From a0c8a9ec8f103558468df24200759a82afee0da2 Mon Sep 17 00:00:00 2001 From: Asaf Peer Date: Mon, 12 Apr 2021 16:00:34 -0400 Subject: [PATCH 01/45] updated jax resources --- conf/jax.config | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/conf/jax.config b/conf/jax.config index 7cf790e..56c0f12 100644 --- a/conf/jax.config +++ b/conf/jax.config @@ -19,7 +19,7 @@ singularity{ cacheDir = params.singularity_cache_dir } params { - max_memory = 768.GB - max_cpus = 70 + max_memory = 320.GB + max_cpus = 32 max_time = 336.h } From 3918e0aa9dc64183da65d38d672b8103aac583be Mon Sep 17 00:00:00 2001 From: MaxUlysse Date: Tue, 13 Apr 2021 15:14:14 +0200 Subject: [PATCH 02/45] feat: remove kraken profile --- .github/workflows/main.yml | 2 +- README.md | 1 - conf/kraken.config | 24 ------------------------ docs/kraken.md | 10 ---------- nfcore_custom.config | 1 - 5 files changed, 1 insertion(+), 37 deletions(-) delete mode 100644 conf/kraken.config delete mode 100644 docs/kraken.md diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index cd2170c..a2bcf8e 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -16,7 +16,7 @@ jobs: needs: test_all_profiles strategy: matrix: - profile: ['abims', 'awsbatch', 'bi','bigpurple', 'binac', 'biohpc_gen', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'uzh'] + profile: ['abims', 'awsbatch', 'bi','bigpurple', 'binac', 'biohpc_gen', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'uzh'] steps: - uses: actions/checkout@v1 - name: Install Nextflow diff --git a/README.md b/README.md index 7637725..3e51bb5 100644 --- a/README.md +++ b/README.md @@ -116,7 +116,6 @@ Currently documentation is available for the following systems: * [HEBBE](docs/hebbe.md) * [ICR_DAVROS](docs/icr_davros.md) * [JAX](docs/jax.md) -* [KRAKEN](docs/kraken.md) * [MPCDF](docs/mpcdf.md) * [MUNIN](docs/munin.md) * [OIST](docs/oist.md) diff --git a/conf/kraken.config b/conf/kraken.config deleted file mode 100644 index 59417e9..0000000 --- a/conf/kraken.config +++ /dev/null @@ -1,24 +0,0 @@ -//Profile config names for nf-core/configs -params { - config_profile_name = 'KRAKEN' - config_profile_description = 'Jenkins cluster provided by nf-core/configs.' - config_profile_contact = 'Maxime Garcia or Johannes Alneberg' - config_profile_url = 'kraken.dyn.scilifelab.se' -} - -process { - executor = 'local' -} - -docker { - enabled = true - mountFlags = 'z' - fixOwnership = true -} - -params { - max_memory = 60.GB - max_cpus = 16 - max_time = 72.h - igenomes_base = '/share/igenomes/' -} diff --git a/docs/kraken.md b/docs/kraken.md deleted file mode 100644 index 9426087..0000000 --- a/docs/kraken.md +++ /dev/null @@ -1,10 +0,0 @@ -# nf-core/configs: KRAKEN Configuration - -This profile can be **only** combined with `jenkins.config`. It is used for -testing pipeline with real data on **in-house** cluster located at SciLifeLab. - -To use, run the pipeline with `-profile kraken`. This will download and launch -the [`kraken.config`](../conf/kraken.config) which has been pre-configured to -test the pipeline using `docker` by default. - -Example: `nextflow run -profile kraken,jenkins` diff --git a/nfcore_custom.config b/nfcore_custom.config index 88d7a62..f208d1b 100644 --- a/nfcore_custom.config +++ b/nfcore_custom.config @@ -36,7 +36,6 @@ profiles { genouest { includeConfig "${params.custom_config_base}/conf/genouest.config" } gis { includeConfig "${params.custom_config_base}/conf/gis.config" } hebbe { includeConfig "${params.custom_config_base}/conf/hebbe.config" } - kraken { includeConfig "${params.custom_config_base}/conf/kraken.config" } mpcdf { includeConfig "${params.custom_config_base}/conf/mpcdf.config" } munin { includeConfig "${params.custom_config_base}/conf/munin.config" } oist { includeConfig "${params.custom_config_base}/conf/oist.config" } From eacdf89e534acd9db3837057f9439875fa3079df Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Tue, 20 Apr 2021 13:17:35 +0200 Subject: [PATCH 03/45] Update eva.config --- conf/pipeline/eager/eva.config | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 2e07d57..fa7667d 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -61,7 +61,7 @@ process { // Fixes for SGE and Java incompatibility due to Java using more memory than you tell it to use withName: makeSeqDict { - clusterOptions = { "-S /bin/bash -v JAVA_OPTS='-XX:ParallelGCThreads=1' -l h_vmem=${(task.memory.toGiga() + 3)}G,virtual_free=${(task.memory.toGiga() + 3)}G" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: fastqc { @@ -212,4 +212,4 @@ profiles { bwaalnl = 16500 } } -} \ No newline at end of file +} From 76b62b478d80161c0c5cc15861e9e93b9d0e60bd Mon Sep 17 00:00:00 2001 From: Phil Ewels Date: Thu, 29 Apr 2021 23:06:56 +0200 Subject: [PATCH 04/45] Fix hebbe withName regex --- conf/hebbe.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/hebbe.config b/conf/hebbe.config index 26296d5..58e1e24 100644 --- a/conf/hebbe.config +++ b/conf/hebbe.config @@ -14,7 +14,7 @@ process { clusterOptions = { "-A $params.project ${params.clusterOptions ?: ''}" } /* The Hebbe scheduler fails if you try to request an amount of memory for a job */ - withName: '*' { memory = null } + withName: '.*' { memory = null } } params { From a849fe991ce709212a705597050886a35e75770b Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Tue, 4 May 2021 21:43:19 +0200 Subject: [PATCH 05/45] Add additional retry allowance for silly big data in markdups --- conf/pipeline/eager/shh.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/pipeline/eager/shh.config b/conf/pipeline/eager/shh.config index 5046df0..14bd00c 100644 --- a/conf/pipeline/eager/shh.config +++ b/conf/pipeline/eager/shh.config @@ -10,7 +10,7 @@ params { // Specific nf-core/eager process configuration process { - maxRetries = 2 + maxRetries = 3 withName: malt { maxRetries = 1 From 3bcd55966df5720f7fc9beef80ac282c62b2b359 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Wed, 5 May 2021 11:39:33 +0200 Subject: [PATCH 06/45] Update eva.config --- conf/pipeline/eager/eva.config | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index fa7667d..0b7bbae 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -79,6 +79,10 @@ process { withName: markduplicates { clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() + 6)}G,virtual_free=${(task.memory.toGiga() + 6)}G" } } + + withName: library_merge { + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() + 6)}G,virtual_free=${(task.memory.toGiga() + 6)}G" } + } withName: malt { clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } From 73fcc4495a302c660ce6ebc10ff2a0df752313e9 Mon Sep 17 00:00:00 2001 From: MaxUlysse Date: Wed, 19 May 2021 20:46:52 +0200 Subject: [PATCH 07/45] feat: update owner of profile --- conf/munin.config | 15 +++++++++------ conf/pipeline/sarek/munin.config | 3 ++- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/conf/munin.config b/conf/munin.config index 09df9c8..5db483e 100644 --- a/conf/munin.config +++ b/conf/munin.config @@ -2,8 +2,8 @@ params { // Specific nf-core/configs params - config_profile_contact = 'Szilveszter Juhos (@szilvajuhos)' - config_profile_description = 'MUNIN profile provided by nf-core/configs.' + config_profile_contact = 'Maxime Garcia (@maxulysse)' + config_profile_description = 'MUNIN profile provided by nf-core/configs' config_profile_url = 'https://ki.se/forskning/barntumorbanken' // Local AWS iGenomes reference file paths on munin @@ -26,8 +26,11 @@ singularity { } // To use docker, use nextflow run -profile munin,docker -docker { - enabled = false - mountFlags = 'z' - fixOwnership = true +profiles { + docker { + docker { + enabled = false + mountFlags = 'z' + fixOwnership = true + } } diff --git a/conf/pipeline/sarek/munin.config b/conf/pipeline/sarek/munin.config index 039d117..7276a27 100644 --- a/conf/pipeline/sarek/munin.config +++ b/conf/pipeline/sarek/munin.config @@ -2,8 +2,9 @@ params { // Specific nf-core/configs params - config_profile_contact = 'Maxime Garcia (@MaxUlysse)' + config_profile_contact = 'Maxime Garcia (@maxulysse)' config_profile_description = 'nf-core/sarek MUNIN profile provided by nf-core/configs' + config_profile_url = 'https://ki.se/forskning/barntumorbanken' // Specific nf-core/sarek params annotation_cache = true From 8166e0f6068f8d6eda2f93a2623f17e2135ec096 Mon Sep 17 00:00:00 2001 From: Olga Botvinnik Date: Wed, 19 May 2021 13:36:15 -0700 Subject: [PATCH 08/45] executor.cli --> aws.batch.cliPath --- conf/czbiohub_aws.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/czbiohub_aws.config b/conf/czbiohub_aws.config index c4b0e7d..7132352 100644 --- a/conf/czbiohub_aws.config +++ b/conf/czbiohub_aws.config @@ -27,7 +27,7 @@ process { workDir = "s3://czb-nextflow/intermediates/" aws.region = 'us-west-2' -executor.awscli = '/home/ec2-user/miniconda/bin/aws' +aws.batch.cliPath = '/home/ec2-user/miniconda/bin/aws' params.tracedir = './' params { From 05548bdb75beaf1531212086fce90ecbe446a4f8 Mon Sep 17 00:00:00 2001 From: MaxUlysse Date: Thu, 20 May 2021 09:37:48 +0200 Subject: [PATCH 09/45] fix: forgotten } --- conf/munin.config | 1 + 1 file changed, 1 insertion(+) diff --git a/conf/munin.config b/conf/munin.config index 5db483e..3902e29 100644 --- a/conf/munin.config +++ b/conf/munin.config @@ -33,4 +33,5 @@ profiles { mountFlags = 'z' fixOwnership = true } + } } From f6578f727d1038c1f59209607b6fff5d4a67437f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=98yvind=20Almelid?= Date: Tue, 25 May 2021 09:54:08 +0100 Subject: [PATCH 10/45] Add TMPDIR and mount for it to singularity configuration --- conf/eddie.config | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/conf/eddie.config b/conf/eddie.config index 70e0dcc..7f7e2e2 100644 --- a/conf/eddie.config +++ b/conf/eddie.config @@ -31,7 +31,7 @@ process { params { saveReference = true // iGenomes reference base - igenomes_base = '/exports/igmm/eddie/NextGenResources/igenomes' + igenomes_base = '/exports/igmm/eddie/BioinformaticsResources/igenomes' max_memory = 384.GB max_cpus = 32 max_time = 240.h @@ -42,8 +42,8 @@ env { } singularity { - envWhitelist = "SINGULARITY_TMPDIR" - runOptions = '-p' + envWhitelist = "SINGULARITY_TMPDIR,TMPDIR" + runOptions = '-p -B "$TMPDIR"' enabled = true autoMounts = true } From 31d46cb0a9fbdc990c644cbfad0788ee430ff28d Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Fri, 4 Jun 2021 12:22:54 +0200 Subject: [PATCH 11/45] Make big_data go by default to medium via run time --- conf/pipeline/eager/shh.config | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/conf/pipeline/eager/shh.config b/conf/pipeline/eager/shh.config index 5046df0..da5d6cf 100644 --- a/conf/pipeline/eager/shh.config +++ b/conf/pipeline/eager/shh.config @@ -106,43 +106,43 @@ 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 } + time = { task.attempt == 3 ? 1440.h : 48.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 } + time = { task.attempt == 3 ? 1440.h : 48.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 } + time = { task.attempt == 3 ? 1440.h : 48.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 } + time = { task.attempt == 3 ? 1440.h : 48.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 } + time = { task.attempt == 3 ? 1440.h : 48.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 } + time = { task.attempt == 3 ? 1440.h : 48.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 } + time = { task.attempt == 3 ? 1440.h : 48.h } } } } From fc8b1162c1df01a5f75f97aea51e697b142a9ad9 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Mon, 7 Jun 2021 10:48:35 +0200 Subject: [PATCH 12/45] Fix HOPS huamn ref path --- conf/pipeline/eager/shh.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/pipeline/eager/shh.config b/conf/pipeline/eager/shh.config index 5046df0..9388ad0 100644 --- a/conf/pipeline/eager/shh.config +++ b/conf/pipeline/eager/shh.config @@ -164,7 +164,7 @@ profiles { params { config_profile_description = 'Rough HOPS screening MPI-SHH profile, provided by nf-core/configs.' fasta = '/projects1/Reference_Genomes/Human/HG19/hg19_complete.fasta' - bwa_index = '/projects1/Reference_Genomes/Human/HG19/hg19_complete.fasta' + bwa_index = '/projects1/Reference_Genomes/Human/HG19/' fasta_index = '/projects1/Reference_Genomes/Human/HG19/hg19_complete.fasta.fai' seq_dict = '/projects1/Reference_Genomes/Human/HG19/hg19_complete.dict' bwaalnn = 0.01 From f196de824618747e243565f15559f43d4b414cef Mon Sep 17 00:00:00 2001 From: mseybold Date: Thu, 10 Jun 2021 12:34:58 +0200 Subject: [PATCH 13/45] Update cfc.config singularity is now installed natively on the nodes, so no more need for a module here --- conf/cfc.config | 1 - 1 file changed, 1 deletion(-) diff --git a/conf/cfc.config b/conf/cfc.config index ffe0395..1948e14 100644 --- a/conf/cfc.config +++ b/conf/cfc.config @@ -11,7 +11,6 @@ singularity { } process { - beforeScript = 'module load devel/singularity/3.4.2' executor = 'slurm' queue = { task.memory > 60.GB || task.cpus > 20 ? 'qbic' : 'compute' } scratch = 'true' From c3385593cbafc9d3e3e2b29d8669428ccdb090a2 Mon Sep 17 00:00:00 2001 From: ggabernet Date: Fri, 11 Jun 2021 14:59:09 +0200 Subject: [PATCH 14/45] revert cfc config --- conf/cfc.config | 1 + 1 file changed, 1 insertion(+) diff --git a/conf/cfc.config b/conf/cfc.config index 1948e14..15d4a47 100644 --- a/conf/cfc.config +++ b/conf/cfc.config @@ -12,6 +12,7 @@ singularity { process { executor = 'slurm' + beforeScript = 'module load devel/singularity/3.4.2' queue = { task.memory > 60.GB || task.cpus > 20 ? 'qbic' : 'compute' } scratch = 'true' } From 2b58a62a9b057b2c0f23a57d5f660da23e234e77 Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Fri, 11 Jun 2021 14:50:58 -0500 Subject: [PATCH 15/45] feat(utd): Add initial sysbio config --- conf/utd_sysbio.config | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 conf/utd_sysbio.config diff --git a/conf/utd_sysbio.config b/conf/utd_sysbio.config new file mode 100644 index 0000000..654ac09 --- /dev/null +++ b/conf/utd_sysbio.config @@ -0,0 +1,38 @@ +//Profile config names for nf-core/configs +params { + config_profile_description = 'University of Texas at Dallas HPC cluster profile provided by nf-core/configs' + config_profile_contact = 'Edmund Miller(@emiller88)' + config_profile_url = 'http://docs.oithpc.utdallas.edu/' + singularity_cache_dir = '/scratch/applied-genomics/singularity' +} + +env { + TMPDIR = '/home/$USER/scratch/tmp' +} + +singularity { + enabled = true + envWhitelist='SINGULARITY_BINDPATH' + autoMounts = true + cacheDir = params.singularity_cache_dir +} + +process { + beforeScript = 'module load singularity/3.4.1' + executor = 'slurm' + queue = { task.memory >= 30.GB && task.cpu <= 16 ? 'normal': 'smallmem' } + + + withLabel:process_high { + cpus = { check_max( 16 * task.attempt, 'cpus' ) } + memory = { check_max( 62.GB * task.attempt, 'memory' ) } + time = { check_max( 16.h * task.attempt, 'time' ) } + } +} + +params { + igenomes_base = '/scratch/applied-genomics/references/iGenomes/references/' + max_memory = 90.GB + max_cpus = 16 + max_time = 96.h +} \ No newline at end of file From 04d0b27e816ed144447906e8be7d76422f5800d2 Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Wed, 16 Jun 2021 21:17:40 -0500 Subject: [PATCH 16/45] fix(sysbio): Reduce memory on high processes --- conf/utd_sysbio.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/utd_sysbio.config b/conf/utd_sysbio.config index 654ac09..a6d6ae0 100644 --- a/conf/utd_sysbio.config +++ b/conf/utd_sysbio.config @@ -25,7 +25,7 @@ process { withLabel:process_high { cpus = { check_max( 16 * task.attempt, 'cpus' ) } - memory = { check_max( 62.GB * task.attempt, 'memory' ) } + memory = { check_max( 60.GB * task.attempt, 'memory' ) } time = { check_max( 16.h * task.attempt, 'time' ) } } } From b11f137901bef7db3529980798e14f9456e07b4e Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Wed, 16 Jun 2021 21:18:28 -0500 Subject: [PATCH 17/45] fix(sysbio): Leave igenomes unfinished --- conf/utd_sysbio.config | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/conf/utd_sysbio.config b/conf/utd_sysbio.config index a6d6ae0..41c9318 100644 --- a/conf/utd_sysbio.config +++ b/conf/utd_sysbio.config @@ -31,7 +31,8 @@ process { } params { - igenomes_base = '/scratch/applied-genomics/references/iGenomes/references/' + // TODO Need to initialize this + // igenomes_base = '/scratch/applied-genomics/references/iGenomes/references/' max_memory = 90.GB max_cpus = 16 max_time = 96.h From 472082254a04f3916a442b10fe1ab401fd3049cc Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Wed, 16 Jun 2021 21:18:48 -0500 Subject: [PATCH 18/45] fix(sysbio): Add Star resources --- conf/utd_sysbio.config | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/conf/utd_sysbio.config b/conf/utd_sysbio.config index 41c9318..bd0eda8 100644 --- a/conf/utd_sysbio.config +++ b/conf/utd_sysbio.config @@ -23,6 +23,10 @@ process { queue = { task.memory >= 30.GB && task.cpu <= 16 ? 'normal': 'smallmem' } + withName:STAR_ALIGN { + memory = 36.GB + } + withLabel:process_high { cpus = { check_max( 16 * task.attempt, 'cpus' ) } memory = { check_max( 60.GB * task.attempt, 'memory' ) } From 2a958f5ce3d5a26a3a2cd583a463a020f072b29c Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Wed, 16 Jun 2021 21:19:38 -0500 Subject: [PATCH 19/45] docs: Add sysbio --- README.md | 1 + docs/utd_sysbio.config | 18 ++++++++++++++++++ nfcore_custom.config | 2 ++ 3 files changed, 21 insertions(+) create mode 100644 docs/utd_sysbio.config diff --git a/README.md b/README.md index 6daff2a..c272420 100644 --- a/README.md +++ b/README.md @@ -130,6 +130,7 @@ Currently documentation is available for the following systems: * [UCT_HPC](docs/uct_hpc.md) * [UPPMAX](docs/uppmax.md) * [UTD_GANYMEDE](docs/utd_ganymede.md) +* [UTD_SYSBIO](docs/utd_sysbio.md) * [UZH](docs/uzh.md) ### Uploading to `nf-core/configs` diff --git a/docs/utd_sysbio.config b/docs/utd_sysbio.config new file mode 100644 index 0000000..ff00de9 --- /dev/null +++ b/docs/utd_sysbio.config @@ -0,0 +1,18 @@ +# nf-core/configs: UTD Sysbio Configuration + +All nf-core pipelines have been successfully configured for use on the Sysbio HPC cluster at the [The Univeristy of Texas at Dallas](https://www.utdallas.edu/). + +To use, run the pipeline with `-profile utd_sysbio`. This will download and launch the [`utd_sysbio.config`](../conf/utd_sysbio.config) which has been pre-configured with a setup suitable for the Sysbio 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 using the environment module system on Sysbio. You can do this by issuing the commands below: + +```bash +## Singularity environment modules +module purge +module load singularity +``` + +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 Sysbio in order to run the pipeline. If in doubt contact OIT. +>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. If in doubt contact OIT. diff --git a/nfcore_custom.config b/nfcore_custom.config index 9b4fbda..dbb4638 100644 --- a/nfcore_custom.config +++ b/nfcore_custom.config @@ -49,6 +49,7 @@ profiles { uct_hpc { includeConfig "${params.custom_config_base}/conf/uct_hpc.config" } uppmax { includeConfig "${params.custom_config_base}/conf/uppmax.config" } utd_ganymede { includeConfig "${params.custom_config_base}/conf/utd_ganymede.config" } + utd_sysbio { includeConfig "${params.custom_config_base}/conf/utd_sysbio.config" } uzh { includeConfig "${params.custom_config_base}/conf/uzh.config" } jax { includeConfig "${params.custom_config_base}/conf/jax.config" } } @@ -70,5 +71,6 @@ params { genouest: ['.genouest.org'], uppmax: ['.uppmax.uu.se'], utd_ganymede: ['ganymede.utdallas.edu'] + utd_sysbio: ['sysbio.utdallas.edu'] ] } From 7ff1c6cc7d2494cfa5ecd7a79640fb625453c1f9 Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Wed, 16 Jun 2021 21:19:49 -0500 Subject: [PATCH 20/45] ci: Add sysbio --- .github/workflows/main.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index 65cabe5..92bfce8 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -16,7 +16,7 @@ jobs: needs: test_all_profiles strategy: matrix: - profile: ['abims', 'awsbatch', 'bi','bigpurple', 'binac', 'biohpc_gen', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'sanger', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'uzh'] + profile: ['abims', 'awsbatch', 'bi','bigpurple', 'binac', 'biohpc_gen', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'sanger', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'utd_sysbio' 'uzh'] steps: - uses: actions/checkout@v1 - name: Install Nextflow From 14a2106c63c975eb8798525ed79593f714d00c7a Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Thu, 17 Jun 2021 08:06:24 -0500 Subject: [PATCH 21/45] fix(sysbio): Move rnaseq specific things to pipeline config --- conf/pipeline/rnaseq/utd_sysbio.config | 13 +++++++++++++ conf/utd_sysbio.config | 11 ----------- 2 files changed, 13 insertions(+), 11 deletions(-) create mode 100644 conf/pipeline/rnaseq/utd_sysbio.config diff --git a/conf/pipeline/rnaseq/utd_sysbio.config b/conf/pipeline/rnaseq/utd_sysbio.config new file mode 100644 index 0000000..1af5ed1 --- /dev/null +++ b/conf/pipeline/rnaseq/utd_sysbio.config @@ -0,0 +1,13 @@ +process { + + withName : "STAR_ALIGN" { + memory = 36.GB + } + + withLabel:process_high { + cpus = { check_max( 16 * task.attempt, 'cpus' ) } + memory = { check_max( 60.GB * task.attempt, 'memory' ) } + time = { check_max( 16.h * task.attempt, 'time' ) } + } + +} diff --git a/conf/utd_sysbio.config b/conf/utd_sysbio.config index bd0eda8..5d02901 100644 --- a/conf/utd_sysbio.config +++ b/conf/utd_sysbio.config @@ -21,17 +21,6 @@ process { beforeScript = 'module load singularity/3.4.1' executor = 'slurm' queue = { task.memory >= 30.GB && task.cpu <= 16 ? 'normal': 'smallmem' } - - - withName:STAR_ALIGN { - memory = 36.GB - } - - withLabel:process_high { - cpus = { check_max( 16 * task.attempt, 'cpus' ) } - memory = { check_max( 60.GB * task.attempt, 'memory' ) } - time = { check_max( 16.h * task.attempt, 'time' ) } - } } params { From 87c8e346e07352070e3e2b644a2bb80256244a23 Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Thu, 17 Jun 2021 08:13:29 -0500 Subject: [PATCH 22/45] fix(sysbio): Change filetype --- docs/{utd_sysbio.config => utd_sysbio.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename docs/{utd_sysbio.config => utd_sysbio.md} (100%) diff --git a/docs/utd_sysbio.config b/docs/utd_sysbio.md similarity index 100% rename from docs/utd_sysbio.config rename to docs/utd_sysbio.md From 41ae99d34a81c364ebede9ea6b951fb52c551419 Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Thu, 17 Jun 2021 08:17:18 -0500 Subject: [PATCH 23/45] feat(sysbio): Add cleanup --- conf/utd_sysbio.config | 3 +++ docs/utd_sysbio.md | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/conf/utd_sysbio.config b/conf/utd_sysbio.config index 5d02901..28460a8 100644 --- a/conf/utd_sysbio.config +++ b/conf/utd_sysbio.config @@ -23,6 +23,9 @@ process { queue = { task.memory >= 30.GB && task.cpu <= 16 ? 'normal': 'smallmem' } } +// Preform work directory cleanup after a successful run +cleanup = true + params { // TODO Need to initialize this // igenomes_base = '/scratch/applied-genomics/references/iGenomes/references/' diff --git a/docs/utd_sysbio.md b/docs/utd_sysbio.md index ff00de9..3ae617a 100644 --- a/docs/utd_sysbio.md +++ b/docs/utd_sysbio.md @@ -12,7 +12,5 @@ module purge module load singularity ``` -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 Sysbio in order to run the pipeline. If in doubt contact OIT. >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. If in doubt contact OIT. From e35c5fd1d87d1b004650db4c1c6194215e48c22f Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Thu, 17 Jun 2021 08:32:31 -0500 Subject: [PATCH 24/45] fix(sysbio): Add nf-core params --- conf/pipeline/rnaseq/utd_sysbio.config | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/conf/pipeline/rnaseq/utd_sysbio.config b/conf/pipeline/rnaseq/utd_sysbio.config index 1af5ed1..5e4c492 100644 --- a/conf/pipeline/rnaseq/utd_sysbio.config +++ b/conf/pipeline/rnaseq/utd_sysbio.config @@ -1,3 +1,10 @@ +params { + config_profile_description = 'University of Texas at Dallas HPC cluster profile provided by nf-core/configs' + config_profile_contact = 'Edmund Miller(@emiller88)' + config_profile_url = 'http://docs.oithpc.utdallas.edu/' + singularity_cache_dir = '/scratch/applied-genomics/singularity' +} + process { withName : "STAR_ALIGN" { From 21e1037e0c61a376edfe0e8f2778808b89fa6be2 Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Thu, 17 Jun 2021 08:36:24 -0500 Subject: [PATCH 25/45] docs(sysbio): Add rnaseq specific docs --- conf/pipeline/rnaseq/utd_sysbio.config | 1 - docs/pipeline/rnaseq/utd_sysbio.md | 23 +++++++++++++++++++++++ 2 files changed, 23 insertions(+), 1 deletion(-) create mode 100644 docs/pipeline/rnaseq/utd_sysbio.md diff --git a/conf/pipeline/rnaseq/utd_sysbio.config b/conf/pipeline/rnaseq/utd_sysbio.config index 5e4c492..0c9dd7d 100644 --- a/conf/pipeline/rnaseq/utd_sysbio.config +++ b/conf/pipeline/rnaseq/utd_sysbio.config @@ -2,7 +2,6 @@ params { config_profile_description = 'University of Texas at Dallas HPC cluster profile provided by nf-core/configs' config_profile_contact = 'Edmund Miller(@emiller88)' config_profile_url = 'http://docs.oithpc.utdallas.edu/' - singularity_cache_dir = '/scratch/applied-genomics/singularity' } process { diff --git a/docs/pipeline/rnaseq/utd_sysbio.md b/docs/pipeline/rnaseq/utd_sysbio.md new file mode 100644 index 0000000..ff228d5 --- /dev/null +++ b/docs/pipeline/rnaseq/utd_sysbio.md @@ -0,0 +1,23 @@ +# nf-core/configs: UTD sysbio rnaseq specific configuration + +Extra specific configuration for rnaseq pipeline + +## Usage + +To use, run the pipeline with `-profile sysbio`. + +This will download and launch the eager specific [`utd_sysbio.config`](../../../conf/pipeline/rnaseq/utd_sysbio.config) which has been pre-configured with a setup suitable for the shh cluster. + +Example: `nextflow run nf-core/rnaseq -profile sysbio` + +## rnaseq specific configurations for UTD sysbio + +Specific configurations for UTD Sysbio has been made for rnaseq. + +### General profiles + + + +### Contextual profiles + + From f9e4ec4a8d5ac96c349dacaa38bd47db611ca1fa Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Thu, 17 Jun 2021 08:50:25 -0500 Subject: [PATCH 26/45] fix(sysbio): Add sysbio to rnaseq --- pipeline/rnaseq.config | 1 + 1 file changed, 1 insertion(+) diff --git a/pipeline/rnaseq.config b/pipeline/rnaseq.config index 1a27463..17a4ca0 100644 --- a/pipeline/rnaseq.config +++ b/pipeline/rnaseq.config @@ -10,4 +10,5 @@ profiles { eddie { includeConfig "${params.custom_config_base}/conf/pipeline/rnaseq/eddie.config" } + utd_sysbio { includeConfig "${params.custom_config_base}/conf/pipeline/rnaseq/utd_sysbio.config" } } From 5ad959a4361a13adeab3e65920a9d6fc930ad824 Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Thu, 17 Jun 2021 09:08:27 -0500 Subject: [PATCH 27/45] fix(sysbio): Missing comma --- nfcore_custom.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nfcore_custom.config b/nfcore_custom.config index dbb4638..75e8309 100644 --- a/nfcore_custom.config +++ b/nfcore_custom.config @@ -70,7 +70,7 @@ params { genotoul: ['.genologin1.toulouse.inra.fr', '.genologin2.toulouse.inra.fr'], genouest: ['.genouest.org'], uppmax: ['.uppmax.uu.se'], - utd_ganymede: ['ganymede.utdallas.edu'] + utd_ganymede: ['ganymede.utdallas.edu'], utd_sysbio: ['sysbio.utdallas.edu'] ] } From cb213a499cfc3044e80f119121f7bcd2d010325a Mon Sep 17 00:00:00 2001 From: Edmund Miller Date: Thu, 17 Jun 2021 09:34:03 -0500 Subject: [PATCH 28/45] ci: Another missing comma --- .github/workflows/main.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index 92bfce8..5dac8ac 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -16,7 +16,7 @@ jobs: needs: test_all_profiles strategy: matrix: - profile: ['abims', 'awsbatch', 'bi','bigpurple', 'binac', 'biohpc_gen', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'sanger', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'utd_sysbio' 'uzh'] + profile: ['abims', 'awsbatch', 'bi','bigpurple', 'binac', 'biohpc_gen', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'sanger', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'utd_sysbio', 'uzh'] steps: - uses: actions/checkout@v1 - name: Install Nextflow From 93cfc48afd7bf36c9df939847f5275ff31fcec0d Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Mon, 21 Jun 2021 21:04:16 +0100 Subject: [PATCH 29/45] Add ARTIC v4 primers to genomes config --- conf/pipeline/viralrecon/genomes.config | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/conf/pipeline/viralrecon/genomes.config b/conf/pipeline/viralrecon/genomes.config index 27f7162..e7b1c2f 100644 --- a/conf/pipeline/viralrecon/genomes.config +++ b/conf/pipeline/viralrecon/genomes.config @@ -20,23 +20,29 @@ params { primer_sets { artic { '1' { - fasta = 'https://github.com/artic-network/primer-schemes/raw/master/nCoV-2019/V1/nCoV-2019.reference.fasta' + fasta = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V1/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' - primer_bed = 'https://github.com/artic-network/primer-schemes/raw/master/nCoV-2019/V1/nCoV-2019.primer.bed' + primer_bed = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V1/nCoV-2019.primer.bed' scheme = 'nCoV-2019' } '2' { - fasta = 'https://github.com/artic-network/primer-schemes/raw/master/nCoV-2019/V2/nCoV-2019.reference.fasta' + fasta = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V2/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' - primer_bed = 'https://github.com/artic-network/primer-schemes/raw/master/nCoV-2019/V2/nCoV-2019.primer.bed' + primer_bed = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V2/nCoV-2019.primer.bed' scheme = 'nCoV-2019' } '3' { - fasta = 'https://github.com/artic-network/primer-schemes/raw/master/nCoV-2019/V3/nCoV-2019.reference.fasta' + fasta = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V3/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' - primer_bed = 'https://github.com/artic-network/primer-schemes/raw/master/nCoV-2019/V3/nCoV-2019.primer.bed' + primer_bed = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V3/nCoV-2019.primer.bed' scheme = 'nCoV-2019' } + '4' { + fasta = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V4/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/SARS-CoV-2.scheme.bed' + scheme = 'SARS-CoV-2' + } } } } From 5f4b915ae8a99f419edf2e4a16dbb5a3f7b52008 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Tue, 29 Jun 2021 11:31:00 +0200 Subject: [PATCH 30/45] Update eva.config --- conf/pipeline/eager/eva.config | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 0b7bbae..87d679e 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -69,7 +69,7 @@ process { } withName: adapter_removal { - clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 4)}G,virtual_free=${(task.memory.toGiga() * 4)}G" } } withName: dedup { @@ -97,7 +97,7 @@ process { } withName: mtnucratio { - clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 4)}G,virtual_free=${(task.memory.toGiga() * 4)}G" } } withName: vcf2genome { From d59d099fe815eb4826b8da9d5aadae4c63fc5a7c Mon Sep 17 00:00:00 2001 From: ggabernet Date: Thu, 1 Jul 2021 10:52:54 +0200 Subject: [PATCH 31/45] remove load module in cfc configs --- conf/cfc.config | 1 - conf/cfc_dev.config | 1 - 2 files changed, 2 deletions(-) diff --git a/conf/cfc.config b/conf/cfc.config index 15d4a47..1948e14 100644 --- a/conf/cfc.config +++ b/conf/cfc.config @@ -12,7 +12,6 @@ singularity { process { executor = 'slurm' - beforeScript = 'module load devel/singularity/3.4.2' queue = { task.memory > 60.GB || task.cpus > 20 ? 'qbic' : 'compute' } scratch = 'true' } diff --git a/conf/cfc_dev.config b/conf/cfc_dev.config index 6190314..1d61baf 100644 --- a/conf/cfc_dev.config +++ b/conf/cfc_dev.config @@ -10,7 +10,6 @@ singularity { } process { - beforeScript = 'module load devel/singularity/3.4.2' executor = 'slurm' queue = { task.memory > 60.GB || task.cpus > 20 ? 'qbic' : 'compute' } scratch = 'true' From ee2e8392ab4c9b13ac2a6d4ee1dd9164527c07a5 Mon Sep 17 00:00:00 2001 From: ggabernet Date: Sat, 3 Jul 2021 12:17:21 +0200 Subject: [PATCH 32/45] add aws_tower profile --- README.md | 1 + conf/aws_tower.config | 21 +++++++++++++++++++++ docs/aws_tower.md | 5 +++++ nfcore_custom.config | 1 + 4 files changed, 28 insertions(+) create mode 100644 conf/aws_tower.config create mode 100644 docs/aws_tower.md diff --git a/README.md b/README.md index 6daff2a..dbe220e 100644 --- a/README.md +++ b/README.md @@ -96,6 +96,7 @@ Currently documentation is available for the following systems: * [ABIMS](docs/abims.md) * [AWSBATCH](docs/awsbatch.md) +* [AWS_TOWER](docs/aws_tower.md) * [BIGPURPLE](docs/bigpurple.md) * [BI](docs/bi.md) * [BINAC](docs/binac.md) diff --git a/conf/aws_tower.config b/conf/aws_tower.config new file mode 100644 index 0000000..ab7786d --- /dev/null +++ b/conf/aws_tower.config @@ -0,0 +1,21 @@ +//Nextflow config file for running on AWS batch +params { + config_profile_description = 'AWS Batch with Tower Profile' + config_profile_contact = 'Gisela Gabernet (@ggabernet)' + config_profile_url = 'https://aws.amazon.com/batch/' +} + +timeline { + overwrite = true +} +report { + overwrite = true +} +trace { + overwrite = true +} +dag { + overwrite = true +} + +process.executor = 'awsbatch' diff --git a/docs/aws_tower.md b/docs/aws_tower.md new file mode 100644 index 0000000..6274bf3 --- /dev/null +++ b/docs/aws_tower.md @@ -0,0 +1,5 @@ +# nf-core/configs: AWS Batch with Tower Configuration + +To be used when submitting jobs to AWS Batch by using Tower Forge. If you are not using Tower Forge, consider using the profile `awsbatch` where you can directly specify the Batch queue, AWS region and AWS cli path. + +This profile defines `awsbatch` as executor, and allows `overwrite` of `trace`, `timeline`, `report` and `dag` to allow resuming pipelines. diff --git a/nfcore_custom.config b/nfcore_custom.config index 9b4fbda..237bc30 100644 --- a/nfcore_custom.config +++ b/nfcore_custom.config @@ -12,6 +12,7 @@ profiles { abims { includeConfig "${params.custom_config_base}/conf/abims.config" } awsbatch { includeConfig "${params.custom_config_base}/conf/awsbatch.config" } + aws_tower { includeConfig "${params.custom_config_base}/conf/aws_tower.config" } bi { includeConfig "${params.custom_config_base}/conf/bi.config" } bigpurple { includeConfig "${params.custom_config_base}/conf/bigpurple.config" } binac { includeConfig "${params.custom_config_base}/conf/binac.config" } From f8690d49e84c92d504843e031b2f0e419cf82431 Mon Sep 17 00:00:00 2001 From: ggabernet Date: Sat, 3 Jul 2021 12:21:03 +0200 Subject: [PATCH 33/45] add to tests --- .github/workflows/main.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index 65cabe5..a6468fa 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -16,7 +16,7 @@ jobs: needs: test_all_profiles strategy: matrix: - profile: ['abims', 'awsbatch', 'bi','bigpurple', 'binac', 'biohpc_gen', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'sanger', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'uzh'] + profile: ['abims', 'awsbatch', 'aws_tower', 'bi','bigpurple', 'binac', 'biohpc_gen', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'sanger', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'uzh'] steps: - uses: actions/checkout@v1 - name: Install Nextflow From f3274c49b56011622cbeacb7fdb59565e7a52017 Mon Sep 17 00:00:00 2001 From: ggabernet Date: Sat, 3 Jul 2021 14:36:56 +0200 Subject: [PATCH 34/45] test profile multiline --- .github/workflows/main.yml | 43 +++++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index a6468fa..7dcdd29 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -16,7 +16,48 @@ jobs: needs: test_all_profiles strategy: matrix: - profile: ['abims', 'awsbatch', 'aws_tower', 'bi','bigpurple', 'binac', 'biohpc_gen', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'sanger', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'uzh'] + profile: + - 'abims' + - 'awsbatch' + - 'aws_tower' + - 'bi' + - 'bigpurple' + - 'binac' + - 'biohpc_gen' + - 'cbe' + - 'ccga_dx' + - 'ccga_med' + - 'cfc' + - 'cfc_dev' + - 'crick' + - 'denbi_qbic' + - 'ebc' + - 'eddie' + - 'eva' + - 'genotoul' + - 'genouest' + - 'gis' + - 'google' + - 'hebbe' + - 'icr_davros' + - 'ifb_core' + - 'imperial' + - 'imperial_mb' + - 'jax' + - 'kraken' + - 'mpcdf' + - 'munin' + - 'oist' + - 'pasteur' + - 'phoenix' + - 'prince' + - 'sanger' + - 'seg_globe' + - 'shh' + - 'uct_hpc' + - 'uppmax' + - 'utd_ganymede' + - 'uzh' steps: - uses: actions/checkout@v1 - name: Install Nextflow From 926f3ba24f8b8b13a313748247283ef6cea4c534 Mon Sep 17 00:00:00 2001 From: ggabernet Date: Sat, 3 Jul 2021 14:52:44 +0200 Subject: [PATCH 35/45] update checker script --- bin/cchecker.py | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/bin/cchecker.py b/bin/cchecker.py index 9629cf8..71dd2c9 100644 --- a/bin/cchecker.py +++ b/bin/cchecker.py @@ -10,6 +10,7 @@ import os import sys import argparse import re +import yaml ############################################ ############################################ @@ -51,13 +52,16 @@ def check_config(Config, Github): ### Ignore these profiles ignore_me = ['czbiohub_aws'] tests.update(ignore_me) - with open(Github, 'r') as ghfile: - for line in ghfile: - if re.search('profile: ', line): - line = line.replace('\'','').replace('[','').replace(']','').replace('\n','') - profiles = line.split(':')[1].split(',') - for p in profiles: - tests.add(p.strip()) + # parse yaml GitHub actions file + try: + with open(Github, 'r') as ghfile: + wf = yaml.safe_load(ghfile) + profile_list = wf["profile_test"]["strategy"]["matrix"]["profile"] + except Exception as e: + return {"failed": ["Could not parse yaml file: {}, {}".format(Github, e)]} + # Add profiles to test + for profile in profile_list: + tests.add(profile.strip()) ###Check if sets are equal if tests == config_profiles: From 6475671c384c8ea48bab33319eac56e6b2fa8eda Mon Sep 17 00:00:00 2001 From: ggabernet Date: Sat, 3 Jul 2021 14:57:58 +0200 Subject: [PATCH 36/45] test that it fails --- .github/workflows/main.yml | 1 - 1 file changed, 1 deletion(-) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index f66db3d..6daa819 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -19,7 +19,6 @@ jobs: profile: - 'abims' - 'awsbatch' - - 'aws_tower' - 'bi' - 'bigpurple' - 'binac' From 2a69b90be62106eec003b789fccc5478cb1dd000 Mon Sep 17 00:00:00 2001 From: ggabernet Date: Sat, 3 Jul 2021 15:09:43 +0200 Subject: [PATCH 37/45] fix cchecker --- bin/cchecker.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/bin/cchecker.py b/bin/cchecker.py index 71dd2c9..8caf920 100644 --- a/bin/cchecker.py +++ b/bin/cchecker.py @@ -58,16 +58,16 @@ def check_config(Config, Github): wf = yaml.safe_load(ghfile) profile_list = wf["profile_test"]["strategy"]["matrix"]["profile"] except Exception as e: - return {"failed": ["Could not parse yaml file: {}, {}".format(Github, e)]} + print("Could not parse yaml file: {}, {}".format(Github, e)) + sys.exit(1) # Add profiles to test for profile in profile_list: tests.add(profile.strip()) ###Check if sets are equal - if tests == config_profiles: - sys.exit(0) - else: - #Maybe report what is missing here too + try: + assert tests == config_profiles + except (AssertionError): print("Tests don't seem to test these profiles properly. Please check whether you added the profile to the Github Actions testing YAML.\n") print(config_profiles.symmetric_difference(tests)) sys.exit(1) From 68e12f85ec437a0a6464294363336a3cad4d1bec Mon Sep 17 00:00:00 2001 From: ggabernet Date: Sat, 3 Jul 2021 15:11:51 +0200 Subject: [PATCH 38/45] fix cchecker --- bin/cchecker.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bin/cchecker.py b/bin/cchecker.py index 8caf920..cac7e4a 100644 --- a/bin/cchecker.py +++ b/bin/cchecker.py @@ -56,7 +56,7 @@ def check_config(Config, Github): try: with open(Github, 'r') as ghfile: wf = yaml.safe_load(ghfile) - profile_list = wf["profile_test"]["strategy"]["matrix"]["profile"] + profile_list = wf["jobs"]["profile_test"]["strategy"]["matrix"]["profile"] except Exception as e: print("Could not parse yaml file: {}, {}".format(Github, e)) sys.exit(1) From e6f1bfaa1a7bebe1796a79f14bc4d0ef69173c88 Mon Sep 17 00:00:00 2001 From: ggabernet Date: Sat, 3 Jul 2021 15:13:10 +0200 Subject: [PATCH 39/45] finally add profile --- .github/workflows/main.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index 6daa819..f66db3d 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -19,6 +19,7 @@ jobs: profile: - 'abims' - 'awsbatch' + - 'aws_tower' - 'bi' - 'bigpurple' - 'binac' From 962dca7a4661665c883037a8f43286b383ab984a Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Mon, 12 Jul 2021 12:24:49 +0100 Subject: [PATCH 40/45] Add ARTIC v1200 primers to genomes config for viralrecon --- conf/pipeline/viralrecon/genomes.config | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/conf/pipeline/viralrecon/genomes.config b/conf/pipeline/viralrecon/genomes.config index e7b1c2f..3e3e299 100644 --- a/conf/pipeline/viralrecon/genomes.config +++ b/conf/pipeline/viralrecon/genomes.config @@ -43,6 +43,12 @@ 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' } + '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' + primer_bed = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/primer_schemes/artic/nCoV-2019/V1200/nCoV-2019.bed' + scheme = 'nCoV-2019' + } } } } From 4ceb369af53ec89bce5dc4852ee28a366c2501d7 Mon Sep 17 00:00:00 2001 From: ameynert Date: Wed, 21 Jul 2021 12:10:43 +0100 Subject: [PATCH 41/45] eddie.config for viralrecon pipeline --- conf/pipeline/viralrecon/eddie.config | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 conf/pipeline/viralrecon/eddie.config diff --git a/conf/pipeline/viralrecon/eddie.config b/conf/pipeline/viralrecon/eddie.config new file mode 100644 index 0000000..38192ef --- /dev/null +++ b/conf/pipeline/viralrecon/eddie.config @@ -0,0 +1,9 @@ +process { + withName : '.*PICARD.*' { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } + + withName : '.*SNPEFF.*' { + clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"} + } +} From 5224eb55742c7fc52b17d6d2938b97623d2a150b Mon Sep 17 00:00:00 2001 From: ameynert Date: Wed, 21 Jul 2021 12:15:17 +0100 Subject: [PATCH 42/45] Updated resources folder & institute name Local resources folder was re-organized & re-named BioinformaticsResources. Added note about viralrecon & atacseq pipeline-specific config. IGMM name-changed recently; updated to IGC. --- docs/eddie.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/docs/eddie.md b/docs/eddie.md index e5dbe5c..485e20a 100644 --- a/docs/eddie.md +++ b/docs/eddie.md @@ -1,10 +1,10 @@ # nf-core/configs: Eddie Configuration -nf-core pipelines sarek, rnaseq, and atacseq have all been tested on the University of Edinburgh Eddie HPC. +nf-core pipelines sarek, rnaseq, atacseq, and viralrecon have all been tested on the University of Edinburgh Eddie HPC. All except atacseq have pipeline-specific config files; atacseq does not yet support this. ## Getting help -There is a Slack channel dedicated to eddie users on the MRC IGMM Slack: [https://igmm.slack.com/channels/eddie3](https://igmm.slack.com/channels/eddie3) +There is a Slack channel dedicated to eddie users on the MRC IGC Slack: [https://igmm.slack.com/channels/eddie3](https://igmm.slack.com/channels/eddie3) ## Using the Eddie config profile @@ -35,13 +35,13 @@ This config enables Nextflow to manage the pipeline jobs via the SGE job schedul ## Singularity set-up -Load Singularity from the module system and, if you have access to `/exports/igmm/eddie/NextGenResources`, set the Singularity cache directory to the NextGenResources path below. If some containers for your pipeline run are not present, please contact the [IGMM Data Manager](data.manager@igmm.ed.ac.uk) to have them added. You can add these lines to the file `$HOME/.bashrc`, or you can run these commands before you run an nf-core pipeline. +Load Singularity from the module system and, if you have access to `/exports/igmm/eddie/BioinformaticsResources`, set the Singularity cache directory to the BioinformaticsResources path below. If some containers for your pipeline run are not present, please contact the [IGC Data Manager](data.manager@igc.ed.ac.uk) to have them added. You can add these lines to the file `$HOME/.bashrc`, or you can run these commands before you run an nf-core pipeline. -If you do not have access to `/exports/igmm/eddie/NextGenResources`, set the Singularity cache directory to somewhere sensible that is not in your `$HOME` area (which has limited space). It will take time to download all the Singularity containers, but you can use this again. +If you do not have access to `/exports/igmm/eddie/BioinformaticsResources`, set the Singularity cache directory to somewhere sensible that is not in your `$HOME` area (which has limited space). It will take time to download all the Singularity containers, but you can use this again. ```bash module load singularity -export NXF_SINGULARITY_CACHEDIR="/exports/igmm/eddie/NextGenResources/nextflow/singularity" +export NXF_SINGULARITY_CACHEDIR="/exports/igmm/eddie/BioinformaticsResources/nf-core/singularity-images" ``` Singularity will create a directory `.singularity` in your `$HOME` directory on eddie. Space on `$HOME` is very limited, so it is a good idea to create a directory somewhere else with more room and link the locations. @@ -68,7 +68,7 @@ If your eddie terminal disconnects your Nextflow job will stop. You can run Next nohup ./nextflow_run.sh & ``` -### On a wild west node - IGMM only +### On a wild west node - IGC only Wild west nodes on eddie can be accessed via ssh (node2c15, node2c16, node3g22). To run Nextflow on one of these nodes, do it within a [screen session](https://linuxize.com/post/how-to-use-linux-screen/). @@ -92,12 +92,12 @@ screen -r ## Using iGenomes references -A local copy of the iGenomes resource has been made available on the Eddie HPC for those with access to `/exports/igmm/eddie/NextGenResources` so you should be able to run the pipeline against any reference available in the `igenomes.config`. +A local copy of the iGenomes resource has been made available on the Eddie HPC for those with access to `/exports/igmm/eddie/BioinformaticsResources` so you should be able to run the pipeline against any reference available in the `igenomes.config`. You can do this by simply using the `--genome ` parameter. ## Adjusting maximum resources -This config is set for IGMM standard nodes which have 32 cores and 384GB memory. If you are a non-IGMM user, please see the [ECDF specification](https://www.wiki.ed.ac.uk/display/ResearchServices/Memory+Specification) and adjust the `--clusterOptions` flag appropriately, e.g. +This config is set for IGC standard nodes which have 32 cores and 384GB memory. If you are a non-IGC user, please see the [ECDF specification](https://www.wiki.ed.ac.uk/display/ResearchServices/Memory+Specification) and adjust the `--clusterOptions` flag appropriately, e.g. ```bash --clusterOptions "-C mem256GB" --max_memory "256GB" From d9abb7d59fddfdda90d011146a0e82ec10403a51 Mon Sep 17 00:00:00 2001 From: ameynert Date: Wed, 21 Jul 2021 12:23:47 +0100 Subject: [PATCH 43/45] Added eddie config to viralrecon --- pipeline/viralrecon.config | 1 + 1 file changed, 1 insertion(+) diff --git a/pipeline/viralrecon.config b/pipeline/viralrecon.config index 76a15d1..04ec882 100644 --- a/pipeline/viralrecon.config +++ b/pipeline/viralrecon.config @@ -5,3 +5,4 @@ */ includeConfig "${params.custom_config_base}/conf/pipeline/viralrecon/genomes.config" +includeConfig "${params.custom_config_base}/conf/pipeline/viralrecon/eddie.config" From 17fad9dd15008c4da074ec9b042091cd3a6e2253 Mon Sep 17 00:00:00 2001 From: ameynert Date: Wed, 21 Jul 2021 12:27:09 +0100 Subject: [PATCH 44/45] Update pipeline/viralrecon.config Co-authored-by: Harshil Patel --- pipeline/viralrecon.config | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/pipeline/viralrecon.config b/pipeline/viralrecon.config index 04ec882..9300c31 100644 --- a/pipeline/viralrecon.config +++ b/pipeline/viralrecon.config @@ -5,4 +5,7 @@ */ includeConfig "${params.custom_config_base}/conf/pipeline/viralrecon/genomes.config" -includeConfig "${params.custom_config_base}/conf/pipeline/viralrecon/eddie.config" + +profiles { + eddie { includeConfig "${params.custom_config_base}/conf/pipeline/viralrecon/eddie.config" } +} From 21121684200382b360fda18f97b3fd17b37a5e30 Mon Sep 17 00:00:00 2001 From: ameynert Date: Thu, 22 Jul 2021 15:07:19 +0100 Subject: [PATCH 45/45] Set BLASTDB_LMDB_MAP_SIZE This environment variable needs to be set in order to prevent memory allocation errors in the MAKEBLASTDB process. --- conf/pipeline/viralrecon/eddie.config | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/conf/pipeline/viralrecon/eddie.config b/conf/pipeline/viralrecon/eddie.config index 38192ef..8f0463d 100644 --- a/conf/pipeline/viralrecon/eddie.config +++ b/conf/pipeline/viralrecon/eddie.config @@ -1,3 +1,7 @@ +env { + BLASTDB_LMDB_MAP_SIZE=100000000 +} + process { withName : '.*PICARD.*' { clusterOptions = {"-l h_vmem=${(task.memory + 4.GB).bytes/task.cpus}"}