From 59af7f0eee7effac0e2847b346e6b6af5ca28a96 Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Fri, 20 Aug 2021 10:15:39 +0200 Subject: [PATCH 1/2] Delete SHH profiles due to decommissioning --- README.md | 2 - conf/pipeline/eager/shh.config | 220 --------------------------------- conf/shh.config | 35 ------ docs/pipeline/eager/shh.md | 36 ------ docs/shh.md | 16 --- nextflow.config | 2 +- nfcore_custom.config | 1 - pipeline/eager.config | 1 - 8 files changed, 1 insertion(+), 312 deletions(-) delete mode 100644 conf/pipeline/eager/shh.config delete mode 100644 conf/shh.config delete mode 100644 docs/pipeline/eager/shh.md delete mode 100644 docs/shh.md diff --git a/README.md b/README.md index 29fbce2..0730271 100644 --- a/README.md +++ b/README.md @@ -127,7 +127,6 @@ Currently documentation is available for the following systems: * [PRINCE](docs/prince.md) * [SANGER](docs/sanger.md) * [SEG_GLOBE](docs/seg_globe.md) -* [SHH](docs/shh.md) * [UCT_HPC](docs/uct_hpc.md) * [UPPMAX](docs/uppmax.md) * [UTD_GANYMEDE](docs/utd_ganymede.md) @@ -180,7 +179,6 @@ Currently documentation is available for the following pipelines within specific * [BINAC](docs/pipeline/ampliseq/binac.md) * [UPPMAX](docs/pipeline/ampliseq/uppmax.md) * eager - * [SHH](docs/pipeline/eager/shh.md) * [EVA](docs/pipeline/eager/eva.md) * rnafusion * [MUNIN](docs/pipeline/rnafusion/munin.md) diff --git a/conf/pipeline/eager/shh.config b/conf/pipeline/eager/shh.config deleted file mode 100644 index b99d038..0000000 --- a/conf/pipeline/eager/shh.config +++ /dev/null @@ -1,220 +0,0 @@ -// Profile config names for nf-core/configs - -params { - // Specific nf-core/configs params - config_profile_contact = 'James Fellows Yates (@jfy133)' - config_profile_description = 'nf-core/eager SHH profile provided by nf-core/configs' - igenomes_base = "/projects1/public_data/igenomes/" -} - -// Specific nf-core/eager process configuration -process { - - maxRetries = 3 - - withName: malt { - maxRetries = 1 - memory = { task.attempt > 1 ? 1900.GB : 725.GB } - cpus = { task.attempt > 1 ? 112 : 64 } - time = 1440.h - queue = { task.memory > 756.GB ? 'supercruncher' : 'long' } - } - - withName: circulargenerator { - cpus = { check_max( 1, 'cpus' ) } - memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = { check_max( 4.h * task.attempt, 'time' ) } - } - - 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 } - } - - 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 } - } - - 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 } - } - - 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 } - } - - 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 } - } - - 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 } - } - - 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 } - } - -} - -profiles { - - big_data { - - params { - // Specific nf-core/configs params - config_profile_contact = 'James Fellows Yates (@jfy133)' - config_profile_description = 'nf-core/eager big-data SHH profile provided by nf-core/configs' - } - - executor { - queueSize = 6 - } - - process { - - maxRetries = 2 - - withName:malt { - maxRetries = 1 - memory = { task.attempt > 1 ? 1900.GB : 725.GB } - cpus = { task.attempt > 1 ? 112 : 64 } - time = 1440.h - queue = { task.memory > 756.GB ? 'supercruncher' : 'long' } - } - - withName:hostremoval_input_fastq { - cpus = { check_max( 1, 'cpus' ) } - memory = { check_max( 32.GB * task.attempt, 'memory' ) } - time = 1440.h - queue = 'long' - } - - withLabel:'sc_tiny'{ - cpus = { check_max( 1, 'cpus' ) } - memory = { check_max( 2.GB * task.attempt, 'memory' ) } - 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 : 48.h } - } - - withLabel:'sc_medium'{ - cpus = { check_max( 1, 'cpus' ) } - memory = { check_max( 16.GB * task.attempt, 'memory' ) } - 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 : 48.h } - } - - withLabel:'mc_medium' { - cpus = { check_max( 4, 'cpus' ) } - memory = { check_max( 16.GB * task.attempt, 'memory' ) } - 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 : 48.h } - } - - withLabel:'mc_huge'{ - cpus = { check_max( 32, 'cpus' ) } - memory = { check_max( 512.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : 48.h } - } - } - } - - microbiome_screening { - process { - // Assuming NCBI NT-sized DB - withName: malt { - maxRetries = 1 - memory = 1900.GB - cpus = 112 - time = 1440.h - queue = 'supercruncher' - } - } - } - // IMPORTANT this profile is not reproducible due to hardcoded paths. For initial/automated screening ONLY. - hops { - 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/' - fasta_index = '/projects1/Reference_Genomes/Human/HG19/hg19_complete.fasta.fai' - seq_dict = '/projects1/Reference_Genomes/Human/HG19/hg19_complete.dict' - bwaalnn = 0.01 - bwaalnl = 16 - run_bam_filtering = true - bam_unmapped_type = 'fastq' - run_metagenomic_screening = true - metagenomic_tool = 'malt' - metagenomic_min_support_reads = 1 - database = '/projects1/malt/databases/indexed/index040/full-bac-full-vir-etal-nov_2017' - percent_identity = 85 - malt_mode = 'BlastN' - malt_alignment_mode = 'SemiGlobal' - malt_top_percent = 1 - malt_min_support_mode = 'reads' - malt_max_queries = 100 - malt_memory_mode = 'load' - run_maltextract = true - maltextract_taxon_list = '/projects1/users/key/anc5h/soi.backup/List_of_pathogens_KB_fmk12_wViruses1.txt' - maltextract_ncbifiles = '/projects1/clusterhomes/huebler/RMASifter/RMA_Extractor_Resources/' - maltextract_filter = 'def_anc' - maltextract_toppercent = 0.01 - maltextract_destackingoff = false - maltextract_downsamplingoff = false - maltextract_duplicateremovaloff = false - maltextract_matches = false - maltextract_megansummary = true - maltextract_percentidentity = 85.0 - maltextract_topalignment = false - } - } - pathogen_loose { - params { - config_profile_description = 'Pathogen (loose) MPI-SHH profile, provided by nf-core/configs.' - bwaalnn = 0.01 - bwaalnl = 16 - } - } - pathogen_strict { - params { - config_profile_description = 'Pathogen (strict) MPI-SHH SDAG profile, provided by nf-core/configs.' - bwaalnn = 0.1 - bwaalnl = 32 - } - } - human { - params { - config_profile_description = 'Human MPI-SHH SDAG profile, provided by nf-core/configs.' - bwaalnn = 0.01 - bwaalnl = 16500 - } - } -} diff --git a/conf/shh.config b/conf/shh.config deleted file mode 100644 index a17c935..0000000 --- a/conf/shh.config +++ /dev/null @@ -1,35 +0,0 @@ -//Profile config names for nf-core/configs -params { - config_profile_description = 'Generic MPI-SHH SDAG cluster profile provided by nf-core/configs.' - config_profile_contact = 'James Fellows Yates (@jfy133), Maxime Borry (@Maxibor)' - config_profile_url = 'https://shh.mpg.de' - max_memory = 2.TB - max_cpus = 128 - max_time = 720.h - //Illumina iGenomes reference file path - igenomes_base = "/projects1/public_data/igenomes/" -} - -// Preform work directory cleanup after a successful run -cleanup = true - -process { - executor = 'slurm' - queue = { task.memory > 756.GB || task.cpus > 64 ? 'supercruncher': task.time <= 2.h ? 'short' : task.time <= 48.h ? 'medium': 'long' } -} - -executor { - queueSize = 8 -} - -profiles { - singularity { - singularity.enabled = true - singularity.autoMounts = true - singularity.cacheDir = "/projects1/singularity_scratch/cache/" - } - // Profile to deactivate automatic cleanup of work directory after a successful run. Overwrites cleanup option. - debug { - cleanup = false - } -} diff --git a/docs/pipeline/eager/shh.md b/docs/pipeline/eager/shh.md deleted file mode 100644 index c09606d..0000000 --- a/docs/pipeline/eager/shh.md +++ /dev/null @@ -1,36 +0,0 @@ -# nf-core/configs: shh eager specific configuration - -Extra specific configuration for eager pipeline - -## Usage - -To use, run the pipeline with `-profile shh`. - -This will download and launch the eager specific [`shh.config`](../../../conf/pipeline/eager/shh.config) which has been pre-configured with a setup suitable for the shh cluster. - -Example: `nextflow run nf-core/eager -profile shh` - -## eager specific configurations for shh - -Specific configurations for shh has been made for eager. - -### General profiles - -* If running with the MALT module turned on, the MALT process by default will be sent to the long queue with a resource requirement minimum of 725GB and 64 cores. If this fails, the process will be tried once more only and sent to the supercruncher queue. The module will not retry after this, and pipeline will fail. Note, this will only work on SDAG. - -### Contextual profiles - -#### Microbiome Sciences - -* `microbiome_screening` runs MALT straight to supercruncher (with no retries!) and full resources requested due to microbiome screening databases often easily reach this size - -#### Human Pop-Gen - -* `human`: optimised for mapping of human aDNA reads (i.e. bwa aln defaults as `-l 16500, -n 0.01`) - -#### Pathogen - -* `pathogen_loose`: optimised for mapping of human aDNA reads (i.e. bwa aln defaults as `-l 16 -n 0.01`) -* `pathogen_strict`: optimised for mapping of human aDNA reads (i.e. bwa aln defaults as `-l 32, -n 0.1`) -* `hops`: profile with default paths and parameters for automated/initial pathogen screening. - * :warning: This is NOT a reproducible profile as it contains hardcoded paths. This should only be used for initial/automated screening where you wish to quickly check for any possible positives; after which you should re-do screening in a reproducible manner for publication! diff --git a/docs/shh.md b/docs/shh.md deleted file mode 100644 index 6f61426..0000000 --- a/docs/shh.md +++ /dev/null @@ -1,16 +0,0 @@ -# nf-core/configs: SHH Configuration - -All nf-core pipelines have been successfully configured for use on the Department of Archaeogenetic's SDAG/CDAG clusters at the [Max Planck Institute for the Science of Human History (MPI-SHH)](http://shh.mpg.de). - -To use, run the pipeline with `-profile shh`. You can further with optimise submissions by specifying which cluster you are using with `-profile shh,sdag` or `-profile shh,cdag`. This will download and launch the [`shh.config`](../conf/shh.config) which has been pre-configured with a setup suitable for the SDAG and CDAG clusters respectively. 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. The image will currently be centrally stored here: - -```bash -/projects1/singularity_scratch/cache/ -``` - -however this will likely change to a read-only directory in the future that will be managed by the IT team. - -This configuration will automatically choose the correct SLURM queue (`short`,`medium`,`long`) depending on the time and memory required by each process. `-profile shh,sdag` additionally allows for submission of jobs to the `supercruncher` queue when a job's requested memory exceeds 756GB. - ->NB: You will need an account and VPN access to use the cluster at MPI-SHH in order to run the pipeline. If in doubt contact the IT team. ->NB: Nextflow will need to submit the jobs via SLURM to the clusters and as such the commands above will have to be executed on one of the head nodes. If in doubt contact IT. diff --git a/nextflow.config b/nextflow.config index f1ffe8a..fab2cd1 100644 --- a/nextflow.config +++ b/nextflow.config @@ -1 +1 @@ -includeConfig("nfcore_custom.config") \ No newline at end of file +includeConfig("nfcore_custom.config") diff --git a/nfcore_custom.config b/nfcore_custom.config index 74d25b9..99a31e4 100644 --- a/nfcore_custom.config +++ b/nfcore_custom.config @@ -48,7 +48,6 @@ profiles { prince { includeConfig "${params.custom_config_base}/conf/prince.config" } sanger { includeConfig "${params.custom_config_base}/conf/sanger.config"} seg_globe { includeConfig "${params.custom_config_base}/conf/seg_globe.config"} - shh { includeConfig "${params.custom_config_base}/conf/shh.config" } uct_hpc { includeConfig "${params.custom_config_base}/conf/uct_hpc.config" } uppmax { includeConfig "${params.custom_config_base}/conf/uppmax.config" } utd_ganymede { includeConfig "${params.custom_config_base}/conf/utd_ganymede.config" } diff --git a/pipeline/eager.config b/pipeline/eager.config index 2827496..3e47276 100644 --- a/pipeline/eager.config +++ b/pipeline/eager.config @@ -9,7 +9,6 @@ */ profiles { - shh { includeConfig "${params.custom_config_base}/conf/pipeline/eager/shh.config" } mpcdf { includeConfig "${params.custom_config_base}/conf/pipeline/eager/mpcdf.config" } eva { includeConfig "${params.custom_config_base}/conf/pipeline/eager/eva.config" } } From f41cb5986f35a230469fd4b2c104559a1d3b92cb Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Fri, 20 Aug 2021 10:18:04 +0200 Subject: [PATCH 2/2] remove from testing --- .github/workflows/main.yml | 1 - 1 file changed, 1 deletion(-) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index c5e6a57..12d23f0 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -54,7 +54,6 @@ jobs: - 'prince' - 'sanger' - 'seg_globe' - - 'shh' - 'uct_hpc' - 'uppmax' - 'utd_ganymede'