edu/cores/ircp/bds' +} + +singularity { + enabled = true + autoMounts = true +} + +process { + executor = 'slurm' + queue = { task.memory <= 50.GB ? (task.time <= 2.h ? 'express' : task.time <= 12.h ? 'short' : task.time <= 50.h ? 'medium' : 'long') : (task.time <= 50.h ? 'largemem' : 'largemem-long')} + maxRetries = 3 + beforeScript = 'module load Singularity' +} + +params { + max_memory = 750.GB + max_cpus = 128 + max_time = 150.h +} diff --git a/conf/eva.config b/conf/eva.config index df6cd21..7f89ac2 100644 --- a/conf/eva.config +++ b/conf/eva.config @@ -31,7 +31,7 @@ profiles { config_profile_description = 'MPI-EVA archgen profile, provided by nf-core/configs.' max_memory = 256.GB max_cpus = 32 - max_time = 720.h + max_time = 365.d //Illumina iGenomes reference file path } diff --git a/conf/imperial.config b/conf/imperial.config index eeb98ae..729d623 100644 --- a/conf/imperial.config +++ b/conf/imperial.config @@ -1,37 +1,80 @@ //Profile config names for nf-core/configs params { - // Config Params - config_profile_description = 'Imperial College London - HPC Profile -- provided by nf-core/configs.' - config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' - config_profile_url = 'https://www.imperial.ac.uk/admin-services/ict/self-service/research-support/rcs/' + // Config Params + config_profile_description = 'Imperial College London - HPC Profile -- provided by nf-core/configs.' + config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' + config_profile_url = 'https://www.imperial.ac.uk/admin-services/ict/self-service/research-support/rcs/' - // Resources - max_memory = 256.GB - max_cpus = 32 - max_time = 72.h + // Resources + max_memory = 480.GB + max_cpus = 40 + max_time = 1000.h +} + +profiles { + imperial { + process { + executor = 'pbspro' + + // Process-specific resource requirements + withLabel:process_low { + // TARGET QUEUE: throughput + cpus = { 2 * task.attempt } + memory = { 12.GB * task.attempt } + time = { 4.h * task.attempt } + } + withLabel:process_medium { + // TARGET QUEUE: throughput + cpus = 8 + memory = { 32.GB * task.attempt } + time = { 8.h * task.attempt } + } + withLabel:process_high { + // TARGET QUEUE: general + cpus = 32 + memory = { 62.GB * task.attempt } + time = { 16.h * task.attempt } + } + withLabel:process_long { + // TARGET QUEUE: long + cpus = 8 + memory = 96.GB + time = { 72.h * task.attempt } + } + withLabel:process_high_memory { + // TARGET QUEUE: large memory + cpus = { 10 * task.attempt } + memory = { 120.GB * task.attempt } + time = { 12.h * task.attempt } + } + } + } + medbio { + process { + executor = 'pbspro' + + queue = 'pqmedbio-tput' + + //queue = 'med-bio' //!! this is an alias and shouldn't be used + } + } } executor { - $pbspro { - queueSize = 50 - } + $pbspro { + queueSize = 50 + } - $local { - cpus = 2 - queueSize = 1 - memory = '32 GB' - } + $local { + cpus = 2 + queueSize = 1 + memory = '6 GB' + } } singularity { - enabled = true - autoMounts = true - runOptions = "-B /rds/,/rds/general/user/$USER/ephemeral/tmp/:/tmp,/rds/general/user/$USER/ephemeral/tmp/:/var/tmp" -} - -process { - - executor = 'pbspro' - + enabled = true + autoMounts = true + runOptions = "-B /rds/,/rds/general/user/$USER/ephemeral/tmp/:/tmp,/rds/general/user/$USER/ephemeral/tmp/:/var/tmp" } diff --git a/conf/imperial_mb.config b/conf/imperial_mb.config deleted file mode 100644 index a89ffcd..0000000 --- a/conf/imperial_mb.config +++ /dev/null @@ -1,44 +0,0 @@ -//Profile config names for nf-core/configs - -params { - // Config Params - config_profile_description = 'Imperial College London - MEDBIO QUEUE - HPC Profile -- provided by nf-core/configs.' - config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' - config_profile_url = 'https://www.imperial.ac.uk/bioinformatics-data-science-group/resources/uk-med-bio/' - - // Resources - max_memory = 640.GB - max_cpus = 32 - max_time = 168.h -} - -executor { - $pbspro { - queueSize = 50 - } - - $local { - cpus = 2 - queueSize = 1 - memory = '32 GB' - } -} - -singularity { - enabled = true - autoMounts = true - runOptions = "-B /rds/,/rdsgpfs/,/rds/general/user/$USER/ephemeral/tmp/:/tmp,/rds/general/user/$USER/ephemeral/tmp/:/var/tmp" -} - -process { - - executor = 'pbspro' - queue = 'pqmedbio-tput' - - //queue = 'med-bio' //!! this is an alias and shouldn't be used - - withLabel:process_large { - queue = 'pqmedbio-large' - } - -} diff --git a/conf/marvin.config b/conf/marvin.config new file mode 100644 index 0000000..f7a4b26 --- /dev/null +++ b/conf/marvin.config @@ -0,0 +1,20 @@ +//Profile config names for nf-core/configs +params { + config_profile_description = 'Config file for Marvin Cluster (UPF-CSIC), based on nf-core/configs' + config_profile_contact = 'pc.quilis@gmail.com (Pablo Carrion)' + config_profile_url = 'https://www.ibe.upf-csic.es' + max_memory = 256.GB + max_cpus = 32 + max_time = 960.h +} + +cleanup = false + +singularity { + enabled = true + autoMounts = true +} + +process { + executor = 'slurm' +} diff --git a/conf/mpcdf.config b/conf/mpcdf.config index 3027d63..281e7bf 100644 --- a/conf/mpcdf.config +++ b/conf/mpcdf.config @@ -18,6 +18,8 @@ profiles { executor { queueSize = 8 + pollInterval = '1 min' + queueStatInterval = '5 min' } // Set $NXF_SINGULARITY_CACHEDIR in your ~/.bash_profile @@ -46,6 +48,8 @@ profiles { executor { queueSize = 8 + pollInterval = '1 min' + queueStatInterval = '5 min' } // Set $NXF_SINGULARITY_CACHEDIR in your ~/.bash_profile @@ -58,7 +62,7 @@ profiles { params { config_profile_description = 'MPCDF raven profile (unofficially) provided by nf-core/configs.' max_memory = 368.GB - max_cpus = 192 + max_cpus = 72 max_time = 24.h } } diff --git a/conf/munin.config b/conf/munin.config index 3902e29..6b854fb 100644 --- a/conf/munin.config +++ b/conf/munin.config @@ -21,8 +21,9 @@ process { } singularity { - enabled = true - cacheDir = '/data1/containers/' + cacheDir = '/data1/containers/' + enabled = true + runOptions = "--bind /media/BTB_2021_01" } // To use docker, use nextflow run -profile munin,docker diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index c5d87e2..0e48e69 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -19,57 +19,60 @@ process { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } + time = '365.d' } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } + time = '365.d' } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } + time = '365.d' } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } + time = '365.d' } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } + time = '365.d' } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } + time = '365.d' } withLabel:'mc_huge'{ cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 256.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } + time = '365.d' } // Fixes for SGE and Java incompatibility due to Java using more memory than you tell it to use withName: makeSeqDict { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: fastqc { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: adapter_removal { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: samtools_flagstat { @@ -82,10 +85,13 @@ process { withName: dedup { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + memory = { check_max( 20.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: library_merge { @@ -113,34 +119,43 @@ process { withName: maltextract { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: multivcfanalyzer { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: mtnucratio { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: vcf2genome { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: qualimap { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : task.exitStatus in [255] ? 'ignore' : 'finish' } } withName: damageprofiler { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + memory = { check_max( 8.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circularmapper { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circulargenerator { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: preseq { @@ -150,6 +165,7 @@ process { withName: genotyping_ug { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } } @@ -180,57 +196,53 @@ profiles { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.5.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 6.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 12.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 6.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 12.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 24.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_huge'{ cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 256.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } // Fixes for SGE and Java incompatibility due to (and also some samtools?!) using more memory than you tell it to use withName: makeSeqDict { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: fastqc { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: adapter_removal { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: samtools_flagstat { @@ -243,10 +255,13 @@ profiles { withName: dedup { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + memory = { check_max( 32.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: library_merge { @@ -270,47 +285,57 @@ profiles { clusterOptions = { "-S /bin/bash -V -l h_vmem=1000G" } cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 955.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName:hostremoval_input_fastq { memory = { check_max( 32.GB * task.attempt, 'memory' ) } - time = 1440.h } withName: maltextract { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: multivcfanalyzer { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: mtnucratio { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: vcf2genome { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: qualimap { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : task.exitStatus in [255] ? 'ignore' : 'finish' } } withName: damageprofiler { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + memory = { check_max( 16.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circularmapper { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circulargenerator { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: genotyping_ug { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: preseq { @@ -345,57 +370,53 @@ profiles { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 2.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 32.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_huge'{ cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 512.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } // Fixes for SGE and Java incompatibility due to Java using more memory than you tell it to use withName: makeSeqDict { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: fastqc { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: adapter_removal { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: samtools_flagstat { @@ -408,10 +429,13 @@ profiles { withName: dedup { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + memory = { check_max( 48.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: library_merge { @@ -430,7 +454,6 @@ profiles { withName:hostremoval_input_fastq { memory = { check_max( 32.GB * task.attempt, 'memory' ) } - time = 1440.h } withName: metagenomic_complexity_filter { @@ -441,42 +464,53 @@ profiles { clusterOptions = { "-S /bin/bash -V -l h_vmem=1000G" } cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 955.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: maltextract { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: multivcfanalyzer { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: mtnucratio { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: vcf2genome { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: qualimap { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : task.exitStatus in [255] ? 'ignore' : 'finish' } } withName: damageprofiler { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + memory = { check_max( 32.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circularmapper { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circulargenerator { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: genotyping_ug { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: preseq { diff --git a/conf/pipeline/raredisease/hasta.config b/conf/pipeline/raredisease/hasta.config index 2c6ed48..96e3332 100644 --- a/conf/pipeline/raredisease/hasta.config +++ b/conf/pipeline/raredisease/hasta.config @@ -1,8 +1,7 @@ process { withName:'PICARD_MARKDUPLICATES' { - cpus = { check_max( 13 * task.attempt, 'cpus' ) } - memory = { check_max( 130.GB * task.attempt, 'memory' ) } + memory = { check_max( 90.GB * task.attempt, 'memory' ) } } withName:'DEEPVARIANT' { cpus = { check_max( 16 * task.attempt, 'cpus' ) } diff --git a/conf/pipeline/rnavar/munin.config b/conf/pipeline/rnavar/munin.config index c2c8335..c573781 100644 --- a/conf/pipeline/rnavar/munin.config +++ b/conf/pipeline/rnavar/munin.config @@ -11,6 +11,7 @@ params { igenomes_ignore = true // Genome references + genome = 'GRCh38' fasta = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa' fasta_fai = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai' gtf = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf' diff --git a/conf/pipeline/scflow/imperial.config b/conf/pipeline/scflow/imperial.config index 7f46466..78a4a8b 100644 --- a/conf/pipeline/scflow/imperial.config +++ b/conf/pipeline/scflow/imperial.config @@ -3,7 +3,7 @@ params { // Config Params config_profile_description = 'Imperial College London - HPC - nf-core/scFlow Profile -- provided by nf-core/configs.' - config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' + config_profile_contact = 'NA' // Analysis Resource Params ctd_folder = "/rds/general/user/$USER/projects/ukdrmultiomicsproject/live/Analyses/scFlowResources/refs/ctd" @@ -15,4 +15,4 @@ singularity { autoMounts = true cacheDir = "/rds/general/user/$USER/projects/ukdrmultiomicsproject/live/.singularity-cache" runOptions = "-B /rds/,/rdsgpfs/,/rds/general/user/$USER/ephemeral/tmp/:/tmp,/rds/general/user/$USER/ephemeral/tmp/:/var/tmp" -} \ No newline at end of file +} diff --git a/conf/pipeline/viralrecon/genomes.config b/conf/pipeline/viralrecon/genomes.config index 8682942..baad834 100644 --- a/conf/pipeline/viralrecon/genomes.config +++ b/conf/pipeline/viralrecon/genomes.config @@ -51,6 +51,12 @@ params { primer_bed = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V4/SARS-CoV-2.scheme.bed' scheme = 'SARS-CoV-2' } + '4.1' { + fasta = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V4.1/SARS-CoV-2.reference.fasta' + gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.gff.gz' + primer_bed = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V4.1/SARS-CoV-2.scheme.bed' + scheme = 'SARS-CoV-2' + } '1200' { fasta = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/primer_schemes/artic/nCoV-2019/V1200/nCoV-2019.reference.fasta' gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.gff.gz' diff --git a/docs/cbe.md b/docs/cbe.md index aa6c60d..b7628d0 100644 --- a/docs/cbe.md +++ b/docs/cbe.md @@ -9,7 +9,7 @@ Before running the pipeline you will need to load Nextflow using the environment ```bash ## Load Nextflow environment module module purge -module load nextflow/19.04.0 +module load nextflow/21.10.6 ``` A local copy of the [AWS-iGenomes](https://registry.opendata.aws/aws-igenomes/) resource has been made available on CBE so you should be able to run the pipeline against any reference available in the `igenomes.config` specific to the nf-core pipeline. You can do this by simply using the `--genome ` parameter. diff --git a/docs/cheaha.md b/docs/cheaha.md new file mode 100644 index 0000000..b4a0eb9 --- /dev/null +++ b/docs/cheaha.md @@ -0,0 +1,32 @@ +# nf-core/configs: Cheaha (UAB HPC) Configuration + +All nf-core pipelines have been successfully configured for use on the Cheaha HPC cluster at the [The University of Alabama at Birmingham](https://www.uab.edu/home/). + +To use, run the pipeline with `-profile cheaha`. This will download and launch the [`cheaha.config`](../conf/cheaha.config) which has been pre-configured with a setup suitable for the Cheaha 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 Singularity and Nextflow using the environment module system on Cheaha. You can do this by issuing the commands below: + +```bash +## Singularity environment modules +module purge +module load Singularity +module load Nextflow +``` + +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. + +>NB: Nextflow will need to submit the jobs via SLURM to the HPC cluster and as such the commands above will have to be executed on one of the login nodes (or alternatively in an interactive partition, but be aware of time limit). If in doubt contact UAB IT Research Computing. + +>NB: Instead of using `module load Nextflow`, you may instead create a conda environment (e.g: `conda create -p $USER_DATA/nf-core_nextflow_env nf-core nextflow`) if you would like to have a more personalized environment of Nextflow (versions which may not be modules yet) and nf-core tools. This __requires__ you to instead do the following: + +```bash +module purge +module load Singularity +module load Anaconda3 +# change path/enviroment name if according to what you created +conda activate $USER_DATA/nf-core_nextflow_env +``` + +>NB: while the jobs for each process of the pipeline are sent to the appropriate nodes, the current session must remain active while the pipeline is running. We recommend to use `screen` prior to loading any modules/environments. Once the pipeline starts you can detach the screen session by typing `Ctrl-a d` so you can safely logout of HPC, while keeping the pipeline active (and you may resume the screen session with `screen -r`). Other similar tools (e.g. `tmux`) may also be used. \ No newline at end of file diff --git a/docs/czbiohub.md b/docs/czbiohub.md index 03f0edd..376460b 100644 --- a/docs/czbiohub.md +++ b/docs/czbiohub.md @@ -125,7 +125,7 @@ For Human and Mouse, we use [GENCODE](https://www.gencodegenes.org/) gene annota ## High Priority Queue -If you would like to run with the _High Priority_ queue, specify the `highpriority` config profile after `czbiohub_aws`. When applied after the main `czbiohub_aws` config, it overwrites the process `queue` identifier. +If you would like to run with the *High Priority* queue, specify the `highpriority` config profile after `czbiohub_aws`. When applied after the main `czbiohub_aws` config, it overwrites the process `queue` identifier. To use it, submit your run with with `-profile czbiohub_aws,highpriority`. diff --git a/docs/imperial.md b/docs/imperial.md index 43fc117..158827c 100644 --- a/docs/imperial.md +++ b/docs/imperial.md @@ -2,15 +2,17 @@ All nf-core pipelines have been successfully configured for use on the CX1 cluster at Imperial College London HPC. -To use, run the pipeline with `-profile imperial`. This will download and launch the [`imperial.config`](../conf/imperial.config) which has been pre-configured with a setup suitable for the CX1 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. +To use, run the pipeline with `-profile imperial,standard`. This will download and launch the [`imperial.config`](../conf/imperial.config) which has been pre-configured with a setup suitable for the CX1 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 on the CX1 cluster. You can do this by issuing the commands below: ```bash ## Load Nextflow and Singularity environment modules -module load Nextflow +module load anaconda3/personal +conda install -c bioconda nextflow ``` >NB: You will need an account to use the HPC cluster CX1 in order to run the pipeline. If in doubt contact IT. >NB: Nextflow will need to submit the jobs via the job scheduler to the HPC cluster and as such the commands above will have to be executed on one of the login nodes. If in doubt contact IT. ->NB: To submit jobs to the Imperial College MEDBIO cluster, use `-profile imperial_mb` instead. +>NB: To submit jobs to the Imperial College MEDBIO cluster, use `-profile imperial,medbio` instead. +>NB: You will need a restricted access account to use the HPC cluster MEDBIO. diff --git a/docs/imperial_mb.md b/docs/imperial_mb.md deleted file mode 100644 index d7f7f15..0000000 --- a/docs/imperial_mb.md +++ /dev/null @@ -1,16 +0,0 @@ -# nf-core/configs: Imperial MEDBIO HPC Configuration - -All nf-core pipelines have been successfully configured for use on the MEDBIO cluster at Imperial College London HPC. - -To use, run the pipeline with `-profile imperial_mb`. This will download and launch the [`imperial_mb.config`](../conf/imperial_mb.config) which has been pre-configured with a setup suitable for the MEDBIO 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 on the head node. You can do this by issuing the commands below: - -```bash -## Load Nextflow and Singularity environment modules -module load Nextflow -``` - ->NB: You will need an account to use the HPC cluster MEDBIO in order to run the pipeline. Access to the MEDBIO queue is exclusive. If in doubt contact IT. ->NB: Nextflow will need to submit the jobs via the job scheduler to the HPC cluster and as such the commands above will have to be executed on one of the login nodes. If in doubt contact IT. ->NB: To submit jobs to the standard CX1 cluster at Imperial College, use `-profile imperial` instead. diff --git a/docs/marvin.md b/docs/marvin.md new file mode 100644 index 0000000..5ac5666 --- /dev/null +++ b/docs/marvin.md @@ -0,0 +1,9 @@ +# nf-core/configs: Marvin Configuration + +All nf-core pipelines have been successfully configured for use on the [Marvin HPC cluster of the Universitat Pompeu Fabra (UPF).] (https://www.upf.edu/web/sct-sit/marvin-cluster). To use, run the pipeline with -profile marvin. + +NB: You will need an account to use the HPC cluster on the Marvin cluster in order to run the pipeline. If in doubt contact IT. NB: Nextflow will need to submit the jobs via the SLURM scheduler to the HPC cluster and as such the commands above will have to be executed on one of the head nodes. If in doubt contact IT. + +## Pipeline Specific profiles + +There are no specific profiles added for now diff --git a/nfcore_custom.config b/nfcore_custom.config index f580206..28939d2 100644 --- a/nfcore_custom.config +++ b/nfcore_custom.config @@ -25,6 +25,7 @@ profiles { ccga_med { includeConfig "${params.custom_config_base}/conf/ccga_med.config" } cfc { includeConfig "${params.custom_config_base}/conf/cfc.config" } cfc_dev { includeConfig "${params.custom_config_base}/conf/cfc_dev.config" } + cheaha { includeConfig "${params.custom_config_base}/conf/cheaha.config" } computerome { includeConfig "${params.custom_config_base}/conf/computerome.config" } crick { includeConfig "${params.custom_config_base}/conf/crick.config" } czbiohub_aws { includeConfig "${params.custom_config_base}/conf/czbiohub_aws.config" } @@ -41,10 +42,10 @@ profiles { icr_davros { includeConfig "${params.custom_config_base}/conf/icr_davros.config" } ifb_core { includeConfig "${params.custom_config_base}/conf/ifb_core.config" } imperial { includeConfig "${params.custom_config_base}/conf/imperial.config" } - imperial_mb { includeConfig "${params.custom_config_base}/conf/imperial_mb.config" } jax { includeConfig "${params.custom_config_base}/conf/jax.config" } lugh { includeConfig "${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" } mpcdf { includeConfig "${params.custom_config_base}/conf/mpcdf.config" } munin { includeConfig "${params.custom_config_base}/conf/munin.config" } nihbiowulf { includeConfig "${params.custom_config_base}/conf/nihbiowulf.config" } diff --git a/pipeline/scflow.config b/pipeline/scflow.config index 8c4697f..0ff19ea 100644 --- a/pipeline/scflow.config +++ b/pipeline/scflow.config @@ -10,5 +10,4 @@ profiles { imperial { includeConfig "${params.custom_config_base}/conf/pipeline/scflow/imperial.config" } - imperial_mb { includeConfig "${params.custom_config_base}/conf/pipeline/scflow/imperial.config" } // intended -} \ No newline at end of file +}