Updated kaust profile

conf/kaust.config

@@ -4,12 +4,11 @@ params {
     config_profile_description = 'Profile for use on King Abdullah Univesity of Science and Technology (KAUST) Ibex Cluster.'
     config_profile_contact = 'Husen Umer (@kaust.edu.sa)'
     config_profile_url = 'https://docs.hpc.kaust.edu.sa/quickstart/ibex.html'
-    save_reference = false
     igenomes_ignore = true
 }
 
 // Load genome resources and assets hosted by the Bioinformatics team on IBEX cluster
-// includeConfig '/biocorelab/BIX/resources/configs/genomes.yaml'
+includeConfig 'https://raw.githubusercontent.com/bcl-bix/reference-config/refs/heads/main/configs/genomes.config'
 
 singularity {
     enabled = true
@@ -18,7 +17,7 @@ singularity {
     // Use existing images from the centralized library, if available
     libraryDir = "/biocorelab/BIX/resources/singularity/images/"
     // Download images that are missing from the library to user space
-    cacheDir = "/home/$USER/.singularity/nf_images/"
+    cacheDir = "/ibex/scratch/$USER/.singularity/nf_images/"
 }
 
 process {
@@ -29,39 +28,34 @@ process {
     beforeScript = 'module load singularity'
     // Max allowed resources per process on Ibex
     resourceLimits = [
-        memory: 1600.GB,
-        cpus: 200,
-        time: 10.d
+        memory: 16.TB,
+        cpus: 1300,
+        time: 14.d
     ]
 }
 
 process {
-
     withLabel:process_single {
         time = 20.h
     }
-
     withLabel:process_low {
         cpus   = { 4 * task.attempt }
         memory = { 16.GB * task.attempt }
         time   = { 6.h  * task.attempt }
     }
-
     withLabel:process_medium {
-        cpus   = { 20 * task.attempt }
-        memory = { 96.GB * task.attempt }
+        cpus   = { 12 * task.attempt }
+        memory = { 97.GB * task.attempt }
         time   = { 12.h  * task.attempt }
     }
-
     withLabel:process_high {
-        cpus   = { 40 * task.attempt }
-        memory = { 256.GB * task.attempt }
+        cpus   = 32
+        memory = { 240.GB * task.attempt }
         time   = { 20.h  * task.attempt }
     }
-
     withLabel:process_long {
         cpus   = { 12 * task.attempt }
-        memory = { 128.GB * task.attempt }
+        memory = { 48.GB * task.attempt }
         time   = { 96.h  * task.attempt }
     }
 }

conf/pipeline/mag/kaust.config

@@ -0,0 +1,192 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    nf-core/mag Nextflow KAUST config file
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    A config file, appropriate for general use on KAUST high performance
+    compute environment - Ibex when using the KAUST profile.
+----------------------------------------------------------------------------------------
+*/
+params {
+    // There is an error on Ibex related to the latest version of meta-spades
+    skip_spades = true
+}
+
+process {
+    cpus          = { 4 * task.attempt }
+    memory        = { 16.GB * task.attempt }
+    time          = { 4.h * task.attempt }
+
+    errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }
+    maxRetries    = 3
+    maxErrors     = '-1'
+
+    // Process-specific resource requirements
+    // NOTE - Please try and reuse the labels below as much as possible.
+    //        These labels are used and recognised by default in DSL2 files hosted on nf-core/modules.
+    //        If possible, it would be nice to keep the same label naming convention when
+    //        adding in your local modules too.
+    // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
+    withLabel: process_single {
+        cpus   = { 1 }
+        memory = { 16.GB * task.attempt }
+        time   = { 6.h * task.attempt }
+    }
+    withLabel: process_low {
+        cpus   = { 4 * task.attempt }
+        memory = { 16.GB * task.attempt }
+        time   = { 6.h * task.attempt }
+    }
+    withLabel: process_medium {
+        cpus   = { 12 * task.attempt }
+        memory = { 97.GB * task.attempt }
+        time   = { 12.h * task.attempt }
+    }
+    withLabel: process_high {
+        cpus   = { 32 }
+        memory = { 240.GB * task.attempt }
+        time   = { 20.h * task.attempt }
+    }
+    withLabel:process_long {
+        cpus   = { 8 * task.attempt }
+        memory = { 32.GB * task.attempt }
+        time   = { 96.h  * task.attempt }
+    }
+    withLabel: process_high_memory {
+        memory = { 360.GB * task.attempt }
+    }
+    withLabel: error_ignore {
+        errorStrategy = 'ignore'
+    }
+    withLabel: error_retry {
+        errorStrategy = 'retry'
+        maxRetries    = 3
+    }
+    withName: BOWTIE2_HOST_REMOVAL_BUILD {
+        cpus   = { 10 * task.attempt }
+        memory = { 40.GB * task.attempt }
+        time   = { 4.h * task.attempt }
+    }
+    // Process-specific resource requirements
+    withName: BOWTIE2_HOST_REMOVAL_BUILD {
+        cpus   = { 12 * task.attempt }
+        memory = { 48.GB * task.attempt }
+        time   = { 8.h * task.attempt }
+    }
+    withName: BOWTIE2_HOST_REMOVAL_ALIGN {
+        cpus   = { 6 * task.attempt }
+        memory = { 24.GB * task.attempt }
+        time   = { 6.h * task.attempt }
+    }
+    withName: BOWTIE2_PHIX_REMOVAL_ALIGN {
+        cpus   = { 6 * task.attempt }
+        memory = { 24.GB * task.attempt }
+        time   = { 6.h * task.attempt }
+    }
+    withName: PORECHOP_PORECHOP {
+        cpus   = { 12 * task.attempt }
+        memory = { 48.GB * task.attempt }
+        time   = { 4.h * task.attempt }
+    }
+    withName: NANOLYSE {
+        cpus   = { 6 * task.attempt }
+        memory = { 24.GB * task.attempt }
+        time   = { 3.h * task.attempt }
+    }
+    //filtlong: exponential increase of memory and time with attempts
+    withName: FILTLONG {
+        cpus   = { 16 * task.attempt }
+        memory = { 97.GB * (2 ** (task.attempt - 1)) }
+        time   = { 24.h * (2 ** (task.attempt - 1)) }
+    }
+    withName: CENTRIFUGE_CENTRIFUGE {
+        cpus   = { 12 * task.attempt }
+        memory = { 48.GB * task.attempt }
+        time   = { 12.h * task.attempt }
+    }
+    withName: KRAKEN2 {
+        cpus   = { 16 * task.attempt }
+        memory = { 240.GB * task.attempt }
+        time   = { 20.h * task.attempt }
+    }
+    withName: KRONA_KTIMPORTTAXONOMY {
+        cpus   = { 16 * task.attempt }
+        memory = { 240.GB * task.attempt }
+        time   = { 20.h * task.attempt }
+    }
+    withName: CAT_DB_GENERATE {
+        memory = { 240.GB * task.attempt }
+        time   = { 16.h * task.attempt }
+    }
+    withName: CAT {
+        cpus   = { 16 * task.attempt }
+        memory = { 240.GB * task.attempt }
+        time   = { 20.h * task.attempt }
+    }
+    withName: GTDBTK_CLASSIFYWF {
+        cpus   = { 16 * task.attempt }
+        memory = { 240.GB * task.attempt }
+        time   = { 20.h * task.attempt }
+    }
+    //MEGAHIT returns exit code 250 when running out of memory
+    withName: MEGAHIT {
+        cpus          = { params.megahit_fix_cpu_1 ? 1 : (16 * task.attempt) }
+        memory        = { 240.GB * task.attempt }
+        time          = { 20.h * task.attempt }
+        errorStrategy = { task.exitStatus in ((130..145) + 104 + 247 + 250) ? 'retry' : 'finish' }
+    }
+    //SPAdes returns error(1) if it runs out of memory (and for other reasons as well...)!
+    //exponential increase of memory and time with attempts, keep number of threads to enable reproducibility
+    withName: SPADES {
+        cpus          = { params.spades_fix_cpus != -1 ? params.spades_fix_cpus : (12 * task.attempt) }
+        memory        = { 240.GB * (2 ** (task.attempt - 1)) }
+        time          = { 24.h * (2 ** (task.attempt - 1)) }
+        errorStrategy = { task.exitStatus in ((130..145) + 104 + 21 + 12 + 1 + 247) ? 'retry' : 'finish' }
+        maxRetries    = 5
+    }
+    withName: SPADESHYBRID {
+        cpus          = { params.spadeshybrid_fix_cpus != -1 ? params.spadeshybrid_fix_cpus : (12 * task.attempt) }
+        memory        = { 240.GB * (2 ** (task.attempt - 1)) }
+        time          = { 24.h * (2 ** (task.attempt - 1)) }
+        errorStrategy = { task.exitStatus in ((130..145) + 104 + 21 + 12 + 1 + 247) ? 'retry' : 'finish' }
+        maxRetries    = 5
+    }
+    //returns exit code 247 when running out of memory
+    withName: BOWTIE2_ASSEMBLY_ALIGN {
+        cpus          = { 12 * task.attempt }
+        memory        = { 97.GB * task.attempt }
+        time          = { 16.h * task.attempt }
+        errorStrategy = { task.exitStatus in ((130..145) + 104 + 247) ? 'retry' : 'finish' }
+    }
+    withName: METABAT2_METABAT2 {
+        cpus   = { 20 * task.attempt }
+        memory = { 180.GB * task.attempt }
+        time   = { 8.h * task.attempt }
+    }
+    withName: MAG_DEPTHS {
+        memory = { 97.GB * task.attempt }
+    }
+    withName: BUSCO {
+        cpus   = { 20 * task.attempt }
+        memory = { 180.GB * task.attempt }
+    }
+    withName: MAXBIN2 {
+        errorStrategy = { task.exitStatus in [1, 255] ? 'ignore' : 'retry' }
+        cpus   = { 20 * task.attempt }
+        memory = { 180.GB * task.attempt }
+    }
+    withName: DASTOOL_DASTOOL {
+        errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : task.exitStatus == 1 ? 'ignore' : 'finish' }
+    }
+    withName: BOWTIE2_ASSEMBLY_BUILD {
+        cpus   = { 20 * task.attempt }
+        memory = { 180.GB * task.attempt }
+    }
+    withName: BOWTIE2_ASSEMBLY_ALIGN {
+        cpus   = { 20 * task.attempt }
+        memory = { 180.GB * task.attempt }
+    }
+    withName: PRODIGAL {
+        cpus   = { 20 * task.attempt }
+        memory = { 180.GB * task.attempt }
+    }
+}

conf/pipeline/rnaseq/kaust.config

@@ -0,0 +1,46 @@
+process {
+
+    cpus   = { 4      * task.attempt }
+    memory = { 16.GB   * task.attempt }
+    time   = { 4.h    * task.attempt }
+
+    errorStrategy = { task.exitStatus in [143,137,104,134,139,151,140,247,12] ? 'retry' : 'finish' }
+    maxRetries    = 3
+    maxErrors     = '-1'
+
+    withLabel:process_single {
+        cpus   = { 4                   }
+        memory = { 32.GB * task.attempt }
+        time   = { 4.h  * task.attempt }
+    }
+    withLabel:process_low {
+        cpus   = { 4 * task.attempt }
+        memory = { 16.GB * task.attempt }
+        time   = { 6.h  * task.attempt }
+    }
+    withLabel:process_medium {
+        cpus   = { 12 * task.attempt }
+        memory = { 97.GB * task.attempt }
+        time   = { 12.h  * task.attempt }
+    }
+    withLabel:process_high {
+        cpus   = 32
+        memory = { 240.GB * task.attempt }
+        time   = { 20.h  * task.attempt }
+    }
+    withLabel:process_long {
+        cpus   = { 12 * task.attempt }
+        memory = { 48.GB * task.attempt }
+        time   = { 96.h  * task.attempt }
+    }
+    withLabel:process_high_memory {
+        memory = { 240.GB * task.attempt }
+    }
+    withLabel:error_ignore {
+        errorStrategy = 'ignore'
+    }
+    withLabel:error_retry {
+        errorStrategy = 'retry'
+        maxRetries    = 3
+    }
+}

docs/kaust.md

@@ -15,7 +15,7 @@ is to use the [module system](https://docs.hpc.kaust.edu.sa/soft_env/prog_env/mo
 
 ```bash
 # Log in to the desired cluster
-ssh <USER>@ilogin.kaust.edu.sa
+ssh <USER>@ilogin.ibex.kaust.edu.sa
 
 # Activate the modules, you can also choose to use a specific version with e.g. `Nextflow/24.04.4`.
 module load nextflow
@@ -24,12 +24,25 @@ module load nextflow
 Launch the pipeline with `-profile kaust` (one hyphen) to run the workflows using the KAUST profile.
 This will download and launch the [`kaust.config`](../conf/kaust.config) which has been pre-configured with a setup suitable for the KAUST servers.
 It will enable `Nextflow` to manage the pipeline jobs via the `Slurm` job scheduler and `Singularity` to run the tasks.
-Using the KAUST profile, `Docker` image(s) containing required software(s) will be downloaded, and converted to `Singularity` image(s) if needed before execution of the pipeline. To avoid downloading same images by multiple users, we provide a singularity `libraryDir` that is configured to use images already downloaded in our central container library. Images missing from our library will be downloaded to your home directory path as defined by `cacheDir`.
+Using the KAUST profile, `Docker` image(s) containing required software(s) will be downloaded, and converted to `Singularity` image(s) if needed before execution of the pipeline. To avoid downloading same images by multiple users, we provide a singularity `libraryDir` that is configured to use images already downloaded in our central container library. Images missing from our library will be downloaded to the user's directory as defined by `cacheDir`.
+
+Additionally, institute-specific pipeline profiles exists for:
+
+- mag
+- rnaseq
+
+### Accessing reference genomes on Ibex
+
+We provide a collection of reference genomes, enabling users to run workflows seamlessly without the need to download the files. To enable access to this resource, add the species name with the `--genome` parameter.
+
+### Run workflows on Ibex
 
 The KAUST profile makes running the nf-core workflows as simple as:
 
 ```bash
 
+# Load Nextflow and Singularity modules
+module purge
 module load nextflow
 module load singularity
 
@@ -40,4 +53,8 @@ $ nextflow run nf-core/<PIPELINE> -profile kaust -r <PIPELINE_VERSION> --genome
 Where `input_csv` contains information about the samples and datafile paths.
 
 Remember to use `-bg` to launch `Nextflow` in the background, so that the pipeline doesn't exit if you leave your terminal session.
-Alternatively, you can also launch `Nextflow` in a `tmux` or a `screen` session.
+Alternatively, you can also launch a `tmux` or a `screen` session to run the commands above. Another good way, is to run it as an independent sbatch job as [explained here](https://bclwiki.kaust.edu.sa/en/bix/analysis/public/bioinformatics-workflows#run-workflow-using-sbatch).
+
+### Workflow specific profiles
+
+Please let us know if there are particular processes that continously fail so that we modify the defaults in the corresponding pipeline profile.

docs/pipeline/mag/kaust.md

@@ -0,0 +1,15 @@
+# nf-core/configs: kaust mag specific configuration
+
+Extra specific configuration for [nf-co.re/mag](https://nf-co.re/mag) pipeline.
+
+## Usage
+
+To use, run the pipeline with `-profile kaust`.
+
+This will download and launch the mag specific [`kaust.config`](../../../conf/pipeline/mag/kaust.config) which has been pre-configured with a setup suitable for the Ibex cluster.
+
+Example: `nextflow run nf-core/mag -profile kaust`
+
+## mag specific configurations for kaust
+
+Specific configurations for kaust has been made for mag, primarily increasing the default resource allocations especeially for high demand processes.

docs/pipeline/rnaseq/kaust.md

@@ -0,0 +1,15 @@
+# nf-core/configs: kaust rnaseq specific configuration
+
+Specific configuration for [nf-co.re/rnaseq](https://nf-co.re/rnaseq) pipeline.
+
+## Usage
+
+To use, run the pipeline with `-profile kaust`.
+
+This will download and launch the rnaseq specific [`kaust.config`](../../../conf/pipeline/rnaseq/kaust.config) which has been pre-configured with a setup suitable for the Ibex cluster.
+
+Example: `nextflow run nf-core/rnaseq -profile kaust`
+
+## rnaseq specific configurations for kaust
+
+Specific configurations for kaust has been made for rnaseq, primarily increasing the default resource allocations especeially for high demand processes.

pipeline/mag.config

@@ -15,4 +15,7 @@ profiles {
     eva {
         includeConfig "${params.custom_config_base}/conf/pipeline/mag/eva.config"
     }
+    kaust {
+        includeConfig "${params.custom_config_base}/conf/pipeline/mag/kaust.config"
+    }
 }